Computer NetworksPub Date : 2024-11-04DOI: 10.1016/j.comnet.2024.110886
Duo Yang , Yunqi Gao , Bing Hu , A-Long Jin , Wei Wang , Yang You
{"title":"GWPF: Communication-efficient federated learning with Gradient-Wise Parameter Freezing","authors":"Duo Yang , Yunqi Gao , Bing Hu , A-Long Jin , Wei Wang , Yang You","doi":"10.1016/j.comnet.2024.110886","DOIUrl":"10.1016/j.comnet.2024.110886","url":null,"abstract":"<div><div>Communication bottleneck is a critical challenge in federated learning. While parameter freezing has emerged as a popular approach, utilizing fine-grained parameters as aggregation objects, existing methods suffer from issues such as a lack of thawing strategy, lag and inflexibility in the thawing process, and underutilization of frozen parameters’ updates. To address these challenges, we propose Gradient-Wise Parameter Freezing (GWPF), a mechanism that wisely controls frozen periods for different parameters through parameter freezing and thawing strategies. GWPF globally freezes parameters with insignificant gradients and excludes frozen parameters from global updates during the frozen period, reducing communication overhead and accelerating training. The thawing strategy, based on global decisions by the server and collaboration with clients, leverages real-time feedback on the locally accumulated gradients of frozen parameters in each round, achieving a balanced approach between mitigating communication and enhancing model accuracy. We provide theoretical analysis and a convergence guarantee for non-convex objectives. Extensive experiments confirm that our mechanism achieves a speedup of up to 4.52 times in time-to-accuracy performance and reduces communication overhead by up to 48.73%. It also improves final model accuracy by up to 2.01% compared to the existing fastest method APF. The code for GWPF is available at <span><span>https://github.com/Dora233/GWPF</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"255 ","pages":"Article 110886"},"PeriodicalIF":4.4,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142594076","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Computer NetworksPub Date : 2024-11-01DOI: 10.1016/j.comnet.2024.110882
Fanfan Shen , Bofan Yang , Jun Zhang , Chao Xu , Yong Chen , Yanxiang He
{"title":"TD3-based trajectory optimization for energy consumption minimization in UAV-assisted MEC system","authors":"Fanfan Shen , Bofan Yang , Jun Zhang , Chao Xu , Yong Chen , Yanxiang He","doi":"10.1016/j.comnet.2024.110882","DOIUrl":"10.1016/j.comnet.2024.110882","url":null,"abstract":"<div><div>Unmanned Aerial Vehicle (UAV) assisted Mobile Edge Computing (MEC) systems provide substantial benefits for task offloading and communication services, especially in situations where traditional communication infrastructure is unavailable. Current research emphasizes maintaining communication quality while minimizing total energy consumption and optimizing UAV flight trajectories. However, several issues remain: First, the energy consumption objective function lacks comprehensiveness, neglecting the impact of UAV flight energy consumption; second, an effective Deep Reinforcement Learning (DRL) algorithm has not been employed to address the non-convexity of the objective function; third, there is insufficient discussion regarding the practical significance of the proposed approach. To address these issues, this paper formulates an objective function aimed at minimizing MEC energy consumption by considering task offloading decisions, communication delays, computational energy consumption, and UAV flight energy consumption. We propose a Population Diversity-based Particle Swarm Optimization-Double Delay Deep Deterministic Policy Gradient (PDPSO-TD3) algorithm to find the optimal solution, enhance UAV flight trajectories through optimized offloading decisions, ensure efficient communication, and minimize the total energy consumption of the MEC system. Furthermore, we discuss the practical applicability of PDPSO-TD3 in detail and present the proposed scheme. Experimental results demonstrate that compared to the Deep Deterministic Policy Gradient (DDPG) algorithm, for transmission delay, MEC energy consumption, UAV flight energy consumption, and User Equipments (UEs) access rate metrics. The proposed PDPSO-TD3 algorithm can improvement the performance by about 14.3%, 10.1%, 6.1%, and 3.3%, respectively.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"255 ","pages":"Article 110882"},"PeriodicalIF":4.4,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142662356","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Computer NetworksPub Date : 2024-10-31DOI: 10.1016/j.comnet.2024.110879
Rameesha Rehman , Saif Ur Rehman Malik , Shahida Hafeezan Qureshi , Syed Atif Moqurrab
