IEEE Communications Surveys and Tutorials最新文献

{"title":"A Decade of Video Analytics at Edge: Training, Deployment, Orchestration, and Platforms","authors":"Tong Bai;Haoran Zhao;Lei Huang;Zhipeng Wang;Dong In Kim;Arumugam Nallanathan","doi":"10.1109/COMST.2025.3563377","DOIUrl":"10.1109/COMST.2025.3563377","url":null,"abstract":"Video analytics (VA), capable of autonomously understanding events in video content, has demonstrated significant potential across various applications, from surveillance to self-driving cars and industrial automation. However, traditional VA, relying on either end-device or cloud-based solutions, faces limitations such as restricted on-device computing power and network congestion at cloud centers. Edge computing offers a promising solution, enabling low-latency, high-accuracy, and bandwidth-efficient performance, thus supporting the rapid growth of VA deployment. This article provides a comprehensive review of VA at the edge, examining aspects of model training, deployment, end-edge-cloud orchestration, and VA platforms. Specifically, we explore model training approaches conducted in the cloud, at the edge, and in hybrid cloud-edge configurations. We also discuss various model deployment techniques, including quantization and network pruning. Furthermore, the article surveys end-edge-cloud orchestration strategies, categorized into VA query offloading and query scheduling. We evaluate practical deployments and review the literature on VA platforms. Finally, we outline several promising future research directions for advancing this field.","PeriodicalId":55029,"journal":{"name":"IEEE Communications Surveys and Tutorials","volume":"28 ","pages":"2127-2162"},"PeriodicalIF":50.6,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143862270","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":"ISAC—A Survey on Its Layered Architecture, Technologies, Standardizations, Prototypes, and Testbeds","authors":"Xuewen Luo;Qingfeng Lin;Ruoyu Zhang;Hsiao-Hwa Chen;Xingwei Wang;Min Huang","doi":"10.1109/COMST.2025.3565534","DOIUrl":"10.1109/COMST.2025.3565534","url":null,"abstract":"Integrated sensing and communication (ISAC) has emerged as a critical convergence of traditional communication and radar systems in terms of spectrum, software, and hardware platforms within a unified framework. This survey aims to provide a comprehensive overview on ISAC, beginning with its layered architecture and continuing to discuss about many key components, such as technologies, standardizations, prototypes and testbeds. ISAC architecture is divided into terminal and signal layer, resource layer, function layer, application layer, and computation layer, each of which is examined in detail to understand its roles and interplay within an ISAC ecosystem. Moving beyond the layered architecture, we explore various enabling technologies that empower ISAC, such as beamforming, antenna array design, etc. Notably, this paper reviews emerging technologies such as reconfigurable intelligent surfaces (RIS), new materials, and innovative approach of software-defined radio/radar (SDR2), as well as near-field (NF) ISAC. In addition, this survey covers the standardization efforts of international bodies, which are instrumental in shaping an evolutional trajectory of ISAC technologies. The prototypes and testbeds are presented to validate theoretical concepts and practical implementations of ISAC. Finally, the survey concludes with open issues and potential future directions for ISAC, providing a roadmap for its ongoing development and integration into next-generation networks.","PeriodicalId":55029,"journal":{"name":"IEEE Communications Surveys and Tutorials","volume":"28 ","pages":"485-526"},"PeriodicalIF":50.6,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143889815","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 on O-RAN Deployment Solutions for 5G: From Simulation to Emulated and Real Testbeds","authors":"Juan Luis Herrera;Sofia Montebugnoli;Domenico Scotece;Luca Foschini;Paolo Bellavista","doi":"10.1109/COMST.2025.3577687","DOIUrl":"10.1109/COMST.2025.3577687","url":null,"abstract":"The Open Radio Access Network (O-RAN), manifested through the specifications established by the O-RAN Alliance, stands ready to transform the telecommunications ecosystem. In particular, the O-RAN Alliance reference architecture proposes hierarchical structures supported by several interfaces, including non-real-time and near-real-time functions. Non-real-time functions, denoted as rApps, encompass services, configurations, policy management, and RAN analytics. Conversely, near-real-time applications, denoted as xApps, serve as an open compute edge platform hosting applications from multiple vendors. Therefore, understanding the testing and deployment processes of rApps and xApps is pivotal for both researchers and practitioners. In this tutorial, we evaluate different 5G RAN deployments to determine the state of the art of available open-source solutions and assess their readiness for real cloud continuum environments by targeting solutions for simulation, emulation, and real testbeds. This tutorial empowers developers to gain a comprehensive understanding of O-RAN technologies, their development, and operations, enabling them to make well-informed choices for their target technologies. It considers both qualitative and quantitative benchmarks, as well as use cases, and facilitates a seamless transition of applications from simulated environments to real-world scenarios. Moreover, this tutorial provides a hands-on guide on setting up and migrating an xApp from