Browse the ITC publications of previous conferences below or visit our grouppage at bibsonomy.org
2022
Main Conference
Mahsa Noroozi, Markus Fidler
Age- and Deviation-of-Information of Time-Triggered and Event-Triggered Systems
In 34th International Teletraffic Congress (ITC-34). Shenzhen, China 2022
[BibTeX]
[Abstract]
[Download]
[BibSonomy]
@inproceedings{ ,
title = { Age- and Deviation-of-Information of Time-Triggered and Event-Triggered Systems },
year = { 2022 },
address = { Shenzhen, China },
author = { Mahsa Noroozi, Markus Fidler },
booktitle = { 34th International Teletraffic Congress (ITC-34) },
month = { September },
pages = { 1 -- 6 }
}
Abstract: Age-of-information is a metric that quantifies the freshness of information obtained by sampling a remote sensor. In signal-agnostic sampling, sensor updates are triggered at certain times without being conditioned on the actual sensor signal. Optimal update policies have been researched and it is accepted that periodic updates achieve smaller age-of-information than random updates. We contribute a study of a signal-aware policy, where updates are triggered by a random sensor event. By definition, this implies random updates and as a consequence inferior age-of-information. Considering a notion of deviation-of-information as a signal-aware metric, our results show, however, that event-triggered systems can perform equally well as time-triggered systems while causing smaller mean network utilization.
Stefan Geissler, Stanislav Lange, Gerhard Hasslinger, Phuoc Tran-Gia, Tobias Hoßfeld
Discrete-Time Analysis of Multi-Component Queuing Networks under Renewal Approximation
In 34th International Teletraffic Congress (ITC-34). Shenzhen, China 2022
[BibTeX]
[Abstract]
[Download]
[BibSonomy]
@inproceedings{ ,
title = { Discrete-Time Analysis of Multi-Component Queuing Networks under Renewal Approximation },
year = { 2022 },
address = { Shenzhen, China },
author = { Stefan Geissler, Stanislav Lange, Gerhard Hasslinger, Phuoc Tran-Gia, Tobias Hoßfeld },
booktitle = { 34th International Teletraffic Congress (ITC-34) },
month = { September },
pages = { 1 -- 6 }
}
Abstract: The analytical and numerical performance evaluation of network components and distributed systems has been a staple in the networking community for many years. However, the ever-growing complexity of modern systems and the need to gain detailed insights into systems consisting of many, interconnected components emphasizes the need for an extension to the classical single-component approach, and although approaches like Jackson Networks exist, their limited application scope lags behind the complexity of modern environments. To this end, we revisit existing models of the common Gi/Gi/1-∞ queue, extend them to allow the concatenation of multiple queueing components, and evaluate the approximation error introduced through renewal approximation. We revisit previously performed parameter studies and evaluate the approximation error for a wide range of parameter combinations that we can solve through the power of modern compute equipment and efficient numerical implementations of our models. We show the main impact factors for the linear concatenation of queueing components, as well as the split and superposition of processes. Our evaluations show that the renewal approximation can be applied to a wide range of parameters while still obtaining results within acceptable error margins.
Jose M Navarro, Alexis Huet, Dario Rossi
Rare Yet Popular: Evidence and Implications from Labeled Datasets for Network Anomaly Detection
In 34th International Teletraffic Congress (ITC-34). Shenzhen, China 2022
[BibTeX]
[Abstract]
[Download]
[BibSonomy]
@inproceedings{ ,
title = { Rare Yet Popular: Evidence and Implications from Labeled Datasets for Network Anomaly Detection },
year = { 2022 },
address = { Shenzhen, China },
author = { Jose M Navarro, Alexis Huet, Dario Rossi },
booktitle = { 34th International Teletraffic Congress (ITC-34) },
month = { September },
pages = { 1 -- 6 }
}
Abstract: Anomaly detection research works generally propose algorithms or end-to-end systems that are designed to automatically discover outliers in a dataset or a stream. While literature abounds concerning algorithms or the definition of metrics for better evaluation, the quality of the ground truth against which they are evaluated is seldom questioned. On this paper, we present a systematic analysis of available public (and additionally our private) ground truth for anomaly detection in the context of network environments, where data is intrinsically temporal, multivariate and, in particular, exhibits spatial properties, which, to the best of our knowledge, we are the first to explore. Our analysis reveals that, while anomalies are, by definition, temporally rare events, their spatial characterization clearly shows some type of anomalies are significantly more popular than others. We find that simple clustering can reduce the need for labeling by a factor of 2 to 10 times, that we are first to quantitatively analyze in the wild.
