Computer Communications最新文献_第4页

Power prediction and energy aware placement of containers over virtual machines 在虚拟机上对容器进行功率预测和能源感知

IF 4.3 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Computer Communications

Pub Date : 2025-12-17 DOI: 10.1016/j.comcom.2025.108340

Rafael Albuquerque, Brigitte Jaumard

The rapid expansion of 5G and the upcoming arrival of 6G have significantly increased the demand for cloud computing resources, especially in edge cloud servers, to meet stringent connectivity and latency requirements. This surge has raised serious energy concerns as data centers now account for about 1–1.5% of global energy consumption and contribute about 1% of global CO

_{2}

emissions. In response to these facts, this study proposes a novel energy-aware machine learning model, using power sensor data from physical machines (PMs) in data centers, to optimize energy consumption while managing container placement as a use case.

We conducted experiments in a testbed using realistic 5G traffic scenarios, deliberately avoiding artificial stressors such as stress-ng, which create synthetic loads that do not accurately reflect real-world resource utilization. Our machine learning model, particularly the XGBoost implementation, proved to be highly effective, achieving an

R^{2}

score of 91.2%. The model demonstrated the ability to reduce energy consumption by 3% and improve task completion times, all without the need for explicit consolidation strategies or cluster reconfiguration.

This approach highlights the power of machine learning in optimizing energy efficiency in dynamic and resource-intensive environments such as edge cloud servers, providing a scalable solution for data centers facing increasing energy demands.

5G的快速扩张和即将到来的6G大幅增加了对云计算资源的需求，特别是在边缘云服务器方面，以满足严格的连接和延迟要求。这种激增引起了严重的能源问题，因为数据中心目前约占全球能源消耗的1-1.5%，并贡献了约1%的全球二氧化碳排放量。针对这些事实，本研究提出了一种新的能源感知机器学习模型，该模型使用数据中心物理机器（pm）的功率传感器数据，以优化能源消耗，同时管理容器放置作为用例。我们在一个使用真实5G流量场景的测试平台上进行了实验，刻意避免了压力-ng等人为压力源，这些压力源会产生无法准确反映真实资源利用率的合成负载。我们的机器学习模型，特别是XGBoost实现，被证明是非常有效的，达到了91.2%的R2分数。该模型表明，在不需要明确的整合策略或集群重新配置的情况下，该模型能够将能耗降低3%，并提高任务完成时间。这种方法突出了机器学习在动态和资源密集型环境（如边缘云服务器）中优化能源效率的强大功能，为面临日益增长的能源需求的数据中心提供了可扩展的解决方案。

{"title":"Power prediction and energy aware placement of containers over virtual machines","authors":"Rafael Albuquerque, Brigitte Jaumard","doi":"10.1016/j.comcom.2025.108340","DOIUrl":"10.1016/j.comcom.2025.108340","url":null,"abstract":"<div><div>The rapid expansion of 5G and the upcoming arrival of 6G have significantly increased the demand for cloud computing resources, especially in edge cloud servers, to meet stringent connectivity and latency requirements. This surge has raised serious energy concerns as data centers now account for about 1–1.5% of global energy consumption and contribute about 1% of global CO<span><math><msub><mrow></mrow><mrow><mn>2</mn></mrow></msub></math></span> emissions. In response to these facts, this study proposes a novel energy-aware machine learning model, using power sensor data from physical machines (PMs) in data centers, to optimize energy consumption while managing container placement as a use case.</div><div>We conducted experiments in a testbed using realistic 5G traffic scenarios, deliberately avoiding artificial stressors such as stress-ng, which create synthetic loads that do not accurately reflect real-world resource utilization. Our machine learning model, particularly the XGBoost implementation, proved to be highly effective, achieving an <span><math><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup></math></span> score of 91.2%. The model demonstrated the ability to reduce energy consumption by 3% and improve task completion times, all without the need for explicit consolidation strategies or cluster reconfiguration.</div><div>This approach highlights the power of machine learning in optimizing energy efficiency in dynamic and resource-intensive environments such as edge cloud servers, providing a scalable solution for data centers facing increasing energy demands.</div></div>","PeriodicalId":55224,"journal":{"name":"Computer Communications","volume":"248 ","pages":"Article 108340"},"PeriodicalIF":4.3,"publicationDate":"2025-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145903969","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Intelligent routing optimization with deep reinforcement learning and Betweenness Centrality Theory in software-defined networks 基于深度强化学习和中间性理论的软件定义网络智能路由优化

IF 4.3 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Computer Communications

