Pub Date : 2025-02-11DOI: 10.1109/LNET.2024.3519937
Hatim Chergui;Kamel Tourki;Jun Wu
The advent of 6G networks heralds a new era of telecommunications characterized by unparalleled connectivity, ultra-low latency, and immersive applications such as holographic communication and Industry 5.0. However, these advancements also introduce significant complexities in network management and service orchestration. This Special Issue of IEEE Networking Letters explores cutting-edge research on Artificial Intelligence (AI)-driven automation techniques designed to address these challenges. The selected works span a diverse array of AI paradigms—ranging from generative AI (GenAI) and reinforcement learning to multi-agent systems and federated learning—showcasing their applications across various 6G technological domains. By highlighting these innovations, this issue aims to provide valuable insights into the pivotal role of AI in shaping the future of 6G networks.
{"title":"Editorial SI on Advances in AI for 6G Networks","authors":"Hatim Chergui;Kamel Tourki;Jun Wu","doi":"10.1109/LNET.2024.3519937","DOIUrl":"https://doi.org/10.1109/LNET.2024.3519937","url":null,"abstract":"The advent of 6G networks heralds a new era of telecommunications characterized by unparalleled connectivity, ultra-low latency, and immersive applications such as holographic communication and Industry 5.0. However, these advancements also introduce significant complexities in network management and service orchestration. This Special Issue of IEEE N<sc>etworking</small> L<sc>etters</small> explores cutting-edge research on Artificial Intelligence (AI)-driven automation techniques designed to address these challenges. The selected works span a diverse array of AI paradigms—ranging from generative AI (GenAI) and reinforcement learning to multi-agent systems and federated learning—showcasing their applications across various 6G technological domains. By highlighting these innovations, this issue aims to provide valuable insights into the pivotal role of AI in shaping the future of 6G networks.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"6 4","pages":"215-216"},"PeriodicalIF":0.0,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10880116","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143388619","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-09DOI: 10.1109/LNET.2024.3512658
C Kiruthika;E. S. Gopi
Deep learning-based CSI compression has shown its efficacy for massive multiple-input multiple-output networks, and on the other hand, federated learning (FL) excels the conventional centralized learning by avoiding privacy leakage issues and training communication overhead. The realization of an FL-based CSI feedback network consumes more computational resources and time, and the continuous reporting of local models to the base station results in overhead. To overcome these issues, in this letter, we propose a FBCNet. The proposed FBCNet combines the advantages of the novel fusion basis (FB) technique and the fully connected complex-valued neural network (CNet) based on gradient (G) and non-gradient (NG) approaches. The experimental results show the advantages of both CNet and FB individually over the existing techniques. FBCNet, the combination of both FB and CNet, outperforms the existing federated averaging-based CNet (FedCNet) with improvement in reconstruction performance, less complexity, reduced training time, and low transmission overhead. For the distributed array-line of sight topology at the compression ratio (CR) of 20:1, it is noted that the NMSE and the cosine similarity of FedCNet-G are −8.2837 dB, 0.9262; FedCNet-NG are −3.5291 dB, 0.8452; proposed FB are −26.8621, 0.9653. Also the NMSE and the cosine similarity of the proposed FBCNet-G are −19.7521, 0.9307; FBCNet-NG are −24.0442, 0.9539 at a high CR of 64:1.