Huang Yijie, Zhiyuan Jiang
Age of Information in an M/M/2 Queue with In-Order Delivery
In 34th International Teletraffic Congress (ITC-34). Shenzhen, China 2022
[BibTeX]
[Abstract]
[Download]
[BibSonomy]
@inproceedings{ ,
title = { Age of Information in an M/M/2 Queue with In-Order Delivery },
year = { 2022 },
address = { Shenzhen, China },
author = { Huang Yijie, Zhiyuan Jiang },
booktitle = { 34th International Teletraffic Congress (ITC-34) },
month = { September },
pages = { 1 -- 6 }
}
Abstract: The emergence of the concept of Age of Information provides a new method to quantify the freshness of information for time-critical network systems. In parallel server networks with out-of-order arrival of updates, this paper studies and analyzes the performance of the time average age with the in-order delivery mode, i.e., the updates are delivered to the destination node according to their generation timestamp. The time average age under the M/M/2 blocking and queuing models is evaluated by a stochastic-hybrid-system approach and a graphical decomposition method, respectively. Numerical results demonstrate that the theoretical expression is consistent with the simulated age, and compared with out-of-order delivery, the performance loss of in-order delivery is within 14.2%.
Gabriele Castellano, Fabio Pianese, Damiano Carra, Tianzhu Zhang, Giovanni Neglia
Regularized Bottleneck with Early Labeling
In 34th International Teletraffic Congress (ITC-34). Shenzhen, China 2022
[BibTeX]
[Abstract]
[Download]
[BibSonomy]
@inproceedings{ ,
title = { Regularized Bottleneck with Early Labeling },
year = { 2022 },
address = { Shenzhen, China },
author = { Gabriele Castellano, Fabio Pianese, Damiano Carra, Tianzhu Zhang, Giovanni Neglia },
booktitle = { 34th International Teletraffic Congress (ITC-34) },
month = { September },
pages = { 1 -- 6 }
}
Abstract: Small IoT devices, such as drones and lightweight battery-powered robots, are emerging as a major platform for the deployment of AI/ML capabilities. Autonomous and semi-autonomous device operation relies on the systematic use of deep neural network models for solving complex tasks, such as image classification. The challenging restrictions of these devices in terms of computing capabilities, network connectivity, and power consumption are the main limits to the accuracy of latency-sensitive inferences. This paper presents ReBEL, a split computing architecture enabling the dynamic remote offload of partial computations or, in alternative, a local approximate labeling based on a jointly-trained classifier. Our approach combines elements of head network distillation, early exit classification, and bottleneck injection with the goal of reducing the average end-to-end latency of AI/ML inference on constrained IoT devices.
Tobias Hoßfeld, Poul E. Heegaard, Martín Varela, Michael Jarschel
User-Centric Markov Reward Model on the Example of Cloud Gaming
In 34th International Teletraffic Congress (ITC-34). Shenzhen, China 2022
[BibTeX]
[Abstract]
[Download]
[BibSonomy]
@inproceedings{ ,
title = { User-Centric Markov Reward Model on the Example of Cloud Gaming },
year = { 2022 },
address = { Shenzhen, China },
author = { Tobias Hoßfeld, Poul E. Heegaard, Martín Varela, Michael Jarschel },
booktitle = { 34th International Teletraffic Congress (ITC-34) },
month = { September },
pages = { 1 -- 6 }
}
Abstract: Markov reward models are commonly used in the analysis of systems by integrating a reward rate to each system state. However, rewards are defined based on system states and reflect the system's perspective. From a user's point of view, it is important to consider the changing system conditions and dynamicity while the user consumes a service. In this paper, we consider online cloud gaming as use case. Cloud gaming essentially moves the processing power required to render a game away from the user into the cloud and streams the entire game experience to the user as a high definition video. According to the available network capacity, the video streaming bitrate is adapted. We conduct experiments on Google Stadia and provide a Markov model based on the measurement results to investigate a scenario where users a sharing a bottleneck link.
