Browse the ITC publications of previous conferences below or visit our grouppage at bibsonomy.org
2001
He, JiaFu and Sohraby, Khosrow
A combinatorial solution of discrete time multi-server queueing systems with Markov sources
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{He20011015,
title = { A combinatorial solution of discrete time multi-server queueing systems with Markov sources },
year = { 2001 },
author = { He, JiaFu and Sohraby, Khosrow },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 1015 - 1026 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80188-8 }
}
Abstract: This paper investigates the discrete time queueing systems with multiple servers. Such models arise frequently in the teletraffic analysis of modern computer and communication networks. The arrival process is considered to be a general discrete Markovian source capturing the correlation in number of arrivals in successive discrete time slots. We provide a novel solution for such models based on the new methodology introduced in [3], which is quite distinct from the traditional methods. We present an explicit analytical formula of the survivor function of the queue length distribution which is readily computable. Some analytical and numerical examples are also provided to illustrate the results.
Nuzman, Carl and Saniee, Iraj and Sweldens, Wim and Weiss, Alan
A compound model for \TCP\ connection arrivals: Empirical study within a general framework
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Nuzman2001409,
title = { A compound model for \TCP\ connection arrivals: Empirical study within a general framework },
year = { 2001 },
author = { Nuzman, Carl and Saniee, Iraj and Sweldens, Wim and Weiss, Alan },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 409 - 420 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80139-6 }
}
Abstract: We propose a two level model for \TCP\ connection arrivals in local area networks. The first level are user sessions whose arrival is time-varying Poisson. The second level are connections within a user session. Their number and mean interrival are independent and biPareto across user session. The interarrivals within a user session are Weibull, and across all users are correlated Weibull. Our model has a small number of parameters which are inferred from real traffic colected at a firewall. We show that traffic synthesized with our model closely characterizes the original data. We extend this approach to a general model involving shot noise that is shown to be asymptotically consistent with more common fractal models used in data networks.
Johansson, N. and Körner, U. and Tassiulas, L.
A distributed scheduling algorithm for a bluetooth scatternet
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Johansson200161,
title = { A distributed scheduling algorithm for a bluetooth scatternet },
year = { 2001 },
author = { Johansson, N. and Körner, U. and Tassiulas, L. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 61 - 72 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80111-6 }
}
Abstract: This paper deals with bandwidth allocation in a Bluetooth scatternet. the proposed assignment of transmission rights provides a controlled traffic transfer between bluetooth piconets and represents a key component in an ad-hoc wireless Bluetooth network in order to provide with efficient data packet passing within and across piconets. This assignment is obtained by executing a distributed algorithm in each node. The algorithm works for unrestricted topologies of both stationary and mobile networks and also deals with assignment changes caused by network re-configurations without the use of a centralized factor. The effect of this re-assignment can be limited to the locality of that topology change. It is also shown that the construction of a link schedule of minimum length in a Bluetooth scatternet is NP-complete.
Scoglio, C. and Anjali, T. and de Oliveira, J.C. and Akyildiz, I.F. and Uhl, G.
A new threshold-based policy for label switched path (LSP) set-up in \MPLS\ networks
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Scoglio20011,
title = { A new threshold-based policy for label switched path (LSP) set-up in \MPLS\ networks },
year = { 2001 },
author = { Scoglio, C. and Anjali, T. and de Oliveira, J.C. and Akyildiz, I.F. and Uhl, G. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 1 - 12 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80106-2 }
}
Abstract: In this paper, a new policy is introduced to determine and adapt the \MPLS\ network topology based on the current traffic load. The objective of the new policy is to minimize the costs involving bandwidth, switching and signaling. The new policy is based on a threshold criterion and requires only the knowledge of some parameters locally stored in the source router. The value of the threshold depends on the cost coefficients and on the length (number of intermediate hops) of the LSP. The new policy also performs a filtering control to avoid oscillations which occur due to highly variable traffic. The new policy has been evaluated by simulation and numerical results show its effectiveness and the according performance improvement.
Hwang, Junseok
A scalable dynamic provisioning mechanism for IntServ-DiffServ networks for guaranteed services
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Hwang2001955,
title = { A scalable dynamic provisioning mechanism for IntServ-DiffServ networks for guaranteed services },
year = { 2001 },
author = { Hwang, Junseok },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 955 - 966 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80183-9 }
}
Abstract: There are various Internet Protocol (IP) QoS support approaches proposed, however no standard interconnection mechanisms have yet been developed to support dynamic provisioning among different \IP\ QoS mechanisms. This paper addresses the particular bandwidth management problems of a backbone ISP, a Differentiated Service (DiffServ) network with an interconnection to an Integrated Service (IntServ) network. This architecture is especially interesting due to the different complementary features shared by these architectures. This study proposes mechanisms to realize the scalable dynamic provisioning and admission controlled interconnection of IntServ and DiffServ networks for guaranteed services using a bandwidth management agent called \BMP\ (Bandwith Management Point).
Menth, Michael
A scalable protocol architecture for end-to-end signaling and resource reservation in \IP\ networks
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Menth2001211,
title = { A scalable protocol architecture for end-to-end signaling and resource reservation in \IP\ networks },
year = { 2001 },
author = { Menth, Michael },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 211 - 222 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80123-2 }
}
Abstract: This paper presents a concept of a scalable networking architecture with end-to-end QoS signaling and resource reservation support. It is a synthesis of both the Differentiated Services and the Integrated Services approach. The approach relies on end-to-end resource reservation and takes advantage of traffic aggregation to reduce the number of reservation states in the router MIBs. Signaling costs are further decreased by making overreservation, i.e. bandwidth efficiency is traded for signaling reduction. We give recommendations to dimension the degree of overreservation and compute the resulting tradeoff analytically. The numerical results show that networks running the proposed architecture can be operated efficiently in spite of overreservation.
Lubacz, J. and Tomaszewski, A.
A systematic approach to network planning
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Lubacz2001605,
title = { A systematic approach to network planning },
year = { 2001 },
author = { Lubacz, J. and Tomaszewski, A. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 605 - 615 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80155-4 }
}
Abstract: The paper introduces a reference model for network planning activities. The planning process is conceptualised in terms of a trajectorya sequence of elementary network planning problems-which traverses a three dimensional planning space. The dimensions of the space pertain to the time horizon of planning, to the type of network resources being planned (to a layered architecture of network resources) and to a set of generic network planning tasks. The model has been successfully exploited by the authors in real-world network planning projects, in the implementation of a comprehensive network planning software and also in academic courses.
Jennings, Brendan and ke Arvidsson and Curran, Thomas
A token-based strategy for co-ordinated, profit-optimal control of multiple \IN\ resources
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Jennings2001245,
title = { A token-based strategy for co-ordinated, profit-optimal control of multiple \IN\ resources },
year = { 2001 },
author = { Jennings, Brendan and ke Arvidsson and Curran, Thomas },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 245 - 257 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80126-8 }
}
Abstract: Dimensioning of Intelligent Networks (IN) to ensure acceptable performance is becoming a very difficult task, given the ongoing evolution of \IN\ into an open and dynamic platform for the delivery of a large number of complex service offerings. To combat this problem we advocate the adoption of network-oriented load control strategies, which not only protect against overload of individual resources but also enforce network operator defined service priorities. In this paper we compare the performance of a network-oriented \IN\ load control, based on optimal allocation of tokens with a similar dynamic, profit-maximising strategy and with the widely-deployed Automatic Code Gapping (ACG) control. We then describe and analyse two significant enhancements to the token-based strategy: the first enables hierarchical, distributed control of multiple Service Control Points (SCPs) and the second facilitates coordinated control of multiple Service Data Points (SDPs) and multiple SCPs.
Viken, Brynjar and Emstad, Peder J.
Accuracy of intrusive measurements of the waiting time in an M/G/1/8 queue
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Viken20011039,
title = { Accuracy of intrusive measurements of the waiting time in an M/G/1/8 queue },
year = { 2001 },
author = { Viken, Brynjar and Emstad, Peder J. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 1039 - 1050 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80190-6 }
}
Abstract: Intrusive measurements are extensively used in \IP\ networks to assess packet delay. The key challenge is to set the measurement intensity high enough to get a sufficient number of observations while avoiding disturbance to regular traffic. This paper investigates the case when the end-to-end path has a single bottleneck node which can be modelled by an M/G/1/8 queue. The waiting time of this queue is measured by injecting probe packets into the network. An analytical expression for the variance of the average waiting time as observed by the probe packets is determined. Further, the optimal measurement intensity is investigated.
Huang, Leping and Sezaki, Kaoru
Adjustment on end-to-end delay to remove the distortion caused by \NTP\ clock adjustment
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Huang20011075,
title = { Adjustment on end-to-end delay to remove the distortion caused by \NTP\ clock adjustment },
year = { 2001 },
author = { Huang, Leping and Sezaki, Kaoru },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 1075 - 1086 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80193-1 }
}
Abstract: End-to-end delay and loss measurement is an efficient way for a host to examine the network performance. Unnoticed clock errors that influence the accuracy of the timestamp may result in fatal system errors. In this paper, we discuss the characteristics and defects of the existing clock distortion adjustment algorithms. Those algorithms are not applicable to process a long-term delay trace, which contains periodical \NTP\ clock adjustment. Therefore, we propose a relatively robust algorithm to resolve the problem. The algorithm employs window function to partition the long-term trace into short segments, improves the precision of the estimation of the time and amount of \NTP\ clock adjustment. To evaluate the performance of our proposed algorithm, we practice it in adjusting the clock distortion of the real delay traces collected from Internet. The results indicate that our proposed algorithm has excellent effect on the removal of the clock distortion from the long-term delay traces.
Courcoubetis, Costas and Dramitinos, Manos P. and Stamoulis, George D.
An auction mechanism for bandwidth allocation over paths
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Courcoubetis20011163,
title = { An auction mechanism for bandwidth allocation over paths },
year = { 2001 },
author = { Courcoubetis, Costas and Dramitinos, Manos P. and Stamoulis, George D. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 1163 - 1173 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80200-6 }
}
Abstract: The demand for bandwidth contracts over networks has recently been growing rapidly. Moreover, due to increased competition among providers, customized short-term bandwidth contracts are now preferred by users to static, long-term contracts of the past. To this end, auctions appear to be a proper trading mechanism. When purchasing bandwidth over a path of a network, it is only meaningful for a user to reserve the same quantity at all the constituent links. We have developed a simple, yet efficient auction for allocating bandwidth on a network basis to users who wish to utilize it for the same time period. This mechanism (referred to as MIDAS) consists of a set of simultaneous multi-unit Dutch (i.e. descending-price) auctions, one per link of the network. In order to win bandwidth over a certain path, it suffices for a user to simultaneously bid for the quantity desired at all relevant auctions. Thus, instant allocation of bandwidth is attained. An important feature of our approach is that prices at the various links are reduced at different rates, so that prices reflect the demand exhibited so far for each link. We have evaluated experimentally two price reduction policies, in terms of the social welfare associated with the resulting allocation, and argue (both theoretically and by means of experimental results) that it is indeed efficient to introduce such rules rather than reduce all prices at the same rate. We have also briefly addressed the issue of incentive compatible pricing.
de Morais Cordeiro, Carlos and Sadok, Djamel F.H. and Kelner, Judith
An in-depth evaluation of bluetooth ad hoc networks
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Cordeiro2001299,
title = { An in-depth evaluation of bluetooth ad hoc networks },
year = { 2001 },
author = { de Morais Cordeiro, Carlos and Sadok, Djamel F.H. and Kelner, Judith },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 299 - 310 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80130-X }
}
Abstract: The emergence of Bluetooth as a default radio interface allows handheld electronic devices to be instantly interconnected into ad hoc networks. These short range ad hoc wireless networks, called piconets, operate in the unlicensed 2.45 Ghz \ISM\ (Industrial-Scientific-Medical) band where up to eight devices may be used to configure single or overlapping piconets. This creates interference on the device from other devices operating in the same frequency band including microwaves and devices enabling various wireless ŁAN\ standards. This papers uses a signal capture model to study piconet \MAC\ performance. Furthermore, simulations are used to validate the throughput obtained from this model. These results reveal important performance implications of the effect of piconets interference on throughput.
Busson, A. and Rougier, J-L and Kofman, D.
Analysis and optimization of hierarchical reliable transport protocols
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Busson200199,
title = { Analysis and optimization of hierarchical reliable transport protocols },
year = { 2001 },
author = { Busson, A. and Rougier, J-L and Kofman, D. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 99 - 110 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80114-1 }
}
Abstract: Several schemes have been proposed that address the problem of scalable reliable multicast. The Tree-based Acknowledgement protocols family achieve scalable reliable transport in one-to-many communications based on a hierarchical approach. It has been recently selected as a standard-track possible protocol architecture by IETF. In these protocols, dedicated servers are used to perform error recovery and statistical aggregations. Nevertheless a number of dimensioning issues remain open, such as the number of required servers, and the optimal number of hierarchical levels. In order to evaluate and dimension such protocols, we consider an analytical model using point processes, where points are scattered in the plane in order to represent receiver locations in the Internet, and a loss model which takes correlated losses into account. We define cost functions based on the number of retransmissions in the control tree for a packet sent by the source. We proposed random geometric model allowing us to find explicit expressions for the cost functions, w.r.t. to a limited set of parameters: number of receivers and number of repair servers. We are then able to deduce optimal control tree structures (optimal number of repair servers), and generic dimensioning rules.