{"title":"FBCNet: Fusion Basis Complex-Valued Neural Network for CSI Compression in Massive MIMO Networks","authors":"C Kiruthika;E. S. Gopi","doi":"10.1109/LNET.2024.3512658","DOIUrl":"https://doi.org/10.1109/LNET.2024.3512658","url":null,"abstract":"Deep learning-based CSI compression has shown its efficacy for massive multiple-input multiple-output networks, and on the other hand, federated learning (FL) excels the conventional centralized learning by avoiding privacy leakage issues and training communication overhead. The realization of an FL-based CSI feedback network consumes more computational resources and time, and the continuous reporting of local models to the base station results in overhead. To overcome these issues, in this letter, we propose a FBCNet. The proposed FBCNet combines the advantages of the novel fusion basis (FB) technique and the fully connected complex-valued neural network (CNet) based on gradient (G) and non-gradient (NG) approaches. The experimental results show the advantages of both CNet and FB individually over the existing techniques. FBCNet, the combination of both FB and CNet, outperforms the existing federated averaging-based CNet (FedCNet) with improvement in reconstruction performance, less complexity, reduced training time, and low transmission overhead. For the distributed array-line of sight topology at the compression ratio (CR) of 20:1, it is noted that the NMSE and the cosine similarity of FedCNet-G are −8.2837 dB, 0.9262; FedCNet-NG are −3.5291 dB, 0.8452; proposed FB are −26.8621, 0.9653. Also the NMSE and the cosine similarity of the proposed FBCNet-G are −19.7521, 0.9307; FBCNet-NG are −24.0442, 0.9539 at a high CR of 64:1.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"6 4","pages":"262-266"},"PeriodicalIF":0.0,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143388486","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-09DOI: 10.1109/LNET.2024.3514357
Hajar Moudoud;Zakaria Abou El Houda;Bouziane Brik
The evolution of Open Radio Access Networks (O-RAN) is crucial for the deployment and operation of 6G networks, providing flexibility and interoperability through its disaggregated and open architecture. However, this openness introduces new security issues. To address these challenges, we propose a novel Zero-Trust architecture tailored for ORAN (ZTORAN). ZTORAN includes two main modules: (1) A blockchain-based decentralized trust management system for secure verification, authentication, and dynamic access control of xApps; and (2) A threat detection module that uses Federated Multi-Agent Reinforcement Learning (FMARL) to monitor network activities continuously and detects anomalies within the ORAN ecosystem. Through comprehensive simulations and evaluations, we demonstrate the effectiveness of ZTORAN in providing a resilient and secure framework for next-generation wireless networks.
{"title":"Zero Trust Security Architecture for 6G Open Radio Access Networks (ORAN)","authors":"Hajar Moudoud;Zakaria Abou El Houda;Bouziane Brik","doi":"10.1109/LNET.2024.3514357","DOIUrl":"https://doi.org/10.1109/LNET.2024.3514357","url":null,"abstract":"The evolution of Open Radio Access Networks (O-RAN) is crucial for the deployment and operation of 6G networks, providing flexibility and interoperability through its disaggregated and open architecture. However, this openness introduces new security issues. To address these challenges, we propose a novel Zero-Trust architecture tailored for ORAN (ZTORAN). ZTORAN includes two main modules: (1) A blockchain-based decentralized trust management system for secure verification, authentication, and dynamic access control of xApps; and (2) A threat detection module that uses Federated Multi-Agent Reinforcement Learning (FMARL) to monitor network activities continuously and detects anomalies within the ORAN ecosystem. Through comprehensive simulations and evaluations, we demonstrate the effectiveness of ZTORAN in providing a resilient and secure framework for next-generation wireless networks.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"6 4","pages":"272-275"},"PeriodicalIF":0.0,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143388570","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-09DOI: 10.1109/LNET.2024.3512659
Jianwen Xu;Kaoru Ota;Mianxiong Dong
As a fundamental component of 6G, Device-to-Device (D2D) communication facilitates direct connections between devices without base stations. In order to support advanced AI applications in ubiquitous scenarios, in this letter, we propose an AI-centric D2D communication infrastructure upon mobile devices, addressing current challenges in bandwidth and transmission speed. This approach aims to leverage 6G’s potential to create more efficient, reliable, and intelligent wireless communication systems, bridging the gap between AI and next-generation D2D communication. The results from real-world case study and simulation show that our design can save time and improve efficiency in D2D transmission and on-device AI processing.
{"title":"AI-Centric D2D in 6G Networks","authors":"Jianwen Xu;Kaoru Ota;Mianxiong Dong","doi":"10.1109/LNET.2024.3512659","DOIUrl":"https://doi.org/10.1109/LNET.2024.3512659","url":null,"abstract":"As a fundamental component of 6G, Device-to-Device (D2D) communication facilitates direct connections between devices without base stations. In order to support advanced AI applications in ubiquitous scenarios, in this letter, we propose an AI-centric D2D communication infrastructure upon mobile devices, addressing current challenges in bandwidth and transmission speed. This approach aims to leverage 6G’s potential to create more efficient, reliable, and intelligent wireless communication systems, bridging the gap between AI and next-generation D2D communication. The results from real-world case study and simulation show that our design can save time and improve efficiency in D2D transmission and on-device AI processing.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"6 4","pages":"257-261"},"PeriodicalIF":0.0,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143388600","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The adoption of the Industrial Internet of Things (IIoT) in industries necessitates advancements in energy efficiency and latency reduction, especially for resource-constrained devices. Services require specific Quality of Service (QoS) levels to function properly, and meeting a threshold QoS can be sufficient for smooth connectivity, reducing the need to maximize perceived QoS due to energy concerns. This is modeled as a satisfactory game, aiming to find minimal power allocation to meet target demands. Due to environmental uncertainties, achieving a Robust Satisfactory Equilibrium (RSE) can be challenging, leading to less satisfaction. We propose a fully distributed, environment-aware power control scheme to enhance satisfaction in dynamic environments. The proposed Robust Banach-Picard (RBP) learning scheme combines deep learning and federated learning to overcome channel and interference impacts and accelerate convergence. Extensive simulations evaluate the scheme under varying channel states and QoS demands, with discussions on convergence speed, energy efficiency, scalability, complexity, and violation rate.