Pub Date : 2025-12-16 DOI: 10.1016/j.comcom.2025.108401

Zongming Wu , Qiang Tang , Jijun Cao , Sihao Wen , Bao Li

For highly dynamic and complex communication networks, existing DRL-based routing optimization solutions suffer from inefficient training, leading to degraded network performance. In this paper, we propose an Intelligent Routing Optimization method with Deep Reinforcement Learning and Betweenness Centrality Theory (IROD-BC). This SDN routing solution based on distributed proximal policy optimization can achieve fast convergence of training and improve the overall performance of the network. First, before training, we select a set of controlled nodes in the network based on the Betweenness Centrality Theory. Second, during training, we adjust the weights of the links in the weighted shortest path algorithm based on this set of controlled nodes to improve the convergence efficiency of distributed proximal policy optimization. The learning agent modifies the weights of the links in the controlled nodes links based on the network traffic state information of this set of controlled nodes to reduce the agent’s dependence on the network topology. We utilize SDN controller to collect network traffic state information including packet loss and latency. Ultimately, the IROD-BC proposed in this paper can learn to make better routing control decisions from its own experience by interacting with the network environment until the learning agent converges and obtains the optimal routing paths. We conducted extensive experiments on three real network topologies to evaluate the performance of IROD-BC. The experimental results show that IROD-BC outperforms existing DRL-based routing solutions and OSPF algorithm in terms of latency, link throughput, and packet loss.

对于高动态、复杂的通信网络，现有基于drl的路由优化方案存在训练效率低下的问题，导致网络性能下降。本文提出了一种基于深度强化学习和中间性理论（IROD-BC）的智能路由优化方法。这种基于分布式近端策略优化的SDN路由解决方案可以实现训练的快速收敛，提高网络的整体性能。首先，在训练前，我们根据中间性中心性理论在网络中选择一组受控节点。其次，在训练过程中，基于该控制节点集调整加权最短路径算法中链路的权值，提高分布式近端策略优化的收敛效率。学习智能体根据这组被控制节点的网络流量状态信息来修改被控制节点链路中链路的权重，以减少智能体对网络拓扑的依赖。我们利用SDN控制器来收集网络流量状态信息，包括丢包和延迟。最终，本文提出的IROD-BC可以通过与网络环境的交互，从自身的经验中学习做出更好的路由控制决策，直到学习代理收敛并获得最优路由路径。我们在三种真实网络拓扑上进行了大量的实验来评估IROD-BC的性能。实验结果表明，IROD-BC在时延、链路吞吐量和丢包方面都优于现有基于drl的路由解决方案和OSPF算法。

{"title":"Intelligent routing optimization with deep reinforcement learning and Betweenness Centrality Theory in software-defined networks","authors":"Zongming Wu , Qiang Tang , Jijun Cao , Sihao Wen , Bao Li","doi":"10.1016/j.comcom.2025.108401","DOIUrl":"10.1016/j.comcom.2025.108401","url":null,"abstract":"<div><div>For highly dynamic and complex communication networks, existing DRL-based routing optimization solutions suffer from inefficient training, leading to degraded network performance. In this paper, we propose an Intelligent Routing Optimization method with Deep Reinforcement Learning and Betweenness Centrality Theory (IROD-BC). This SDN routing solution based on distributed proximal policy optimization can achieve fast convergence of training and improve the overall performance of the network. First, before training, we select a set of controlled nodes in the network based on the Betweenness Centrality Theory. Second, during training, we adjust the weights of the links in the weighted shortest path algorithm based on this set of controlled nodes to improve the convergence efficiency of distributed proximal policy optimization. The learning agent modifies the weights of the links in the controlled nodes links based on the network traffic state information of this set of controlled nodes to reduce the agent’s dependence on the network topology. We utilize SDN controller to collect network traffic state information including packet loss and latency. Ultimately, the IROD-BC proposed in this paper can learn to make better routing control decisions from its own experience by interacting with the network environment until the learning agent converges and obtains the optimal routing paths. We conducted extensive experiments on three real network topologies to evaluate the performance of IROD-BC. The experimental results show that IROD-BC outperforms existing DRL-based routing solutions and OSPF algorithm in terms of latency, link throughput, and packet loss.</div></div>","PeriodicalId":55224,"journal":{"name":"Computer Communications","volume":"247 ","pages":"Article 108401"},"PeriodicalIF":4.3,"publicationDate":"2025-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145791357","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Indoor positioning with Wi-Fi Location: A survey of IEEE 802.11mc/az/bk fine timing measurement research 基于Wi-Fi定位的室内定位：IEEE 802.11mc/az/bk精细定时测量研究综述

IF 4.3 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Computer Communications

Pub Date : 2025-12-12 DOI: 10.1016/j.comcom.2025.108400

Katarzyna Kosek-Szott , Szymon Szott , Wojciech Ciezobka , Maksymilian Wojnar , Krzysztof Rusek , Jonathan Segev

Indoor positioning is an enabling technology for home, office, and industrial network users because it provides numerous information and communication technology (ICT) and Internet of things (IoT) functionalities such as indoor navigation, smart meter localization, asset tracking, support for emergency services, and detection of hazardous situations. The IEEE 802.11mc fine timing measurement (FTM) protocol (commercially known as Wi-Fi Location) has great potential to enable indoor positioning in future generation devices, primarily because of the high availability of Wi-Fi networks, FTM’s high accuracy and device support. Furthermore, new FTM enhancements are available in the released (802.11az) and recently completed (802.11bk) amendments. Despite the multitude of literature reviews on indoor positioning, a survey dedicated to FTM and its recent enhancements has so far been lacking. We fill this gap by classifying and reviewing over 180 research papers related to the practical accuracy achieved with FTM, methods for improving its accuracy (also with machine learning), combining FTM with other indoor positioning systems, FTM-based applications, and security issues. Based on the conducted survey, we summarize the most important research achievements and formulate open areas for further research.