a simulated environment to a real testbed. It includes a guide on deploying Service Management, Orchestration, and Non-Real-Time RAN Intelligent Controller and rApp. Finally, we identify existing open challenges and trace future directions to enhance the availability, portability, reliability, and configurability of 5G RAN deployments.","PeriodicalId":55029,"journal":{"name":"IEEE Communications Surveys and Tutorials","volume":"28 ","pages":"1709-1748"},"PeriodicalIF":50.6,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11028899","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144252221","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":"Convergence of MEC and DRL in Non-Terrestrial Wireless Networks: Key Innovations, Challenges, and Future Pathways","authors":"Syed Asad Ullah;Syed Ali Hassan;Hatem Abou-Zeid;Hassaan Khaliq Qureshi;Haejoon Jung;Aamir Mahmood;Mikael Gidlund;Muhammad Ali Imran;Ekram Hossain","doi":"10.1109/COMST.2025.3576571","DOIUrl":"10.1109/COMST.2025.3576571","url":null,"abstract":"The rapid growth in mobile communication technologies has turned mobile edge computing (MEC) into a paradigm-shifting technology that extends cloud-like capabilities and storage resources to the edge of the network. This allows computation-intensive and latency-sensitive applications to be performed in close proximity to the end-users, thereby overcoming the bottleneck issues of resource-constrained devices. However, ensuring efficient operations in MEC-empowered systems requires intelligent task execution and resource allocation across MEC servers. To this end, MEC-empowered non-terrestrial wireless networks (MeNT-WiN) systems represent a promising domain where deep reinforcement learning (DRL) can serve as a powerful tool to enhance the MEC abilities in edge servers and network entities. This paper presents a thorough overview of the applications of DRL in MeNT-WiNs. In particular, it underlines the main contribution of DRL in enhancing the performance of MeNT-WiNs, including autonomous aerial vehicles (AAV) and satellite communications networks. This paper investigates how DRL can meet the unique requirements of MeNT-WiNs by enhancing system efficiency, scalability, and decision-making processes across MEC architectures. First, the article reviews the fundamentals of DRL, it later discusses its integration with MeNT-WiNs and demonstrates its relevance for the optimization of satellite communications and management of AAV swarms, as well as enhancing connectivity in remote areas. The survey also identifies key challenges for DRL-driven MeNT-WiN systems, such as computational complexity and real-time adaptability, while being scalable. Finally, it discusses future research possibilities, emphasizing the importance of new solutions that integrate DRL with MEC in order to fully exploit the potential of MeNT-WiNs.","PeriodicalId":55029,"journal":{"name":"IEEE Communications Surveys and Tutorials","volume":"28 ","pages":"1950-1985"},"PeriodicalIF":50.6,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144218740","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":"Distributed Machine Learning for Autonomous Agent Swarm: A Survey","authors":"Xiangwang Hou;Jingjing Wang;Jun Du;Chunxiao Jiang;Yong Ren","doi":"10.1109/COMST.2025.3594713","DOIUrl":"10.1109/COMST.2025.3594713","url":null,"abstract":"Autonomous agents, including unmanned aerial vehicles (UAVs), unmanned ground vehicles (UGVs), unmanned surface vessels (USVs), and unmanned underwater vehicles (UUVs), are widely applied across diverse fields, such as environmental monitoring, logistics, exploration, and military applications, due to their ability to operate autonomously in complex environments. As tasks grow in complexity, there is a shift from individual autonomous agents to collaborative autonomous agent swarms (AASs). These swarms, connected through wireless links, leverage collective intelligence to perform more sophisticated tasks than individual autonomous agents can achieve alone. Deploying AASs introduces challenges in coordination, resource utilization, and adaptability, which traditional model-based methods struggle to address. Recent advancements in machine learning (ML), particularly distributed machine learning (DML) techniques such as federated learning (FL) and multi-agent reinforcement learning (MARL), offer promising solutions. These techniques enable autonomous agents to learn collaboratively without centralizing data, thereby preserving efficiency while adapting to dynamic environments. However, applying DML in AASs presents unique challenges due to autonomous agents’ dynamic movement, unreliable communication links, harsh operating conditions, heterogeneity, and resource constraints. Therefore, this survey provides a comprehensive review of integrating DML into AASs. Specifically, we analyze four representative types of autonomous agents in a unified perspective examining their fundamental characteristics, communication models, and dynamic behaviors. Then, we discuss the limitations of basic ML models in AASs, highlighting the need for DML and the key requirements and metrics for its successful implementation. Furthermore, we explore recent advancements in FL and MARL as applied to AASs, highlighting use cases and key techniques. By identifying current technological progress and gaps in the literature, this survey offers valuable insights for researchers and practitioners and outlines potential directions for future research to enhance the capabilities of AASs through DML.","PeriodicalId":55029,"journal":{"name":"IEEE Communications Surveys and