IEEE Open Journal of the Communications Society最新文献

{"title":"DDPG Optimization for Hybrid RIS-Assisted Secure Multi-User-MISO Networks","authors":"Muhammad Iqbal;Burhan Wafai;Tabinda Ashraf;Syed Muhammad Jameel;Wali Ullah Khan;Muhammad Saad;Sangarapillai Lambotharan;Jen-Yi Pan","doi":"10.1109/OJCOMS.2026.3675029","DOIUrl":"https://doi.org/10.1109/OJCOMS.2026.3675029","url":null,"abstract":"This paper investigates a Deep Reinforcement Learning (DRL) based optimization framework for secure communications in hybrid reconfigurable intelligent surface (RIS)-assisted multi-user multiple-input single-output (MU-MISO) systems. A secrecy-aware actor-critic model is developed using deep deterministic policy gradient (DDPG) to optimize the hybrid RIS reflection and amplification coefficients with a fixed Zero-Forcing transmit beamformer under secrecy constraints. A novel reward design is proposed that incorporates both user fairness and secrecy rate maximization, penalizing imbalance and eavesdropper leakage. Unlike conventional DRL-based RIS designs that maximize only aggregate secrecy rate, the proposed fairness-aware secrecy reward explicitly regulates the standard deviation of per-user secrecy rates to promote balanced performance across users. The channel model captures both direct and reflected links, with independent Rayleigh fading for all paths. The simulation results reveal that the proposed approach significantly improves the average sum secrecy rate and user throughput as transmit power and RIS size increase. The results also demonstrate that the hybrid RIS outperforms the passive RIS and achieves secrecy performance comparable to that of an active RIS with reduced power consumption. Furthermore, the proposed DDPG-based method achieves secure and efficient resource allocation, making it a promising candidate for next-generation secure RIS-assisted wireless networks.","PeriodicalId":33803,"journal":{"name":"IEEE Open Journal of the Communications Society","volume":"7 ","pages":"2700-2713"},"PeriodicalIF":6.3,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11436049","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147557629","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}

{"title":"Lightweight Adaptation of Foundation Models for Optical Network Failure Management","authors":"Emilio Paolini;Luca Valcarenghi","doi":"10.1109/OJCOMS.2026.3672881","DOIUrl":"https://doi.org/10.1109/OJCOMS.2026.3672881","url":null,"abstract":"Machine Learning is increasingly used for optical network automation, yet current solutions require extensive model engineering and lack generalization across heterogeneous domains. This paper introduces a foundation-model pipeline for optical failure management that addresses this limitation by reusing a single frozen LLM backbone as a universal encoder for optical telemetry, while lightweight adapter modules enable efficient task specialization across domains. Evaluations on both an experimental optical dataset and a large-scale simulated soft-failure classification dataset show that adapters preserve most of the predictive performance of full fine-tuning, achieving an F1 of <inline-formula> <tex-math>$approx {mathbf {0.885}}$ </tex-math></inline-formula> on the experimental dataset and an accuracy of <inline-formula> <tex-math>$approx {mathbf {0.91}}$ </tex-math></inline-formula> on the simulated dataset, while reducing computational cost by up to one order of magnitude compared to full fine-tuning. Adapters also remain robust under aggressive compression, maintaining F1 and accuracy within (0.86–0.88) and (0.865–0.945) ranges, respectively, even at reduction factors up to <inline-formula> <tex-math>${mathbf {96}}times $ </tex-math></inline-formula>. Few-shot experiments further demonstrate strong data efficiency: with only 64–128 labeled samples, the proposed architecture reaches near-perfect performance in one transfer direction and reliably adapts in the more fine-grained case. These results highlight the viability of Parameter-Efficient Fine-Tuning-enabled foundation models for scalable, cross-domain optical failure management.","PeriodicalId":33803,"journal":{"name":"IEEE Open Journal of the Communications Society","volume":"7 ","pages":"2577-2587"},"PeriodicalIF":6.3,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11430566","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147557326","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}

{"title":"Energy-Efficient and Learning-Aware Edge Intelligence With Probabilistic Scheduling","authors":"Haihui Xie;Pingping Xu;Zhaogang Shu;Shuwu Chen;Changsheng You","doi":"10.1109/OJCOMS.2026.3674612","DOIUrl":"https://doi.org/10.1109/OJCOMS.2026.3674612","url":null,"abstract":"In edge intelligence networks, various applications exist based on different users and datasets. To realize intelligence, many works design various edge learning models to process these data. However, different types of users and models have negative influence on the learning performance, even degrading the learning gain. To address these issues, we propose a learning-aware optimization model with probabilistic scheduling. First, we design users scheduling to reveal the relationships between resource allocation and learning performance. Then, we also develop a fast proximal linearized algorithm in the large-scale communication networks. Next, we derive tasks scheduling in asymptotic cases to improve resource utilization efficiency. At last, extensive experimental results corroborate that probabilistic scheduling and multi-objective learning models improve the distinct edge learning gain efficiently compared with the state-of-the-art benchmark algorithms.","PeriodicalId":33803,"journal":{"name":"IEEE Open Journal of the Communications Society","volume":"7 ","pages":"2894-2907"},"PeriodicalIF":6.3,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11435380","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147606169","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}