室内定位是一项适用于家庭、办公室和工业网络用户的使能技术，因为它提供了许多信息和通信技术（ICT）和物联网（IoT）功能，如室内导航、智能电表定位、资产跟踪、紧急服务支持和危险情况检测。IEEE 802.11mc精细定时测量（FTM）协议（商业上称为Wi-Fi定位）在下一代设备中具有实现室内定位的巨大潜力，主要是因为Wi-Fi网络的高可用性，FTM的高精度和设备支持。此外，在已发布的（802.11az）和最近完成的（802.11bk）修订中提供了新的FTM增强功能。尽管有大量关于室内定位的文献综述，但迄今为止还缺乏专门针对FTM及其近期增强功能的调查。我们通过分类和审查180多篇研究论文来填补这一空白，这些论文涉及FTM实现的实际精度、提高其精度的方法（也包括机器学习）、FTM与其他室内定位系统的结合、基于FTM的应用以及安全问题。在调查的基础上，我们总结了最重要的研究成果，并提出了进一步研究的开放领域。

{"title":"Indoor positioning with Wi-Fi Location: A survey of IEEE 802.11mc/az/bk fine timing measurement research","authors":"Katarzyna Kosek-Szott , Szymon Szott , Wojciech Ciezobka , Maksymilian Wojnar , Krzysztof Rusek , Jonathan Segev","doi":"10.1016/j.comcom.2025.108400","DOIUrl":"10.1016/j.comcom.2025.108400","url":null,"abstract":"<div><div>Indoor positioning is an enabling technology for home, office, and industrial network users because it provides numerous information and communication technology (ICT) and Internet of things (IoT) functionalities such as indoor navigation, smart meter localization, asset tracking, support for emergency services, and detection of hazardous situations. The IEEE 802.11mc fine timing measurement (FTM) protocol (commercially known as Wi-Fi Location) has great potential to enable indoor positioning in future generation devices, primarily because of the high availability of Wi-Fi networks, FTM’s high accuracy and device support. Furthermore, new FTM enhancements are available in the released (802.11az) and recently completed (802.11bk) amendments. Despite the multitude of literature reviews on indoor positioning, a survey dedicated to FTM and its recent enhancements has so far been lacking. We fill this gap by classifying and reviewing over 180 research papers related to the practical accuracy achieved with FTM, methods for improving its accuracy (also with machine learning), combining FTM with other indoor positioning systems, FTM-based applications, and security issues. Based on the conducted survey, we summarize the most important research achievements and formulate open areas for further research.</div></div>","PeriodicalId":55224,"journal":{"name":"Computer Communications","volume":"247 ","pages":"Article 108400"},"PeriodicalIF":4.3,"publicationDate":"2025-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145791356","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Energy saving in Fixed Wireless Access networks utilizing scheduled coordinated sleeping time 利用预定的协调睡眠时间节约固定无线接入网络的能源

IF 4.3 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Computer Communications

Pub Date : 2025-12-09 DOI: 10.1016/j.comcom.2025.108399

Ozgur Ozkaya, Jetmir Haxhibeqiri, Ingrid Moerman, Jeroen Hoebeke

Fixed Wireless Access (FWA) networks are used to extend connectivity to areas with limited or no access, especially where the deployment of wired infrastructure is costly. In such networks, the infrastructure can take the form of a multi-hop mesh network consisting of Distribution Nodes (DNs) and Client Nodes (CNs). A CN is served by a DN and extends connectivity within homes by acting as an access point (AP). Due to fluctuations in traffic over time, network utilization also fluctuates. When the network is scarcely utilized, it leads to energy waste due to powering the network during these times. In this paper, we explore methods to reduce energy consumption in wireless mesh networks (WMNs) by implementing coordinated sleeping times for APs of the last hop and the DNs inside the FWA network. By dynamically scheduling sleep patterns in the last hop, the solution achieves network-wide energy savings without compromising the quality of service for traffic flows in terms of latency and reliability. Moreover, in this paper, we reduce the Orthogonal Frequency Division Multiple Access (OFDMA) overhead and utilize this to organize time-critical traffic in the last hop of FWA, benefiting from the coordinated sleeping time. Our results show that in medium-load scenarios, this approach can achieve up to 33% energy savings in FWA mesh networks combined with NextGen Wi-Fi while maintaining bounded latency for time-critical applications and serving non-time-critical traffic.

