Pub Date : 2024-10-03DOI: 10.1109/LNET.2024.3472034
Weibiao Tian;Ye Li;Jinwei Zhao;Sheng Wu;Jianping Pan
System-level performance evaluation over satellite networks often requires a simulated or emulated environment for reproducibility and low cost. However, the existing tools may not meet the needs for scenarios such as the low-earth orbit (LEO) satellite networks. To address the problem, this letter proposes and implements a trace-driven emulation method based on Linux’s eBPF technology. Building a Starlink traces collection system, we demonstrate that the method can effectively and efficiently emulate the connection conditions, and therefore provides a means for evaluating applications on local hosts.
卫星网络的系统级性能评估通常需要模拟或仿真环境，以实现可重复性和低成本。然而，现有工具可能无法满足低地轨道（LEO）卫星网络等场景的需求。为解决这一问题，本文基于 Linux 的 eBPF 技术，提出并实现了一种跟踪驱动的仿真方法。通过建立 Starlink 跟踪收集系统，我们证明了该方法可以有效地模拟连接条件，从而为评估本地主机上的应用程序提供了一种方法。
{"title":"An eBPF-Based Trace-Driven Emulation Method for Satellite Networks","authors":"Weibiao Tian;Ye Li;Jinwei Zhao;Sheng Wu;Jianping Pan","doi":"10.1109/LNET.2024.3472034","DOIUrl":"https://doi.org/10.1109/LNET.2024.3472034","url":null,"abstract":"System-level performance evaluation over satellite networks often requires a simulated or emulated environment for reproducibility and low cost. However, the existing tools may not meet the needs for scenarios such as the low-earth orbit (LEO) satellite networks. To address the problem, this letter proposes and implements a trace-driven emulation method based on Linux’s eBPF technology. Building a Starlink traces collection system, we demonstrate that the method can effectively and efficiently emulate the connection conditions, and therefore provides a means for evaluating applications on local hosts.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"6 3","pages":"188-192"},"PeriodicalIF":0.0,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142517934","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-27DOI: 10.1109/LNET.2024.3469175
Koya Sato;Katsuya Suto
This letter proposes an adaptive experimental design framework for a channel-simulation-based base station (BS) design that supports the joint optimization of transmission power and placement. We consider a system in which multiple transmitters provide wireless services over a shared frequency band. Our objective is to maximize the average throughput within an area of interest. System operators can design the system configurations prior to deployment by iterating them through channel simulations and updating the parameters. However, accurate channel simulations are computationally expensive; therefore, it is preferable to configure the system using a limited number of simulation iterations. We develop a solver for the problem based on Bayesian optimization (BO), a black-box optimization method. The numerical results demonstrate that our proposed framework can achieve 18-22% higher throughput performance than conventional placement and power optimization strategies.
{"title":"Bayesian Optimization Framework for Channel Simulation-Based Base Station Placement and Transmission Power Design","authors":"Koya Sato;Katsuya Suto","doi":"10.1109/LNET.2024.3469175","DOIUrl":"https://doi.org/10.1109/LNET.2024.3469175","url":null,"abstract":"This letter proposes an adaptive experimental design framework for a channel-simulation-based base station (BS) design that supports the joint optimization of transmission power and placement. We consider a system in which multiple transmitters provide wireless services over a shared frequency band. Our objective is to maximize the average throughput within an area of interest. System operators can design the system configurations prior to deployment by iterating them through channel simulations and updating the parameters. However, accurate channel simulations are computationally expensive; therefore, it is preferable to configure the system using a limited number of simulation iterations. We develop a solver for the problem based on Bayesian optimization (BO), a black-box optimization method. The numerical results demonstrate that our proposed framework can achieve 18-22% higher throughput performance than conventional placement and power optimization strategies.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"6 4","pages":"217-221"},"PeriodicalIF":0.0,"publicationDate":"2024-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10697138","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143388621","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-24DOI: 10.1109/LNET.2024.3467031
Anastasios C. Politis;Constantinos S. Hilas
This letter evaluates the performance of the slotted Aloha protocol defined by the European Telecommunication Standard Institute (ETSI) SmartBAN specification, under saturation conditions. For this purpose, we develop a two-dimensional discrete time Markov chain (DTMC) to model the operational details of the protocol and assess its performance in terms of saturation throughput and average end-to-end delay. The accuracy of the proposed model is validated by means of simulation which reveals a very good match among theoretical and simulation results. The model can be used for protocol performance prediction and optimization purposes.
