Annals of Telecommunications最新文献_第7页

Efficient VM consolidation: deep reinforcement learning approach based PM workload awareness 高效的VM整合：基于PM工作负载感知的深度强化学习方法

IF 2.2 4区计算机科学

Annals of Telecommunications Pub Date : 2025-06-13 DOI: 10.1007/s12243-025-01100-5

Imene El-taani, Mohand Cherif Boukala, Samia Bouzefrane, Anissa Imen Amrous

{"title":"Efficient VM consolidation: deep reinforcement learning approach based PM workload awareness","authors":"Imene El-taani, Mohand Cherif Boukala, Samia Bouzefrane, Anissa Imen Amrous","doi":"10.1007/s12243-025-01100-5","DOIUrl":"10.1007/s12243-025-01100-5","url":null,"abstract":"<div><p>Network function virtualization (NFV) transforms telecommunication services by replacing hardware with software-based virtual network functions (VNFs), which run as virtual machines (VMs) on physical machines (PMs) in cloud data centers. Minimizing energy consumption in a data center while maintaining service level agreements (SLAs) is one of the major challenges in cloud computing. Dynamic VM consolidation (DVMC) offers a potential solution to this issue. However, traditional DVMC solutions rely on workload detection methods that result in unnecessary VM migrations. Furthermore, existing heuristic approaches for VM placement typically lack global optimization. Many recent studies have proposed solutions based on reinforcement learning, particularly the deep Q-network (DQN). However, these solutions do not address several practical challenges that could enhance the stability of the learning process. This paper introduces an efficient VM consolidation approach to tackle these challenges. We propose a dynamic algorithm for detecting underloaded PMs using an admission threshold (AT), which is calculated based on LSTM predictions, to minimize unnecessary migrations. Furthermore, we present an enhanced DQN-based method for VM placement. Our approach stands out by improving the interaction between the DQN-agent and its cloud environment. It introduces a new field in the Replay Buffer and incorporates new messages to enhance this interaction. Moreover, we propose new state composition and reward calculation methods, which take into account the original PM load of the VM being placed. Simulation results using CloudSim and the PlanetLab database demonstrate that our approach outperforms recent state-of-the-art methods by approximately 22% in the Energy-SLA (ESV) metric.</p></div>","PeriodicalId":50761,"journal":{"name":"Annals of Telecommunications","volume":"81 3-4","pages":"191 - 210"},"PeriodicalIF":2.2,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147617885","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

Proximity service for vehicular passengers: modeling and analyzing D2D implementation for VoIP application using vehicular mobility models 车辆乘客的接近服务：使用车辆移动模型建模和分析VoIP应用的D2D实现

IF 2.2 4区计算机科学

Annals of Telecommunications Pub Date : 2025-06-02 DOI: 10.1007/s12243-025-01101-4

Ayesha Urooj, Sundus Ali, Irfan Ahmed, Muhammad Imran Aslam

{"title":"Proximity service for vehicular passengers: modeling and analyzing D2D implementation for VoIP application using vehicular mobility models","authors":"Ayesha Urooj, Sundus Ali, Irfan Ahmed, Muhammad Imran Aslam","doi":"10.1007/s12243-025-01101-4","DOIUrl":"10.1007/s12243-025-01101-4","url":null,"abstract":"<div><p>Implementing Voice over IP (VoIP) at vehicular speeds presents several challenges that include maintaining a stable and reliable connection, handling potential signal dropouts, and ensuring low latency to provide a seamless and natural conversation experience. This study presents system modeling and a comprehensive analysis of the performance of time-critical applications such as VoIP over Device-to-Device (D2D) communication at vehicular speeds. Moreover, vehicular mobility attributes such as speed and direction variations significantly affect the overall performance of the VoIP implementation. We investigated the impact of vehicle mobility on the system performance using a linear mobility model and a more realistic Gaussian Markov mobility (GMM) model to simulate vehicular movement at various speeds and directions. We simulated the system model using an event-based simulator and measured the signal-to-interference and noise ratio (SINR) and channel quality indicators (CQI) of both the uplink and D2D links. Moreover, we evaluated the mode switching between the side link and infrastructure modes, as well as the mean opinion score (MOS) level for different scenarios. Our comparative analysis of both mobility models demonstrates that the GMM model not only produces substantially different performance metric outcomes but also offers a more realistic characterization of D2D network behavior under vehicular conditions. We further extended the simulation framework to evaluate how increasing the number of vehicular users density using the GMM affects SINR, CQI, MOS, and packet loss intensity.</p></div>","PeriodicalId":50761,"journal":{"name":"Annals of Telecommunications","volume":"81 3-4","pages":"175 - 190"},"PeriodicalIF":2.2,"publicationDate":"2025-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147617937","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