固定无线接入（FWA）网络用于将连接扩展到接入有限或没有接入的地区，特别是在有线基础设施部署成本高昂的地区。在这种网络中，基础设施可以采用由分布节点（DNs）和客户端节点（CNs）组成的多跳网状网络的形式。CN由DN提供服务，并通过充当接入点（AP）来扩展家庭内部的连通性。由于流量随时间的波动，网络利用率也会波动。当网络很少被利用时，由于在这些时间为网络供电，导致能源浪费。在本文中，我们探讨了通过在无线网状网络（WMNs）中实现最后一跳ap和FWA网络内DNs的协调睡眠时间来降低能量消耗的方法。通过在最后一跳中动态调度睡眠模式，该解决方案实现了全网范围的节能，而不会在延迟和可靠性方面影响流量流的服务质量。此外，本文还减少了正交频分多址（OFDMA）的开销，并利用它来组织FWA最后一跳的时间关键型业务，从而受益于协调的休眠时间。我们的研究结果表明，在中等负载情况下，这种方法可以在FWA网状网络与NextGen Wi-Fi相结合的情况下节省高达33%的能源，同时为时间关键型应用和服务非时间关键型流量保持有限的延迟。

{"title":"Energy saving in Fixed Wireless Access networks utilizing scheduled coordinated sleeping time","authors":"Ozgur Ozkaya, Jetmir Haxhibeqiri, Ingrid Moerman, Jeroen Hoebeke","doi":"10.1016/j.comcom.2025.108399","DOIUrl":"10.1016/j.comcom.2025.108399","url":null,"abstract":"<div><div>Fixed Wireless Access (FWA) networks are used to extend connectivity to areas with limited or no access, especially where the deployment of wired infrastructure is costly. In such networks, the infrastructure can take the form of a multi-hop mesh network consisting of Distribution Nodes (DNs) and Client Nodes (CNs). A CN is served by a DN and extends connectivity within homes by acting as an access point (AP). Due to fluctuations in traffic over time, network utilization also fluctuates. When the network is scarcely utilized, it leads to energy waste due to powering the network during these times. In this paper, we explore methods to reduce energy consumption in wireless mesh networks (WMNs) by implementing coordinated sleeping times for APs of the last hop and the DNs inside the FWA network. By dynamically scheduling sleep patterns in the last hop, the solution achieves network-wide energy savings without compromising the quality of service for traffic flows in terms of latency and reliability. Moreover, in this paper, we reduce the Orthogonal Frequency Division Multiple Access (OFDMA) overhead and utilize this to organize time-critical traffic in the last hop of FWA, benefiting from the coordinated sleeping time. Our results show that in medium-load scenarios, this approach can achieve up to 33% energy savings in FWA mesh networks combined with NextGen Wi-Fi while maintaining bounded latency for time-critical applications and serving non-time-critical traffic.</div></div>","PeriodicalId":55224,"journal":{"name":"Computer Communications","volume":"247 ","pages":"Article 108399"},"PeriodicalIF":4.3,"publicationDate":"2025-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145738565","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

User Plane Performance in Beyond 5G Networks: Comprehensive Analysis and Evaluation 超5G网络中的用户平面性能：综合分析与评估

IF 4.3 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Computer Communications

Pub Date : 2025-12-05 DOI: 10.1016/j.comcom.2025.108397

Fridolin Siegmund , Ralf Kundel , Tobias Meuser , Ralf Steinmetz

Emerging applications such as autonomous driving, virtual reality, and smart factories place greater demands on the Quality of Service of existing network infrastructure, particularly radio networks. The current 5th and new 6th generation of cellular networks aim to meet these requirements and provide ubiquitous connectivity to devices with diverse demands. These networks comprise a control plane and a user plane. While the control plane is responsible for managing the network and its devices, the user plane forwards data and directly influences the experienced Quality of Service. A key network function in the user plane is the User Plane Function (UPF), which forwards packets between cellular network devices and the data network, such as the Internet or an edge data center. However, the extent to which existing UPF implementations can provide sufficient Quality of Service for emerging applications remains largely unexplored. In this work, we analyze and compare various UPF implementations from both theoretical and practical perspectives. We consider both software-based and hardware-accelerated implementations and compare them in terms of performance and latency under load. The setup enables up to 10,000 subscriber sessions while enforcing QoS mechanisms such as rate limiting. The evaluation demonstrates that three of the four investigated UPFs provide QoS enforcement, while their latency behavior differs by orders of magnitude depending on the employed technology.