Galmés, S.
Analysis of the (batch-on/off)/D/1 queue
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Galmes2001979,
title = { Analysis of the (batch-on/off)/D/1 queue },
year = { 2001 },
author = { Galmés, S. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 979 - 990 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80185-2 }
}
Abstract: In this paper the batch-on/off model is introduced and the related queueing behavior is analyzed. The batch-on/off model is the natural extension of the single source for describing aggregate \ATM\ traffic. Hence, in addition to the distributions of the busy and idle periods, a batch size distribution needs to be specified. As it is shown in the paper, batch-on/off models constitute a very interesting tool in research, since besides their flexibility (no particular distributions are assumed), they retain the analytical tractability and to a large extent provide explicit and very comprehensive results. Particularly, the paper deals with the (Batch-On/Off)/D/1 queue, for which the batch response time, an upper bound on the response time of cells, and the mean response time are obtained. These results can be decomposed into two contributions: single bursts or low time scale effects, for which exact closed-form expressions are calculated, and the interaction between bursts or higher time scale effects, whose evaluation relies on the solution of a general random walk problem.
Liu, E. and Schormans, J. and Cuthbert, L. and Phillips, C. and Stoneley, G.
*Application of neural networks to accelerated simulation of internet type \WANs*
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Liu20011127,
title = { Application of neural networks to accelerated simulation of internet type \WANs\ },
year = { 2001 },
author = { Liu, E. and Schormans, J. and Cuthbert, L. and Phillips, C. and Stoneley, G. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 1127 - 1137 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80197-9 }
}
Abstract: This paper proposes a new application of neural networks in network simulation. A high-level abstracted analytical model, based on intensive investigation of packet queuing behaviour, substantially speeds up the basic simulation. Comparing results of the simulation model against experimental validation on a testbed leads to some difference between them, an expected result given the level of the abstraction. Thus a neural network, which is capable of self-learning the complex relation between the model parameters and the output difference above, is applied to the model and prediction of the neural network is used to fine-tune the model accordingly. Study results indicate that the proposed hybrid method (abstracted model plus neural network prediction) not only achieves fast simulation but also remains accurate. This approach is particularly useful in the area of large-scale network designing and planning, where concern is more about overall performance of a network than detailed behaviour of network nodes.
Mannersalo, Petteri and Norros, Ilkka
Approximate formulae for Gaussian priority queues
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Mannersalo2001991,
title = { Approximate formulae for Gaussian priority queues },
year = { 2001 },
author = { Mannersalo, Petteri and Norros, Ilkka },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 991 - 1002 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80186-4 }
}
Abstract: Queueing theory with general Gaussian traffic has no exact results, but reasonably good approximations are easy to obtain. In the context of Differentiated Services, \FIFO\ queues play a minor role. Instead, it is important to understand how priority queues behave when the inputs are Gaussian. This paper focuses on developing practically usable estimates for distributions of Gaussian priority queues. The key idea is to identify the most probable paths along which a big queue arises. Some of the approximations are compared to simulations, and the results are promising.
Altman, Eitan and Azouzi, Rachid El and Pourtallier, Odile
Avoiding paradoxes in routing games
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Altman2001643,
title = { Avoiding paradoxes in routing games },
year = { 2001 },
author = { Altman, Eitan and Azouzi, Rachid El and Pourtallier, Odile },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 643 - 654 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80158-X }
}
Abstract: Strange behavior may occur in networks due to the non-cooperative nature of decision making, when the latter are taken by individual agents. In particular, the well known Braess paradox illustrates that when upgrading a network by adding a link, the resulting equilibrium may exhibit larger delays for all users. We present here some guidelines to avoid the Braess paradox when upgrading a network. We furthermore present conditions for the delays to be monotone increasing in the total demand.
Pióro, M. and Szymanski, T.
Basic reconfiguration options in multi-layer robust telecommunication networks design and performance issues
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Pioro2001271,
title = { Basic reconfiguration options in multi-layer robust telecommunication networks design and performance issues },
year = { 2001 },
author = { Pióro, M. and Szymanski, T. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 271 - 284 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80128-1 }
}
Abstract: The paper formulates a set of fundamental optimisation problems for designing multi-layer telecommunication networks robust to failures and/or to predicted changes in demand patterns. The considered problems correspond to basic flow restoration options associated with reconfiguration capabilities of individual network resources' layers. It is shown in detail how the Benders' Decomposition technique can be applied for solving the problems, yielding an effective means for evaluating the cost of different restoration options in large B-ISDN, ATM, IP, \SDH\ networks. Effectiveness of the proposed approach is illustrated by means of a numerical study.
Karvo, Jouni and Aalto, Samuli and Virtamo, Jorma
Blocking probabilities of two-layer statistically indistinguishable multicast streams
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Karvo2001769,
title = { Blocking probabilities of two-layer statistically indistinguishable multicast streams },
year = { 2001 },
author = { Karvo, Jouni and Aalto, Samuli and Virtamo, Jorma },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 769 - 779 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80168-2 }
}
Abstract: We study calculation of blocking probability for two-layer multicast streams assuming Poisson arrivals and exponential holding times, and that blocked calls are lost. Users may join and leave the multicast connections freely, thus creating dynamic multicast trees. We define the state space, and give a recursive algorithm for the special case where all multicast channels are statistically indistinguishable. Our recursive algorithm is linear with respect to the number of links and polynomial with respect to the number of channels. We give blocking probabilities for both layers for an example network, and devise upper and lower bounds for layer 2 blocking probability.
Hämäläinen, Timo and Wallenius, Eero
Case study for 3G/UMTS services and billing methods
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Haemaelaeinen20011201,
title = { Case study for 3G/UMTS services and billing methods },
year = { 2001 },
author = { Hämäläinen, Timo and Wallenius, Eero },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 1201 - 1208 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80203-1 }
}
Abstract: The 3G/UMTS-networks and services will provide a wide range of telecommunication services. To achieve, this, we need a new view to networks, network services and service abilities. The amount of service providers in the 3G networks will be at least the same than in the present Internet. The amount of users in the 3G networks will overgrow the user amount of Internet forming a global worldwide communication society. This paper discusses customer billing in the 3G world. There are some main issues that are not very, clear to all 3G service and network providers, which however, should be settled before, 3G networks are operational. One of the most important matters is the QoS (Quality of Service), which is needed to achieve all benefits of the 3G networks. Here, we present the roles of the different providers that will interact with each other. New service types that will be developed and exploited with the new technology and the ways to charge services in 3G world in an appropriate manner for customers and operators is also presented. Not all of the details will be discussed here, but the main issues are covered and the one goal is to start discussions of this important issue among customers and service providers.
Boukhatem, L. and Beylot, A.L. and Gaïti, D. and Pujolle, G.
Channel assignment with handover queuing in ŁEO\ satellite systems based on an earth-fixed cell coverage
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Boukhatem2001311,
title = { Channel assignment with handover queuing in ŁEO\ satellite systems based on an earth-fixed cell coverage },
year = { 2001 },
author = { Boukhatem, L. and Beylot, A.L. and Gaïti, D. and Pujolle, G. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 311 - 321 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80131-1 }
}
Abstract: Low-Earth Orbit (LEO) satellite systems are intended to have an important part of the future generation of mobile telecommunication systems. They aim to provide different services to various populations of users. Each class of users requires a certain Quality of Service (QoS) and thus a given part of the shared channel resource. In this paper, ŁEO\ satellite systems based on an earth-fixed cell concept are considered, and different channel allocation strategies with handover queuing are discussed. Two channel allocation techniques have been investigated: fixed and dynamic channel allocation \FCA\ and DCA. Moreover, in order to reduce the handover failure probability, we have assumed that handover attempts can be queued. An analytical model has been derived in the \FCA\ case considering both handover queuing and users diversity. Implementation aspects for the \DCA\ scheme have been discussed in comparison with \FCA\ results.
Agrawal, Rajeev and Bedekar, Anand and La, Richard J. and Subramanian, Vijay
Class and channel condition based weighted proportional fair scheduler
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Agrawal2001553,
title = { Class and channel condition based weighted proportional fair scheduler },
year = { 2001 },
author = { Agrawal, Rajeev and Bedekar, Anand and La, Richard J. and Subramanian, Vijay },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 553 - 567 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80151-7 }
}
Abstract: In this paper we outline a scheme to perform packet-level scheduling and resource allocation at the wireless node that takes into account the notions of both efficiency and fairness and presents a means to explore the trade-off between these two notions. As a part of this scheme we see the scheduling problem as deciding not just the packet transmission schedule but also the power allocation, the modulation and coding scheme allocation and the spreading code determination since the latter three directly influence the radio resources consumed. Using a utility maximization formulation based on the data-rates that the mobiles can transmit at, we decide on the weights for a weighted proportionally fair allocation based scheduling algorithm. We conclude with a simulation based performance analysis for infinitely-backlogged sources on a \UMTS\ system.
Mitra, Debasis and Ramakrishnan, K.G. and Wang, Qiong
Combined economic modeling and traffic engineering: Joint optimization of pricing and routing in multi-service networks
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Mitra200173,
title = { Combined economic modeling and traffic engineering: Joint optimization of pricing and routing in multi-service networks },
year = { 2001 },
author = { Mitra, Debasis and Ramakrishnan, K.G. and Wang, Qiong },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 73 - 85 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80112-8 }
}
Abstract: We consider a network, with fixed topology and link bandwidths, that offers multiple services, such as voice and data, each having characteristic price elasticity to demand, and quality of service and policy requirements on routing. We develop a revenue maximization model in which pricing and routing are jointly optimized. In this model, prices, which depend on service type and origin-destination, determine demands, that are routed, subject to their constraints, so as to maximize revenue, which is earned when the demand is delivered to its destination. The model is flow-based. We study the basic properties of the optimal solution and prove that link shadow costs provide the basis for selecting optimal prices and determining optimal routing policies. We present illustrative numerical examples in which network bandwidth is scaled to grow.
Barceló, Francisco
Comparison of handoff resource allocation strategies through the state-dependent rejection scheme
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Barcelo2001323,
title = { Comparison of handoff resource allocation strategies through the state-dependent rejection scheme },
year = { 2001 },
author = { Barceló, Francisco },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 323 - 334 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80132-3 }
}
Abstract: The State-Dependent Rejection scheme (SRS) provides a common framework for analyzing existing handoff schemes and for designing new ones easily. Designing new \SRS\ schemes is made simple by determining the appropriate set of state-dependent probabilities. The Markov analysis of \SRS\ is simple and useful for drawing initial conclusions on handoff strategies. The analysis carried out here demonstrates the capability of \SRS\ to adapt to different mobility and load scenarios and to achieve good performance while targeting QoS performance metrics.
Zaim, A. Halim and Rouskas, George N. and Perros, Harry G.
Computing call blocking probabilities in ŁEO\ satellite networks: The single orbit case
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{HalimZaim2001505,
title = { Computing call blocking probabilities in ŁEO\ satellite networks: The single orbit case },
year = { 2001 },
author = { Zaim, A. Halim and Rouskas, George N. and Perros, Harry G. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 505 - 516 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80147-5 }
}
Abstract: We study the problem of carrying voice calls over a ŁEO\ satellite network, and we present an analytical model for computing call blocking probabilities for a single orbit of a satellite constellation. We have devised a method to solve the corresponding Markov process efficiently for up to 5-satellite orbits. For orbits consisting of a larger number of satellites, we have developed an approximate decomposition algorithm to compute the call blocking probabilities by decomposing the system into smaller sub-systems, and iteratively solving each sub-system in isolation using the exact Markov process. Our approach can capture blocking due to hand-offs for both satellite-fixed and earth-fixed constellations. Numerical results demonstrate that our method is accurate for a wide range of traffic patterns and for orbits with a number of satellites that is representative of commercial satellite systems.
Sato, Shohei and Kobayashi, Kazutomo and Pan, Huanxu and Tartarelli, Sandra and Banchs, Albert
Configuration rule and performance evaluation for DiffServ parameters
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Sato2001931,
title = { Configuration rule and performance evaluation for DiffServ parameters },
year = { 2001 },
author = { Sato, Shohei and Kobayashi, Kazutomo and Pan, Huanxu and Tartarelli, Sandra and Banchs, Albert },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 931 - 942 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80181-5 }
}
Abstract: The Internet is becoming an important communication infrastructure of the society, and thus it is no longer sufficient to simply be able to provide connections: a higher quality of service (QoS) in communications is increasingly being required. As a new framework for providing QoS services, DiffServ is undergoing a speedy standardization process at the IETF. DiffServ not only can offer tiered levels of services, but can also provide guaranteed QoS to a certain extent. In this paper, we examine a single DiffServ node model which utilizes a token bucket as the policing mechanism, and propose a way of configuring various control parameters in order to accommodate various UDP/TCP traffic. Then, through simulation, we evaluate the throughput characteristics in various cases where \TCP\ and \UDP\ are mixed or separated in different queues, and study the appropriateness of the configurations. The results indicate that the throughputs can be maintained as specified in the Service Level Agreements (SLA) over a considerably wide range of bucket sizes and discard thresholds in the QoS control mechanism.