The key contributions are proper definitions for (i) system-centric reward and (ii) user-centric reward of the cloud gaming model, as well as (iii) the analysis of the relationships between those metrics. Our key result allows a simple computation of the user-centric rewards. We provide (iv) numerical results on the trade-off between user-centric rewards and blocking probabilities to access the online cloud servers. We use Kleinrock's approach to identify operational points based on the power metric. This work gives relevant and important insights how to integrate the user's perspective in the analysis of Markov reward models and is a blueprint for the analysis of other services beyond cloud gaming.
Shutao Zhang, Xinzhi Ning, Xi Zheng, Qingjiang Shi, Tsung-Hui Chang, Zhi-Quan Luo
A Physics-based and Data-driven Approach for Localized Statistical Channel Modeling
In 34th International Teletraffic Congress (ITC-34). Shenzhen, China 2022
[BibTeX]
[Abstract]
[Download]
[BibSonomy]
@inproceedings{ ,
title = { A Physics-based and Data-driven Approach for Localized Statistical Channel Modeling },
year = { 2022 },
address = { Shenzhen, China },
author = { Shutao Zhang, Xinzhi Ning, Xi Zheng, Qingjiang Shi, Tsung-Hui Chang, Zhi-Quan Luo },
booktitle = { 34th International Teletraffic Congress (ITC-34) },
month = { September },
pages = { 1 -- 6 }
}
Abstract: Localized channel modeling is crucial for offline performance optimization of 5G cellular networks, but the existing channel models are for general scenarios and do not capture local geographical structures. In this paper, we propose a novel physics-based and data-driven localized statistical channel modeling (LSCM), which is capable of sensing the physical geographical structures of the targeted cellular environment. The proposed channel modeling solely relies on the reference signal receiving power (RSRP) of the user equipment, unlike the traditional methods which use full channel impulse response matrices. The key is to build the relationship between the RSRP and the channel's angular power spectrum. Based on it, we formulate the task of channel modeling as a sparse recovery problem where the non-zero entries of the sparse vector indicate the channel paths' powers and angles of departure. A computationally efficient weighted non-negative orthogonal matching pursuit (WNOMP) algorithm is devised for solving the formulated problem. Finally, experiments based on synthetic and real RSRP measurements are presented to examine the performance of the proposed method.
Lehan Wang and Jingzhou Sun, Yuxuan Sun, Sheng Zhou and Zhisheng Niu
A Grouping-based Scheduler for Efficient Channel Utilization under Age of Information Constraints
In 34th International Teletraffic Congress (ITC-34). Shenzhen, China 2022
[BibTeX]
[Abstract]
[Download]
[BibSonomy]
@inproceedings{ ,
title = { A Grouping-based Scheduler for Efficient Channel Utilization under Age of Information Constraints },
year = { 2022 },
address = { Shenzhen, China },
author = { Shutao Zhang, Xinzhi Ning, Xi Zheng, Qingjiang Shi, Tsung-Hui Chang, Zhi-Quan Luo },
booktitle = { 34th International Teletraffic Congress (ITC-34) },
month = { September },
pages = { 1 -- 6 }
}
Abstract: We consider a status information updating system where a fusion center collects the status information from a large number of sources and each of them has its own age of information (AoI) constraints. A novel grouping-based scheduler is proposed to solve this complex large-scale problem by dividing the sources into different scheduling groups. The problem is then transformed into deriving the optimal grouping scheme. A two-step grouping algorithm (TGA) is proposed: 1) Given AoI constraints, we first identify the sources with harmonic AoI constraints, then design a fast grouping method and an optimal scheduler for these sources. Under harmonic AoI constraints, each constraint is divisible by the smallest one and the sum of reciprocals of the constraints with the same value is divisible by the reciprocal of the smallest one. 2) For the other sources without such a special property, we pack the sources which can be scheduled together with minimum update rates into the same group. Simulations show the channel usage of the proposed TGA is significantly reduced as compared to a recent work and is 0.42% larger than a derived lower bound when the number of sources is large.