{"title":"Throughput and Delay Performance of Slotted Aloha in SmartBANs Under Saturation Conditions","authors":"Anastasios C. Politis;Constantinos S. Hilas","doi":"10.1109/LNET.2024.3467031","DOIUrl":"https://doi.org/10.1109/LNET.2024.3467031","url":null,"abstract":"This letter evaluates the performance of the slotted Aloha protocol defined by the European Telecommunication Standard Institute (ETSI) SmartBAN specification, under saturation conditions. For this purpose, we develop a two-dimensional discrete time Markov chain (DTMC) to model the operational details of the protocol and assess its performance in terms of saturation throughput and average end-to-end delay. The accuracy of the proposed model is validated by means of simulation which reveals a very good match among theoretical and simulation results. The model can be used for protocol performance prediction and optimization purposes.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"6 3","pages":"168-172"},"PeriodicalIF":0.0,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142517770","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-23DOI: 10.1109/LNET.2024.3465516
Ayaka Oki;Yukio Ogawa;Kaoru Ota;Mianxiong Dong
We apply federated learning (FL) to a distributed intrusion detection system (IDS), in which we deploy numerous detection servers on the edge of a network. FL can mitigate the impact of decreased training data in each server and exhibit almost the same detection rate as that of the non-distributed IDS for all attack classes. We verify the effect of FL using explainable artificial intelligence (XAI); this effect is demonstrated by the distance between the feature set of each attack class in the distributed IDS and that in the non-distributed IDS. The distance increases for independent learning and decreases for FL.
{"title":"Evaluation of Applying Federated Learning to Distributed Intrusion Detection Systems Through Explainable AI","authors":"Ayaka Oki;Yukio Ogawa;Kaoru Ota;Mianxiong Dong","doi":"10.1109/LNET.2024.3465516","DOIUrl":"https://doi.org/10.1109/LNET.2024.3465516","url":null,"abstract":"We apply federated learning (FL) to a distributed intrusion detection system (IDS), in which we deploy numerous detection servers on the edge of a network. FL can mitigate the impact of decreased training data in each server and exhibit almost the same detection rate as that of the non-distributed IDS for all attack classes. We verify the effect of FL using explainable artificial intelligence (XAI); this effect is demonstrated by the distance between the feature set of each attack class in the distributed IDS and that in the non-distributed IDS. The distance increases for independent learning and decreases for FL.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"6 3","pages":"198-202"},"PeriodicalIF":0.0,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142518019","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-14DOI: 10.1109/LNET.2024.3444495
Omid Abbasi;Georges Kaddoum
Satellite communication systems encounter channel aging issues due to the substantial distance that separates users and satellites. In such systems, the estimated channel state at a given time slot reflects the channel state from several time slots in the past. This letter proposes a long short-term memory (LSTM)-based architecture for channel prediction to mitigate the channel aging problem. The proposed scheme predicts the next time slot’s channel based on a block of estimated channel state information (CSI) from previous time slots. We consider the effect of channel aging in the training phase so that channel prediction in the testing phase is performed based on available data. We demonstrated through simulation experiments on new radio non-terrestrial network tapped delay line (NR NTN TDL) channel models, that our proposed scheme can effectively mitigate channel aging, and that it performs better than outdated channels. The proposed scheme improves the reliability and efficiency of satellite communication systems with long propagation delays.
{"title":"Channel Aging-Aware LSTM-Based Channel Prediction for Satellite Communications","authors":"Omid Abbasi;Georges Kaddoum","doi":"10.1109/LNET.2024.3444495","DOIUrl":"https://doi.org/10.1109/LNET.2024.3444495","url":null,"abstract":"Satellite communication systems encounter channel aging issues due to the substantial distance that separates users and satellites. In such systems, the estimated channel state at a given time slot reflects the channel state from several time slots in the past. This letter proposes a long short-term memory (LSTM)-based architecture for channel prediction to mitigate the channel aging problem. The proposed scheme predicts the next time slot’s channel based on a block of estimated channel state information (CSI) from previous time slots. We consider the effect of channel aging in the training phase so that channel prediction in the testing phase is performed based on available data. We demonstrated through simulation experiments on new radio non-terrestrial network tapped delay line (NR NTN TDL) channel models, that our proposed scheme can effectively mitigate channel aging, and that it performs better than outdated channels. The proposed scheme improves the reliability and efficiency of satellite communication systems with long propagation delays.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"6 3","pages":"183-187"},"PeriodicalIF":0.0,"publicationDate":"2024-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142517984","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-13DOI: 10.1109/LNET.2024.3442833
Mohamed elShehaby;Aditya Kotha;Ashraf Matrawy
Adversarial training enhances the robustness of Machine Learning (ML) models against adversarial attacks. However, obtaining labeled training and adversarial training data in network/cybersecurity domains is challenging and costly. Therefore, this letter introduces Adaptive Continuous Adversarial Training (ACAT), a novel method that integrates adversarial training samples into the model during continuous learning sessions using real-world detected adversarial data. Experimental results with a SPAM detection dataset demonstrate that ACAT reduces the time required for adversarial sample detection compared to traditional processes (up to 4 times faster when dealing with 10,000 samples). Moreover, the accuracy of the under-attack ML-based SPAM filter increased from 69% to over 88% after just three retraining sessions.