Vleeschauwer, D De and Moffaert, A. Van and Büchli, M.J.C. and Janssen, J. and Petit, G.H. and Steyaert, B. and Bruneel, H.
Determining the tolerable load generated by a set of packet-based phones on a multiplexing node
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{DeVleeschauwer2001433,
title = { Determining the tolerable load generated by a set of packet-based phones on a multiplexing node },
year = { 2001 },
author = { Vleeschauwer, D De and Moffaert, A. Van and Büchli, M.J.C. and Janssen, J. and Petit, G.H. and Steyaert, B. and Bruneel, H. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 433 - 444 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80141-4 }
}
Abstract: To determine the voice load that can be supported by a packet-based node, we study the MMBP/D/1 model. Using this load the number of phones that can be supported by that node is calculated. We investigate the case of homogeneous and heterogeneous traffic and phones with and without silence suppression, and study the impact of the link rate, the activity grade and the codec bit rate. We also compare the number of phones that can be supported by the node according to the MMBP/D/1 model with the number of phones that can be supported according to the M/D/1 model.
da Fonseca, Nelson L.S. and Rubinsztejn, Hana K.
Dimensioning the capacity of interactive video servers
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{daFonseca2001383,
title = { Dimensioning the capacity of interactive video servers },
year = { 2001 },
author = { da Fonseca, Nelson L.S. and Rubinsztejn, Hana K. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 383 - 394 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80137-2 }
}
Abstract: To reduce the huge bandwidth demand of video-on-demand, techniques based on multicast have been considered for the dep?oyment of such services in large scale. Interactiveness, a desirable feature of video services, encompasses the capability of performing \VCR\ operations. Whenever a viewer issues a \VCR\ operation, his/her video stream unsynchronizes with the stream of his/her multicast group. This paper introduces an approach to determine the number of video channels needed to support interactiveness. Moreover, the performance of interactive systems with reserved pool of channels for the support of \VCR\ operations, as well systems with batching and piggybacking are analysed.
Christensen, Thomas Kaare and Nielsen, Bo Friis and Iversen, Villy B?k
Distribution of channel holding times in cellular communication systems
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Christensen2001471,
title = { Distribution of channel holding times in cellular communication systems },
year = { 2001 },
author = { Christensen, Thomas Kaare and Nielsen, Bo Friis and Iversen, Villy B?k },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 471 - 480 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80144-X }
}
Abstract: In this paper we derive the channel holding time when both cell residence time and call holding times are phase-type distributions. Also the distribution of the number of hand-overs and the conditional channel holding time distributions are derived. The channel holding times are of importance in performance evaluation and simulation of cellular mobile communication systems.
Emstad, Peder J. and Osland, Per-Oddvar
Dynamic load balancing in a two-server system
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Emstad2001581,
title = { Dynamic load balancing in a two-server system },
year = { 2001 },
author = { Emstad, Peder J. and Osland, Per-Oddvar },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 581 - 592 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80153-0 }
}
Abstract: In communication networks servers are duplicated for dependability reasons. To utilize then efficiently a controller distributes the load between them in a best possible way. In this paper we study dynamic load balancing based on the states of the servers at the start of the load balancing interval. The servers are modeled as M/M/1/n queuing systems. The transient loss of this system is found using renewal type of argument. This result is used for dynamic load balancing to minimize the sum of lost tasks over the load balancing interval. The result is compared with ideal load balancing and weighted load balancing of tasks to the two servers.
Zimmermann, S. and Hamann, T. and Killat, U.
Dynamics of different congestion pricing strategies
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Zimmermann20011187,
title = { Dynamics of different congestion pricing strategies },
year = { 2001 },
author = { Zimmermann, S. and Hamann, T. and Killat, U. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 1187 - 1200 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80202-X }
}
Abstract: Congestion pricing is a strategy based on a mathematical framework from optimization theory and economics. A congestion measure (shadow price) is computed at each network node and fed back to the sources. The sources adapt their rates according to a utility function and the aggregate price information. It can be shown that this will lead to a social optimum of the entire network while maintaining low queue sizes and high utilization. This work focuses on the implementation issues such as price feedback strategies and scalability of the concept. Single and multiple bit marking strategies are compared to high-resolution explicit price feedback in an extended network scenario. Furthermore, different algorithms describing the sources' rate adaptation are evaluated.
Reichl, Peter and Stiller, Burkhard
Edge pricing in space and time: Theoretical and practical aspects of the cumulus pricing scheme
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Reichl20011151,
title = { Edge pricing in space and time: Theoretical and practical aspects of the cumulus pricing scheme },
year = { 2001 },
author = { Reichl, Peter and Stiller, Burkhard },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 1151 - 1162 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80199-2 }
}
Abstract: In the context of the rapidly increasing commercialization of the Internet, the design of suitable pricing models for packet-based networks becomes a necessity for offering approaches for financially-driven sharing of global resources between multiple customers with varying requirements. Addressing such differentiated services both from a customer and a provider point of view has lead to the Cumulus Pricing Scheme (CPS) framework as established recently. In this paper, important aspects of \CPS\ are investigated in further detail. Together with a number of simulation results, these investigations demonstrate that \CPS\ is an excellent example for a simple, transparent, market-managed, and feasible Internet pricing scheme that eventually extends the well-known spatial edge pricing paradigm into the time dimension.
Yang, Jiangbin and Lambadaris, Ioannis
Effective bandwidths for \TES\ processes
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Yang2001569,
title = { Effective bandwidths for \TES\ processes },
year = { 2001 },
author = { Yang, Jiangbin and Lambadaris, Ioannis },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 569 - 580 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80152-9 }
}
Abstract: In this paper, we derive the effective bandwidth functions of \TES\ (Transform-Expand-Sample) processes. These processes are particularly important for modeling of video and other multimedia traffic patterns found in broadband networks. Such processes are highly autocorrelated and have general marginal distributions. To examine the impact of autocorrelation on effective bandwidths and illustrate the computational procedure, we compute the effective bandwidth functions of some specific \TES\ processes with different autocorrelation structures. We simulate some queues with \TES\ processes as input, numerically study the exponential decay of their queue length tail probabilities, and show how well the derived effective bandwidth functions can characterize the exponential decay rates.
Hartmann, Harro L.
Engineering and routing of connection-oriented multirate reference networks
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Hartmann2001395,
title = { Engineering and routing of connection-oriented multirate reference networks },
year = { 2001 },
author = { Hartmann, Harro L. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 395 - 408 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80138-4 }
}
Abstract: This contribution proceeds to connection-oriented networks by combining full fairness multi-services bufferless switching and nonhierarchical routing (NHR). The near explicit solution of the recently elaborated first order recurrence equation for multirate loss systems is justified to provide a decomposition of the huge state space into two near independent areas which are subject to full fairness bandwidth reservation and aggregated state reservation in the access and subnetwork areas, respectively. Thus, the former supports connection admission control and the latter admits a near independent engineering and routing. In view of many particular solutions the focus remains devoted to reference networks (RN) which are symmetric but admit asymmetric demand pairs. Nevertheless a link by link capacity and flow assignment reduces to an evolutionary networking supported by approximate rules and accurate performing operators. For example the admissable \STM\ 1 load in Erl bitrate units subject to a unique backbone network call level \GOS\ of 0.1% typically saves 5% of capacity subject to \NHR\ with one alternative route only. In contrast to this, the completely uncontrolled \RN\ yields service class blocking until 5% subject to the same capacity at the engineered load and a \CBR\ range until 30 bitrate units.
Carpenter, Tami and Krishnan, K.R. and Shallcross, David
Enhancements to traffic engineering for multi protocol label switching
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Carpenter2001529,
title = { Enhancements to traffic engineering for multi protocol label switching },
year = { 2001 },
author = { Carpenter, Tami and Krishnan, K.R. and Shallcross, David },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 529 - 540 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80149-9 }
}
Abstract: Multi Protocol Label Switching (MPLS) is a flexible routing mechanism based on the assignment of traffic flows to complete end-to-end paths, and can be used to reduce congestion in an \IP\ network by means of traffic engineering, the intelligent matching of flows to capacities of paths. For the basic \MPLS\ traffic engineering problem, Telcordia has proposed an efficient algorithm, using a Linear Program to generate traffic paths and a Non-Linear Program to allocate flows to the paths. In this paper, we present three enhancements to the algorithm, for additional capabilities to respond to different operational requirements: (a) expanding the set of paths to increase the robustness of the network to uncertainties in the offered load, (b) limiting the path-selection to the choice of just a single explicit path for each node-pair, when such a restriction is made for reasons of administrative simplicity, and (c) restricting admission to a reduced set of demands, when the existing network capacity is inadequate to carry all the offered demands. We present illustrative examples to demonstrate these enhanced features of \MPLS\ traffic engineering.
Ziviani, A. and de Rezende, J.F. and Duarte, O.C.M.B. and Fdida, S.
Evaluating voice traffic in a differentiated services environment
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Ziviani2001907,
title = { Evaluating voice traffic in a differentiated services environment },
year = { 2001 },
author = { Ziviani, A. and de Rezende, J.F. and Duarte, O.C.M.B. and Fdida, S. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 907 - 918 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80179-7 }
}
Abstract: This paper evaluates the performance achieved by voice traffic when using Expedited Forwarding (EF) and Assured Forwarding (AF) schemes in a Differentiated Services (DS) environment. The mutual influence of the two schemes is evaluated: (i) when a controlled amount of voice bursts are allowed into a \DS\ domain; (ii) in the presence of an increasing number of voice flows handled by EF; and (iii) for different packet sizes of the best-effort traffic. Results show that allowing controlled \EF\ traffic bursts into a \DS\ domain does not significantly increase the delay and jitter of the \AF\ traffic if idle periods from \EF\ traffic do not become scarce. Results also show that different packet sizes of the best-effort traffic exert a stronger influence on the delay of \AF\ packets than on the delay of \EF\ packets.
Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A.
Executive Committee
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[BibSonomy]
@incollection{tagkey2001ix,
title = { Executive Committee },
year = { 2001 },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { ix - x },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80104-9 }
}
Olivier, P. and Benameur, N.
Flow level \IP\ traffic characterization
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Olivier200125,
title = { Flow level \IP\ traffic characterization },
year = { 2001 },
author = { Olivier, P. and Benameur, N. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 25 - 36 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80108-6 }
}
Abstract: In this paper we perform a detailed statistical analysis of \IP\ traffic at flow level, based on data traces collected on the France Telecom wide area \IP\ network. We particularly focus on the assessment of assumptions commonly used in flow level performance models, i. e. Poisson flow arrival process, both for \UDP\ and \TCP\ traffic. We first discuss the concept of flow and present a method to estimate an adequate Time Out value to distinguish different flows within a traffic stream. To model the flow arrival process, we find that Gamma and Weibull distributions provide excellent fits to the empirical flow inter-arrival time distributions. In addition, a fairly low level of correlation is detected between successive flow arrivals. Flow size distributions, though more difficult to model due to their composite aspect, show a very well marked heavy-tailed character of the Pareto type. We found that these results were very consistent among all the data traces we analyzed.
Laskin, N. and Lambadaris, I. and Harmantzis, F.C. and Devetsikiotis, M.
Fractional lévy motion and its application to network traffic modeling
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Laskin2001457,
title = { Fractional lévy motion and its application to network traffic modeling },
year = { 2001 },
author = { Laskin, N. and Lambadaris, I. and Harmantzis, F.C. and Devetsikiotis, M. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 457 - 470 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80143-8 }
}
Abstract: We introduce a general non-Gaussian, self-similar, stochastic process called the fractional Lévy motion (fLm). We formally expand the family of traditional fractal network traffic models, by including the fLm process. The main findings are the probability density function of the fLm process, several scaling results related to a single-server infinite buffer queue fed by fLm traffic, e.g., scaling of the queue length, and its distribution, scaling of the queuing delay when independent fLm streams are multiplexed, and an asymptotic lower bound for the probability of overflow (decreases hyperbolically as a function of the buffer size).