ISIVC 2024 special issue—signal and audio processing, digital communications, and networking ISIVC 2024特刊-信号和音频处理，数字通信和网络

IF 2.2 4区计算机科学

Annals of Telecommunications Pub Date : 2025-05-24 DOI: 10.1007/s12243-025-01099-9

Abdellah Adib, Sofia Ben Jebara, Raja Elassali, Khalid Minaoui, Samir Saoudi

引用次数: 0

End-to-end trusted computing architecture for vehicular over-the-air updates 车载无线更新的端到端可信计算架构

IF 2.2 4区计算机科学

Annals of Telecommunications Pub Date : 2025-05-06 DOI: 10.1007/s12243-025-01096-y

Guilherme A. Thomaz, Thierno Barry, Matteo Sammarco, Miguel Elias M. Campista

{"title":"End-to-end trusted computing architecture for vehicular over-the-air updates","authors":"Guilherme A. Thomaz, Thierno Barry, Matteo Sammarco, Miguel Elias M. Campista","doi":"10.1007/s12243-025-01096-y","DOIUrl":"10.1007/s12243-025-01096-y","url":null,"abstract":"<div><p>Connected vehicles have software that must be updated to fix vulnerabilities or add new functionalities. While over-the-air updates prevent car owners from bringing their vehicles to a service center, they introduce significant security risks. This paper proposes a vehicular over-the-air update architecture combining the two most adopted trusted execution environment solutions: Intel SGX at the server and ARM TrustZone at the client. The main contribution is the protection of software updates from attackers that manipulate the entire operating system at both ends aiming to reverse engineering the software or introducing a malicious behavior. The implementation uses a device with OP-TEE and a software repository implemented with CACIC-DevKit. The paper also extends our previous work by evaluating an alternative server implementation using Gramine-SGX. Our experiments reveal that the impact of the TEE is negligible, even for small software block transfers. Compared with CACIC-DevKit, Gramine-SGX doubles the latency, despite the development simplification. This indicates that CACIC-DevKit better suits a high mobility scenario, such as vehicular networks, where the connection with the server may be short term.</p></div>","PeriodicalId":50761,"journal":{"name":"Annals of Telecommunications","volume":"80 9-10","pages":"823 - 834"},"PeriodicalIF":2.2,"publicationDate":"2025-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145210476","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

Reducing communication overhead through one-shot model pruning in federated learning 通过联邦学习中的一次性模型修剪减少通信开销

IF 2.2 4区计算机科学

Annals of Telecommunications Pub Date : 2025-05-05 DOI: 10.1007/s12243-025-01097-x

Rómulo Bustincio, Allan M. de Souza, Joahannes B. D. da Costa, Luis F. G. Gonzalez, Luiz F. Bittencourt