自动驾驶、虚拟现实和智能工厂等新兴应用对现有网络基础设施（尤其是无线网络）的服务质量提出了更高的要求。目前的第5代和新的第6代蜂窝网络旨在满足这些要求，并为具有不同需求的设备提供无处不在的连接。这些网络包括控制平面和用户平面。控制平面负责管理网络及其设备，而用户平面负责转发数据，并直接影响体验到的服务质量。用户平面的一个关键网络功能是UPF (user plane function)，它负责蜂窝网络设备与数据网络（如Internet或边缘数据中心）之间的报文转发。然而，现有的UPF实现在多大程度上能够为新兴的应用程序提供足够的服务质量，这在很大程度上仍未得到探索。在这项工作中，我们从理论和实践的角度分析和比较了各种UPF实现。我们考虑了基于软件和硬件加速的实现，并比较了它们在负载下的性能和延迟。该设置支持多达10,000个订阅者会话，同时强制执行速率限制等QoS机制。评估表明，四个被调查的upf中有三个提供QoS强制，而它们的延迟行为因所采用的技术而异。

{"title":"User Plane Performance in Beyond 5G Networks: Comprehensive Analysis and Evaluation","authors":"Fridolin Siegmund , Ralf Kundel , Tobias Meuser , Ralf Steinmetz","doi":"10.1016/j.comcom.2025.108397","DOIUrl":"10.1016/j.comcom.2025.108397","url":null,"abstract":"<div><div>Emerging applications such as autonomous driving, virtual reality, and smart factories place greater demands on the Quality of Service of existing network infrastructure, particularly radio networks. The current 5th and new 6th generation of cellular networks aim to meet these requirements and provide ubiquitous connectivity to devices with diverse demands. These networks comprise a control plane and a user plane. While the control plane is responsible for managing the network and its devices, the user plane forwards data and directly influences the experienced Quality of Service. A key network function in the user plane is the User Plane Function (UPF), which forwards packets between cellular network devices and the data network, such as the Internet or an edge data center. However, the extent to which existing UPF implementations can provide sufficient Quality of Service for emerging applications remains largely unexplored. In this work, we analyze and compare various UPF implementations from both theoretical and practical perspectives. We consider both software-based and hardware-accelerated implementations and compare them in terms of performance and latency under load. The setup enables up to 10,000 subscriber sessions while enforcing QoS mechanisms such as rate limiting. The evaluation demonstrates that three of the four investigated UPFs provide QoS enforcement, while their latency behavior differs by orders of magnitude depending on the employed technology.</div></div>","PeriodicalId":55224,"journal":{"name":"Computer Communications","volume":"247 ","pages":"Article 108397"},"PeriodicalIF":4.3,"publicationDate":"2025-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145738563","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Redundancy in WiFi 7: Combining multi-link operation with IEEE 802.1CB FRER WiFi 7中的冗余：将多链路操作与IEEE 802.1CB frr相结合

IF 4.3 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Computer Communications

Pub Date : 2025-12-04 DOI: 10.1016/j.comcom.2025.108373

Doğanalp Ergenç, Tobias Reisinger, Falko Dressler

The increasing complexity of modern industrial and manufacturing systems, featuring numerous sensors and mobile components, demands reliable, low-latency communication over wireless networks. WiFi 7 addresses these requirements through enhancements such as Multi-Link Operation (MLO), enabling simultaneous use of multiple frequency bands and offering inherent link diversity. This raises the question of whether MLO can be effectively leveraged for reliability in critical systems. In this paper, we explore the integration of IEEE 802.1CB Frame Replication and Elimination for Reliability (FRER), a core Time-Sensitive Networking (TSN) standard, over MLO to address this question. We present an open-source implementation of FRER over MLO in the OMNeT++ simulator, highlight key challenges in combining these technologies, and evaluate its effectiveness in improving reliability under wireless-specific conditions such as mobility and congestion. Our results demonstrate that FRER can enhance packet delivery ratio and ensure bounded latency, albeit at the expense of reduced channel efficiency due to redundancy.

现代工业和制造系统日益复杂，具有众多传感器和移动组件，需要通过无线网络进行可靠、低延迟的通信。WiFi 7通过多链路操作（MLO）等增强功能解决了这些要求，可以同时使用多个频段并提供固有的链路分集。这就提出了一个问题，即MLO是否可以有效地用于关键系统的可靠性。在本文中，我们探讨了IEEE 802.1CB帧复制和消除可靠性（FRER）的集成，这是一个核心的时间敏感网络（TSN）标准，通过MLO来解决这个问题。我们在omnet++模拟器中提出了基于MLO的FRER的开源实现，强调了结合这些技术的关键挑战，并评估了其在提高无线特定条件下（如移动性和拥堵）可靠性方面的有效性。我们的研究结果表明，尽管以冗余降低信道效率为代价，但frr可以提高分组传送率并确保有界延迟。

{"title":"Redundancy in WiFi 7: Combining multi-link operation with IEEE 802.1CB FRER","authors":"Doğanalp Ergenç, Tobias Reisinger, Falko Dressler","doi":"10.1016/j.comcom.2025.108373","DOIUrl":"10.1016/j.comcom.2025.108373","url":null,"abstract":"<div><div>The increasing complexity of modern industrial and manufacturing systems, featuring numerous sensors and mobile components, demands reliable, low-latency communication over wireless networks. WiFi 7 addresses these requirements through enhancements such as Multi-Link Operation (MLO), enabling simultaneous use of multiple frequency bands and offering inherent link diversity. This raises the question of whether MLO can be effectively leveraged for reliability in critical systems. In this paper, we explore the integration of IEEE 802.1CB Frame Replication and Elimination for Reliability (FRER), a core Time-Sensitive Networking (TSN) standard, over MLO to address this question. We present an open-source implementation of FRER over MLO in the OMNeT++ simulator, highlight key challenges in combining these technologies, and evaluate its effectiveness in improving reliability under wireless-specific conditions such as mobility and congestion. Our results demonstrate that FRER can enhance packet delivery ratio and ensure bounded latency, albeit at the expense of reduced channel efficiency due to redundancy.</div></div>","PeriodicalId":55224,"journal":{"name":"Computer Communications","volume":"247 ","pages":"Article 108373"},"PeriodicalIF":4.3,"publicationDate":"2025-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145738562","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Characterizing the performance of classification models through conformal correlation matrices 用共形相关矩阵来表征分类模型的性能