Urvoy-Keller, Guillaume and Hébuterne, Gérard
Guaranteeing deterministic QoS in a multipoint-to-point network
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{UrvoyKeller2001943,
title = { Guaranteeing deterministic QoS in a multipoint-to-point network },
year = { 2001 },
author = { Urvoy-Keller, Guillaume and Hébuterne, Gérard },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 943 - 954 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80182-7 }
}
Abstract: The need to guarantee QoS to multimedia sources leads to a convergence between the routing and forwarding functions in the Internet. \MPLS\ provides a solution to this integration. In the context of MPLS, multipoint-to-point (m-t-p) architectures appear as key architectures since they provide a cheaper way to connect edge nodes than point-to-point connections, in an Internet Service Provider backbone. Th m-t-p architecture has been mainly studied for its ability to balance load. In the present work, we go a step further and evaluate two traffic management schemes that provide deterministic QoS guarantees for multimedia constrained sources in a m-t-p network. The first scheme is based on the \FIFO\ policy and manages the multimedia sources as variable bit rate sources. The second scheme shapes the sources before they enter the network so as to manage them as constant bit rate sources in the network. We prove that the second scheme performs better in terms of scalability and resource requirements.
de Miranda, M.N. and Lima, R.N.B. and Pedroza, A.C.P. and Filho, A.C. Mesquita
HW/SW codesign of protocols based on performance optimization using genetic algorithms
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{deMiranda2001259,
title = { HW/SW codesign of protocols based on performance optimization using genetic algorithms },
year = { 2001 },
author = { de Miranda, M.N. and Lima, R.N.B. and Pedroza, A.C.P. and Filho, A.C. Mesquita },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 259 - 269 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80127-X }
}
Abstract: A design-to-hardware methodology applied to the synthesis of communication protocols based on performance analysis techniques and genetic algorithms is presented. The process requires a choice between the tasks to be implemented in hardware and those to be implemented in software, i.e., the selection of the best HW/SW partition. The proposed methodology uses a genetic algorithm to optimize an error function defined by the required performance and the implementation cost of the protocol. The protocol performance is analyzed by a modelling environment called Tangram-II. The cost of the hardware corresponding to a given implementation is calculated by the Synopsys and \ALTERA\ tools. The methodology is intended as a tool to help protocol designers to select the best performance/cost compromise.
Fekete, A. and Vattay, G. and Veres, A.
Improving the law for single and parallel \TCP\ flows
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Fekete2001869,
title = { Improving the law for single and parallel \TCP\ flows },
year = { 2001 },
author = { Fekete, A. and Vattay, G. and Veres, A. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 869 - 882 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80176-1 }
}
Abstract: In this paper we analyzed the congestion window distributions in certain basic cases where parallel \TCP\ flows share the networking environment. We derived new analytical distributions for the distribution of generic congestion window values in ŁAN\ and \WAN\ situations. Our distributions fitted well to the distributions we got from direct simulations. We improved the 1 / p rule so that it describes now correctly the whole p=0.0010.05 packet loss range. We used the mean field approximation for situations where exact calculations were not possible. Surprisingly, in these situations the results are almost as good as in the exactly solvable cases. We think, that the main virtue of our work is the new level of precision of the results.
Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A.
Index of authors
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[BibSonomy]
@incollection{tagkey20011209,
title = { Index of authors },
year = { 2001 },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 1209 - 1211 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80204-3 }
}
Bonald, T. and Proutière, A. and Régnié, G. and Roberts, J.W.
Insensitivity results in statistical bandwidth sharing
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Bonald2001125,
title = { Insensitivity results in statistical bandwidth sharing },
year = { 2001 },
author = { Bonald, T. and Proutière, A. and Régnié, G. and Roberts, J.W. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 125 - 136 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80116-5 }
}
Abstract: We show that statistical bandwidth sharing performance under an assumption of perfect fairness is insensitive to both the flow size distribution and the flow arrival process, given only that session arrivals are Poisson. Observed self-similarity phenomena at packet and flow levels can be explained by the interaction between high level traffic characteristics and the way link bandwidth is shared. We show in particular that long range dependence in the flow arrival process is due to the heavy-tailed nature of the distribution of the number of flows per session.
Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A.
List of reviewers
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[BibSonomy]
@incollection{tagkey2001xi,
title = { List of reviewers },
year = { 2001 },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { xi - xii },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80105-0 }
}
Gall, Pierre Le
Local queue in single link packet switched networks with variable packet lengths
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{LeGall20011139,
title = { Local queue in single link packet switched networks with variable packet lengths },
year = { 2001 },
author = { Gall, Pierre Le },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 1139 - 1150 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80198-0 }
}
Abstract: To decrease the packet rejection rate we give new rules of buffer dimensioning in single link packet switched networks when packet lengths are highly varying, needing the use of a new double faced traffic model. For a low bit rate and a possible high rejection rate, the tandem queue effect with the derived agglutination phenomenon can appear in case of upstream link overload, where packets (including premature departures) become indistinguishable. The buffer capacity has to be higher than the maximum agglutination size, depending on the packet length variation but not on the load (case of Intelligent Networks). In case of broadband transmission and a wanted very low packet rejection rate (case of IP-based Networks), the upstream correlations disappear with premature departures which unveil the classical local M/G/1 queue (without any existence of distinguishable local traffic sources) leading to overdimension the buffer in a great extent at heavy load, due to the increasing size of the busy period.
Chahed, T. and Hébuterne, G. and Pujolle, G.
*Mapping of performance metrics between intserv and \ATM*
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Chahed2001185,
title = { Mapping of performance metrics between intserv and \ATM\ },
year = { 2001 },
author = { Chahed, T. and Hébuterne, G. and Pujolle, G. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 185 - 196 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80121-9 }
}
Abstract: End-to-end QoS requires mapping of performance metrics between sub-networks of the end-to-end system. In this work, we map loss and delay between \IP\ Integrated Services (intserv) and ATM, using deterministic service curves. First, we recall our method for mapping of backlog, loss and delay between a single \IP\ flow and ATM. Second, we extend our mapping method to the case of the three intserv classes served by an \ATM\ switch implementing a priority-based discriminatory discipline. Third, we focus on cases of non-conformant traffic and congested systems. Extensive numerical simulations yield qualitative as well as quantitative mapping of loss and delay between intserv and ATM.
Charzinski, Joachim
Measured T̋TP\ performance and fun factors
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Charzinski20011063,
title = { Measured T̋TP\ performance and fun factors },
year = { 2001 },
author = { Charzinski, Joachim },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 1063 - 1074 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80192-X }
}
Abstract: Recent work has emphasized the importance of delay and rate components in the user perceived performance of elastic Internet applications, especially Web browsing. Fun factors have been previously introduced [1] to describe the obtained performance with respect to the maximum possible performance on a scale of zero (no fun) to one (maximum fun). In this paper, several options for defining such fun factors using delay and rate components are presented. In order to better understand the influence of delays and transmission rates, two extensive traffic traces have been evaluated (i) to yield information about the way browsers use persistent and parallel HTTP/TCP connections to access Web servers and (ii) to serve as an example for quantifying quality of service by fun factors.
Fredj, S. Ben and Oueslati-Boulahia, S. and Roberts, J.W.
Measurement-based admission control for elastic traffic
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{BenFredj2001161,
title = { Measurement-based admission control for elastic traffic },
year = { 2001 },
author = { Fredj, S. Ben and Oueslati-Boulahia, S. and Roberts, J.W. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 161 - 172 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80119-0 }
}
Abstract: We propose and evaluate an implicit measurement-based scheme for elastic flow admission control in the Internet. We first discuss the nature of \IP\ traffic and present a simple fluid flow model of statistical bandwidth sharing on an isolated bottleneck link. This model is used to guide our choice of admission control algorithms. The main contribution of the paper is to demonstrate by means of detailed packet level simulations that the proposed scheme is efficient and perfectly feasible.
Dziong, Zbigniew and Bharath, Ramana and Samadi, Behrokh
Model for location mobility area design
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Dziong200149,
title = { Model for location mobility area design },
year = { 2001 },
author = { Dziong, Zbigniew and Bharath, Ramana and Samadi, Behrokh },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 49 - 60 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80110-4 }
}
Abstract: The mobility model described in the paper is used in \GLAD\ which is a tool developed for the design of location areas in \GSM\ networks. The objective of the design is to balance the load on different system resources, including processors, in order to maximize the capacity of the system. In this paper we give a general overview of GLAD, but the focus is on the mobility model which constitutes a critical element of this tool although the model can be applied to any type of wireless networks that uses the location area concept. The proposed mobility model allows us to approximate the number of mobiles crossing the boundary between two neighbouring cells. This information is needed to calculate the number of location updates. The calculation of the mobile flows between the neighbouring cells is based on total number of handovers in cells (measured or assumed) and information available from the network design stage such as cell coverage, road and subscriber density maps. The proposed mathematical model for calculation of the mobile flows between the neighbouring cells is based on the best fit approach. The influence of the location area design on the network resource utilization is illustrated using a realistic example.
Ohsaki, Hiroyuki and Murata, Masayuki and Miyahara, Hideo
Modeling end-to-end packet delay dynamics of the internet using system identification
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Ohsaki20011027,
title = { Modeling end-to-end packet delay dynamics of the internet using system identification },
year = { 2001 },
author = { Ohsaki, Hiroyuki and Murata, Masayuki and Miyahara, Hideo },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 1027 - 1038 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80189-X }
}
Abstract: Understanding the end-to-end packet delay dynamics of the Internet is of crucial importance since (1) it directly affects the QoS (Quality of Services) of realtime applications, and (2) it enables us to design an efficient congestion control mechanism for both realtime and non-realtime applications In this paper, we propose a novel approach for modeling the end-to-end packet delay dynamics of the Internet. The key idea of our approach is treating the network, seen by specific source and destination hosts, as a black-box, and modeling the end-to-end packet delay dynamics using system identification, having been throughly used in the field of control engineering. The end-to-end packet delay dynamics is modeled as a \SISO\ (Single-Input and Single-Output) system. The input to the system is a packet inter-departure time from the source host, and the output from the system is an end-to-end packet delay variation measured by the destination host. In this paper, the \ARX\ (Auto-Regressive eXogenous) model is used and its coefficients are determined using system identification. Several topics such as model validation and selection of the orders of the \ARX\ model are also discussed. We show that the \ARX\ model accurately captures the end-to-end packet delay dynamics if the orders of the \ARX\ model are appropriately chosen. We also show that the effect of other \UDP\ and \TCP\ traffic can be modeled by white noise by using the end-to-end packet delay variation.
Dupuis, Alain and Guillemin, Fabrice and Robert, Philippe
Modeling max-min fairness for elastic flows in telecommunication networks
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Dupuis200187,
title = { Modeling max-min fairness for elastic flows in telecommunication networks },
year = { 2001 },
author = { Dupuis, Alain and Guillemin, Fabrice and Robert, Philippe },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 87 - 98 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80113-X }
}
Abstract: An analytical model is developed in this paper to study max-min fairness in telecommunication networks. This bandwidth sharing principle is very popular in packet networks and is used to allocate bandwidth to elastic flows sharing the transmission capacity of the links of a network. The model considered in the present paper is a linear single link network, on which originating points of data flows appear as a Poisson process; the length of a data flow is exponential with unit mean and the link transmission capacity is taken as unity. While the definition of the max-min fair share is algorithmically clear, any analytical computation rapidly proves intractable. To overcome this technical difficulty, we develop simple heuristic approximations. It turns out that the obtained formulae yield a satisfactory approximation of the max-min fair share. Moreover, one approximation proves fairly accurate when considering the amount of unused bandwidth due to max-min fairness.
Heyman, Daniel and Lucantoni, David
Modeling multiple \IP\ traffic streams with rate limits
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Heyman2001445,
title = { Modeling multiple \IP\ traffic streams with rate limits },
year = { 2001 },
author = { Heyman, Daniel and Lucantoni, David },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 445 - 456 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80142-6 }
}
Abstract: We start with the premise, and provide evidence that it's valid. that a Markov modulated Poisson process (MMPP) is a good model for Internet traffic at the packet/byte level. We present an algorithm to estimate the size, and parameters, of a discrete \MMPP\ from a data trace. This algorithm requires only two passes through the data. In tandem-network queueing models, the input to a downstream queue is the output from an upstream queue, so the arrival rate is limited by the rate of the upstream queue. We show how to modify the \MMPP\ describing the arrivals to the upstream queue to approximate this effect. To extend this idea to networks that aren't tandem, we show how to approximate the superposition of \MMPPs\ describing the arrivals to the upstream queue to approximate this effect. To extend this idea to networks that arent's tandem, we show how to approximate the superposition of \MMPPs\ without encountering the state-space explosion that occurs in exact computations. Numerical examples that demonstrate the accuracy of these methods are given. We also present a method to convert our estimated discrete \MMPP\ to a continuous-time MMPP, which is used as the arrival process in a matrix-analytic queueing model for performance prediction.
