Computer Communications最新文献_第3页

Meta-reinforcement learning driven model architecture and algorithm optimization in intelligent driving task offloading 元强化学习驱动的智能驾驶任务卸载模型架构及算法优化

IF 4.3 3区计算机科学

Computer Communications Pub Date : 2025-08-19 DOI: 10.1016/j.comcom.2025.108310

Peiying Zhang , Jiamin Liu , Zhiyuan Ren , Lizhuang Tan , Neeraj Kumar , Konstantin Igorevich Kostromitin

{"title":"Meta-reinforcement learning driven model architecture and algorithm optimization in intelligent driving task offloading","authors":"Peiying Zhang , Jiamin Liu , Zhiyuan Ren , Lizhuang Tan , Neeraj Kumar , Konstantin Igorevich Kostromitin","doi":"10.1016/j.comcom.2025.108310","DOIUrl":"10.1016/j.comcom.2025.108310","url":null,"abstract":"<div><div>In the process of rapid development of intelligent driving technology, the amount of data generated by vehicles increases dramatically, while the bottleneck of storage and computation capacity of in-vehicle devices becomes more and more prominent, and task offloading becomes the key to improve the performance of intelligent driving systems. In this context, this paper proposes the MRL-ADTO algorithm, which innovatively applies meta-reinforcement learning (MRL) to the field of intelligent driving task offloading, optimizes the directed acyclic graph (DAG) synthesis logic and the task priority ranking algorithm, designs a neural network model based on the sequence to sequence (Seq2Seq) structure, and introduces the mechanism of multi-head attention at the same time. The experimental results show that MRL-ADTO can significantly reduce the task execution delay in multiple scenarios compared with the existing algorithms, and has obvious advantages in terms of training efficiency and convergence performance, providing an efficient and reliable solution for smart driving task offloading.</div></div>","PeriodicalId":55224,"journal":{"name":"Computer Communications","volume":"242 ","pages":"Article 108310"},"PeriodicalIF":4.3,"publicationDate":"2025-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144889387","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

Private networks: Evolution, ecosystem, use cases, architecture, spectrum, and deployment challenges 专用网络：演进、生态系统、用例、体系结构、频谱和部署挑战

IF 4.3 3区计算机科学

Computer Communications Pub Date : 2025-08-16 DOI: 10.1016/j.comcom.2025.108295

Onur Sahin , Vanlin Sathya , Mehmet Yavuz

{"title":"Private networks: Evolution, ecosystem, use cases, architecture, spectrum, and deployment challenges","authors":"Onur Sahin , Vanlin Sathya , Mehmet Yavuz","doi":"10.1016/j.comcom.2025.108295","DOIUrl":"10.1016/j.comcom.2025.108295","url":null,"abstract":"<div><div>Private networks have reshaped enterprise communications by providing unmatched control, security, and tailored solutions for various industries. This paper presents an in-depth survey of private networks, covering their evolution, current landscape, and future outlook. Key topics include the use cases, architecture, spectrum management, and deployment strategies. The study examines the transition from private 4G/LTE to private 5G networks, fueled by demands for higher data throughput and ultra-low latency across sectors. It highlights the advantages of private 5G over public mobile networks (MNOs) and Wi-Fi, with a special focus on spectrum sharing as a means to optimize frequency use. Additionally, the paper reviews global spectrum allocations for private 5G, providing an overview of regulatory frameworks and available frequency bands across countries. It also explores future prospects, including private 6G networks and emerging spectrum technologies. Key challenges such as high deployment costs, interoperability issues, and security concerns are discussed alongside potential solutions. Through this comprehensive analysis, the paper aims to provide valuable insights for researchers, practitioners, and policymakers in the field of private networks.</div></div>","PeriodicalId":55224,"journal":{"name":"Computer Communications","volume":"242 ","pages":"Article 108295"},"PeriodicalIF":4.3,"publicationDate":"2025-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144878238","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

A multi-feature fusion approach for physical layer authentication in LEO satellites 低轨道卫星物理层认证的多特征融合方法