Tutorials","volume":"28 ","pages":"1597-1636"},"PeriodicalIF":50.6,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144763426","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":"ComAI: The Convergence of Communication and Artificial Intelligence","authors":"Ping Zhang;Kai Niu;Xiaoyun Wang;Yiming Liu;Zijian Liang;Chen Dong;Jincheng Dai;Xiaodong Xu;Wenjun Xu;Zhi Zhang;Guangyu Wang;Yanlu Li;Di Wu;Hequan Wu","doi":"10.1109/COMST.2025.3608174","DOIUrl":"10.1109/COMST.2025.3608174","url":null,"abstract":"The convergence of communication and artificial intelligence (AI) is transforming next-generation wireless networks. Inspired by natural intelligence, particularly in how data, information, and knowledge are processed for cognition, reasoning, learning, decision-making, and environmental interaction, we introduce a new paradigm called ComAI. This paradigm is expected to play a key role in future wireless networks. In this paper, we highlight the motivations behind the convergence of communications and AI and present a roadmap that outlines the evolution of wireless communications alongside advancements in AI. Then, we introduce the key idea of ComAI and provide a general framework of ComAI, which includes information sensing and data collection, information cognition through intellicise semantic communication networks, and information decision with large-scale models. In particular, intellicise semantic communication networks refer to intelligent and concise communication systems that leverage semantic-level information to simplify and restructure signal processing, information cognition, and network organization. We further discuss the foundational theories and key techniques for the convergence of communication and AI. Additionally, we provide experimental validations, including insights from the 6G test network, and highlight potential application scenarios such as embodied AI robots and multi-agent collaborative communications. Finally, we outline the future directions and open issues in the development of ComAI, sharing our thoughts and insights on potential solutions.","PeriodicalId":55029,"journal":{"name":"IEEE Communications Surveys and Tutorials","volume":"28 ","pages":"2163-2197"},"PeriodicalIF":50.6,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145035819","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":"Future Digital Identity Management With Quantum Secure Blockchain","authors":"Siddhartha Siddhiprada Bhoi;Akanksha Saini;Abebe Diro;Shahriar Kaisar;Asha Rao","doi":"10.1109/COMST.2025.3608794","DOIUrl":"10.1109/COMST.2025.3608794","url":null,"abstract":"Quantum computing poses a significant threat to the cryptographic foundations of traditional blockchain-based identity management systems and could compromise the security and privacy of digital identities. This survey critically evaluates the emerging landscape of quantum-secure blockchain solutions for digital identity management. We analyze the technical underpinnings, strengths, weaknesses, and potential applications of post-quantum, hybrid-quantum, and fully quantum blockchain approaches. Post-quantum blockchains leveraging quantum-resistant cryptographic algorithms such as lattice-based (e.g., CRYSTALS-Dilithium), hash-based (e.g., SPHINCS+), code-based (e.g., McEliece), and multivariate schemes offer near-term feasibility by integrating into existing infrastructures but face performance trade-offs and potential long-term risks. Hybrid quantum blockchains combining classical blockchain mechanisms with quantum technologies enable enhanced security and gradual transitions but require complex integration efforts and specialized infrastructure. Fully quantum blockchains utilizing quantum entanglement and quantum key distribution (QKD) promise unmatched theoretical security but remain constrained by the immaturity of quantum hardware and algorithms. To provide actionable insights, this paper introduces the Quantum Blockchain Digital Identity Framework (QBDIF) and examines practical implementations such as the Quantum Resistant Ledger (QRL), highlighting critical trade-offs between security, scalability, and practicality in quantum-secure identity management. Our survey emphasizes the need for future research in scalable and efficient quantum-resistant cryptographic algorithms, hybrid consensus mechanisms, and innovative applications of quantum machine learning for blockchain-based identity systems.","PeriodicalId":55029,"journal":{"name":"IEEE Communications Surveys and Tutorials","volume":"28 ","pages":"1679-1708"},"PeriodicalIF":50.6,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145035448","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 of Pinching-Antenna Systems (PASS)","authors":"Yuanwei Liu;Hao Jiang;Xu Gan;Xiaoxia Xu;Jia Guo;Zhaolin Wang;Chongjun Ouyang;Xidong Mu;Zhiguo Ding;Arumugam Nallanathan;Octavia A. Dobre;George K. Karagiannidis;Robert Schober","doi":"10.1109/COMST.2026.3731727","DOIUrl":"10.1109/COMST.2026.3731727","url":null,"abstract":"The pinching-antenna system (PASS), recently proposed as a flexible-antenna technology, has been regarded as a promising solution for several challenges in next-generation wireless networks. It provides large-scale antenna reconfiguration, establishes stable line-of-sight links, mitigates signal blockage, and exploits near-field advantages through its distinctive architecture. This article aims to present a comprehensive overview of the state of the art in PASS. The fundamental principles of PASS are first discussed, including its hardware architecture, circuit and physical models, and signal models. Several