Park, Kihong and Tuan, Tsunyi
Multiple time scale TCP: Harnessing proactivity in self-similar burstiness
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Park2001421,
title = { Multiple time scale TCP: Harnessing proactivity in self-similar burstiness },
year = { 2001 },
author = { Park, Kihong and Tuan, Tsunyi },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 421 - 432 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80140-2 }
}
Abstract: Measurements of network traffic have shown that self-similarity is an ubiquitous phenomenon present across diverse network environments. In previous work, we studied the feasibility of exploiting long-range correlation structure in self-similar traffic in the context of rate-based congestion control. In this work, we extend the multiple time scale control framework to window-based congestion control, in particular, TCP. This is performed by interfacing \TCP\ with a large time scale control module which adjusts the aggressiveness of bandwidth consumption behavior exhibited by \TCP\ as a function of large time scale network state, i.e., information that exceeds the time horizon of the feedback loop as determined by RTT. How to effectively utilize such informationdue to its probabilistic nature, dispersion over multiple time scales, and affection on top of existing window-based congestion controlsis a nontrivial problem. We define a modular extension of TCPa function call with a simple interfacethat applies to various flavours of \TCP\ (e.g., Tahoe, Reno, Vegas) and show that it significantly improves throughput performance. We show that multiple time scale \TCP\ endows the underlying feedback control with proactivity by bridging the uncertainty gap associated with reactive controls which is exacerbated by the high delay-bandwidth product in broadband WANs. By harnessing large time scale correlation structure in network traffic, we are able to mitigate the reactive cost of TCP's feedback congestion control.
Jelenkovic, Predrag and Momcilovic, Petar
Network multiplexer with generalized processor sharing and heavy-tailed on-off flows
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Jelenkovic2001719,
title = { Network multiplexer with generalized processor sharing and heavy-tailed on-off flows },
year = { 2001 },
author = { Jelenkovic, Predrag and Momcilovic, Petar },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 719 - 730 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80164-5 }
}
Abstract: We consider a set of fluid On-Off flows that share a common server of capacity c and a finite buffer B. The server capacity is divided using Generalized Processor Sharing scheduling discipline. Each flow has a minimum service rate guarantee that exceeds its long term average demand ?i. The buffer sharing is unrestricted as long as there is available space; if the buffer is full, the necessary amount of fluid from the most demanding flows is discarded. When the On periods are heavy-tailed, we show that the loss rate of a particular flow i is asymptotically equal to the loss rate in a reduced system with capacity c-Sj?i?j and buffer B, where this flow is served in isolation. In particular, each flow perceives to have the whole buffer B to itself. This insight provides a new guideline for efficiently engineering differentiated quality of service in integrated multimedia networks.
Roughan, Matthew and Erramilli, Ashok and Veitch, Darryl
Network performance for \TCP\ networks Part I: Persistent sources
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Roughan2001857,
title = { Network performance for \TCP\ networks Part I: Persistent sources },
year = { 2001 },
author = { Roughan, Matthew and Erramilli, Ashok and Veitch, Darryl },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 857 - 868 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80175-X }
}
Abstract: A method is presented which can form the basis for capacity planning for \TCP\ traffic from persistent sources. The method estimates the rates of flows across an arbitrary network as determined by the \TCP\ flow control, and can therefore estimate the performance of a \TCP\ network. The method is simple, fast and provides good 1st order estimates with significant robustness. The method is extendible to a-persistent sources.
Dolzer, K. and Gauger, C.
On burst assembly in optical burst switching networksA performance evaluation of just-enough-time
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Dolzer2001149,
title = { On burst assembly in optical burst switching networksA performance evaluation of just-enough-time },
year = { 2001 },
author = { Dolzer, K. and Gauger, C. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 149 - 160 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80118-9 }
}
Abstract: On the way towards an architecture for a new QoS-supporting and scalable Internet, the IP-over-photonics approach seems to be very promising. One possible solution in this domain is optical burst switching (OBS), a concept combining advantages of optical circuit and packet switching. After an introduction to ØBS\ as well as the reservation mechanism Just-Enough-Time (JET) we present an approximative analysis of the burst loss probability in an ØBS\ node for an arbitrary number of service classes. Based on analytical and simulation results, we show the impact of traffic characteristics on service differentiation in a single node. Finally, we investigate service differentiation for various parameters in an ØBS\ network scenario.
Malouch, Naceur M. and Liu, Zhen
On steady state analysis of \TCP\ in networks with differentiated services
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Malouch2001693,
title = { On steady state analysis of \TCP\ in networks with differentiated services },
year = { 2001 },
author = { Malouch, Naceur M. and Liu, Zhen },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 693 - 704 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80162-1 }
}
Abstract: This paper presents analytical results on the throughput of \TCP\ in networks with differentiated services. A token bucket mechanism is used at edge routers to mark the packets generated by the \TCP\ source. Core routers use the Random Early Detection (RED) to drop packets belonging to different classes. A general loss model is considered where the packet discarding functions of different classes of core routers are arbitrary. Analyses of the steady-state window size and the throughput of a bulky \TCP\ connection are provided for such networks with differentiated services. The expressions of the congestion window allow us to better understand the effect of marking packets in TCP. Simulation results are also shown to validate these analytical formulae. The presentation is focused on the case of two classes (in and out packets). However, the same method applies to the general case with more than two classes of packets.
Cavendish, D. and Goudreau, M. and Ishii, A.
On the fairness of scheduling algorithms for input-queued switches
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Cavendish2001829,
title = { On the fairness of scheduling algorithms for input-queued switches },
year = { 2001 },
author = { Cavendish, D. and Goudreau, M. and Ishii, A. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 829 - 841 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80173-6 }
}
Abstract: Many schedulers for Virtual Output Queue (VOQ) architectures have been designed to provide reasonable bandwidth at high speed while preventing the starvation of any queue. However, it is not clear to what extent these schedulers incorporate both fair sharing of resources and high utilization. In this paper, we undertake the first comprehensive experimental evaluation of the fairness of several \VOQ\ schedulers. Formalizing the problem by applying a max-min fairness criterion, we discover that the schedulers are frequently unfair. To improve the fairness of \VOQ\ schedulers, we propose a simple and inexpensive throttling mechanism that can be used in conjunction with any scheduler. We demonstrate that under many circumstances the throttling mechanism can substantially improve system fairness.
Sridharan, A. and Bhattacharyya, S. and Diot, C. and Guérin, R. and Jetcheva, J. and Taft, N.
On the impact of aggregation on the performance of traffic aware routing
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Sridharan2001111,
title = { On the impact of aggregation on the performance of traffic aware routing },
year = { 2001 },
author = { Sridharan, A. and Bhattacharyya, S. and Diot, C. and Guérin, R. and Jetcheva, J. and Taft, N. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 111 - 123 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80115-3 }
}
Abstract: This paper investigates the impact of traffic aggregation on the performance of routing algorithms that incorporate traffic information. We focus on two issues. Firstly, we explore the relationship between average network performance and the coarseness (granularity) of traffic splitting across routes. Specifically, we are interested in how average network performance improves with our ability to distribute traffic arbitrarily across multiple paths. Secondly, we shift our attention from average to short-term performance, with again a focus on the impact of traffic granularity. In particular, we explore the relation between the level of traffic aggregation and its variability, which directly affects short-term routing performance. Our investigation relies on traffic traces collected from an operational network, and its results provide insight into the cost-performance trade-off associated with deploying traffic aware routing protocols.
Schwefel, H.-P. and Lipsky, L. and Jobmann, M.
On the necessity of transient performance analysis in telecommunication networks
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Schwefel20011087,
title = { On the necessity of transient performance analysis in telecommunication networks },
year = { 2001 },
author = { Schwefel, H.-P. and Lipsky, L. and Jobmann, M. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 1087 - 1099 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80194-3 }
}
Abstract: Most analytic models of telecommunication networks are based on steady-state methods. This paper discusses potential drawbacks of steady-state parameters, in particular of the steady-state buffer-overflow or cell-loss probability when used as quality of service (QoS) criteria. The importance of transient performance analysis is demonstrated for long-range dependent (multiplexed) ON/OFF traffic. A transient parameter pair is proposed as replacement for the steady-state overflow or loss probabilities. The in-depth discussion of the behavior of those transient parameters reveals surprising results that allow for characterization and understanding of the fluctuations that are being observed in actual network behavior under traffic loads with long-range dependent properties.
ke Arvidsson and Roughan, Matthew and Rydén, Tobias
On the origins of long-range dependence in \TCP\ traffic
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Arvidsson2001895,
title = { On the origins of long-range dependence in \TCP\ traffic },
year = { 2001 },
author = { ke Arvidsson and Roughan, Matthew and Rydén, Tobias },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 895 - 906 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80178-5 }
}
Abstract: Since the discovery of self-similarity and Long-Range Dependence (LRD) in data traffic there has been a great deal of research into both its ramifications, and its origins. For instance there are now many studies of the effect of ŁRD\ on network performance. However the majority of these studies are open loop in the sense that they use the data measurements to construct a model which has the ŁRD\ property, and then they use this model as an arrival process for a queuing system. This methodology is clearly suspect when applied to \TCP\ traffic as this traffic is carried over a window flow control which limits its rate when congestion is experienced. Clearly, a closed-loop model that incorporates feedback is required to model such a system. On the other side of the coin, the origin of ŁRD\ in traffic has been ascribed to the heavy-tailed nature of the carried traffic. However, once again open-loop models such as the superposition of On/Off sources have been used to produce ŁRD\ traffic. Even when the observed traffic shows heavy-tailed On/Off behavior, a simple On/Off model which does not contain feedback shold not be used to explain the occurrence of LRD. This paper uses a very simple construction which includes the idea of feedback, and thus provides a more rigorous explanation for why ŁRD\ is seen even when there are flow controls involved.
Mathar, R. and Remiche, M.-A.
On the outage probability in \CDMA\ cellular networks with adaptive antennas
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Mathar2001481,
title = { On the outage probability in \CDMA\ cellular networks with adaptive antennas },
year = { 2001 },
author = { Mathar, R. and Remiche, M.-A. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 481 - 492 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80145-1 }
}
Abstract: We assume that a base transmitter station (BTS) in a code division multiple access (CDMA) mobile network is equipped with a smart antenna. Each transmitting user is tracked by a beam of fixed width centered at the user. Mobiles are assumed to apply perfect power control such that each is received with the same unit power at the BTS. Under these assumptions outage occurs if the number of overlapping beams exceeds a certain threshold. The according probability is calculated under different random traffic models. Particularly homogeneous Poisson fields and isotropic planar phase processes are considered. The investigations are strongly related to the first hitting time in a M/D/8 queue as well as object recognition for a photon detector.
Dube, Parijat and Altman, Eitan
On the workload process in a fluid queue with bursty input and selective discarding
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Dube2001757,
title = { On the workload process in a fluid queue with bursty input and selective discarding },
year = { 2001 },
author = { Dube, Parijat and Altman, Eitan },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 757 - 768 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80167-0 }
}
Abstract: In this paper we analyse a finite buffer fluid queue with an on-off Markov Modulated Fluid Process (MMFP) as the arrival process. We call each on-period of the arrival process a message/burst. The queue incorporates a threshold message discarding policy. We work within the framework of Poisson Counter Driven Stochastic Differential equations and obtain the moment generating function and hence the probability density function of the stationary workload process. We then comment on the stability of this fluid queue.
Yang, Jiangbin and Devetsikiotis, Mihail
On-line estimation, network design and performance analysis with effective bandwidths
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Yang2001347,
title = { On-line estimation, network design and performance analysis with effective bandwidths },
year = { 2001 },
author = { Yang, Jiangbin and Devetsikiotis, Mihail },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 347 - 358 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80134-7 }
}
Abstract: Effective bandwidth is a tool for characterizing the queueing behavior of a traffic stream when it is fed to a queue. In this paper, we propose a method for on-line recursive estimation of effective bandwidths, a formula relating average queueing delay to the space parameter in effective bandwidths, and a network design scheme using effective bandwidths for bandwidth allocation and buffer dimensioning under quality of service (QoS) requirements on both average queueing delay and packet loss probability. We conduct experiments in a simulation testbed, and study the performance of our proposed network design scheme with both analytical and estimated effective bandwidths. Results show that QoS requirement with respect to average queueing delay can be roughly satisfied, and that packet loss probability target can be roughly or conservatively met by our design scheme. We also discuss the problems and refinement of effective bandwidths and our design scheme.
Ben-Ameur, W. and Besiktasliyan, S. and Decocq, B.
Optimal dimensioning of a ring
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{BenAmeur2001617,
title = { Optimal dimensioning of a ring },
year = { 2001 },
author = { Ben-Ameur, W. and Besiktasliyan, S. and Decocq, B. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 617 - 628 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80156-6 }
}
Abstract: A ring architecture is of practical interest for a telecommunication operator. It makes it possible to implement automatic protection mechanisms without a substantial increase in cost. This paper deals with the problem of dimensioning a ring a routing its demands such that the total cost of the network is minimized. In a single ring network, the traffic policy has a heavy impact on the cost. Several routing strategies are compared, namely bi-path routing, single-path routing and shortest path routing according to a metric (IP rings). Furthermore, various solutions were introduced to optimize routing and dimensioning: an exact method based on cutting plane algorithms, and a heuristic. Each variant was tested with randomly generated data and some real world networks.