IF 4.3 3区计算机科学

Computer Communications Pub Date : 2025-08-15 DOI: 10.1016/j.comcom.2025.108308

Rongjun Yan, Fan Jia

{"title":"A multi-feature fusion approach for physical layer authentication in LEO satellites","authors":"Rongjun Yan, Fan Jia","doi":"10.1016/j.comcom.2025.108308","DOIUrl":"10.1016/j.comcom.2025.108308","url":null,"abstract":"<div><div>Spatial information networks (SINs) have emerged as a means to enhance the expanse and dependability of communication and data transmission services. SINs rely on satellite systems to provide these services, among which low earth orbit (LEO) satellites are widely concerned because of their advantages of low orbital altitude, small network transmission delay, small path loss, and high signal strength. However, due to the frequent switching of communication links between LEO satellites and the ground, the authentication mechanism of the ground users to the satellites is vulnerable to spoofing attacks, and the traditional upper layer authentication method based on encryption usually requires a lot of overhead and delay. In this case, the lightweight physical layer authentication (PLA) mechanism utilizes the inherent distinctiveness and unpredictable nature of channel physical properties, serving as a vital application in SINs for ensuring authentication. Therefore, our work introduces a PLA method incorporating multi-feature integration, aimed at delivering effective identity verification tailored for LEO satellites. The approach employs doppler frequency shift (DS), angles of arrival (AOAs), and received power (RP) features, fusing an support vector machine (SVM) classifier, to distinguish between legal and illegal satellites in different simulation scenarios. The satellite toolkit (STK) is used to collect data from the actual orbit of satellites and assess the efficacy of the scheme. The findings indicate that the scheme offers enhanced authentication capabilities.</div></div>","PeriodicalId":55224,"journal":{"name":"Computer Communications","volume":"242 ","pages":"Article 108308"},"PeriodicalIF":4.3,"publicationDate":"2025-08-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144860226","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

Source-rate planning in self-powered wireless multi-hop D2D settings under stochasticity: A scenario-based iterative optimization approach 随机条件下自供电无线多跳D2D设置的源速率规划：一种基于场景的迭代优化方法

IF 4.3 3区计算机科学

Computer Communications Pub Date : 2025-08-12 DOI: 10.1016/j.comcom.2025.108299

Georgia Stavropoulou, Eleni Stai, Maria Diamanti, Symeon Papavassiliou

{"title":"Source-rate planning in self-powered wireless multi-hop D2D settings under stochasticity: A scenario-based iterative optimization approach","authors":"Georgia Stavropoulou, Eleni Stai, Maria Diamanti, Symeon Papavassiliou","doi":"10.1016/j.comcom.2025.108299","DOIUrl":"10.1016/j.comcom.2025.108299","url":null,"abstract":"<div><div>Multi-hop Device-to-Device (D2D) communications are emerging as the foundation for numerous compelling 6G applications, enabling seamless information flow between distributed nodes. In the context of such uncertain wireless multi-hop D2D settings, jointly optimizing source data rates, routing, and transmission power decisions is both an essential task and a highly complex problem, particularly due to uncertainties introduced by the wireless channel states and the energy harvesting processes on the nodes. In the current literature, this problem is mostly tackled in a future agnostic sense, and/or using specific distributions to model the uncertainties. In contrast, in this paper, we compute a future energy and resource allocation plan of the network’s operation, using scenario-based optimization techniques to account for stochasticities. Scenarios can model generic distributions of uncertain quantities in a tractable manner. The formulated problem is inherently non-convex and to solve it, we propose CoNetPlan-E, a heuristic iterative method that at each iteration solves appropriately parameterized convex approximations of the original problem. We prove that CoNetPlan-E converges under realistic assumptions, while ensuring that the obtained solution at convergence is feasible for the original non-convex problem. Numerical evaluations showcase the effectiveness of the proposed method compared to existing baseline solutions, while considering three levels of increasing network topology complexity. Importantly, CoNetPlan-E is superior with respect to scalability and runtime while leading to close-to-optimal solutions as these are determined by the standard non-convex solver Ipopt.</div></div>","PeriodicalId":55224,"journal":{"name":"Computer Communications","volume":"242 ","pages":"Article 108299"},"PeriodicalIF":4.3,"publicationDate":"2025-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144860230","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

Improving satellite network efficiency with terminal traffic prediction and SQP-SRA algorithm 利用终端流量预测和SQP-SRA算法提高卫星网络效率