{"title":"AI-Driven Energy-Efficient UAV-Assisted 6G Communications: A Comprehensive Survey and Research Roadmap","authors":"Fendy Santoso","doi":"10.1109/OJCOMS.2026.3673848","DOIUrl":"https://doi.org/10.1109/OJCOMS.2026.3673848","url":null,"abstract":"Unmanned aerial vehicles (UAVs) are poised to become the key enablers of 6G—extending coverage, sensing, and edge intelligence—yet their potential remains constrained by severe energy limitations. This survey unifies the rapidly expanding field of AI-driven, energy-efficient UAV communications through a cross-layer perspective linking propulsion, radio, computation, and control. It consolidates advances in renewable-powered airframes, reconfigurable intelligent surfaces, non-orthogonal multiple access (NOMA), millimeter-wave communications, mobile edge computing, and reinforcement-learning-based coordination into a coherent analytical framework. A new taxonomy of energy costs—spanning propulsion, RF transmission, computation, sensing, and security—is introduced to benchmark mechanisms that genuinely reduce joules per bit and extend endurance. Case studies in disaster response, smart cities, precision agriculture, and rural connectivity demonstrate how trajectory–power co-optimization, learning-augmented control, and cooperative energy sharing translate theory into practice. The paper further identifies critical research gaps—including scalable swarm coordination, interference- and safety-aware learning, and reproducible energy reporting—and outlines a roadmap toward long-endurance, self-optimizing UAV–6G networks that are intelligent, efficient, and sustainable. Unlike previous reviews that examined UAV communications or 6G architectures in isolation, this work unifies the two domains through an AI-centric perspective and systematically evaluates energy-efficient design principles. This survey synthesizes more than 200 peer-reviewed works (2020–2025) across four architectural layers, offering the first bibliometric and taxonomy-based synthesis of UAV–AI–6G integration.","PeriodicalId":33803,"journal":{"name":"IEEE Open Journal of the Communications Society","volume":"7 ","pages":"2838-2875"},"PeriodicalIF":6.3,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11441325","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147606222","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}

{"title":"Enhancing PLS of Indoor IRS-VLC Systems for Colluding and Non-Colluding Eavesdroppers","authors":"Rashid Iqbal;Ahmed Zoha;Salama Ikki;Muhammad Ali Imran;Hanaa Abumarshoud","doi":"10.1109/OJCOMS.2026.3672982","DOIUrl":"https://doi.org/10.1109/OJCOMS.2026.3672982","url":null,"abstract":"Most intelligent reflecting surface (IRS)-aided indoor visible light communication (VLC) studies ignore the time delays introduced by reflected paths, even though these delays are inherent in practical wideband systems. In this work, we adopt a realistic assumption of IRS-induced time delay for physical layer security (PLS) enhancement. We consider an indoor VLC system where an IRS is used to shape the channel so that the reflected signals add constructively at the legitimate user and create intersymbol interference at eavesdroppers located inside the coverage area. The resulting secrecy capacity maximisation over the IRS element allocation is formulated as a complex combinatorial optimisation problem and is solved using deep reinforcement learning with proximal policy optimisation (PPO). The approach is evaluated for both colluding eavesdroppers, which combine their received signals, and non-colluding eavesdroppers, which act independently. Simulation results are presented for a range of indoor layouts and user placements, demonstrating significant secrecy capacity gains. In a worst-case scenario, where the eavesdroppers have stronger channels than the legitimate user, the proposed PPO-based IRS allocation improves secrecy capacity by 107% and 235% in the colluding and non-colluding cases, respectively, compared with allocating all IRS elements to the legitimate user. These results demonstrate that time-delay-based IRS control can provide a strong secrecy advantage in practical indoor VLC scenarios.","PeriodicalId":33803,"journal":{"name":"IEEE Open Journal of the Communications Society","volume":"7 ","pages":"2765-2776"},"PeriodicalIF":6.3,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11430559","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147557596","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}

