IEEE Communications Surveys and Tutorials最新文献

{"title":"Fluid Antennas: Pioneering a New Era in Next-Generation Wireless Communications","authors":"Dipen Bepari;Soumen Mondal;Anirban Bhowal;Keshav Singh;Hyundong Shin;Kai-Kit Wong;Derrick Wing Kwan Ng","doi":"10.1109/COMST.2026.3678505","DOIUrl":"10.1109/COMST.2026.3678505","url":null,"abstract":"The evolution towards sixth-generation (6G) wireless communication demands antenna technologies that are highly flexible, energy efficient, and scalable to satisfy the demands of massive connectivity, ultra-low latency, and dynamic propagation environments. Fluid antenna systems (FAS) have emerged as a promising solution, offering superior spatial reconfigurability through utilization of a single radio frequency (RF) chain. By dynamically adapting to channel conditions, FAS supports simplified hardware architectures, efficient interference suppression, and enhanced user separation, thereby eliminating the need for complex signal processing methods such as precoding or Successive Interference Cancellation (SIC). This survey presents a comprehensive review of FAS, starting with a tutorial-style introduction to its structural fundamentals, core multiple access mechanisms, and synergy with key 6G enablers including Non-Orthogonal Multiple Access (NOMA), Reconfigurable Intelligent Surfaces (RIS), Simultaneous Wireless Information and Power Transfer (SWIPT), Artificial Intelligence (AI) and Terahertz (THz) communication. In addition, it explores fluid material selection, port selection strategies, and recent advances in Channel State Information (CSI) acquisition, while providing a cross-layer perspective that links fluid material properties to communication performance. The transformative potential of FAS is further explored in the context of Multiple-Input Multiple-Output (MIMO) integration, AI-driven enhancements, and compatibility with other emerging wireless communication paradigms. The paper concludes by highlighting critical open challenges and proposing future research directions essential for fully realizing the capabilities of FAS in next-generation wireless systems.","PeriodicalId":55029,"journal":{"name":"IEEE Communications Surveys and Tutorials","volume":"28 ","pages":"5596-5631"},"PeriodicalIF":34.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147524170","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hardware Impairments in ISAC Systems: A Comprehensive Survey","authors":"Bingqing Li;Jie Yang;Le Liang;Hua Zhang;Yixuan Huang;Tao Du;Yan Li;Hang Que;Shi Jin;Geoffrey Ye Li","doi":"10.1109/COMST.2026.3733082","DOIUrl":"10.1109/COMST.2026.3733082","url":null,"abstract":"Integrated sensing and communication (ISAC) systems are instrumental in shaping the future of 6G by enabling the dual functions. In addition, the emergence of smart electromagnetic (EM) environments based on a heterogeneous deployment of EM entities further strengthens the ISAC paradigm by enabling fine-grained control and adaptation of wireless propagation conditions. However, the performance of this paradigm is significantly hindered by hardware impairments (HWIs), especially those arising from non-ideal radio-frequency components. In this paper, we provide a comprehensive overview of HWIs in transceivers and EM entities within ISAC systems. Specifically, we systematically identify and categorize various impairments, offering a detailed analysis of their sources, impact mechanisms, and commonly used models for characterization. We further compare their effects on communication and sensing performance, highlighting the similarities, differences, and resulting trade-offs between the two functions. Furthermore, we comprehensively review existing signal-processing-based compensation and utilization approaches for representative HWIs and compare their practical strengths and limitations. Beyond the technical review, we examine relevant standardization and industry activities and provide practical design guidelines for HWI-aware ISAC systems. Finally, we discuss open challenges and emerging opportunities in addressing HWIs for ISAC systems, providing a roadmap for future research. This work offers a valuable foundation for developing next-generation ISAC systems capable of overcoming HWI-induced performance limitations and supporting robust practical deployment.","PeriodicalId":55029,"journal":{"name":"IEEE Communications Surveys and Tutorials","volume":"28 ","pages":"7315-7353"},"PeriodicalIF":50.6,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148946708","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Electromagnetic Information Theory for Holographic MIMO Communications","authors":"Li Wei;Tierui Gong;Chongwen Huang;Zhaoyang Zhang;Wei E. I. Sha;Zhi Ning Chen;Linglong Dai;Mérouane Debbah;Chau Yuen","doi":"10.1109/COMST.2026.3689548","DOIUrl":"https://doi.org/10.1109/COMST.2026.3689548","url":null,"abstract":"Holographic multiple-input multiple-output (HMIMO) has recently emerged as a key enabler for next-generation wireless systems due to its capability to form nearly continuous apertures, enabling ultra-high spatial resolution and significantly enhanced capacity. However, this paradigm also raises fundamental questions about the applicability of Shannon’s information theory (SIT) to HMIMO systems and whether physical constraints—such as aperture size, electromagnetic (EM) coupling, resonance, and wavefront curvature—introduce additional limits beyond conventional statistical models. Classical SIT focuses on the probabilistic input–output relationship but does not explicitly incorporate the EM field interactions that fundamentally govern wave propagation. To bridge this gap, this paper introduces an electromagnetic information theory (EIT) framework for HMIMO systems, which unifies EM field theory with both Shannon’s probabilistic and Kolmogorov’s functional formulations of information theory to establish a physically consistent and mathematically complete foundation for performance evaluation. The paper establishes the fundamental physical limits—including constraints on antenna design, gain, and beamwidth—and examines their implications for HMIMO implementations. It then characterizes the excitation–field relationship and the corresponding field sampling and spatial degrees of freedom under physical constraints. Subsequently, field-based and operator-theoretic channel models are developed to describe EM-compliant propagation in HMIMO systems. By combining the statistical representation of SIT with the functional representation of Kolmogorov’s information theory, the proposed EIT framework provides a unified perspective on channel capacity, information flow, and field representation. Finally, we outline open research directions, including EM environment control, 3D superdirective HMIMO design, efficient field sampling, scattering and EM noise modeling, and excitation/field-based encoding and modulation. These developments mark a paradigm shift toward physically grounded, high-capacity, and adaptive wireless communication systems empowered by HMIMO and EIT.","PeriodicalId":55029,"journal":{"name":"IEEE Communications Surveys and Tutorials","volume":"28 ","pages":"6211-6240"},"PeriodicalIF":34.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147937510","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Survey on Deep Multi-Task Learning in Connected Autonomous Vehicles","authors":"Jiayuan Wang;Farhad Pourpanah;Q. M. Jonathan Wu;Ning Zhang","doi":"10.1109/COMST.2026.3699223","DOIUrl":"10.1109/COMST.2026.3699223","url":null,"abstract":"Connected autonomous vehicles (CAVs) must simultaneously perform multiple tasks, such as perception, prediction, planning, and control, to ensure safe and reliable navigation in complex environments. Moreover, through vehicle-to-everything (V2X) communication, cooperative perception and driving among CAVs can be enabled, thereby mitigating the limitations of individual vehicles, while it also introduces stringent latency, reliability, and bandwidth constraints. Traditionally, tasks are addressed using separate models, which leads to high deployment costs, increased computational overhead, and challenges in achieving real-time performance. Multi-task learning (MTL) has recently emerged as a promising solution that enables the joint learning of multiple tasks within a unified model. This offers improved efficiency and resource utilization. To the best of our knowledge, this survey is the first comprehensive review focusing on deep MTL in CAVs. We begin with an overview of CAVs and MTL to provide foundational background. Then, we review MTL approaches across key functional domains in CAVs, including perception, prediction, planning, control, as well as V2X communications and radio resource management (RRM). For the first four domains, we categorize existing works under ego vehicle-only (onboard-only) and V2X-enhanced cooperative (multi-agent) paradigms. We further discuss V2X communications and RRM