{"title":"A novel multi-modal Federated Learning based thermal-aware job scheduling framework","authors":"Rameesha Rehman , Saif Ur Rehman Malik , Shahida Hafeezan Qureshi , Syed Atif Moqurrab","doi":"10.1016/j.comnet.2024.110879","DOIUrl":"10.1016/j.comnet.2024.110879","url":null,"abstract":"<div><div>Cooling costs constitute more than half of the total data center energy expenditure. Thermal imbalance results in hotspot regions requiring additional cooling power. To reduce it, thermal aware job scheduling is a well-known software solution that is subject to predicting correct server temperatures. Existing solutions have not explored intelligent solutions and rely only on logic based algorithms to allocate tasks that work on predefined rules. Few deep learning based solutions that are proposed, have not explored its alternatives and existing data modalities in data centers, resulting in inefficient models. Existing literature only proposes solutions based on unimodal tabular data. Therefore, we propose a multimodal architecture that considers different underlying data modalities in data centers to increase the model’s efficiency and predict correct server temperatures. The increasing production of data and the need for storage and processing units has led to the development of distributed data centers. Existing techniques are limited to individual data centers which fail to consider the data privacy restrictions that arise while dealing with distributed scenarios. Findings from our simulations affirm our proposed scheme in terms of the objectives mentioned above. We propose a federated learning architecture that efficiently deals with distributed data centers while ensuring privacy. Our simulation results show an overall increase in the efficiency of the model in comparison to an existing intelligent solution. Furthermore, we provide comparative results that show how our model performs better and achieves lower thermal imbalance as compared to an existing scheme.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"255 ","pages":"Article 110879"},"PeriodicalIF":4.4,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142662730","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Computer NetworksPub Date : 2024-10-29DOI: 10.1016/j.comnet.2024.110868
Yingxu Lai , Jingwen Wei , Ye Chen
{"title":"Gradient correlation based detection of adversarial attacks on vehicular networks","authors":"Yingxu Lai , Jingwen Wei , Ye Chen","doi":"10.1016/j.comnet.2024.110868","DOIUrl":"10.1016/j.comnet.2024.110868","url":null,"abstract":"<div><div>The controller area network (CAN) bus, which controls real-time communication and data transmission among vehicle electronic control units, lacks security mechanisms and is highly vulnerable to attacks. Existing in-vehicle network intrusion detection systems (IDSs) typically rely on deep learning models for detection, which are susceptible to interference from adversarial attacks owing to the vulnerability of the models themselves, thereby compromising the detection performance. In this study, we propose an adversarial attack detection method based on gradient correlation that achieves a high accuracy rate using a linear approach to detect adversarial samples. The experimental results show that the proposed model does not require retraining of the original detection model and demonstrates better detection performance for multiple adversarial attacks.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"255 ","pages":"Article 110868"},"PeriodicalIF":4.4,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142662731","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Computer NetworksPub Date : 2024-10-29DOI: 10.1016/j.comnet.2024.110878
Mourice Otieno Ojijo , Daniel Ramotsoela , Ruth A. Oginga
{"title":"Slice admission control in 5G wireless communication with multi-dimensional state space and distributed action space: A sequential twin actor-critic approach","authors":"Mourice Otieno Ojijo , Daniel Ramotsoela , Ruth A. Oginga","doi":"10.1016/j.comnet.2024.110878","DOIUrl":"10.1016/j.comnet.2024.110878","url":null,"abstract":"<div><div>Network slicing represents a paradigm shift in the way resources are allocated for different 5G network functions through network function virtualization. This innovation aims to facilitate logical resource allocation, accommodating the anticipated surge in network resource requirements. This will harness automatic processing, scheduling, and orchestration for efficient management. To overcome the challenge of managing network resources under heavy demand, slice providers need to leverage both artificial intelligence and slice admission control strategies. While 5G network resources can be allocated to maintain a slice, the logical allocation and real-time network evaluation must be continuously examined and adjusted if network resilience is to be maintained. The complex task of leveraging slice admission control to maintain 5G network resilience has not been fully investigated. To tackle this problem, we propose a machine learning approach for slice admission control and resource allocation optimization so as to maintain network resilience. Machine learning algorithms offer a powerful tool for making robust and autonomous decisions, which are crucial for effective slice admission control. By intelligently allocating resources based on real-time demand and network conditions, these algorithms can help ensure long-term network resilience and achieve key objectives. While various machine learning algorithms hold promise for 5G resource management and admission control, reinforcement learning (RL) has emerged as a particularly exciting solution. Its ability to mimic human learning processes makes it a versatile solution, well-suited to tackle the complex challenges of network control. To fill this gap, we propose a new technique known as sequential twin actor critic (STAC). Simulations show that the STAC improves network resilience through enhanced admission probability and overall utility.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"255 ","pages":"Article 110878"},"PeriodicalIF":4.4,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142587237","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Computer NetworksPub Date : 2024-10-28DOI: 10.1016/j.comnet.2024.110874