IF 4.3 3区计算机科学

Computer Communications Pub Date : 2025-08-07 DOI: 10.1016/j.comcom.2025.108293

Liangang Qi , Enqiang Wang , Tianfang Xu , Yuan Zhu , Yun Zhao

{"title":"Improving satellite network efficiency with terminal traffic prediction and SQP-SRA algorithm","authors":"Liangang Qi , Enqiang Wang , Tianfang Xu , Yuan Zhu , Yun Zhao","doi":"10.1016/j.comcom.2025.108293","DOIUrl":"10.1016/j.comcom.2025.108293","url":null,"abstract":"<div><div>To address the low resource utilization in satellite networks caused by heterogeneous regional traffic demands, this paper proposes a resource allocation strategy for LEO satellite internet based on terminal traffic prediction. An improved LSTM-GRU hybrid model is developed using real-world datasets to forecast ground traffic, accounting for periodic patterns and weather effects. A leaseable EOSN differentiated transmission framework is designed to enable targeted resource allocation and inter-satellite leasing, enhancing network coverage. To optimize data transmission ratios, user bandwidth, and service pricing, we introduce a sequential quadratic programming-based satellite resource allocation (SQP-SRA) algorithm that balances latency and energy consumption. Compared with LSTM, GRU, Transformer, and wavelet neural networks, the proposed model reduces traffic prediction error by approximately 26%. Simulation results demonstrate that, relative to the DDTOA, FCFS, and TOMRA algorithms, the proposed strategy improves user benefits by approximately 60% and enhances satellite service provider revenues by approximately 80%.</div></div>","PeriodicalId":55224,"journal":{"name":"Computer Communications","volume":"242 ","pages":"Article 108293"},"PeriodicalIF":4.3,"publicationDate":"2025-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145018509","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

Network traffic classification through high-order L-moments and multi-objective optimization 基于高阶l矩和多目标优化的网络流量分类

IF 4.3 3区计算机科学

Computer Communications Pub Date : 2025-08-05 DOI: 10.1016/j.comcom.2025.108290

Jesús Galeano-Brajones , Mihaela I. Chidean , Francisco Luna , Jesús Calle-Cancho , Javier Carmona-Murillo

{"title":"Network traffic classification through high-order L-moments and multi-objective optimization","authors":"Jesús Galeano-Brajones , Mihaela I. Chidean , Francisco Luna , Jesús Calle-Cancho , Javier Carmona-Murillo","doi":"10.1016/j.comcom.2025.108290","DOIUrl":"10.1016/j.comcom.2025.108290","url":null,"abstract":"<div><div>The exponential growth of encrypted and dynamic network traffic poses significant challenges to traditional traffic analysis methods, underscoring the need for robust and scalable solutions. Statistical approaches like L-moments have demonstrated exceptional potential in characterizing traffic flows, offering reduced sensitivity to outliers and the ability to capture higher-order distributional properties with minimal data. Building on previous work by the authors, this study introduces significant enhancements to the L-moment-based methodology for flow analysis and classification, specifically addressing limitations in feature selection and sample size requirements, aspects crucial for achieving deployable configurations in high-performance network environments. Key contributions include the integration of the fifth-order L-moment ratio (<span><math><msub><mrow><mi>τ</mi></mrow><mrow><mn>5</mn></mrow></msub></math></span>) for enriched traffic representation and a multi-objective optimization framework based on a multi-objective evolutionary algorithm that balances competing goals: minimizing flow features selected for flow classification, reducing sample sizes for L-moment estimation, and maximizing classification quality. The enhanced methodology was applied to the CIC-DDoS2019 dataset, previously used in the authors’ earlier work, enabling direct comparison. Results show a reduction in sample size requirements from 200 to as few as 10, while simultaneously improving classification accuracy and selecting minimal features. These findings demonstrate the scalability and effectiveness of the proposed framework, designed for resource-constrained environments in Next-Generation Networks (NGNs), and make it publicly available for reproducibility and future research.</div></div>","PeriodicalId":55224,"journal":{"name":"Computer Communications","volume":"242 ","pages":"Article 108290"},"PeriodicalIF":4.3,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144779264","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

A blockchain solution for decentralized training in machine learning for IoT 物联网机器学习分散训练的区块链解决方案

IF 4.3 3区计算机科学

Computer Communications Pub Date : 2025-07-28 DOI: 10.1016/j.comcom.2025.108289

Carlos Beis-Penedo , Francisco Troncoso-Pastoriza , Rebeca P. Díaz-Redondo , Ana Fernández-Vilas , Manuel Fernández-Veiga , Martín González Soto