{"title":"Reducing communication overhead through one-shot model pruning in federated learning","authors":"Rómulo Bustincio, Allan M. de Souza, Joahannes B. D. da Costa, Luis F. G. Gonzalez, Luiz F. Bittencourt","doi":"10.1007/s12243-025-01097-x","DOIUrl":"10.1007/s12243-025-01097-x","url":null,"abstract":"<div><p>In the realm of federated learning, a collaborative yet decentralized approach to machine learning, communication efficiency is a critical concern, particularly under constraints of limited bandwidth and resources. This paper evaluates FedSNIP, a novel method that leverages the SNIP (Single-shot Network Pruning based on Connection Sensitivity) technique within this context. By utilizing SNIP, FedSNIP effectively prunes neural networks, converting numerous weights to zero and resulting in sparser weight representations. This substantial reduction in weight density significantly decreases the volume of parameters that need to be communicated to the server, thereby reducing the communication overhead. Our experiments on the CIFAR-10 and UCI-HAR dataset demonstrate that FedSNIP not only lowers the data transmission between clients and the server but also maintains competitive model accuracy, comparable to conventional federated learning models. Additionally, we analyze various compression algorithms applied after pruning, specifically evaluating the compressed sparse row, coordinate list, and compressed sparse column formats to identify the most efficient approach. Our results show that compressed sparse row not only compresses the data more effectively and quickly but also achieves the highest reduction in data size, making it the most suitable format for enhancing the efficiency of federated learning, particularly in scenarios with restricted communication capabilities.</p></div>","PeriodicalId":50761,"journal":{"name":"Annals of Telecommunications","volume":"80 9-10","pages":"901 - 913"},"PeriodicalIF":2.2,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145210472","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

Reconfigurable intelligent surfaces (RIS) using NOMA with energy harvesting from vibrations for 6G 可重构智能表面（RIS）采用NOMA技术，可从6G的振动中收集能量

IF 2.2 4区计算机科学

Annals of Telecommunications Pub Date : 2025-04-29 DOI: 10.1007/s12243-025-01095-z

Hatem Boujemaa, Musaed Alhussein, Ghaya Rekaya

引用次数: 0

Transport efficiency for data-intensive science: deployment experiences and bottleneck analysis 数据密集型科学的传输效率：部署经验和瓶颈分析

IF 2.2 4区计算机科学

Annals of Telecommunications Pub Date : 2025-04-24 DOI: 10.1007/s12243-025-01094-0

Vitor F. Zanotelli, Edgard C. Pontes, Magnos Martinello, Jordi Ros-Giralt, Everson S. Borges, Giovanni Comarela, Moisés R. N. Ribeiro, Harvey Newman

{"title":"Transport efficiency for data-intensive science: deployment experiences and bottleneck analysis","authors":"Vitor F. Zanotelli, Edgard C. Pontes, Magnos Martinello, Jordi Ros-Giralt, Everson S. Borges, Giovanni Comarela, Moisés R. N. Ribeiro, Harvey Newman","doi":"10.1007/s12243-025-01094-0","DOIUrl":"10.1007/s12243-025-01094-0","url":null,"abstract":"<div><p>Transferring massive datasets in data-intensive science (DIS) systems often relies on physical WAN infrastructure for network connectivity. This infrastructure is typically provided by various National Research and Education Networks (NRENs), including ESnet, GÉANT, Internet2, and RNP. Studying these systems presents significant challenge due to their complexity, scale, and the numerous factors influencing data transport. Traditionally, network performance studies focus on a single bottleneck. In contrast, the Quantitative Theory of Bottlenecks Structures (QTBS) provides a mathematical framework that analyzes performance through the network’s entire bottleneck structure, offering valuable insights for optimizing and understanding overall network performance. This paper tackles such challenges by employing QTBS and by deploying and evaluating a virtual infrastructure for data transport within a national-scale WAN. Our approach focuses on three key aspects: (i) assessing flow completion times related to bandwidth allocation for interdependent transfers within a network slice, (ii) evaluating the performance of TCP congestion control algorithms (BBR versus Cubic) for data transport, and (iii) conducting QTBS analysis to compute flow allocation shares, ultimately aiming for an optimal design. Results show BBR outperforming Cubic in scenarios with high number of threads and data volume and the high influence of the number of threads.</p></div>","PeriodicalId":50761,"journal":{"name":"Annals of Telecommunications","volume":"80 9-10","pages":"793 - 805"},"PeriodicalIF":2.2,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145210479","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

Analyzing the stability, efficiency, and cost of a dynamic data replica balancing architecture for HDFS 分析HDFS动态数据副本均衡架构的稳定性、效率和成本