Redha Abderrahmane Alliche, Tiago Da Silva Barros, Ramon Aparicio-Pardo, Lucile Sassatelli
Impact Evaluation of Control Signalling onto Distributed Learning-based Packet Routing
In 34th International Teletraffic Congress (ITC-34). Shenzhen, China 2022
[BibTeX]
[Abstract]
[Download]
[BibSonomy]
@inproceedings{ ,
title = { A Grouping-based Scheduler for Efficient Channel Utilization under Age of Information Constraints },
year = { 2022 },
address = { Shenzhen, China },
author = { Shutao Zhang, Xinzhi Ning, Xi Zheng, Qingjiang Shi, Tsung-Hui Chang, Zhi-Quan Luo },
booktitle = { 34th International Teletraffic Congress (ITC-34) },
month = { September },
pages = { 1 -- 6 }
}
Abstract: In recent years, several works have studied Multi-Agent Deep Reinforcement Learning for the Distributed Packet Routing problem, with promising results in various scenarios where network status changes dynamically, is uncertain, or is partially hidden (e.g., wireless ad hoc networks or wired multi-domain networks). Unfortunately, these previous works focus on an ideal scenario where the impact of control signalling is neglected, and network simulation is tailored to simplistic assumptions. In this article, we present the first experimental investigation of control signalling mechanisms for distributed learning-based packet routing. We rely on PRISMA, our open-source simulation ns-3-based module. We formulate two signalling mechanisms between agents (value sharing and model sharing). We investigate the net gains considering in-band signalling and show that routing policies close to those provided by an oracle with full knowledge of traffic and network topology can be discovered with a control overhead of 150 % with respect to injected data packets, if neighboring agents share their Deep Neural Network models. We discuss the generality of our results to underline the importance of assessing net gains of Multi-Agent Deep Reinforcement Learning (MA-DRL)-based routing.
Nicolai Kröger, Hasanin Harkous, Fidan Mehmeti, Wolfgang Kellerer
Looking Beyond the First Moment: Analysis of Packet-related Distributions in P4 Systems with Controller Feedback
In 34th International Teletraffic Congress (ITC-34). Shenzhen, China 2022
[BibTeX]
[Abstract]
[Download]
[BibSonomy]
@inproceedings{ ,
title = { Looking Beyond the First Moment: Analysis of Packet-related Distributions in P4 Systems with Controller Feedback },
year = { 2022 },
address = { Shenzhen, China },
author = { Nicolai Kröger, Hasanin Harkous, Fidan Mehmeti, Wolfgang Kellerer },
booktitle = { 34th International Teletraffic Congress (ITC-34) },
month = { September },
pages = { 1 -- 6 }
}
Abstract: The ubiquitous spread of programmable data planes has been conditioned by the development and use of domain specific languages. One such very convenient programming language is P4, which enables devices, like switches, to be configurable and protocol-independent, making it a perfect match for Software Defined Networks. Therefore, analyzing the metrics of interest in such a network is of paramount importance to understand what actually happens in the system. However, while previously there were studies dealing with performance analysis on P4-enabled systems, these were mostly bounded to obtaining the first moment of the metrics of interest. This does not provide a full picture of how P4-programmable switches operate. Hence, in this paper, we provide an analysis of the distributions of the metrics of interest in the system, modeling its behavior as a queueing network. We provide arguments as to why a normal distribution can mimic the service time distribution of the data plane. We consider the behavior under different distributions of the service times in the control plane. Results show that the variance of the sojourn time tends to decrease when a higher number of packets is sent back to the controller, which is more emphasized with the medium-rate and slow controllers, where the coefficient of variation can be reduced by at least 35%.
Alexander Scheffler, Steffen Bondorf, Jens Schmitt
Short Paper: Analyzing FIFO-Multiplexing Tandems with Network Calculus and a Tailored Grid Search
In 34th International Teletraffic Congress (ITC-34). Shenzhen, China 2022
[BibTeX]
[Abstract]
[Download]
[BibSonomy]
@inproceedings{ ,
title = { Short Paper: Analyzing FIFO-Multiplexing Tandems with Network Calculus and a Tailored Grid Search },
year = { 2022 },
address = { Shenzhen, China },
author = { Alexander Scheffler, Steffen Bondorf, Jens Schmitt },
booktitle = { 34th International Teletraffic Congress (ITC-34) },
month = { September },
pages = { 1 -- 6 }
}
Abstract: Safety-critical applications are increasingly deployed on shared networks. Among the features of current standards, there is one prominent, common characteristic: At queuing locations, different applications' traffic flows multiplex in a First-In First-Out (FIFO) fashion. The Network Calculus framework provides several FIFO analyses for computing a bound on the end-to-end delay of a data flow. However, tracing FIFO relations increases the computational cost and an accurate analysis is typically a slow one. Therefore, we propose a two-step heuristic in this paper. We devise a new, fast analysis to rank alternative tandem designs before a more costly analysis is applied to the top-ranked ones. Our new analysis employs a tailored grid search to resolve the FIFO effects between flows. Numerical evaluations show that we create a ranking that is very close to the one by the accurate yet slower FIFO analysis we base our work on.