{"title":"Introducing Adaptive Continuous Adversarial Training (ACAT) to Enhance Machine Learning Robustness","authors":"Mohamed elShehaby;Aditya Kotha;Ashraf Matrawy","doi":"10.1109/LNET.2024.3442833","DOIUrl":"https://doi.org/10.1109/LNET.2024.3442833","url":null,"abstract":"Adversarial training enhances the robustness of Machine Learning (ML) models against adversarial attacks. However, obtaining labeled training and adversarial training data in network/cybersecurity domains is challenging and costly. Therefore, this letter introduces Adaptive Continuous Adversarial Training (ACAT), a novel method that integrates adversarial training samples into the model during continuous learning sessions using real-world detected adversarial data. Experimental results with a SPAM detection dataset demonstrate that ACAT reduces the time required for adversarial sample detection compared to traditional processes (up to 4 times faster when dealing with 10,000 samples). Moreover, the accuracy of the under-attack ML-based SPAM filter increased from 69% to over 88% after just three retraining sessions.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"6 3","pages":"208-212"},"PeriodicalIF":0.0,"publicationDate":"2024-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142518018","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-30DOI: 10.1109/LNET.2024.3435723
Yanzhuo Jiang;Xueman Wang;Yingxu Lai;Yipeng Wang
Anomalies in packet length sequences caused by network topology structure and congestion greatly impact the performance of early network traffic classification. Additionally, insufficient differentiation of packet length sequences using a small number of packets also affects the performance. In this letter, we propose SePeric, a packet sequence permutation-aware approach to robust network traffic classification. By exploring the correlations within packet length sequences and adjusting them to eliminate the effects of anomalous sequence orders, as well as extracting additional features from the byte sequence of the first packet to supplement the insufficient differentiation in packet length sequences.
{"title":"A Packet Sequence Permutation-Aware Approach to Robust Network Traffic Classification","authors":"Yanzhuo Jiang;Xueman Wang;Yingxu Lai;Yipeng Wang","doi":"10.1109/LNET.2024.3435723","DOIUrl":"https://doi.org/10.1109/LNET.2024.3435723","url":null,"abstract":"Anomalies in packet length sequences caused by network topology structure and congestion greatly impact the performance of early network traffic classification. Additionally, insufficient differentiation of packet length sequences using a small number of packets also affects the performance. In this letter, we propose SePeric, a packet sequence permutation-aware approach to robust network traffic classification. By exploring the correlations within packet length sequences and adjusting them to eliminate the effects of anomalous sequence orders, as well as extracting additional features from the byte sequence of the first packet to supplement the insufficient differentiation in packet length sequences.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"6 3","pages":"203-207"},"PeriodicalIF":0.0,"publicationDate":"2024-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142518020","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-18DOI: 10.1109/LNET.2024.3430313
Yousef N. Shnaiwer;Megumi Kaneko
This letter presents a novel method for optimizing the outage performance of Reconfigurable Intelligent Surfaces (RIS)-assisted Rate-Splitting Multiple Access (RSMA) systems. The objective is to minimize the maximum outage probability for all messages to improve fairness. A new formulation based on minimizing the Entropic Value-at-Risk (EVaR) of the perceived minimum rate among all messages in the system is proposed to simplify the objective. We show that this formulation is equivalent to minimizing an upper bound on the maximum outage probability, then we transform it into a tractable smooth problem by devising a twice-differentiable approximation to it. In addition to its lower complexity, our method is shown by numerical results to outperform two benchmarks, namely, Discrete Exhaustive Search (DES) and Sequential Quadratic Programming (SQP)-based search methods.