McArdle, Conor and Curran, Thomas
Optimal object placement, load distribution and load control for distributed telecommunication service applications
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{McArdle2001371,
title = { Optimal object placement, load distribution and load control for distributed telecommunication service applications },
year = { 2001 },
author = { McArdle, Conor and Curran, Thomas },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 371 - 382 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80136-0 }
}
Abstract: This paper presents a method for optimising the placement of software objects on network nodes, for multi-service distributed applications. Also addressed are the related problems of optimal distribution of traffic between distributed software object instances and optimal admission control for the network. The object placement problem is formulated as a Mixed Integer Programming (MIP) flow problem. The solution yields the placement of application objects that gives the maximum allowable arrival intensities to the network under the constraints of object installation costs. Given the optimal object placement, a further method is developed for optimising routing between object instances to maximise network revenue when arrival intensities vary over time from the original design point. This problem is formulated as a Linear Programming (LP) problem that is constrained by the solution of the original \MIP\ problem. The solution gives the basis for a load distribution and load control algorithm for the optimised network. An example of a telecommunication service application (Intelligent Network services) executing on a distributed platform is given. The solutions to the example network have been simulated and results are presented in this paper.
Kalyanasundaram, Suresh and Chong, Edwin K.P. and Shroff, Ness B.
Optimal resource allocation in multiclass networks with user-specified utility functions
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Kalyanasundaram20011175,
title = { Optimal resource allocation in multiclass networks with user-specified utility functions },
year = { 2001 },
author = { Kalyanasundaram, Suresh and Chong, Edwin K.P. and Shroff, Ness B. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 1175 - 1186 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80201-8 }
}
Abstract: In this work, we consider the problem of resource allocation in multi-class networks, where users specify the value they attach to obtaining different amounts of resource by means of a utility function. We develop a resource allocation scheme that maximizes the average aggregate utility per unit time. We formulate this resource allocation problem as a Markov decision process. We present numerical results that illustrate that our scheme performs better than the greedy, resource allocation policy. We also discuss the implications of deliberate lying by users about their utility functions and develop a pricing scheme that prevents such lying.
Kar, K. and Sarkar, S. and Tassiulas, L.
Optimization based rate control for multipath sessions
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Kar2001805,
title = { Optimization based rate control for multipath sessions },
year = { 2001 },
author = { Kar, K. and Sarkar, S. and Tassiulas, L. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 805 - 816 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80171-2 }
}
Abstract: In this paper, we consider the rate control problem for multipath sessions with the objective of maximizing the total user (session) utility. This problem provides a framework in which flow control and routing are jointly optimized. We consider two cases of this problem, and develop two different rate control algorithms for these two cases. The first algorithm is an end-to-end rate control algorithm which requires, on the part of the user, explicit knowledge of the paths that the user uses. The second algorithm is a hop-by-hop rate control algorithm which does not require the user to keep track of the paths it uses. Both the algorithms are distributed and do not require the network to know the user utility functions. We analyze the convergence properties of these algorithms, and discuss how they can be implemented in a real network. Both of these algorithms are computationally simple, and have very low communication overhead.
Fodor, Gábor and Malicskó, Gábor and Pióro, Michal and Szymanski, Tomasz
Path optimization for elastic traffic under fairness constraints
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Fodor2001667,
title = { Path optimization for elastic traffic under fairness constraints },
year = { 2001 },
author = { Fodor, Gábor and Malicskó, Gábor and Pióro, Michal and Szymanski, Tomasz },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 667 - 680 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80160-8 }
}
Abstract: We study optimal path selection and bandwidth allocation algorithms for elastic flows under fairness constraints. We assume that traffic demands between origin-destination (O-D) pairs are given and are characterized by a minimum and a maximum bandwidth requirement. We consider the case when between each O-D pair there is a set of admissible paths through which the flows realizing the demand may be routed. (We say that a set of flows realizes a demand associated with an O-D pair, if the sum of the allocated bandwidths of these flows is at least this demand.) The allocation task is thus not only to determine the bandwidth of each flow realizing the demands, but also to identify the specific path for each demand such that a fairness specific utility is maximized. In the max-min fairness case this implies the maximization of the minimum allocated bandwidth, whereas in the proportional fairness case it implies the maximization of a logarithmic utility function. As an interesting (and practically relevant) generalization, we also allow multiple paths to realize a given demand (demand-split). We propose algorithms that solve the respective optimization tasks associated with the popular max-min and proportional fair sharing constraints. We demonstrate the efficiency and usefulness of these algorithms through numerical examples based on the backbone Polish public network. We believe that the results can be used in traffic engineering of networks carrying elastic traffic.
Rakocevic, Veselin and Griffiths, John and Cope, Graham
Performance analysis of bandwidth allocation schemes in multiservice \IP\ networks using utility functions
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Rakocevic2001233,
title = { Performance analysis of bandwidth allocation schemes in multiservice \IP\ networks using utility functions },
year = { 2001 },
author = { Rakocevic, Veselin and Griffiths, John and Cope, Graham },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 233 - 243 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80125-6 }
}
Abstract: The Internet needs to evolve from a single-service data network into the multiservice intelligent network capable of satisfying diverse performance requirements. The way network resources, primarily bandwidth, is shared, is one of the key issues in this evolution. This paper analyses the concept of bandwidth partitioning, in which each link in the network is partitioned into a number of sublinks, each sublink serving a single traffic class. We analyse a new approach to bandwidth partitioning, Dynamic Bandwidth Partitioning. In this scheme bandwidth partitioning is related to the average level of end-user satisfaction with the network performance according to a simple linear control algorithm. The scheme is user-oriented and adaptive, designed to maximise the overall end-user utility. Furthermore, this paper observes a number of bandwidth allocation schemes in the mutliservice Internet environment, and compares their performance by comparing the average connection utilitythe quality of service level which a user of an Internet application derives from the network performance. Our analysis shows that Dynamic Bandwidth Partitioning generates higher overall utility in the multiservice Internet environment than the current best-effort scheme, mainly because it takes account of the quality of service requirements of the real-time Internet traffic.
Leibnitz, Kenji and Krauß, Armin
Performance evaluation of interference and cell loading in \UMTS\ networks
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Leibnitz2001493,
title = { Performance evaluation of interference and cell loading in \UMTS\ networks },
year = { 2001 },
author = { Leibnitz, Kenji and Krauß, Armin },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 493 - 504 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80146-3 }
}
Abstract: The introduction of third generation (3G) wireless systems operating with Wideband Code Division Multiple Access (WCDMA) will offer new data services with bit rates of up to 2 Mbps and varying quality of service requirements in terms of received bit-energy-to-noise ratio. In order to reduce the interference in the cell and thus maximize the capacity \WCDMA\ systems require a tight power control mechanism. In this paper we will present a performance evaluation of the \WCDMA\ uplink power control loops by means of simulation. Our main goal is to investigate the influence of the traffic, given by the spatial user distribution and their data services, on the interference in a cell. We will also show that it is possible to use approximations of the power control loops to evaluate more complex scenarios.
Schüler, J. and Gruhl, S. and Schwabe, T. and Schweigel, M.
Performance improvements for \TCP\ in mobile networks with high packet delay variations
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Schueler2001517,
title = { Performance improvements for \TCP\ in mobile networks with high packet delay variations },
year = { 2001 },
author = { Schüler, J. and Gruhl, S. and Schwabe, T. and Schweigel, M. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 517 - 528 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80148-7 }
}
Abstract: Previous \TCP\ performance investigations for wireless systems focus on \TCP\ throughput degradation due to packet loss on the error-prone wireless link. Since cellular mobile networks like \GPRS\ and \UMTS\ include a strong link layer error protection, using adaptive Forward Error Correction and Automatic Repeat Request schemes, a bad quality of the wireless link does not mainly result in \IP\ packet loss but rather in an additional packet delay. Furthermore \TCP\ congestion control has to deal with hand-offs and temporary link layer disconnections in cellular mobile networks leading to a significant packet delay variation and packet disordering. This paper analyzes the performance of \TCP\ in cellular mobile networks, focusing on the packet delay and disordering problem. We find spurious retransmissions and \TCP\ timeouts being a dominant cause for throughput degradation. Finally we propose an algorithm to filter spurious \TCP\ retransmissions at the Base Station to increase \TCP\ performance and increase overall wireless link capacity.
Ehrlich, W.K. and Hariharan, R. and Reeser, P.K. and van der Mei, R.D.
Performance of Web servers in a distributed computing environment
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Ehrlich2001137,
title = { Performance of Web servers in a distributed computing environment },
year = { 2001 },
author = { Ehrlich, W.K. and Hariharan, R. and Reeser, P.K. and van der Mei, R.D. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 137 - 148 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80117-7 }
}
Abstract: Over the past few years the applicability of Web technology has evolved from standard document retrieval functionality to the ability to provide end-user interfaces in distributed computing environments. Consequently, Web technology is becoming an integral part of the \IT\ infrastructure of service providers, which raises the need to be able to predict and understand the performance capabilities and limitations of Web servers in a distributed computing environment. In this paper, we propose an end-to-end performance model for Web servers engaged in object-oriented distributed computing, including the impact of new features that have not been included in performance models of Web servers before: the object scope, threading model and location. We have implemented the model in a simulation tool. The performance predictions based on the model are shown to match very well with the performance of Web servers measured in a test lab environment.
van der Mei, R.D.
Polling Systems with correlated arrivals
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{vanderMei2001967,
title = { Polling Systems with correlated arrivals },
year = { 2001 },
author = { van der Mei, R.D. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 967 - 978 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80184-0 }
}
Abstract: We study asymmetric cyclic polling models with general mixtures of gated and exhaustive service, with generally distributed service times and switch-over times, and in which batches of customers may arrive simultaneously at the different queues. We present closed-form expressions for the Laplace-Stieljties Transform of the steady-state delay incurred at each of the queues when the load tends to unity (under proper scalings), in a general parameter setting. The results are strikingly simple and show explicity how the distribution of the delay depends on the system parameters, and in particular, on the batch-size distributions and the simultaneity of the batch arrivals. In addition, the exact results lead to simple and fast approximations for the tail probabilities and the moments of the delay in stable polling systems, explicity capturing the impact of the correlation structure in the arrival processes on the delay incurred at each of the queues. Numerical experiments indicate that the approximations are highly accurate for medium and heavily loaded systems.
de Souza, Jorge Moreira and da Fonseca, Nelson L.S. and de Souza e Silva, Edmundo A.
Preface: Teletraffic engineering in the internet era
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[BibSonomy]
@incollection{MoreiradeSouza2001vii,
title = { Preface: Teletraffic engineering in the internet era },
year = { 2001 },
author = { de Souza, Jorge Moreira and da Fonseca, Nelson L.S. and de Souza e Silva, Edmundo A. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { vii - viii },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80103-7 }
}
Pan, Ping and Schulzrinne, Henning
Processing overhead studies in resource reservation protocols
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Pan200113,
title = { Processing overhead studies in resource reservation protocols },
year = { 2001 },
author = { Pan, Ping and Schulzrinne, Henning },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 13 - 24 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80107-4 }
}
Abstract: We study the signaling cost factors from two aspects: reservation retry process (or how to recover from reservation blocking), and one-pass signaling. Through simulation, we discover that the reservation retry mechanism used in \RSVP\ is not only process intensive, but also the reservations are slow to converge. We thus explore several design options that can speed up reservation setup and quickly recover from partial reservations. To gain a better understanding of reservation overhead, we have implemented a lightweight one-pass reservation protocol, YESSIR. We show that with careful implementation and by using some of basic hashing techniques to manage flow states, we can achieve good performance with low processing cost. Our \YESSIR\ implementation can support up to 10,000 flow setups per second (or about 300,000 active flows) on a commodity 700 \MHz\ Pentium PC.
Fernandez, Marcial P. and de C.P. Pedroza, Aloysio and Rezende, José F.
Quality of service in a DiffServ domain using policy-based management
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Fernandez2001919,
title = { Quality of service in a DiffServ domain using policy-based management },
year = { 2001 },
author = { Fernandez, Marcial P. and de C.P. Pedroza, Aloysio and Rezende, José F. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 919 - 930 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80180-3 }
}
Abstract: The Differentiated Services architecture has been proposed to offer quality of service in the Internet. Most works on Diffserv (DS) handles QoS guarantees in a per node basis, which assumes that assuring QoS in a single node also leads to the desired QoS in the entire \DS\ domain. Nevertheless, this is not always true. This paper proposes a framework that offers QoS in a \DS\ domain using Policy-based Management and fuzzy logic techniques. The QoS controller reconfigures all \DS\ nodes according to ingress traffic and domain policies. Policy Based Management is used in this framework to provide QoS in \DS\ domain, controlling heterogeneous equipments of different manufacturers. The performance and functionalities of a prototype are shown by simulation of a voice over \IP\ application.
Athuraliya, S. and Li, V.H. and Low, S.H. and Yin, Q.