{"title":"Serve Yourself! Federated Power Control for AI-Native 5G and Beyond","authors":"Saad Abouzahir;Essaid Sabir;Halima Elbiaze;Mohamed Sadik","doi":"10.1109/LNET.2024.3509792","DOIUrl":"https://doi.org/10.1109/LNET.2024.3509792","url":null,"abstract":"The adoption of the Industrial Internet of Things (IIoT) in industries necessitates advancements in energy efficiency and latency reduction, especially for resource-constrained devices. Services require specific Quality of Service (QoS) levels to function properly, and meeting a threshold QoS can be sufficient for smooth connectivity, reducing the need to maximize perceived QoS due to energy concerns. This is modeled as a satisfactory game, aiming to find minimal power allocation to meet target demands. Due to environmental uncertainties, achieving a Robust Satisfactory Equilibrium (RSE) can be challenging, leading to less satisfaction. We propose a fully distributed, environment-aware power control scheme to enhance satisfaction in dynamic environments. The proposed Robust Banach-Picard (RBP) learning scheme combines deep learning and federated learning to overcome channel and interference impacts and accelerate convergence. Extensive simulations evaluate the scheme under varying channel states and QoS demands, with discussions on convergence speed, energy efficiency, scalability, complexity, and violation rate.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"6 4","pages":"252-256"},"PeriodicalIF":0.0,"publicationDate":"2024-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143388599","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-20DOI: 10.1109/LNET.2024.3503289
Navid Keshtiarast;Oliver Renaldi;Marina Petrova
In this letter, we propose a novel Multi-Agent Deep Reinforcement Learning (MADRL) framework for MAC protocol design. Unlike centralized approaches, which rely on a single entity for decision-making, MADRL empowers individual network nodes to autonomously learn and optimize their MAC from local observations. Our framework is the first of a kind that enables distributed multi-agent learning within the ns-3 environment, and facilitates the design and synthesis of adaptive MAC protocols tailored to specific environmental conditions. We demonstrate the effectiveness of the MADRL framework through extensive simulations, showcasing superior performance compared to legacy protocols across diverse scenarios.
在这封信中,我们为 MAC 协议设计提出了一种新颖的多代理深度强化学习(MADRL)框架。与依赖单一实体进行决策的集中式方法不同,MADRL 使单个网络节点能够根据本地观测结果自主学习和优化其 MAC。我们的框架是首个能在 ns-3 环境中实现分布式多代理学习的框架,有助于设计和合成适应特定环境条件的自适应 MAC 协议。我们通过大量仿真证明了 MADRL 框架的有效性,并在各种场景中展示了与传统协议相比更优越的性能。
{"title":"Wireless MAC Protocol Synthesis and Optimization With Multi-Agent Distributed Reinforcement Learning","authors":"Navid Keshtiarast;Oliver Renaldi;Marina Petrova","doi":"10.1109/LNET.2024.3503289","DOIUrl":"https://doi.org/10.1109/LNET.2024.3503289","url":null,"abstract":"In this letter, we propose a novel Multi-Agent Deep Reinforcement Learning (MADRL) framework for MAC protocol design. Unlike centralized approaches, which rely on a single entity for decision-making, MADRL empowers individual network nodes to autonomously learn and optimize their MAC from local observations. Our framework is the first of a kind that enables distributed multi-agent learning within the ns-3 environment, and facilitates the design and synthesis of adaptive MAC protocols tailored to specific environmental conditions. We demonstrate the effectiveness of the MADRL framework through extensive simulations, showcasing superior performance compared to legacy protocols across diverse scenarios.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"6 4","pages":"242-246"},"PeriodicalIF":0.0,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143388624","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}