as communication-centric MTL problems. Finally, we discuss the strengths and limitations of existing methods, identify key research gaps, and provide future research directions aimed at advancing MTL methodologies for CAV systems.","PeriodicalId":55029,"journal":{"name":"IEEE Communications Surveys and Tutorials","volume":"28 ","pages":"6415-6446"},"PeriodicalIF":50.6,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148290015","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep Reinforcement Learning in Software Defined Networking: A Survey, Research Challenges, and Future Perspectives","authors":"Vijay Prakash Bijlwan;Neetesh Kumar","doi":"10.1109/COMST.2026.3656733","DOIUrl":"10.1109/COMST.2026.3656733","url":null,"abstract":"Recent advancements in mobile and internet communication technologies have resulted in the increased complexity and heterogeneity of networking systems. In order to manage these heterogeneous systems more efficiently, there is a requirement for greater intelligence. Since traditional networks with decentralized architecture face challenges in implementing machine learning (ML) techniques to manage the network, the Software Defined Networking (SDN) paradigm offers a solution by decoupling the network’s control functions and data forwarding functions, and centralizing network management through a programmable controller. The centralized controller enables ML techniques to optimize network-wide policies. However, traditional ML techniques, like Reinforcement Learning (RL), face challenges in managing complex networks due to a large state space. Deep Reinforcement Learning (DRL) addresses these issues by combining RL with Deep Learning (DL) that improves the learning efficiency of traditional RL. In this paper, we provide a survey of DRL applications in various SDN domains. First, related work and a brief background of SDN and DRL are provided. Then, we present an overview of existing DRL methods. Further, we systematically review how DRL methods are applied in the SDN from various perspectives, including Traffic Engineering, Quality of Service/Quality of Experience optimization, and Security. We present case studies that highlight the effectiveness of DRL in dynamic network environments, and also analyze the training architecture of DRL in SDN. Finally, we highlight current research challenges, recent advances, and outline future research directions.","PeriodicalId":55029,"journal":{"name":"IEEE Communications Surveys and Tutorials","volume":"28 ","pages":"4624-4653"},"PeriodicalIF":50.6,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146042879","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Tutorial-Cum-Survey on Self-Supervised Learning for Wi-Fi Sensing: Trends, Challenges, and Outlook","authors":"Ahmed Y. Radwan;Mustafa Yildirim;Navid Hasanzadeh;Hina Tabassum;Shahrokh Valaee","doi":"10.1109/COMST.2025.3586212","DOIUrl":"10.1109/COMST.2025.3586212","url":null,"abstract":"Wi-Fi technology has evolved from simple communication routers to sensing devices. Wi-Fi sensing leverages conventional Wi-Fi transmissions to extract and analyze channel state information (CSI) for applications like proximity detection, occupancy detection, activity recognition, and health monitoring. By leveraging existing infrastructure, Wi-Fi sensing offers a privacy-preserving, non-intrusive, and cost-effective solution which, unlike cameras, is not sensitive to lighting conditions. Beginning with a comprehensive review of the Wi-Fi standardization activities, this tutorial-cum-survey first introduces fundamental concepts related to Wi-Fi CSI, outlines the CSI measurement methods, and examines the impact of mobile objects on CSI. The mechanics of a simplified testbed for CSI extraction are also described. Then, we present a qualitative comparison of the existing Wi-Fi sensing datasets, their specifications, and pin-point their shortcomings. Next, a variety of preprocessing techniques are discussed that are beneficial for feature extraction and explainability of machine learning (ML) algorithms. We then provide a qualitative review of recent ML approaches in the domain of Wi-Fi sensing and present the significance of self-supervised learning (SSL) in that context. Specifically, the mechanics of contrastive and non-contrastive learning solutions is elaborated in detail and a quantitative comparative analysis is presented in terms of classification accuracy. Finally, the article concludes by highlighting emerging technologies