{"title":"Resilient Resource Allocation in OFDMA Systems: A Scalable Recurrent MARL Framework for Channel Aging Compensation","authors":"Haozhe Gu;Ningyan Guo;Tianjiao Sun;Yuanhao Cui;Haoxuan Xu;Zhiyong Feng","doi":"10.1109/OJCOMS.2026.3690255","DOIUrl":"https://doi.org/10.1109/OJCOMS.2026.3690255","url":null,"abstract":"In downlink orthogonal frequency division multiple access (OFDMA) systems, efficient joint optimization of user scheduling and link adaptation is crucial for meeting the high data rates and connectivity demands of future wireless communications. However, the inherent feedback delays in practical systems cause channel state information (CSI) acquired by base stations to become outdated, a phenomenon known as channel aging. This temporal state mismatch leads to erroneous selection of modulation and coding schemes (MCS) and ineffective user scheduling, resulting in significant degradation of system throughput and user fairness. To address this challenge, this paper proposes a Resilient Resource Allocation Strategy based on a scalable recurrent multi-agent reinforcement learning (MARL) framework. To ensure scalability, we formulate the problem as a decentralized partially observable Markov decision process (Dec-POMDP), where a multi-agent approach is used to decompose the global action space, allowing for distributed scalability and avoiding the exponential complexity of centralized optimization. Temporal processing capabilities are integrated into the agents via gated recurrent units. This framework implicitly predicts real-time channel states using historical observations, effectively overcoming the challenge of partially observable states. Simulation results demonstrate that the proposed approach maintains robust performance under varying channel aging conditions. Compared to traditional baseline algorithms, the proposed algorithm achieves an average 14.47% improvement in proportional fairness utility, with performance gains reaching up to 22.31% under severe channel aging conditions. This framework effectively balances user fairness while significantly enhancing system throughput and transmission reliability.","PeriodicalId":33803,"journal":{"name":"IEEE Open Journal of the Communications Society","volume":"7 ","pages":"5255-5267"},"PeriodicalIF":6.3,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11505886","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148003604","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}

{"title":"Enhancing Coverage and Sensing in Space–Air–Ground Networks via a UAV-Assisted ISAC Framework With Satellite Backhaul","authors":"Zhaoxia Ding;Zhaogui Zeng;Shuaishuai Guo;Ruidong Li;Ji Zhong;Tong-Xing Zheng;Hong-Ning Dai;Dengwang Li;Xuran Li","doi":"10.1109/OJCOMS.2026.3697478","DOIUrl":"https://doi.org/10.1109/OJCOMS.2026.3697478","url":null,"abstract":"Space–air–ground integrated networks (SAGINs) are expected to support ubiquitous communication and sensing in next-generation wireless systems. In this paper, we develop a stochastic-geometry-based analytical framework for a three-tier integrated sensing and communication (ISAC) network composed of ground base stations (BSs), unmanned aerial vehicles (UAVs), and low-earth-orbit (LEO) satellites. In the proposed architecture, ground BSs are spatially distributed according to an independent homogeneous Poisson point process (HPPP), UAVs perform sensing and uplink transmission with horizontal locations modeled by an HPPP, and LEO satellites provide relay/backhaul support with ground projections following an independent HPPP. Analytical expressions for the hop-wise communication coverage probability and the single-UAV sensing detection probability are derived. The end-to-end coverage probability is rigorously formulated as a joint event, and a tractable product-form expression is obtained by exploiting the independence of the three-tier spatial processes. Monte Carlo simulations validate the analysis and illustrate how satellite relaying, UAV deployment parameters, and propagation conditions affect communication reliability and sensing detectability. The proposed framework provides useful benchmark-level insights for the design of SAGIN-enabled ISAC systems and establishes analytical building blocks for future studies on cooperative sensing fusion.","PeriodicalId":33803,"journal":{"name":"IEEE Open Journal of the Communications Society","volume":"7 ","pages":"5858-5870"},"PeriodicalIF":6.3,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11535832","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148171919","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}