Shiksha Singhal and Veeraruna Kavitha, Sreenath Ramanath
Short Paper: AoI-Based Opportunistic-Fair mmWave Schedulers
In 34th International Teletraffic Congress (ITC-34). Shenzhen, China 2022
[BibTeX]
[Abstract]
[Download]
[BibSonomy]
@inproceedings{ ,
title = { Short Paper: AoI-Based Opportunistic-Fair mmWave Schedulers },
year = { 2022 },
address = { Shenzhen, China },
author = { Shiksha Singhal and Veeraruna Kavitha, Sreenath Ramanath },
booktitle = { 34th International Teletraffic Congress (ITC-34) },
month = { September },
pages = { 1 -- 6 }
}
Abstract: We consider a system with a Base Station (BS) and multiple mobile/stationary users. BS uses millimeter waves (mmWaves) for data transmission and hence needs to align beams in the directions of the end-users. The idea is to avail regular user-position estimates, which help in accurate beam alignment towards multiple users, paving way for opportunistic mmWave schedulers. We propose an online algorithm that uses a dual opportunistic and fair scheduler to allocate data as well as position-update channels, in each slot. Towards this, well-known alpha-fair objective functions of utilities of various users, which further depend upon the age of position-information, are optimized. We illustrate the advantages of the opportunistic scheduler, by comparing it with the previously proposed mmWave schemes; these schedulers choose one user in each slot and start data transmission only after accurate beam alignment. We also discuss two ways of introducing fairness in such schemes, both of which perform inferior to the proposed age-based opportunistic scheduler.
Vartika Singh, Veeraruna Kavitha
Short Paper: Fair opportunistic schedulers for Lossy Polling systems
In 34th International Teletraffic Congress (ITC-34). Shenzhen, China 2022
[BibTeX]
[Abstract]
[Download]
[BibSonomy]
@inproceedings{ ,
title = { Short Paper: Fair opportunistic schedulers for Lossy Polling systems },
year = { 2022 },
address = { Shenzhen, China },
author = { Vartika Singh, Veeraruna Kavitha },
booktitle = { 34th International Teletraffic Congress (ITC-34) },
month = { September },
pages = { 1 -- 6 }
}
Abstract: Polling systems with losses are useful mathematical objects that can model many practical systems like travelling salesman problem with recurrent requests. One of the less studied yet an important aspect in such systems is the disparity in the utilities derived by the individual stations. Further, the random fluctuations of the travel conditions can have significant impact on the performance. This calls for a scheduler that caters to the fairness aspect, depends upon the travel conditions and the dynamic system state.
Joint Workshop of Smart Industrial Networking and Satellite Based IoT
Jinzhou Li, Shouye Lv, Chenglin Wang, Shuai Liao, Shaoqiong Zhou, Yang Liu
Single Observer Geolocation for Periodic Communication Signals based on Doppler and TOA
In Joint Workshop of Smart Industrial Networking and Satellite Based IoT. Shenzhen, China 2022
[BibTeX]
[Abstract]
[Download]
[BibSonomy]
@inproceedings{ ,
title = { Single Observer Geolocation for Periodic Communication Signals based on Doppler and TOA },
year = { 2022 },
address = { Shenzhen, China },
author = { Jinzhou Li, Shouye Lv, Chenglin Wang, Shuai Liao, Shaoqiong Zhou, Yang Liu },
booktitle = { 34th International Teletraffic Congress (ITC-34) },
month = { September },
pages = { 1 -- 6 }
}
Abstract: The disadvantages of single observer localization
based on Doppler are poor geolocation accuracy and long
cumulative time. Therefore, it is significant to improve geolocation
accuracy without increasing the cost of payload. In this paper,
the authors propose a single observer geolocation method for
periodic communication signals based on Doppler and time
delay. We first compare the Cram´er-Rao lower bound (CRLB)
differences with and without using time of arriving (TOA).