that can be leveraged to enhance the performance of Wi-Fi sensing and opportunities for further research in this domain.","PeriodicalId":55029,"journal":{"name":"IEEE Communications Surveys and Tutorials","volume":"28 ","pages":"2345-2376"},"PeriodicalIF":50.6,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144566292","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Path to Diversity: A Primer on ISAC-izing Commodity Wi-Fi for Practical Deployments","authors":"Hongbo Wang;Xin Li;Yinghui He;Jingzhi Hu;Mingming Xu;Zhe Chen;Fu Xiao;Jun Luo","doi":"10.1109/COMST.2026.3720687","DOIUrl":"https://doi.org/10.1109/COMST.2026.3720687","url":null,"abstract":"Integrated Sensing and Communication (ISAC) has emerged as a key paradigm in next-generation wireless networks. While the ubiquity and low deployment cost of commodity Wi-Fi render it an ideal platform for wide-scale sensing, it is the continuous evolution of Wi-Fi standards—towards higher frequency bands, wider bandwidths, and larger antenna arrays—that fundamentally unlocks the physical resources required for high-performance ISAC, thereby triggering a surge of related proposals. To structure this rapidly expanding field, a plethora of surveys have appeared. However, prevailing literature predominantly adopts a top-down perspective, emphasizing upper-layer applications or deep learning models while treating the physical layer as an opaque abstraction. Consequently, these works often fail to touch the “bottom layer” of signal formation and lack substantive technical guidance on how to overcome the fundamental physical barriers that constrain sensing performance. To bridge this gap, this tutorial takes a bottom-up approach, systematically analyzing the sensing gains brought by Wi-Fi advancements through the lens of physical-layer diversity. We organize the technical framework around four orthogonal dimensions: 1) Temporal Diversity addresses synchronization gaps to enable absolute ranging; 2) Frequency Diversity expands the effective bandwidth to sharpen range resolution; 3) Link Diversity leverages distributed topologies and digital feedback to achieve ubiquitous observability; and 4) Spatial Diversity utilizes multi-antenna arrays to combine passive angular discrimination with active directional control. Collectively, these orthogonal dimensions resolve fundamental ambiguities in time, range, and space, thereby bridging physical capabilities with challenging sensing diversities such as general-purpose multi-person sensing. By synthesizing these dimensions, this tutorial provides a comprehensive guide for “ISAC-izing” commodity Wi-Fi, paving the way for future standardization and robust deployment.","PeriodicalId":55029,"journal":{"name":"IEEE Communications Surveys and Tutorials","volume":"28 ","pages":"6949-6982"},"PeriodicalIF":50.6,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11643414","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148925389","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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":"Transformer-Enhanced Reinforcement Learning: Fundamentals and Applications in Communication Networks","authors":"Nguyen Cong Luong;Shaohan Feng;Nguyen Duc Hai;Zeping Sui;Bo Ma;Min Xu;Zhihao Dong;Qiushi Zhao;Nguyen Duc Duy Anh;Nguyen Quoc Khanh;Ngoc Hung Nguyen;Zitian Zhang;Jie Cao","doi":"10.1109/COMST.2026.3725159","DOIUrl":"10.1109/COMST.2026.3725159","url":null,"abstract":"Reinforcement Learning (RL) has long been a powerful solution to various problems in communication networks. However, traditional RL models still face several limitations. Not only do they rely on large numbers of interactions with the environment, but they are also limited in terms of modeling long-term relationships and tackling partial observability. In recent years, the Transformer model has demonstrated the ability to enhance RL models, allowing them to overcome these issues. Particularly, the self-attention mechanism within the Transformer enables efficient modeling of long-range dependencies and global correlations, as well as accelerates training processes and handles heterogeneous data modalities. In this paper, we present a comprehensive survey of Transformer-based RL algorithms and their applications in communication networks. Specifically, the paper provides the mathematical background of RL and Transformer architectures, along with insights into key issues such as resource allocation, computation offloading, routing, trajectory