emerging PASS designs, such as segmented waveguide-enabled PASS (SWAN), center-fed PASS (C-PASS), and multi-mode PASS (M-PASS), are subsequently introduced, and their design features are discussed. In addition, the properties and promising applications of PASS for wireless sensing are reviewed. On this basis, recent progress in the performance analysis of PASS for both communications and sensing is surveyed, and the performance gains achieved by PASS are highlighted. Existing research contributions in optimization and machine learning are also summarized, with the practical challenges of beamforming and resource allocation being identified in relation to the unique transmission structure and propagation characteristics of PASS. Finally, several variants of PASS are presented, and key implementation challenges that remain open for future study are discussed.","PeriodicalId":55029,"journal":{"name":"IEEE Communications Surveys and Tutorials","volume":"28 ","pages":"7250-7280"},"PeriodicalIF":50.6,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148909259","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 Energy-Efficient Next-Generation Wireless Terahertz Communications","authors":"Shikha Maurya;Soumen Mondal;Rahul Pal;Keshav Singh;Hyundong Shin","doi":"10.1109/COMST.2026.3727776","DOIUrl":"10.1109/COMST.2026.3727776","url":null,"abstract":"The emergence of sixth-generation (6G) wireless networks demands unprecedented improvements in data rates, connectivity, and energy-efficiency (EE), making the terahertz (THz) band a key enabler due to its vast, underutilized spectrum and high spatial resolution. This survey stands apart from previous studies by providing the first comprehensive, energy-centric analysis of THz communications, along with key 6G technologies and applications to offer a holistic roadmap toward sustainable, high-performance THz communication systems. The survey begins with a detailed examination of THz band characteristics, including propagation models and environmental influences. Key technical hurdles are identified alongside a survey of the current landscape, which includes standardization efforts, real-world testbeds, and industry adoption trends in THz technology. The critical importance of EE in 6G systems is emphasized through a comprehensive assessment of key energy challenges and optimization initiatives, followed by an in-depth analysis of energy-efficient THz communication techniques, such as hybrid beamforming and energy harvesting (EH), with a particular focus on material and device innovations, system-level modeling, and network-level adaptive communication protocols. Furthermore, the integration of THz communication with emerging technologies is analyzed from an energy-centric perspective, supported by comparative tables. This survey also maps diverse application scenarios, from nano-networks and healthcare to Industry 4.0 and military, and concludes with a discussion of open research challenges and future directions for THz system development.","PeriodicalId":55029,"journal":{"name":"IEEE Communications Surveys and Tutorials","volume":"28 ","pages":"7092-7135"},"PeriodicalIF":50.6,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148821028","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":"“X of Information” Continuum: A Survey on AI-Driven Multi-Dimensional Metrics for Next-Generation Networked Systems","authors":"Beining Wu;Jun Huang;Shui Yu","doi":"10.1109/COMST.2026.3670279","DOIUrl":"10.1109/COMST.2026.3670279","url":null,"abstract":"The development of next-generation networking systems has shifted from throughput-based paradigms towards intelligent, information-aware designs that emphasize information quality, relevance, and utility rather than data volume. Classical network metrics such as latency and packet loss remain significant but are insufficient for modern intelligent applications that include autonomous vehicles, digital twins, and metaverse environments. This survey presents the first comprehensive study of the “X of Information” continuum through a systematic four-dimensional taxonomic framework that structures information metrics along temporal, quality/utility, reliability/robustness, and network/communication dimensions. We uncover increasing interdependencies among these dimensions, where temporal freshness triggers quality evaluation, which enables reliability appraisal that supports effective network delivery. Our analysis reveals that artificial intelligence technologies such as deep reinforcement learning, multi-agent systems, and neural optimization models enable adaptive, context-aware optimization of competing information quality objectives. Our study of six critical application domains that span autonomous transportation, industrial IoT, healthcare digital twins, UAV communications, LLM ecosystems, and metaverse settings illustrates the promise of multi-dimensional information metrics for diverse operational needs. The survey identifies key implementation challenges that include metric integration, information-driven resource allocation, semantic communication, and federated learning optimization. We highlight critical research agendas in unified theoretical models, AI-augmented dynamic optimization, and cross-layer orchestration mechanisms that lay the foundation for intelligent, value-aware communication systems.","PeriodicalId":55029,"journal":{"name":"IEEE Communications Surveys and Tutorials","volume":"28 ","pages":"5307-5344"},"PeriodicalIF":34.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147361088","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}