{"title":"Accurate Interference and Coverage Modelling in Finite OWC Networks","authors":"Ali Mahbas;John Cosmas;Nila Nilavalan;Hamed Al-Raweshidy","doi":"10.1109/OJCOMS.2026.3699444","DOIUrl":"https://doi.org/10.1109/OJCOMS.2026.3699444","url":null,"abstract":"Accurate modelling of interference and coverage in optical wireless communication (OWC) systems remains challenging due to the limitations of conventional approaches, which typically rely on infinite-network assumptions or simplified disc-shaped cell models. In practical deployments, OWC networks are finite and regularly structured, resulting in spatially varying interference patterns that are not captured by existing models. This paper proposes a comprehensive analytical framework for evaluating interference and coverage probability in finite OWC networks with regularly deployed grid-based nodes. The framework is developed for a baseline line-of-sight (LOS)-dominant scenario with regularly spaced nodes, ideal transmitter–receiver alignment, and unobstructed propagation conditions (i.e., without blockage or misalignment effects). It explicitly accounts for three-dimensional distances, inter-node spacing, system dimensions, and transmitter–receiver height differences, while incorporating boundary effects. To capture spatial variability, the network is partitioned into core, mid, and boundary zones. Semi-analytical expressions for the interference distribution are derived for each zone, revealing distinct behaviours and pronounced performance degradation in cell-edge regions. Analytical and simulation results demonstrate that commonly adopted disc-assumption models significantly overestimate system performance by neglecting edge effects. For example, at a signal-to-interference-plus-noise ratio (SINR) threshold of −3 dB, disc-based models predict approximately 95% coverage, whereas the proposed framework and simulations show that only about 75% of the core and mid zones satisfy this threshold. The results further show that increasing inter-node distance and adopting higher reuse factors substantially improve coverage, while larger height differences degrade performance by increasing the number of visible interferers. Overall, the proposed framework provides a realistic and generalisable tool for analysing finite OWC networks, enabling more accurate performance evaluation and more reliable network design and deployment.","PeriodicalId":33803,"journal":{"name":"IEEE Open Journal of the Communications Society","volume":"7 ","pages":"6369-6392"},"PeriodicalIF":6.2,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11547209","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148433242","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}

{"title":"Anchor-Free Collaborative Learning for Label Noise-Resilient RF Fingerprint Identification","authors":"Kefeng Song;Jianbing Li;Dongfang Zhou;Hailin Deng;Haitao Li","doi":"10.1109/OJCOMS.2026.3697126","DOIUrl":"https://doi.org/10.1109/OJCOMS.2026.3697126","url":null,"abstract":"RF fingerprint identification (RFFI) leverages unique physical-layer features for device authentication and provides an additional layer of security in wireless communications. While deep learning has significantly advanced RFFI, accurately labeling large-scale RF datasets is challenging, and manual annotation inevitably introduces label noise. Deep neural networks tend to memorize such noisy labels, resulting in degraded generalization. Collaborative learning (co-learning) is an effective approach for mitigating the impact of label noise, but its reliance on the small-loss criterion requires setting an appropriate forgetting rate. Conventional methods that estimate the noise transition matrix require clean anchor samples that are difficult to obtain for RF signals lacking intuitive semantic content, limiting their practical applicability. To address these challenges, we propose an Anchor-free Co-Learning (ACL) method for robust RFFI under label noise. ACL performs dynamic sample exchange between two complex-valued neural networks and introduces the Prediction Change Attenuation Ratio (PCAR), a novel metric that captures the degree of label corruption to adaptively compensate the base forgetting rate. This design eliminates the need for anchor samples and also avoids full noise transition matrix estimation, and is therefore well suited to RFFI while reducing unnecessary computational overhead. Experiments on real-world outdoor ADS-B and indoor WiFi datasets demonstrate that ACL maintains over 90% mean accuracy under 55% symmetric label noise, consistently outperforms representative baselines, and remains viable under asymmetric noise. Ablation studies further confirm the contribution of each component.","PeriodicalId":33803,"journal":{"name":"IEEE Open Journal of the Communications Society","volume":"7 ","pages":"6393-6408"},"PeriodicalIF":6.2,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11535454","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148433272","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}

{"title":"Blockage-Aware Hierarchical Codebook Design for RIS-Assisted Movable Antenna Systems","authors":"Yan Zhang;Indrakshi Dey;Nicola Marchetti","doi":"10.1109/OJCOMS.2026.3676576","DOIUrl":"https://doi.org/10.1109/OJCOMS.2026.3676576","url":null,"abstract":"In this paper, we propose a novel blockage-aware hierarchical beamforming framework for movable antenna (MA) systems operating at millimeter-wave (mm-Wave) frequencies. While existing works on MA systems have demonstrated performance gains over conventional systems, they often neglect the design of specialized codebooks to leverage MA’s unique capabilities and address the challenges of increased energy consumption and latency inherent to MA systems. To address these aspects, we first integrate blockage detection into the codebook design process based on the Gerchberg-Saxton (GS) algorithm, significantly reducing inefficiencies due to beam evaluations done in blocked directions. Then, we use a two-stage approach to reduce the complexity of the joint beamforming and Reconfigurable Intelligent Surfaces (RIS) optimization problem. The simulations demonstrate that the proposed adaptive codebook successfully improves the Energy Efficiency (EE) and reduces the beam training overhead, substantially boosting the practical deployment potential of RIS-assisted MA systems in future wireless networks.","PeriodicalId":33803,"journal":{"name":"IEEE Open Journal of the Communications Society","volume":"7 ","pages":"3094-3112"},"PeriodicalIF":6.2,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11450412","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148489270","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}