{"title":"A blockchain solution for decentralized training in machine learning for IoT","authors":"Carlos Beis-Penedo , Francisco Troncoso-Pastoriza , Rebeca P. Díaz-Redondo , Ana Fernández-Vilas , Manuel Fernández-Veiga , Martín González Soto","doi":"10.1016/j.comcom.2025.108289","DOIUrl":"10.1016/j.comcom.2025.108289","url":null,"abstract":"<div><div>The rapid growth of Internet of Things (IoT) devices and applications has led to an increased demand for advanced analytics and machine learning techniques capable of handling the challenges associated with data privacy, security, and scalability. Federated learning (FL) and blockchain technologies have emerged as promising approaches to address these challenges by enabling decentralized, secure, and privacy-preserving model training on distributed data sources. In this paper, we present a novel IoT solution that combines the incremental learning vector quantization algorithm (XuILVQ) with Ethereum blockchain technology to facilitate secure and efficient data sharing, model training, and prototype storage in a distributed environment. Our proposed architecture addresses the shortcomings of existing blockchain-based FL solutions by reducing computational and communication overheads while maintaining data privacy and security. We assess the performance of our system through a series of experiments, showing its potential to enhance the accuracy and efficiency of machine learning tasks in IoT settings.</div></div>","PeriodicalId":55224,"journal":{"name":"Computer Communications","volume":"242 ","pages":"Article 108289"},"PeriodicalIF":4.3,"publicationDate":"2025-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144722950","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

Deep reinforcement learning based interference optimization for coordinated beamforming in ultra-dense Wi-Fi networks 基于深度强化学习的超密集Wi-Fi网络协同波束形成干扰优化

IF 4.3 3区计算机科学

Computer Communications Pub Date : 2025-07-27 DOI: 10.1016/j.comcom.2025.108286

Jamshid Bacha , Anatolij Zubow , Szymon Szott , Katarzyna Kosek-Szott , Falko Dressler

{"title":"Deep reinforcement learning based interference optimization for coordinated beamforming in ultra-dense Wi-Fi networks","authors":"Jamshid Bacha , Anatolij Zubow , Szymon Szott , Katarzyna Kosek-Szott , Falko Dressler","doi":"10.1016/j.comcom.2025.108286","DOIUrl":"10.1016/j.comcom.2025.108286","url":null,"abstract":"<div><div>Next-generation Wi-Fi networks are expected to have an ultra-dense deployment of access points (APs), thus, interference from overlapping basic service sets (OBSSs) poses challenges for interference management. Wi-Fi 8 aims at mitigating such interference using multi-access point coordination (MAPC). One of the MAPC variants is coordinated beamforming (Co-BF), where neighboring APs direct their signals towards specific users. Besides beam steering, APs can also perform null steering, which is more complex but can bring greater performance gains. In this paper, we present a centralized approach named intelligent null steering by reinforcement learning (IntelliNull), designed to reduce interference from neighboring transmitters by coordinated nulling while maximizing the signal quality at each station. We show that training the beam and null steering mechanism with a deep deterministic policy gradient (DDPG), it is possible to steer beams toward associated stations while intelligently nulling the most destructive interference from OBSS rather than nulling random interference directions. This method enhances communication between the AP and neighboring stations by reducing channel access contention, enabling transmissions at full power, and reducing worst-case latency. The proposed IntelliNull agent continuously adapts to changes in the network environment, including node mobility using channel state information (CSI) collected in real-time. We also compare our IntelliNull, which is based on beamforming plus nulling, with the baseline which is based on beamforming only. Our results demonstrate that IntelliNull outperforms the baseline by effectively mitigating interference, leading to higher throughput and better signal-to-interference-plus-noise ratio (SINR), especially in dense deployment scenarios where beamforming alone fails to sufficiently suppress OBSS interference.</div></div>","PeriodicalId":55224,"journal":{"name":"Computer Communications","volume":"242 ","pages":"Article 108286"},"PeriodicalIF":4.3,"publicationDate":"2025-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144750833","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

FLoV2T: A fine-grained malicious traffic classification method based on federated learning for AIoT FLoV2T：一种基于联邦学习的AIoT细粒度恶意流量分类方法