IF 2.2 4区计算机科学

Annals of Telecommunications Pub Date : 2025-04-23 DOI: 10.1007/s12243-025-01093-1

Rhauani Weber Aita Fazul, Odorico Machado Mendizabal, Patrícia Pitthan Barcelos

{"title":"Analyzing the stability, efficiency, and cost of a dynamic data replica balancing architecture for HDFS","authors":"Rhauani Weber Aita Fazul, Odorico Machado Mendizabal, Patrícia Pitthan Barcelos","doi":"10.1007/s12243-025-01093-1","DOIUrl":"10.1007/s12243-025-01093-1","url":null,"abstract":"<div><p>Hadoop Distributed File System (HDFS) is known for its specialized strategies and policies tailored to enhance replica placement. This capability is critical for ensuring efficient and reliable access to data replicas, particularly as HDFS operates best when data are evenly distributed within the cluster. In this paper, we build upon earlier practical evaluations and conduct a thorough analysis of the replica balancing process in HDFS, focusing on two critical performance metrics: stability and efficiency. We evaluated these aspects alongside balancing operational cost by contrasting them with conventional HDFS solutions and employing a novel dynamic architecture for data replica balancing. On top of that, we delve into the optimizations in data locality brought about by effective replica balancing and their benefits for data-intensive applications, including enhanced read performance. Our findings reveal the extent to which data imbalance in HDFS directly affects the file system and highlight the struggles of the default replica placement policy in maintaining cluster balance. We examined the real but intricate and temporary effectiveness of on-demand balancing, underscoring the importance of regular and adaptable balancing interventions. This reaffirms the significance of context-aware replica balancing, as provided by the proposed dynamic architecture, not only for maintaining data equilibrium but also for ensuring efficient system performance.</p></div>","PeriodicalId":50761,"journal":{"name":"Annals of Telecommunications","volume":"80 9-10","pages":"867 - 883"},"PeriodicalIF":2.2,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145210578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

Crosstalk-aware circuit reallocation to reduce blocking in spatial division multiplexed elastic optical networks 空域复用弹性光网络中串扰感知电路重分配减少阻塞

IF 2.2 4区计算机科学

Annals of Telecommunications Pub Date : 2025-04-22 DOI: 10.1007/s12243-025-01092-2

Selles G. F. C. Araújo, André C. B. Soares

引用次数: 0

A two-stage Q-learning routing approach for quantum entanglement networks 量子纠缠网络的两阶段q学习路由方法

IF 2.2 4区计算机科学

Annals of Telecommunications Pub Date : 2025-04-22 DOI: 10.1007/s12243-025-01090-4

Diego Abreu, Arthur Pimentel, David Moura, Christian Rothenberg, Antônio Abelém

{"title":"A two-stage Q-learning routing approach for quantum entanglement networks","authors":"Diego Abreu, Arthur Pimentel, David Moura, Christian Rothenberg, Antônio Abelém","doi":"10.1007/s12243-025-01090-4","DOIUrl":"10.1007/s12243-025-01090-4","url":null,"abstract":"<div><p>The emerging field of quantum internet offers multiple applications, enabling quantum communication across diverse networks. However, the current entanglement networks exhibit complex processes, characterized by variable entanglement generation rates, limited quantum memory capacity, and susceptibility to decoherence rates. Addressing these issues, we propose a two-stage routing system that harnesses the power of reinforcement learning (RL). The first stage focuses on identifying the most efficient routes for quantum data transmission. The second stage concentrates on establishing these routes and improving how and when to apply entanglement swapping and purification. Our extensive evaluations across various network sizes and configurations reveal that our method not only sustains superior end-to-end route fidelity but also achieves significantly higher request success rates compared to traditional methods. These findings highlight the efficacy of our approach in managing the complex dynamics of quantum networks, ensuring robust and scalable quantum communication. Our method’s adaptability to changing network conditions and its proactive management of quantum resources make an important contribution to quantum network efficiency.</p></div>","PeriodicalId":50761,"journal":{"name":"Annals of Telecommunications","volume":"80 9-10","pages":"807 - 822"},"PeriodicalIF":2.2,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145210576","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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