REM: Active queue management
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Athuraliya2001817,
title = { REM: Active queue management },
year = { 2001 },
author = { Athuraliya, S. and Li, V.H. and Low, S.H. and Yin, Q. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 817 - 828 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80172-4 }
}
Abstract: \REM\ is an active queue management scheme that measures congestion not by a performance measure such as loss or delay, but by a quantity we call price. Price is computed by each link distributively using local information and is fed back to the sources through packet dropping or marking. This decoupling of congestion and performance measures allows \REM\ to achieve high utilization with negligible delays and buffer overflow regardless of the number of sources. We prove that \REM\ is asymptotically stable and compare its performance with \RED\ using simulations.
Boujelben, Yassine and Girard, André and Gregoire, Jean-Charles
Ring-based ordering for multipoint-to-multipoint communications
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Boujelben2001593,
title = { Ring-based ordering for multipoint-to-multipoint communications },
year = { 2001 },
author = { Boujelben, Yassine and Girard, André and Gregoire, Jean-Charles },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 593 - 604 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80154-2 }
}
Abstract: Multipoint-to-multipoint applications will represent a significant part of added value services for the future Internet, Network and Converged Network service providers. These services need, in addition to reliability and high bandwidth availability, a set of specific requirements such as message ordering. In this paper, we examine two ring-based ordering methods for \IP\ multicasting and show that one of them is significantly better than the other. We give some new mathematical formulations for multicast ring construction that globally maximize the profit of the service provider. We consider two connection approaches: 1) a shared ring in which all accepted multicast groups are connected by a single ring, and 2) specific rings in which each accepted multicast group is connected on a separate ring. We propose in each case an algorithm to compute the optimal ring topology and we show by simulation that the Specific ring approach is more efficient, up to 4 times more, when the network size increases.
Penttinen, Aleksi and Virtamo, Jorma
Robust adaptive capacity allocation algorithm
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Penttinen2001223,
title = { Robust adaptive capacity allocation algorithm },
year = { 2001 },
author = { Penttinen, Aleksi and Virtamo, Jorma },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 223 - 231 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80124-4 }
}
Abstract: We consider the capacity allocation problem arising, e.g. in the capacity management of a \VP\ in an \ATM\ network, where the occupancy of the \VP\ is periodically observed and based on this information new capacity allocation is made for the beginning period. We show that with a simple stochastic allocation policy it is possible, without any knowledge of the intensity of the Poissonian call arrival process, to obtain a long term blocking probability which for any practical purposes has exactly a prescribed constant value. Thus, the algorithm is inherently robust. Moreover, since the algorithm is adaptive in the sense that the achieved blocking probability is practically independent on the arrival intensity, it is plausible that the same blocking probability prevails even when the intensity is a slowly varying function of time.
Li, Chengzhi and Knightly, Edward W.
Schedulability criterion and performance analysis of coordinated schedulers
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Li2001743,
title = { Schedulability criterion and performance analysis of coordinated schedulers },
year = { 2001 },
author = { Li, Chengzhi and Knightly, Edward W. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 743 - 756 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80166-9 }
}
Abstract: Inter-server coordinated scheduling is a mechanism for dowstream nodes to increase or decrease a packet's priority according to the congestion incurred at upstream nodes. In this paper, we derive an end-to-end schedulability condition for a broad class of coordinated schedulers that includes \CJVC\ and CEDF. In contrast to previous approaches, our technique purposely allows flows to violate their local priority indexes while still providing an end-to-end delay bound. We show that under a simple priority assignment scheme, coordinated schedulers can outperform \WFQ\ schedulers, while replacing per-flow scheduling operations with a simple coordination rule. Finally, we illustrate the performance advantages of coordination through numerical examples and simulation experiments.
Shakkottai, Sanjay and Stolyar, Alexander L.
*Scheduling algorithms for a mixture of real-time and non-real-time data in D̋R*
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Shakkottai2001793,
title = { Scheduling algorithms for a mixture of real-time and non-real-time data in D̋R\ },
year = { 2001 },
author = { Shakkottai, Sanjay and Stolyar, Alexander L. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 793 - 804 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80170-0 }
}
Abstract: High Data Rate (HDR) technology has recently been proposed as an overlay to \CDMA\ as a means of providing packet data service to mobile users. In this paper, we study various scheduling algorithms for a mixture of real-time and non-real-time data over HDR/CDMA and compare their performance. We study the performance with respect to packet delays and also average throughput, where we use a token based mechanism to give minimum throughput guarantees. We find that a rule which we call the exponential rule performs well with regard to both these criteria. (In a companion paper, we show that this rule is throughput-optimal, i.e., it makes the queues stable if it is feasible to do so with any other scheduling rule). Our main conclusion is that intelligent scheduling algorithms in conjunction with token based rate control provide an efficient framework for supporting a mixture of real-time and non-real-time data applications in a single carrier.
Sarkar, Saswati and Tassiulas, Leandros
Scheduling for quality of service based service differentiation
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Sarkar2001781,
title = { Scheduling for quality of service based service differentiation },
year = { 2001 },
author = { Sarkar, Saswati and Tassiulas, Leandros },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 781 - 792 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80169-4 }
}
Abstract: We consider a utility based fairness model for service differentiation among different users. Every user has a utility function and the network allocates bandwidth so as to obtain a fair allocation of the utilities. We present a scheduling policy which attains a provably fair utility allocation. The policy uses a combination of differential sampling, estimation and back pressure based congestion control in order to attain a globally fair allocation via local information based scheduling.
Leelahakriengkrai, Rangsan and Agrawal, Rajeev
Scheduling in multimedia wireless networks
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Leelahakriengkrai2001285,
title = { Scheduling in multimedia wireless networks },
year = { 2001 },
author = { Leelahakriengkrai, Rangsan and Agrawal, Rajeev },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 285 - 298 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80129-3 }
}
Abstract: Wireless systems in the future will have to provide multimedia services where different users have different physical-layer and network-layer QoS requirements. We investigate the use of power control, processing gain, and scheduling in \CDMA\ systems to accommo-data these diverse service requirements. In [4], we have derived the time-sharing capacity region for any channel state which is given in terms of the convex hull of the set of user bit rates that can be supported simultaneously subject to physical-layer QoS requirements. Therefore by choosing any bit rate vector in the time-sharing capacity region, we automatically satisfy the physical-layer QoS requirements. Thus, it is the control knob used by the scheduler to satisfy the network layer QoS requirements. We consider the problem of scheduling on fading channels where channel state often changes rapidly. We design a class of scheduling policies that guarantees system stability. We use simulation to compare the performance of various policies in this class. Specially, we show that the new Minimum Draining Time policy has certain desirable qualities vis-a-vis the Cone policy and Modified Cone policy. All three are special cases of the class of policies for which we show stability.
Sarker, Jahangir H. and Halme, Seppo J.
Slowly decreasing throughput algorithms for random access channel
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Sarker2001335,
title = { Slowly decreasing throughput algorithms for random access channel },
year = { 2001 },
author = { Sarker, Jahangir H. and Halme, Seppo J. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 335 - 346 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80133-5 }
}
Abstract: A multiple power level transmission system augments the maximum throughput by selecting the power levels randomly, exhibiting the similar behavior to the standard Slotted ALOHA, where the throughput decreasing abruptly at higher traffic load conditions and consequently, drops to almost zero, leading to unstable condition. Three slowly decreasing throughput algorithms for Slotted \ALOHA\ are developed to prevent that throughput-collapse. Herein, a mobile terminal can transmit any packet to the lower power levels at a higher probability that increases the probability of only one packet at the highest power levels and thereby enhancing the capture probability. It needs no information about the network, amplifying the implementation privilege. Extensive comparisons show that the proposed slowly decreasing throughput algorithms prevent throughput-collapse under higher offered traffic load condition compared with the traditional random power level selection algorithm.
Vojnovic, Milan and Boudec, Jean-Yves Le
Some observations on equation-based rate control
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Vojnovic2001173,
title = { Some observations on equation-based rate control },
year = { 2001 },
author = { Vojnovic, Milan and Boudec, Jean-Yves Le },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 173 - 184 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80120-7 }
}
Abstract: We consider one aspect of the general problem of unicast equation-based rate control in the Internet, which we formulate as follows. When a so called loss-event occurs, a data source updates its sending rate by setting it to f(n), where n is an estimate of, the loss-event ratio. Function f (the target loss-throughput function) defines the objective of the control method: we would like that the throughput, attained by the source, satisfies the equation =f(). If so, we say that the control is conservative. In the internet, function f is obtained by analyzing the dependency of throughput versus the loss-event ratio for a real \TCP\ source. A non-TCP source which implements a control system as we describe is said to be TCP-friendly if the control is conservative. Our main finding is a set of two conditions whose conjuction is sufficient for the control to be conservative. Suppose that 1/n is an unbiased estimator of 1/n. Then, it is sufficient that (1) f(p) is a concave function with 1/p, and (2) the expected time between two consecutive loss-events, given the current rate x, is non-increasing with x. To verify our finding, we formulate a model of the control and study numerical and simulation results for some special cases. We show there exists statistics of the loss-event inter-arrival times such that the control is non-conservative, even if f(p) is a concave function of 1/p, which should necessarily imply that our second sufficient condition does not hold in those cases. As a by-product, our theory explains why the control is overly conservative when the loss-event ratio is high. Another aspect of unicast equation-based rate control in the Internet is the influence of the variability of round-trip times, which is not analyzed in this paper.
Kuusela, P. and Lassila, P. and Virtamo, J.
Stability of TCP-RED congestion control
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Kuusela2001655,
title = { Stability of TCP-RED congestion control },
year = { 2001 },
author = { Kuusela, P. and Lassila, P. and Virtamo, J. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 655 - 666 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80159-1 }
}
Abstract: We present a method for deriving necessary and sufficient conditions for the local stability of the TCP-RED congestion control. The analysis is based on a system of differential equations modeling the behavior of the system. One equation describes the dynamics of the \TCP\ source population operating in the congestion avoidance phase. The \TCP\ dynamics are driven by another differential equation representing the \RED\ controlled queue, which determines, in the form of a packet loss function, the feedback to the \TCP\ population. The stability of the system is characterized in terms of stability parameters and we illustrate how the physical \RED\ parameters affect the stability. Finally, different stability conditions (sufficient vs. necessary) are compared by analyzing a further simplified \TCP\ model, where the queue feedback is a packet loss function depending only on the aggregate traffic rate of the \TCP\ population.
Xie, M. and Bensaou, B. and Chua, K.C.
Stochastic bounds in a \GPS\ system fed by two leaky bucket regulated on-off sources
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Xie2001731,
title = { Stochastic bounds in a \GPS\ system fed by two leaky bucket regulated on-off sources },
year = { 2001 },
author = { Xie, M. and Bensaou, B. and Chua, K.C. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 731 - 742 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80165-7 }
}
Abstract: In this paper, we study stochastic performance bounds of a Generalized Processor Sharing (GPS) scheduler fed by two leaky bucket regulated on-off traffic sources. Following a decomposition approach, we propose a virtual system of leaky buckets from which we are able to derive both upper and lower bounds on the queue length distribution, as well as stochastic upper bound on the delay of each session.
Elizondo-Armengol, Antonio J.
TCP-friendly policy functions: Capped leaky buckets
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{ElizondoArmengol2001681,
title = { TCP-friendly policy functions: Capped leaky buckets },
year = { 2001 },
author = { Elizondo-Armengol, Antonio J. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 681 - 692 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80161-X }
}
Abstract: Since a few years ago, DiffServ standardisation is being developed by IETF. This paper studies performance problems associated with \TCP\ flows under Assured Service, one of the proposed services under development by IETF. Several policy functions are suggested in this paper: Capped Leaky Buckets and modifications of them. By using simulation, performance of \TCP\ with these new conditioners and with traditional ones is studied.
Markovitch, Natalia M. and Krieger, Udo R.
The estimation of heavy-tailed probability density functions and their mixtures
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Markovitch20011113,
title = { The estimation of heavy-tailed probability density functions and their mixtures },
year = { 2001 },
author = { Markovitch, Natalia M. and Krieger, Udo R. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 1113 - 1126 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80196-7 }
}
Abstract: The paper is devoted to the estimation of heavy-tailed probability density functions (p.d.f.s) and their mixtures. We propose a new combined parametric and non-parametric approach applying both the bootstrap and the structural risk-minimization method. It is illustrated using some relevant mixtures of heavy-tailed p.d.f.s. and its effectiveness is shown by an application to real data arising from Web-traffic characteristics.
pontes, R. and Coelho, R.
The scaling characteristics of the video traffic and its impact on acceptance regions
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{pontes2001197,
title = { The scaling characteristics of the video traffic and its impact on acceptance regions },
year = { 2001 },
author = { pontes, R. and Coelho, R. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 197 - 210 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80122-0 }
}
Abstract: The impact of time-dependence or scaling characteristics on video acceptance regions is examined in this paper. We considered two different \CAC\ mechanisms; i) a descriptor-based \CAC\ (DBCAC) mechanism and ii) a measurement-based \CAC\ (MBCAC) mechanism. the proposed \MBCAC\ is a hybrid measurement scheme that includes a Kalman filter and a real-time Hurst estimation. We investigated serveral buffer sizes and video sequences with different dependence degrees. For the accuracy of the Hurst estimation, we developed a Hurst parameter package (HEP). The package consists of three different estimators, R/S, Higuchi and Abry-Veitch (wavelet). An important result showed that video connections with long-range dependence (LRD) and short-range dependence (SRD) have similar admission regions.