IF 4.3 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Computer Communications

Pub Date : 2025-12-04 DOI: 10.1016/j.comcom.2025.108398

Alessandro Perlo , Carla Fabiana Chiasserini , Gustavo De Veciana , Francesco Malandrino

In classification tasks, it is critical to accurately distinguish between specific classes, as misclassifications can undermine system reliability and user trust. In this paper, we study how client selection in both centralized and federated learning environments affects the performance of classification models trained on heterogeneous data. When training datasets across clients are statistically diverse, careful client selection becomes crucial to improve the ability of the model to discriminate between classes, while preserving privacy. In particular, we introduce a novel metric based on conformal prediction outcomes – the conformal correlation matrix – which captures the likelihood of class pairs co-occurring within conformal prediction sets. Unlike the traditional confusion matrix, which quantifies actual misclassifications, our metric characterizes potential ambiguities between classes, thus offering a complementary perspective on model performance and uncertainty. Through a series of examples, we demonstrate how our proposed metric can guide informed client selection and enhance model performance in both centralized and federated training settings. Our results highlight the potential of conformal-based metrics to improve classification reliability while safeguarding sensitive information about individual client data.

在分类任务中，准确区分特定的类是至关重要的，因为错误的分类会破坏系统可靠性和用户信任。在本文中，我们研究了集中式和联邦学习环境中的客户端选择如何影响在异构数据上训练的分类模型的性能。当跨客户端的训练数据集具有统计多样性时，谨慎的客户选择对于提高模型区分类别的能力，同时保护隐私至关重要。特别是，我们引入了一种基于共形预测结果的新度量-共形相关矩阵-它捕获了类对在共形预测集中共同出现的可能性。与量化实际错误分类的传统混淆矩阵不同，我们的度量描述了类之间潜在的模糊性，从而提供了模型性能和不确定性的互补视角。通过一系列示例，我们演示了我们提出的度量如何在集中式和联合式训练设置中指导明智的客户选择并增强模型性能。我们的研究结果强调了基于一致性的度量在保护个人客户数据敏感信息的同时提高分类可靠性的潜力。

{"title":"Characterizing the performance of classification models through conformal correlation matrices","authors":"Alessandro Perlo , Carla Fabiana Chiasserini , Gustavo De Veciana , Francesco Malandrino","doi":"10.1016/j.comcom.2025.108398","DOIUrl":"10.1016/j.comcom.2025.108398","url":null,"abstract":"<div><div>In classification tasks, it is critical to accurately distinguish between specific classes, as misclassifications can undermine system reliability and user trust. In this paper, we study how client selection in both centralized and federated learning environments affects the performance of classification models trained on heterogeneous data. When training datasets across clients are statistically diverse, careful client selection becomes crucial to improve the ability of the model to discriminate between classes, while preserving privacy. In particular, we introduce a novel metric based on conformal prediction outcomes – the conformal correlation matrix – which captures the likelihood of class pairs co-occurring within conformal prediction sets. Unlike the traditional confusion matrix, which quantifies actual misclassifications, our metric characterizes potential ambiguities between classes, thus offering a complementary perspective on model performance and uncertainty. Through a series of examples, we demonstrate how our proposed metric can guide informed client selection and enhance model performance in both centralized and federated training settings. Our results highlight the potential of conformal-based metrics to improve classification reliability while safeguarding sensitive information about individual client data.</div></div>","PeriodicalId":55224,"journal":{"name":"Computer Communications","volume":"247 ","pages":"Article 108398"},"PeriodicalIF":4.3,"publicationDate":"2025-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145685748","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Enhancing cellular-enabled collaborative robots planning through GNSS data for SAR scenarios 通过GNSS数据为SAR场景增强蜂窝支持的协作机器人规划

IF 4.3 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Computer Communications