control, and network security. We conclude the paper by discussing challenges, open issues, and notable future research directions, including Transformer-enhanced DRL algorithms for semantic communication and network optimization.","PeriodicalId":55029,"journal":{"name":"IEEE Communications Surveys and Tutorials","volume":"28 ","pages":"6908-6948"},"PeriodicalIF":50.6,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148756051","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Latency-Optimized IoT Communications Through Information-Centric Caching: A Survey","authors":"Muhammad Ali Naeem;Ikram Ud Din;Ahmad Almogren;Nehad Ali Shah;Khan Muhammad;Arumugam Nallanathan;Paolo Bellavista","doi":"10.1109/COMST.2026.3729370","DOIUrl":"https://doi.org/10.1109/COMST.2026.3729370","url":null,"abstract":"This paper aims to survey the integration of Information-Centric Networking (ICN) with the Internet of Things (IoT), considering various aspects, including the role of Named Data Networking (NDN) caching schemes in mitigating latency in IoT use cases. Current IP-based protocols may not adequately meet IoT system requirements, as they are not sufficient for dynamic and latency-sensitive IoT applications, such as health-care. NDN provides a shift from location-based to content-based information retrieval, which improves data availability and network efficiency by bringing cached content closer to users and reducing the bandwidth required for data delivery. This paper also reviews and classifies current caching approaches for NDN-based IoT, including content delivery and placement, and discusses the advantages, drawbacks, and effects of these caching schemes on content retrieval latency. It further provides a comparative evaluation of representative caching strategies to highlight their latency-performance trade-offs. This survey outlines the present issues, suggests future work, and provides useful information for improving latency-aware caching schemes for IoT networks.","PeriodicalId":55029,"journal":{"name":"IEEE Communications Surveys and Tutorials","volume":"28 ","pages":"7281-7314"},"PeriodicalIF":50.6,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11673150","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149034114","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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":"A Survey on Reinforcement Learning Methods for Seamless Connectivity in 6G Non-Terrestrial Networks: Algorithms and Key Findings","authors":"Soyi Jung;Huiyeon Jang;Seoyeong Park;Junyoung Kim;Jiseok Jang;In-Sop Cho;Minsu Shin;Tony Q. S. Quek;Zhu Han;Joongheon Kim","doi":"10.1109/COMST.2026.3740875","DOIUrl":"10.1109/COMST.2026.3740875","url":null,"abstract":"The vision of sixth-generation (6G) communications aims to achieve global hyperconnectivity by integrating terrestrial, aerial, and maritime domains. Non-terrestrial networks (NTNs) are key enablers of this vision but face inherent challenges such as high mobility, long propagation delays, and limited onboard computation. To address these challenges, reinforcement learning (RL) has emerged as a promising solution. This paper presents a comprehensive tutorial on RL-based methods for seamless 6G NTN connectivity. It adopts a dual perspective: (i) how RL addresses core NTN problems such as handover, beamforming, and resource allocation and (ii) how NTN constraints inspire the development of advanced RL techniques, including quantum RL, graph-based RL, and federated RL. Based on Third Generation Partnership Project (3GPP) Technical Report (TR) 38.811, the paper identifies 14 optimization challenges across four categories of NTN characteristics—platform dynamics, altitude-dependent propagation, system design constraints, and network architecture—surveys state-of-the-art RL approaches, and analyzes their suitability under real-world NTN conditions. It further discusses performance evaluation results and future research directions, identifying open problems and emerging paradigms that will shape the next phase of intelligent NTN systems. By bridging the gap between theory and practical deployment, this work positions RL as a foundational technology for intelligent, adaptive, and resilient 6G NTN systems.","PeriodicalId":55029,"journal":{"name":"IEEE Communications Surveys and Tutorials","volume":"28 ","pages":"7472-7511"},"PeriodicalIF":50.6,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149093077","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}