Kaj, Ingemar and Olsén, Jörgen
Throughput modeling and simulation for single connection TCP-Tahoe
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Kaj2001705,
title = { Throughput modeling and simulation for single connection TCP-Tahoe },
year = { 2001 },
author = { Kaj, Ingemar and Olsén, Jörgen },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 705 - 718 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80163-3 }
}
Abstract: We present a stochastic model for the window dynamics in \TCP\ and investigate the throughput performance of TCP-Tahoe during persistent transmission of a bulk data flow. Our overall purpose is to investigate the impact of packet loss probability on the resulting \TCP\ throughput. We analyze several distinct aspects of the \TCP\ flow control, such as maximal advertised window, large initial window, fast retransmit, time-out delays, and duplicate \ACK\ threshold, as well as combinations of these. In this manner we gain insight into each features effect on throughput. Under the further assumption that packets are lost independently of each other, we obtain numerically explicit formulas for the throughput. The main tools are the application of renewal-reward arguments and a new technique to approximate window size and cycle lengths by continuous quantities, which greatly simplifies calculations. Validation of the model is done by simulations using the ns simulator.
Pióro, M. and Jüttner, A. and Harmatos, J. and Szentesi, Á. and Gajowniczek, P. and Mys?ek, A.
Topological design of telecommunication networks Nodes and links localization under demand constraints
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Pioro2001629,
title = { Topological design of telecommunication networks Nodes and links localization under demand constraints },
year = { 2001 },
author = { Pióro, M. and Jüttner, A. and Harmatos, J. and Szentesi, Á. and Gajowniczek, P. and Mys?ek, A. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 629 - 642 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80157-8 }
}
Abstract: The paper addresses the classical network optimization problem consisting in realizing the assumed set of demands in a given network with a given list of potential nodes' and links' locations and with the objective function reflecting the cost of the actual links' capacities as well as the fixed cost of installing nodes and links. We assume that the network nodes are composed of two disjoint sets: the set of access nodes and the set of transit nodes. The access (end) nodes only generate demands and do not transit the end-to-end flows realizing the demands while the transit nodes do not generate demands and do transit the end-to-end flows. The selection of the actually installed transit nodes and of the links interconnecting all the network nodes is the major subject of optimization. Although similar problems have been considered in the past, also in the context of the road traffic, it is the authors' conviction that there is still a lot of room for improvement as far as solution methods are concerned. In the paper we overview the existing problem formulations and solution methods. We also propose our own approaches, based both on original ideas and on improvements of the existing ones. The effectiveness of the solutions is illustrated by means of a numerical study.
Leão, Rosa M.M. and de Souza e Silva, Edmundo and Diniz, Morganna C.
Traffic engineering using reward models
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Leaeo20011101,
title = { Traffic engineering using reward models },
year = { 2001 },
author = { Leão, Rosa M.M. and de Souza e Silva, Edmundo and Diniz, Morganna C. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 1101 - 1112 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80195-5 }
}
Abstract: Traffic engineering has been a highly important area since the early days of telephony. The constant increase in the complexity of multimedia networks of today requires sophisticated tools and modeling techniques to be developed and constantly improved to cope with the needs of the traffic engineer and performance analyst. Due to the very high transmission rates with respect to those of other events in the system model, many recent modeling work have used fluid sources as replacement for packet-level traffic sources. This includes both analytical as well as simulation work. The object of this paper is twofold. We first introduce new algorithms to calculate several transient measures of interest that are useful in the traffic characterization and subsequent performance evaluation of network resources. We then present a modeling environment that implements these algorithms and includes unique features to aid the user in the evaluation task.
DaSilva, Luiz A. and Dham, Vikram and Phanse, Kaustubh and Kidambi, Kalyan
*Traffic management for voice/data convergence in \ADSL*
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{DaSilva2001359,
title = { Traffic management for voice/data convergence in \ADSL\ },
year = { 2001 },
author = { DaSilva, Luiz A. and Dham, Vikram and Phanse, Kaustubh and Kidambi, Kalyan },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 359 - 370 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80135-9 }
}
Abstract: Asymmetric Digital Subseriber Line (ADSL) is one of the leading technologies to enable the convergence of voice and data in the last mile. Much effort has been put into the development of voice over \DSL\ (VoDSL) solutions that efficiently harness the bandwidth available in existing copper infrastructure in the local loop for the transmission of high-speed data as well as multiple voice calls. In this paper, we address the different VoDSL architectures that are being considered. We then present simulation results pertaining to acknowledgment filtering and regeneration, which have the potential to significantly improve data throughput over asymmetric links. Finally, we argue for queuing and scheduling mechanisms to separate data from acknowledgement traffic; our preliminary results show that service differentiation is key in obtaining good \TCP\ performance in the presence of bidirectional data traffic over ADSL. This may lead to a hierarchical scheduling scheme when voice traffic is added to the mix.
Gama, Gustavo and Jr., Wagner Meira and Carvalho, Márcio Bunte and Guedes, Dorgival
Traffic-aware distribution of e-commerce services
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Gama2001541,
title = { Traffic-aware distribution of e-commerce services },
year = { 2001 },
author = { Gama, Gustavo and Jr., Wagner Meira and Carvalho, Márcio Bunte and Guedes, Dorgival },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 541 - 552 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80150-5 }
}
Abstract: e-Commerce services have become a promising and profitable application of the Internet. Nevertheless, the use of the Internet as the communication environment in this case is not without its problems. For an e-commerce site to be successful it has to reduce the negative effects of unreliable connections and high network latencies, among others. Such problems may compromise customer satisfaction and therefore the success of the virtual business. Techniques based on improving the quality of a centralized server do not provide a reliable solution, since the difficulties faced are inherent to the network infrastructure itself, not just the server. A better solution tends to be the distribution of the service over the network, placing servers in multiple locations closer to the final users. The existence of multiple servers tends to increase availability, and assuming the placement is well planned, it tends to reduce delays and traffic-related costs. In this paper we discuss the distribution of e-commerce services by introducing a traffic-aware cost model and evaluating it through an actual log from an e-tailer. The results show that the model allow system designers to investigate cost compromises and the impact of the application workload on the effectiveness of the distribution in terms of reducing traffic, and thus operational costs and user-perceived latency.
Borst, Sem and Boxma, Onno and van Uitert, Miranda
Two coupled queues with heterogeneous traffic
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Borst20011003,
title = { Two coupled queues with heterogeneous traffic },
year = { 2001 },
author = { Borst, Sem and Boxma, Onno and van Uitert, Miranda },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 1003 - 1014 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80187-6 }
}
Abstract: We consider a system with two heterogeneous traffic classes, one having light-tailed characteristics, the other one exhibiting heavy-tailed properties. When both classes are backlogged, the two corresponding queues are each served at a certain nominal rate. However, when one queue empties, the service rate for the other class increases. This dynamic sharing of surplus service capacity is reminiscent of the Generalized Processor Sharing (GPS) discipline. GPS-based scheduling algorithms, such as Weighted Fair Queuing, provide a candidate implementation mechanism for achieving differentiated Quality-of-Service in a DiffServ architecture. We characterize the workload asymptotics for the light-tailed traffic class. We show a sharp dichotomy in the qualitative behavior, depending on whether its traffic load exceeds its nominal service rate or not. In underload scenarios, the tail of the workload distribution is equivalent to that when the light-tailed class is served in isolation, multiplied with a certain pre-factor. The pre-factor represents the probability that the heavy-tailed class is backlogged long enough for the light-tailed class to build up a large workload. This provides a measure for the extent to which the light-tailed class benefits from sharing surplus capacity with the heavy-tailed class. In contrast, in overload situations, the light-tailed class is adversely affected by the heavy-tailed class, and inherits its traffic characteristics.
Reeser, P.
Using stress test results to drive performance modeling: A case study in Gray-Box vendor analysis
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Reeser20011051,
title = { Using stress test results to drive performance modeling: A case study in Gray-Box vendor analysis },
year = { 2001 },
author = { Reeser, P. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 1051 - 1061 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80191-8 }
}
Abstract: In this case study, we present the results of analysis of a Java-based vendor product that performs dynamic Web page construction in a distributed environment. Since the vendor's scripts are proprietary, we must rely on gray-box stress test results to identify performance bottlenecks and determine system capacity. We present a methodology for reverse-engineering stress test results to build performance models of the system internals, and use those models to see inside the box. This approach provided significant insights into the performance of the vendor's proprietary code, and afforded us better leverage in the vendor management process. In particular, the approach identified significant bottlenecks in the Java code that prevented the system from fully utilizing the hardware resources. The approach also exposed the system's behavior under overload, and revealed the need for overload controls. Based on our success, we recommend that stress testing be incorporated into the software development process, especially when development consists largely of integrating external vendor components. Furthermore, in the case of vendor-provided software, this approach offers perhaps the only way to see inside the code, and in the case of new programming languages such as Java, exposes anomalies that could not be predicted from past experience.
Vendictis, A. De and Baiocchi, A.
Wavelet based synthetic generation of internet packet delays
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{DeVendictis200137,
title = { Wavelet based synthetic generation of internet packet delays },
year = { 2001 },
author = { Vendictis, A. De and Baiocchi, A. },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 37 - 48 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80109-8 }
}
Abstract: End-to-end packet delays play a key role, along with other network impairments (e.g. packet losses), in shaping the performance of application traffic carried through the Internet, both via \TCP\ and by means of \UDP\ (e.g. real time applications). In this paper we present a statistical analysis of the packet Round Trip Delays (RTDs) in Internet. We measured ten very long and high resolution traces of packet RTD, collected in different network conditions. We analyze these traces under many aspects. Our main goal is to define a Wavelet based algorithm to generate a sequence of \RTDs\ that mimics the statistical behavior of measured data. Its main application is in modeling and simulation of \IP\ networks. We extensively test the algorithm to highlight its ability to match relevant features measured from Internet \RTD\ traces and its high accuracy when used to predict delay dependent performance metrics.
Brennan, Rob and Curran, Thomas
\SCTP\ congestion control: Initial simulation studies
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Brennan2001843,
title = { \SCTP\ congestion control: Initial simulation studies },
year = { 2001 },
author = { Brennan, Rob and Curran, Thomas },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 843 - 856 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80174-8 }
}
Abstract: This paper uses simulation studies to explore the behaviour of \SCTP\ congestion control. Several possible variants of \SCTP\ congestion control are identified and each is compared with the behaviour of Reno TCP, a well-known \TCP\ variant. We identify three flaws in the current \SCTP\ congestion control mechanisms. 1. Recovery without a timeout after a packet loss is only possible if \SCTP\ generates the optional Gap Ack Blocks in \SACK\ messages. 2. The \SCTP\ fast retransmit procedure is vulnerable to being mistakenly triggered multiple times leading to under-utilization of the network during recovery and duplicate retransmissions of the lost packet. 3. The \SCTP\ fast retransmit procedure must wait for half a window of data to be acknowledged before retransmitting a lost packet yielding a slow response to packet loss. We also provide suggested remedies for these flaws. Finally we demonstrate how \SCTP\ congestion control mechanisms can cause a burst of packets after recovery from a packet loss.
Altman, Eitan and Avrachenkov, Kostia and Barakat, Chadi and Núñez-Queija, Rudesindo
\TCP\ modeling in the presence of nonlinear window growth
In Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7. 2001
[BibTeX]
[Abstract]
[BibSonomy]
@incollection{Altman2001883,
title = { \TCP\ modeling in the presence of nonlinear window growth },
year = { 2001 },
author = { Altman, Eitan and Avrachenkov, Kostia and Barakat, Chadi and Núñez-Queija, Rudesindo },
booktitle = { Teletraffic Engineering in the Internet EraProceedings of the International Teletraffic Congress - ITC-I7 },
editor = { Jorge Moreira de Souza, Nelson L.S. da Fonseca and de Souza e Silva, Edmundo A. },
pages = { 883 - 894 },
publisher = { Elsevier },
series = { Teletraffic Science and Engineering },
volume = { 4 },
misc = { issn = 1388-3437,
doi = http://dx.doi.org/10.1016/S1388-3437(01)80177-3 }
}
Abstract: We develop a model for \TCP\ that accounts for both sublinearity and limitation of window growth. Sublinear window growth is observed when the round-trip time of the connection increases with the window size. Limitation is due to the window advertised by the receiver. First, we derive the conditions for the stability of the model. Then, we write the Kolmogorov equation under Markovian assumptions. The model is solved analytically for some particular cases. A good match between the throughput predicted by the model and the throughput measured on real \TCP\ connections is reported at the end.