Pub Date : 2025-12-04 DOI: 10.1016/j.comcom.2025.108376

Arnau Romero , Carmen Delgado , Jana Baguer , Raúl Suárez , Xavier Costa-Pérez

Cellular-enabled collaborative robots are becoming paramount in Search-and-Rescue (SAR) and emergency response. Crucially dependent on resilient mobile network connectivity, they serve as invaluable assets for tasks like rapid victim localization and the exploration of hazardous, otherwise unreachable areas. However, their reliance on battery power and the need for persistent, low-latency communication limit operational time and mobility. To address this, and considering the evolving capabilities of 5G/6G networks, we propose a novel SAR framework that includes Mission Planning and Mission Execution phases and that optimizes robot deployment. By considering parameters such as the exploration area size, terrain elevation, robot fleet size, communication-influenced energy profiles, desired exploration rate, and target response time, our framework determines the minimum number of robots required and their optimal paths to ensure effective coverage and timely data backhaul over mobile networks. Our results demonstrate the trade-offs between number of robots, explored area, and response time for wheeled and quadruped robots. Further, we quantify the impact of terrain elevation data on mission time and energy consumption, showing the benefits of incorporating real-world environmental factors that might also affect mobile signal propagation and connectivity into SAR planning. This framework provides critical insights for leveraging next-generation mobile networks to enhance autonomous SAR operations.

支持蜂窝的协作机器人在搜索与救援（SAR）和应急响应中变得至关重要。它们主要依赖于弹性的移动网络连接，对于快速定位受害者和探索危险的、否则无法到达的地区等任务来说，它们是无价的资产。然而，它们对电池动力的依赖以及对持久、低延迟通信的需求限制了操作时间和移动性。为了解决这个问题，并考虑到5G/6G网络不断发展的能力，我们提出了一个新的SAR框架，包括任务规划和任务执行阶段，并优化机器人部署。通过考虑勘探区域大小、地形高程、机器人队伍规模、通信影响的能量分布、期望的勘探率和目标响应时间等参数，我们的框架确定了所需机器人的最小数量及其最佳路径，以确保移动网络的有效覆盖和及时的数据回程。我们的研究结果展示了轮式和四足机器人在机器人数量、探索区域和响应时间之间的权衡。此外，我们量化了地形高程数据对任务时间和能耗的影响，显示了将可能影响移动信号传播和连接的现实环境因素纳入SAR规划的好处。该框架为利用下一代移动网络增强自主SAR操作提供了关键见解。

{"title":"Enhancing cellular-enabled collaborative robots planning through GNSS data for SAR scenarios","authors":"Arnau Romero , Carmen Delgado , Jana Baguer , Raúl Suárez , Xavier Costa-Pérez","doi":"10.1016/j.comcom.2025.108376","DOIUrl":"10.1016/j.comcom.2025.108376","url":null,"abstract":"<div><div>Cellular-enabled collaborative robots are becoming paramount in Search-and-Rescue (SAR) and emergency response. Crucially dependent on resilient mobile network connectivity, they serve as invaluable assets for tasks like rapid victim localization and the exploration of hazardous, otherwise unreachable areas. However, their reliance on battery power and the need for persistent, low-latency communication limit operational time and mobility. To address this, and considering the evolving capabilities of 5G/6G networks, we propose a novel SAR framework that includes Mission Planning and Mission Execution phases and that optimizes robot deployment. By considering parameters such as the exploration area size, terrain elevation, robot fleet size, communication-influenced energy profiles, desired exploration rate, and target response time, our framework determines the minimum number of robots required and their optimal paths to ensure effective coverage and timely data backhaul over mobile networks. Our results demonstrate the trade-offs between number of robots, explored area, and response time for wheeled and quadruped robots. Further, we quantify the impact of terrain elevation data on mission time and energy consumption, showing the benefits of incorporating real-world environmental factors that might also affect mobile signal propagation and connectivity into SAR planning. This framework provides critical insights for leveraging next-generation mobile networks to enhance autonomous SAR operations.</div></div>","PeriodicalId":55224,"journal":{"name":"Computer Communications","volume":"247 ","pages":"Article 108376"},"PeriodicalIF":4.3,"publicationDate":"2025-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145738577","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Scalable FSO-enhanced data center networks: A hybrid-optimized topology and expansion path 可扩展的fso增强数据中心网络：混合优化的拓扑和扩展路径

IF 4.3 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Computer Communications

Pub Date : 2025-11-29 DOI: 10.1016/j.comcom.2025.108374

Qian Kong , Jianning Su , Xiaowei Lu , Liming Liu , Guiyuan Zhang , Haijun Yuan

To address the growing traffic demands and scalability challenges in next-generation Data Center Networks (DCNs), this paper proposes and validates a scalable multi-layer topology enhanced with Free-Space Optical (FSO) links and introduces a hybrid strategy framework for its optimization. This framework integrates two complementary strategies: a Deep Reinforcement Learning (DRL)-based Dynamic Degree-Aware Free-Space Optics (DDA-FSO) policy and a greedy heuristic. Building upon this topology and framework, we establish and validate an “Optimal Expansion Path”, a data-driven roadmap for the scalable expansion of DCNs. Packet-level simulations in OMNeT++ confirm that following this path significantly reduces network delay. By validating that the Average Shortest Path Length (ASPL) can serve as an effective proxy for network delay, this study provides a theoretical value for the design and optimization of reconfigurable and scalable DCNs.