IF 4.3 3区计算机科学

Computer Communications Pub Date : 2025-07-26 DOI: 10.1016/j.comcom.2025.108288

Fanyi Zeng, Chen Xu, Dapeng Man, Junhui Jiang, Wu Yang

{"title":"FLoV2T: A fine-grained malicious traffic classification method based on federated learning for AIoT","authors":"Fanyi Zeng, Chen Xu, Dapeng Man, Junhui Jiang, Wu Yang","doi":"10.1016/j.comcom.2025.108288","DOIUrl":"10.1016/j.comcom.2025.108288","url":null,"abstract":"<div><div>With the rapid development of Artificial Intelligence of Things (AIoT), the network security risks associated with AIoT have surged, making precise fine-grained malicious traffic classification (MTC) technology essential, but the reliance on large datasets raises privacy concerns. Federated Learning (FL) offers a privacy-preserving alternative, but existing FL-based solutions still suffer from suboptimal classification accuracy, limited terminal resources, and the non-independent and identically distributed (non-IID) IoT data that hinder effective global model aggregation. To address these issues, this paper introduces <strong>FLoV2T</strong> — a FL-based fine-grained MTC method for AIoT. To improve classification performance, we first employ a pretrained Vision Transformer (ViT) to extract discriminative features by visualizing raw network traffic as images, thereby tackling the problem of inadequate feature representation. To alleviate the burden of resource constraints and high communication costs, we then implement a local parameter fine-tuning mechanism based on Low-Rank Adaptation (LoRA), significantly reducing the parameter for model learning and communication at the edge. Furthermore, to counteract the model bias towards clients’ non-IID data on model aggregation, we design a regularized parameter aggregation strategy to enhance global model robustness. Experimental results show that FLoV2T achieves an average accuracy of 97.26% and an F1 score of 96.99%, surpassing the baseline by 10.94% and 11.47%. Moreover, LoRA reduces parameter count by approximately 64 times while maintaining high classification performance, and under non-IID conditions, overall performance reaches an average accuracy of 96.17% and an average F1 score of 95.81%, underscoring FLoV2T’s potential in future AIoT communication networks.</div></div>","PeriodicalId":55224,"journal":{"name":"Computer Communications","volume":"242 ","pages":"Article 108288"},"PeriodicalIF":4.3,"publicationDate":"2025-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144889389","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

Performance model and system optimization of an energy-saving strategy based on adaptive service rate tuning in cloud data centers with micro-burst traffic 基于自适应服务速率调优的微突发云数据中心节能策略性能模型与系统优化

IF 4.3 3区计算机科学

Computer Communications Pub Date : 2025-07-25 DOI: 10.1016/j.comcom.2025.108281

Xuena Yan , Shunfu Jin

{"title":"Performance model and system optimization of an energy-saving strategy based on adaptive service rate tuning in cloud data centers with micro-burst traffic","authors":"Xuena Yan , Shunfu Jin","doi":"10.1016/j.comcom.2025.108281","DOIUrl":"10.1016/j.comcom.2025.108281","url":null,"abstract":"<div><div>With the increasing competition in cloud market, reducing operating costs and improving Quality of Service (QoS) are two of the key issues that cloud vendors need to consider. In order to reduce the power consumption while mitigating the negative impact of micro-burst traffic in Cloud Data Centers (CDCs) on performance, and make cloud vendors more competitive, we design an Energy-saving Strategy based on Sleep and Adaptive Service-rate Tuning (ES-SAST) in this paper. We model the arrivals of the cloud task requests as an environment-dependent <span><math><mi>R</mi></math></span>-phase Markov Arrival Process (MAP<span><math><mrow><mo>(</mo><mi>R</mi><mo>)</mo></mrow></math></span>), and we establish a multi-server synchronous multi-vacation queue with adaptive service rate tuning. We construct a four-dimensional Markov chain to analyze the queue, and we calculate some measures to evaluate the energy efficiency and QoS in the steady state. Then we develop an objective function composed of three performance measures. Finally, we propose an Improved Fire Hawk Optimizer (IFHO) with multi-strategy integration, and IFHO jointly optimizes two system parameters. An empirical study shows that IFHO chooses a lower system expected cost, where the power consumption of the system falls by 3%, the latency of tasks decreases by 19%, and the loss rate of the system reduces by 37%, on average.</div></div>","PeriodicalId":55224,"journal":{"name":"Computer Communications","volume":"242 ","pages":"Article 108281"},"PeriodicalIF":4.3,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144722761","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