CRLBs comparison shows the theoretical geolocation accuracy
could be improved significantly by TOA for periodic signal. In
the sequel we propose a maximum likelihood iterative geolocation
approach. Simulation results show that the estimation accuracy
approximately attains the CRLB and demonstrate the feasibility
of the accuracy analysis.
Zhilin Liu, Yao Zhu, Yulin Hu, Peng Sun, Ning Guo, and Anke Schmeink
Joint Time and Power Allocation for NOMA-Assisted Low-Latency Mobile Edge Computing
In Joint Workshop of Smart Industrial Networking and Satellite Based IoT. Shenzhen, China 2022
[BibTeX]
[Abstract]
[Download]
[BibSonomy]
@inproceedings{ ,
title = { Joint Time and Power Allocation for NOMA-Assisted Low-Latency Mobile Edge Computing },
year = { 2022 },
address = { Shenzhen, China },
author = { Zhilin Liu, Yao Zhu, Yulin Hu, Peng Sun, Ning Guo, and Anke Schmeink },
booktitle = { 34th International Teletraffic Congress (ITC-34) },
month = { September },
pages = { 1 -- 6 }
}
Abstract: In this paper, we study a mobile edge computing
(MEC) network supporting latency-critical tasks. Data informa
tion generated at multiple devices are offloaded to and processed
at the MEC node. Each service in the network is divided into two
phases, i.e., a non-orthogonal multiple access (NOMA)-assisted
communication phase and a MEC server computation phase,
while the whole task offloading process is required to satisfy high
reliability and low-latency. We characterize the overall service
error probability of the network, while taking into account the
finite blocklength (FBL) impacts on both the communication
and the queuing impacts on computation. Accordingly, a joint
optimal design is introduced to minimize the overall service
error probability by determining the phase lengths and transmit
power at NOMA users. In particular, the formulated problem is
nonconvex, for which a modified block coordinate descent method
is proposed in order to decompose the problem into sub-problems
which are characterized and solved efficiently. By means of
simulations, we validate our analytical model and evaluate the
considered network.
Bruce Mareri, Ruijie Ou, Yu Pang
** DeepSmart: A Deep Learning Strategy for Real-time B5G/6G Edge Analytics and Anomaly Detection*
In *Joint Workshop of Smart Industrial Networking and Satellite Based IoT. Shenzhen, China 2022
[BibTeX]
[Abstract]
[Download]
[BibSonomy]
@inproceedings{ ,
title = { DeepSmart: A Deep Learning Strategy for Real-time B5G/6G Edge Analytics and Anomaly Detection },
year = { 2022 },
address = { Shenzhen, China },
author = { Bruce Mareri, Ruijie Ou, Yu Pang },
booktitle = { 34th International Teletraffic Congress (ITC-34) },
month = { September },
pages = { 1 -- 6 }
}
Abstract: Wireless communication has increased signifi
cantly in recent years. To address future connectivity require
ments, some researchers are focused on Beyond 5G (B5G)
and Sixth-Generation (6G) wireless technology that capitalizes
on Internet of Things (IoT) technologies to convert sensory
data into actionable knowledge. Intelligent factories that are
networked require real-time, low-latency applications. As IIoT
devices become more widely deployed, real-time data process
ing at the network edge rather than in cloud data centers is
critical. As a result, deep learning may be a viable choice for
real-time processing. This research proposes DeepSmart, a deep
learning-powered framework for IIoT forecasting and anomaly
detection is proposed in this study. DeepSmart’s hierarchical
architecture for processing correlated time series workflow
model, constructed with long short-term memory (LSTM) as
a significant component, is demonstrated. DeepSmart is evalu
ated using real-world datasets, and the results demonstrate that
it outperforms established classical approaches in forecasting.