为了解决下一代数据中心网络（DCNs）日益增长的流量需求和可扩展性挑战，本文提出并验证了一种可扩展的多层拓扑结构，并引入了一种用于优化的混合策略框架。该框架集成了两种互补策略：基于深度强化学习（DRL）的动态度感知自由空间光学（DDA-FSO）策略和贪婪启发式策略。在此拓扑和框架的基础上，我们建立并验证了“最优扩展路径”，这是一个数据驱动的dcn可扩展路线图。omnet++中的包级模拟证实，遵循此路径可显著减少网络延迟。通过验证平均最短路径长度（ASPL）可以作为网络延迟的有效代理，本研究为可重构和可扩展的DCNs的设计和优化提供了理论价值。

引用次数: 0

5GCID: Dataset of 5GC intrusion detection system 5GCID: 5GC入侵检测系统数据集

IF 4.3 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Computer Communications

Pub Date : 2025-11-29 DOI: 10.1016/j.comcom.2025.108375

Yangliu Hu , Qian Sun , Tianbin Dang , Guangzhi Wu , Lin Tian

The widespread application of fifth-generation (5G) networks brings great convenience but also poses security threats to the 5G core networks (5GC). To effectively detect and prevent these attacks, deep learning (DL)-based anomaly detection methods are crucial. Existing DL-based methods need anomalous data to train the models. Those open-source anomalous datasets of wired networks cannot accurately represent the characteristics of the 5G protocol, such as sequence and fields, resulting in poor detection performance. To address this issue, this paper constructs a dataset for the 5GC intrusion detection system (5GCID), which consolidates the security vulnerabilities of the radio access network (RAN) domain and the 5GC user domain. These threats are analyzed, guiding the design of illustrative threat scenarios and the bespoke tools. Utilizing our 5G network security experimental platform, we gather protocol data to compile the 5GCID dataset as tools are executed on the platform. Furthermore, it provides two preprocessing methods for the 5GCID dataset, focusing on traffic characteristics and control signal structures, respectively. Additionally, we design an intrusion protection method for 5GC, underpinned by explainable artificial intelligence (XAI), referred to as X-5GCIPS. The proposed X-5GCIPS can be viewed as an application of the 5GCID dataset, promising to advance the field of intelligent cybersecurity measures in next-generation networks.

5G（第五代）网络的广泛应用给5G核心网（5GC）带来了极大的便利，但也带来了安全威胁。为了有效地检测和预防这些攻击，基于深度学习（DL）的异常检测方法至关重要。现有的基于dl的方法需要异常数据来训练模型。这些开源的有线网络异常数据集无法准确表征5G协议的序列、字段等特征，导致检测性能较差。针对这一问题，本文构建了5GC入侵检测系统（5GCID）数据集，该数据集整合了无线接入网（RAN）域和5GC用户域的安全漏洞。对这些威胁进行了分析，指导设计说明性威胁场景和定制工具。利用我们的5G网络安全实验平台，我们收集协议数据来编译5G cid数据集，并在平台上执行工具。并针对5GCID数据集提供了两种预处理方法，分别针对交通特征和控制信号结构进行预处理。此外，我们设计了一种基于可解释人工智能（XAI）的5GC入侵保护方法，称为X-5GCIPS。拟议的X-5GCIPS可以被视为5GCID数据集的应用，有望推进下一代网络中的智能网络安全措施领域。

{"title":"5GCID: Dataset of 5GC intrusion detection system","authors":"Yangliu Hu , Qian Sun , Tianbin Dang , Guangzhi Wu , Lin Tian","doi":"10.1016/j.comcom.2025.108375","DOIUrl":"10.1016/j.comcom.2025.108375","url":null,"abstract":"<div><div>The widespread application of fifth-generation (5G) networks brings great convenience but also poses security threats to the 5G core networks (5GC). To effectively detect and prevent these attacks, deep learning (DL)-based anomaly detection methods are crucial. Existing DL-based methods need anomalous data to train the models. Those open-source anomalous datasets of wired networks cannot accurately represent the characteristics of the 5G protocol, such as sequence and fields, resulting in poor detection performance. To address this issue, this paper constructs a dataset for the 5GC intrusion detection system (5GCID), which consolidates the security vulnerabilities of the radio access network (RAN) domain and the 5GC user domain. These threats are analyzed, guiding the design of illustrative threat scenarios and the bespoke tools. Utilizing our 5G network security experimental platform, we gather protocol data to compile the 5GCID dataset as tools are executed on the platform. Furthermore, it provides two preprocessing methods for the 5GCID dataset, focusing on traffic characteristics and control signal structures, respectively. Additionally, we design an intrusion protection method for 5GC, underpinned by explainable artificial intelligence (XAI), referred to as X-5GCIPS. The proposed X-5GCIPS can be viewed as an application of the 5GCID dataset, promising to advance the field of intelligent cybersecurity measures in next-generation networks.</div></div>","PeriodicalId":55224,"journal":{"name":"Computer Communications","volume":"247 ","pages":"Article 108375"},"PeriodicalIF":4.3,"publicationDate":"2025-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145738564","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0