Juan A. Fraire , Santiago Henn , Gregory Stock , Robin Ohs , Holger Hermanns , Felix Walter , Lynn Van Broock , Gabriel Ruffini , Federico Machado , Pablo Serratti , Jose Relloso
{"title":"Quantitative analysis of segmented satellite network architectures: A maritime surveillance case study","authors":"Juan A. Fraire , Santiago Henn , Gregory Stock , Robin Ohs , Holger Hermanns , Felix Walter , Lynn Van Broock , Gabriel Ruffini , Federico Machado , Pablo Serratti , Jose Relloso","doi":"10.1016/j.comnet.2024.110874","DOIUrl":"10.1016/j.comnet.2024.110874","url":null,"abstract":"<div><div>This paper presents an in-depth trade-off analysis of a Swarm Satellite Constellation (SSC) Mission for Earth observation that leverages Segmented Architecture (SA), a concept designed by the Argentinian Space Agency (CONAE) within the New Space philosophy. This architecture consists of a scenario featuring a networked constellation of small, cooperative satellites to enhance mission flexibility, reliability, coverage, and cost-effectiveness. Despite its promising prospects, SA features challenges in its mission design and definition phases due to the complex interplay between distributed space systems, technological innovation, and geographical landscapes. Our study analyzes an innovative quantitative analysis framework integrated with Ansys’ Systems Toolkit (STK). The resulting software tool models critical components, including ground and space segments, orbital dynamics, coverage, onboard processing, and communication links. We focus on a hypothetical SARE mission to detect illicit maritime activity near Argentina’s Exclusive Economic Zone (EEZ). This case study constitutes an archetypal mission elucidating the architecture’s benefits and complexities, addressing swarm coverage, contact dynamics, and data handling strategies. Results contribute to discussions on the practical trade-off in current and future Segmented Satellite Architectures with multiple mission objectives.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"255 ","pages":"Article 110874"},"PeriodicalIF":4.4,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142552345","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Computer NetworksPub Date : 2024-10-28DOI: 10.1016/j.comnet.2024.110875
Mehmet Ali Aygul , Halise Turkmen , Hakan Ali Cirpan , Huseyin Arslan
{"title":"Machine learning-driven integration of terrestrial and non-terrestrial networks for enhanced 6G connectivity","authors":"Mehmet Ali Aygul , Halise Turkmen , Hakan Ali Cirpan , Huseyin Arslan","doi":"10.1016/j.comnet.2024.110875","DOIUrl":"10.1016/j.comnet.2024.110875","url":null,"abstract":"<div><div>Non-terrestrial networks (NTN)s are essential for achieving the persistent connectivity goal of sixth-generation networks, especially in areas lacking terrestrial infrastructure. However, integrating NTNs with terrestrial networks presents several challenges. The dynamic and complex nature of NTN communication scenarios makes traditional model-based approaches for resource allocation and parameter optimization computationally intensive and often impractical. Machine learning (ML)-based solutions are critical here because they can efficiently identify patterns in dynamic, multi-dimensional data, offering enhanced performance with reduced complexity. ML algorithms are categorized based on learning style—supervised, unsupervised, and reinforcement learning—and architecture, including centralized, decentralized, and distributed ML. Each approach has advantages and limitations in different contexts, making it crucial to select the most suitable ML strategy for each specific scenario in the integration of terrestrial and non-terrestrial networks (TNTN)s. This paper reviews the integration architectures of TNTNs as outlined in the 3rd Generation Partnership Project, examines ML-based existing work, and discusses suitable ML learning styles and architectures for various TNTN scenarios. Subsequently, it delves into the capabilities and challenges of different ML approaches through a case study in a specific scenario.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"255 ","pages":"Article 110875"},"PeriodicalIF":4.4,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142560806","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Computer NetworksPub Date : 2024-10-25DOI: 10.1016/j.comnet.2024.110877
Javier Blanco-Romero, Vicente Lorenzo, Florina Almenares, Daniel Díaz-Sánchez, Carlos García Rubio, Celeste Campo, Andrés Marín