Daniel Ayepah-Mensah, Guolin Sun, Yu Pang, Wei Jiang
** Adaptive Digital Twin and Communication-Efficient Federated Learning Network Slicing for 5G-enabled Internet of Things*
In *Joint Workshop of Smart Industrial Networking and Satellite Based IoT. Shenzhen, China 2022
[BibTeX]
[Abstract]
[Download]
[BibSonomy]
@inproceedings{ ,
title = { Adaptive Digital Twin and Communication-Efficient Federated Learning Network Slicing for 5G-enabled Internet of Things },
year = { 2022 },
address = { Shenzhen, China },
author = { Daniel Ayepah-Mensah, Guolin Sun, Yu Pang, Wei Jiang},
booktitle = { 34th International Teletraffic Congress (ITC-34) },
month = { September },
pages = { 1 -- 6 }
}
Abstract: Wireless communication has increased significantly in recent years. To address future connectivity require
ments, some researchers are focused on Beyond 5G (B5G)
and Sixth-Generation (6G) wireless technology that capitalizes
on Internet of Things (IoT) technologies to convert sensory
data into actionable knowledge. Intelligent factories that are
networked require real-time, low-latency applications. As IIoT
devices become more widely deployed, real-time data process
ing at the network edge rather than in cloud data centers is
critical. As a result, deep learning may be a viable choice for
real-time processing. This research proposes DeepSmart, a deep
learning-powered framework for IIoT forecasting and anomaly
detection is proposed in this study. DeepSmart’s hierarchical
architecture for processing correlated time series workflow
model, constructed with long short-term memory (LSTM) as
a significant component, is demonstrated. DeepSmart is evalu
ated using real-world datasets, and the results demonstrate that
it outperforms established classical approaches in forecasting.
Gordon Owusu Boateng, Guisong Liu
Cooperative Resource Trading for Network Slicing in Industrial IoT: A Multi-Agent DRL Approach
In Joint Workshop of Smart Industrial Networking and Satellite Based IoT. Shenzhen, China 2022
[BibTeX]
[Abstract]
[Download]
[BibSonomy]
@inproceedings{ ,
title = { Cooperative Resource Trading for Network Slicing in Industrial IoT: A Multi-Agent DRL Approach },
year = { 2022 },
address = { Shenzhen, China },
author = { Gordon Owusu Boateng, Guisong Liu },
booktitle = { 34th International Teletraffic Congress (ITC-34) },
month = { September },
pages = { 1 -- 6 }
}
Abstract: Wireless communication has increased significantly in recent years. To address future connectivity require
ments, some researchers are focused on Beyond 5G (B5G)
and Sixth-Generation (6G) wireless technology that capitalizes
on Internet of Things (IoT) technologies to convert sensory
data into actionable knowledge. Intelligent factories that are
networked require real-time, low-latency applications. As IIoT
devices become more widely deployed, real-time data process
ing at the network edge rather than in cloud data centers is
critical. As a result, deep learning may be a viable choice for
real-time processing. This research proposes DeepSmart, a deep
learning-powered framework for IIoT forecasting and anomaly
detection is proposed in this study. DeepSmart’s hierarchical
architecture for processing correlated time series workflow
model, constructed with long short-term memory (LSTM) as
a significant component, is demonstrated. DeepSmart is evalu
ated using real-world datasets, and the results demonstrate that
it outperforms established classical approaches in forecasting.
Anjie Qiu, Donglin Wang, Sanket Partani and Hans D. Schotten
Modern OpenAI Gym Simulation Platforms for Vehicular Ad-hoc Network Systems
In Joint Workshop of Smart Industrial Networking and Satellite Based IoT. Shenzhen, China 2022
[BibTeX]
[Abstract]
[Download]
[BibSonomy]
@inproceedings{ ,
title = { Modern OpenAI Gym Simulation Platforms for Vehicular Ad-hoc Network Systems },
year = { 2022 },
address = { Shenzhen, China },
author = { Anjie Qiu, Donglin Wang, Sanket Partani and Hans D. Schotten },
booktitle = { 34th International Teletraffic Congress (ITC-34) },
month = { September },
pages = { 1 -- 6 }
}
Abstract: The great demands of Machine Learning (ML) are
required in many application domains. In the vehicular commu
nications, new technologies and applications based on ML appear
more frequently. Many studies already show significant benefits
of deploying ML to the Intelligent Transport Systems (ITS),
among which Reinforcement Learning (RL) delivers the best
compatibility. Many vehicular networks have chosen Simulation
of Urban MObility (SUMO) as the mobility simulator, which
provides realistic traffic traces and real-world road maps. In
recent years, many simulation platforms based on the SUMO as
traffic/mobility part and the OpenAI Gym platform are put into
usage, hence, this work serves as an overview of these modern
and realistic simulation platforms, and a comparison is made
from different aspects. Also, the advantages and disadvantages of
each simulator are discussed, and recommendations on different
simulators for researchers are introduced based on their research
topics.