{"title":"A Risk-Averse Outage Probability Minimization Method for RIS-Aided RSMA Systems","authors":"Yousef N. Shnaiwer;Megumi Kaneko","doi":"10.1109/LNET.2024.3430313","DOIUrl":"https://doi.org/10.1109/LNET.2024.3430313","url":null,"abstract":"This letter presents a novel method for optimizing the outage performance of Reconfigurable Intelligent Surfaces (RIS)-assisted Rate-Splitting Multiple Access (RSMA) systems. The objective is to minimize the maximum outage probability for all messages to improve fairness. A new formulation based on minimizing the Entropic Value-at-Risk (EVaR) of the perceived minimum rate among all messages in the system is proposed to simplify the objective. We show that this formulation is equivalent to minimizing an upper bound on the maximum outage probability, then we transform it into a tractable smooth problem by devising a twice-differentiable approximation to it. In addition to its lower complexity, our method is shown by numerical results to outperform two benchmarks, namely, Discrete Exhaustive Search (DES) and Sequential Quadratic Programming (SQP)-based search methods.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"6 3","pages":"173-178"},"PeriodicalIF":0.0,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142517935","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-03DOI: 10.1109/LNET.2024.3422482
Shirwan Piroti;Ashima Chawla;Tahar Zanouda
There are vast number of configurable parameters in a Radio Access Telecom Network. A significant amount of these parameters is configured by Radio Node or cell based on their deployment setting. Traditional methods rely on domain knowledge for individual parameter configuration, often leading to sub-optimal results. To improve this, a framework using a Deep Generative Graph Neural Network (GNN) is proposed. It encodes the network into a graph, extracts subgraphs for each RAN node, and employs a Siamese GNN (S-GNN) to learn embeddings. The framework recommends configuration parameters for a multitude of parameters and detects misconfigurations, handling both network expansion and existing cell reconfiguration. Tested on real-world data, the model surpasses baselines, demonstrating accuracy, generalizability, and robustness against concept drift.
无线接入电信网络中有大量可配置参数。其中大量参数由无线节点或小区根据其部署设置进行配置。传统方法依赖领域知识进行单个参数配置，往往会导致次优结果。为了改善这种情况，我们提出了一个使用深度生成图神经网络（GNN）的框架。它将网络编码成图，为每个 RAN 节点提取子图，并采用连体 GNN（S-GNN）来学习嵌入。该框架为众多参数推荐配置参数，并检测错误配置，同时处理网络扩展和现有小区的重新配置。该模型在真实世界数据上进行了测试，其准确性、通用性和对概念漂移的稳健性均超过了基准。
{"title":"Mobile Network Configuration Recommendation Using Deep Generative Graph Neural Network","authors":"Shirwan Piroti;Ashima Chawla;Tahar Zanouda","doi":"10.1109/LNET.2024.3422482","DOIUrl":"https://doi.org/10.1109/LNET.2024.3422482","url":null,"abstract":"There are vast number of configurable parameters in a Radio Access Telecom Network. A significant amount of these parameters is configured by Radio Node or cell based on their deployment setting. Traditional methods rely on domain knowledge for individual parameter configuration, often leading to sub-optimal results. To improve this, a framework using a Deep Generative Graph Neural Network (GNN) is proposed. It encodes the network into a graph, extracts subgraphs for each RAN node, and employs a Siamese GNN (S-GNN) to learn embeddings. The framework recommends configuration parameters for a multitude of parameters and detects misconfigurations, handling both network expansion and existing cell reconfiguration. Tested on real-world data, the model surpasses baselines, demonstrating accuracy, generalizability, and robustness against concept drift.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"6 3","pages":"179-182"},"PeriodicalIF":0.0,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142518017","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-19DOI: 10.1109/LNET.2024.3416555
Solomon Orduen Yese;Sara Berri;Arsenia Chorti
This letter proposes a slice admission control scheme to maximize profit and resource utilization. It considers an online scenario where the infrastructure provider (InP) does not have full knowledge of future requests and requests can renege after their waiting time is exceeded. Moreover, it employs a dynamic priority and a capacity sharing mechanism to buy back idle resources from already accepted slices. The performance evaluation demonstrates that the proposed algorithm yields about 26%, 7%, and 7.3% higher profit, acceptance rate and resource utilization gains over the state of the art schemes, respectively.
{"title":"Efficient Online Slice Admission Control Scheme in Next Generation Networks","authors":"Solomon Orduen Yese;Sara Berri;Arsenia Chorti","doi":"10.1109/LNET.2024.3416555","DOIUrl":"https://doi.org/10.1109/LNET.2024.3416555","url":null,"abstract":"This letter proposes a slice admission control scheme to maximize profit and resource utilization. It considers an online scenario where the infrastructure provider (InP) does not have full knowledge of future requests and requests can renege after their waiting time is exceeded. Moreover, it employs a dynamic priority and a capacity sharing mechanism to buy back idle resources from already accepted slices. The performance evaluation demonstrates that the proposed algorithm yields about 26%, 7%, and 7.3% higher profit, acceptance rate and resource utilization gains over the state of the art schemes, respectively.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"6 3","pages":"163-167"},"PeriodicalIF":0.0,"publicationDate":"2024-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142517865","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：