{"title":"Evaluating integration methods of a quantum random number generator in OpenSSL for TLS","authors":"Javier Blanco-Romero, Vicente Lorenzo, Florina Almenares, Daniel Díaz-Sánchez, Carlos García Rubio, Celeste Campo, Andrés Marín","doi":"10.1016/j.comnet.2024.110877","DOIUrl":"10.1016/j.comnet.2024.110877","url":null,"abstract":"<div><div>The rapid advancement of quantum computing poses a significant threat to conventional cryptography. Whilst post-quantum cryptography (PQC) stands as the prevailing trend for fortifying the security of cryptographic systems, the coexistence of quantum and classical computing paradigms presents an opportunity to leverage the strengths of both technologies, for instance, nowadays the use of Quantum Random Number Generators (QRNGs) – considered as True Random Number Generators (TRNGs) – opens up the possibility of discussing hybrid systems. In this paper, we evaluate both aspects, on the one hand, we use hybrid TLS (Transport Layer Security) protocol that leverages the widely used secure protocol on the Internet and integrates PQC algorithms, and, on the other hand, we evaluate two approaches to integrate a QRNG, i.e., Quantis PCIe-240M, in OpenSSL 3.0 to be used by TLS. Both approaches are compared through a Nginx Web server, that uses OpenSSL’s implementation of TLS 1.3 for secure web communication. Our findings highlight the importance of optimizing such integration method, because while direct integration can lead to performance penalties specific to the method and hardware used, alternative methods demonstrate the potential for efficient QRNG deployment in cryptographic systems.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"255 ","pages":"Article 110877"},"PeriodicalIF":4.4,"publicationDate":"2024-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142571412","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Traffic evolution in Software Defined Networks","authors":"Usman Ashraf , Adnan Ahmed , Stefano Avallone , Pasquale Imputato","doi":"10.1016/j.comnet.2024.110852","DOIUrl":"10.1016/j.comnet.2024.110852","url":null,"abstract":"<div><div>Software Defined Networking (SDN) offers unprecedented traffic engineering possibilities due to optimal centralized decision making. However, network traffic evolves over time and changes the underlying optimization problem. Frequent application of the model to reflect traffic evolution causes flooding of control messages, traffic re-routing and synchronization problems. This paper addresses the problem of graceful traffic evolution in SDNs (Software Defined Networks) minimizing rule installations and modifications, optimizing the global objectives of minimization of Maximum Link Utilization (MLU) and minimization of the Maximum Switch Table Space Utilization (MSTU). The problem is formulated as multi-objective optimization using Mixed Integer Linear Programming (MILP). Proof of NP-Hardness is provided. Then, we re-formulate the problem as a single-objective problem and propose two greedy algorithms to solve the single-objective problem, namely MIRA-Im and MIRA-Im with Conflict Detection, and experiments are performed to show the effectiveness of the algorithms in comparison to previous state of the art proposals. Simulation results show significant improvements of MIRA-Im with Conflict Detection, especially in terms of number of installed rules (with a gain till 80% with the highest number of flows) and flow table space utilization (with a gain till 55% with the highest number of flows), compared to MIRA-Im and other algorithms available in the literature, while the other metrics are essentially stable.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"255 ","pages":"Article 110852"},"PeriodicalIF":4.4,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533939","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Computer NetworksPub Date : 2024-10-23DOI: 10.1016/j.comnet.2024.110848
Liushun Zhao , Deke Guo , Lailong Luo , Yulong Shen , Bangbang Ren , Shi Zhu , Fangliao Yang
{"title":"Concordit: A credit-based incentive mechanism for permissioned redactable blockchain","authors":"Liushun Zhao , Deke Guo , Lailong Luo , Yulong Shen , Bangbang Ren , Shi Zhu , Fangliao Yang","doi":"10.1016/j.comnet.2024.110848","DOIUrl":"10.1016/j.comnet.2024.110848","url":null,"abstract":"<div><div>Malicious attacks and the introduction of illegal data put blockchains at risk, and blockchain governance is gaining increasing attention. The redactable blockchain technology has become a mainstream solution for blockchain governance. However, a low completion rate for redaction tasks limits current redactable blockchain technologies, primarily due to the absence of an effective incentive mechanism for participants. This gap underscores the urgent need for designing and implementing robust incentive mechanisms in redactable blockchains. Incentive mechanisms can motivate and guide entities to participate and perform desired behaviors through awards and punishments. This paper proposes Concordit, the first deployable credit-based incentive mechanism for redactable blockchains. Its purpose is to encourage submitters to submit legal redaction requests, modifiers to perform legal redaction operations, and verifiers to maintain the behavior consistent with the consensus algorithm. In the context of permissioned blockchains, Concordit utilizes a credit value system for awards and punishments. Additionally, we use a game theory-based mechanism to analyze and model participants’ behavior utilities in the redactable blockchain. Meanwhile, we evaluate the credibility of nodes by combining their static initial credit values and dynamic behavior-related credit values. This system prioritizes high-credibility nodes as participants, thereby enhancing the completion rate for redaction tasks. Finally, the implementation and performance evaluation of our Concordit incentive mechanism demonstrate its effectiveness and practicality.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"255 ","pages":"Article 110848"},"PeriodicalIF":4.4,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142571411","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}