{"title":"Iterative Joint Detection of Kalman Filter and Channel Decoder for Sensor-to-Controller Link in Wireless Networked Control Systems","authors":"Jinnan Piao, Dong Li, Yiming Sun, Zhibo Li, Ming Yang, Xueting Yu","doi":"10.1109/lwc.2025.3645782","DOIUrl":"https://doi.org/10.1109/lwc.2025.3645782","url":null,"abstract":"","PeriodicalId":13343,"journal":{"name":"IEEE Wireless Communications Letters","volume":"159 1","pages":""},"PeriodicalIF":6.3,"publicationDate":"2025-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145777905","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Heterogeneous services such as broadband and latency-constrained Internet-of-Things (IoT), with diverse requirements, make efficient resource sharing challenging. Two canonical strategies are radio access network (RAN) Slicing, which allocates disjoint resources per service, and RAN Sharing, where services coexist on a common resource. Under either regime, grant-free repetition-based access is a key enabler of IoT connectivity, prompting latency-aware policies tuned to the regimes’ density and interference profiles. Prior work on repetition-policy optimisation mainly employs base station (BS)-centric reinforcement learning (RL) or irregular repetition slotted ALOHA (IRSA)-based approaches focused on throughput/packet loss rate (PLR) in asymptotic regimes. The former requires central orchestration, leading to high control overhead and reduced adaptability; the latter typically degrades when targeting performance at finite frame lengths. This motivates decentralised multi-agent RL (MARL), where each IoT device learns its own policy to meet latency targets in dense, finite frame-length, mixed-service deployments. To this end, we investigate an uplink scenario where a broadband user coexists with multiple latency-constrained IoT devices employing grant-free access. We formulate IoT access policy optimisation as a decentralised, model-free MARL problem, enabling devices to learn their transmission strategies under finite frame length structures and strict latency requirements. Under both RAN Slicing and RAN Sharing regimes, the proposed scheme outperforms baseline decentralised approaches; in each regime it achieves substantial IoT latency gains while sustaining broadband throughput and energy efficiency (EE). Furthermore, the results highlight and compare regime-specific trade-offs.
{"title":"Reinforcement Learning-Based Policy Optimization for Heterogeneous Radio Access","authors":"Anup Mishra;Čedomir Stefanović;Petar Popovski;Israel Leyva-Mayorga","doi":"10.1109/LWC.2025.3642168","DOIUrl":"10.1109/LWC.2025.3642168","url":null,"abstract":"Heterogeneous services such as broadband and latency-constrained Internet-of-Things (IoT), with diverse requirements, make efficient resource sharing challenging. Two canonical strategies are radio access network (RAN) Slicing, which allocates disjoint resources per service, and RAN Sharing, where services coexist on a common resource. Under either regime, grant-free repetition-based access is a key enabler of IoT connectivity, prompting latency-aware policies tuned to the regimes’ density and interference profiles. Prior work on repetition-policy optimisation mainly employs base station (BS)-centric reinforcement learning (RL) or irregular repetition slotted ALOHA (IRSA)-based approaches focused on throughput/packet loss rate (PLR) in asymptotic regimes. The former requires central orchestration, leading to high control overhead and reduced adaptability; the latter typically degrades when targeting performance at finite frame lengths. This motivates decentralised multi-agent RL (MARL), where each IoT device learns its own policy to meet latency targets in dense, finite frame-length, mixed-service deployments. To this end, we investigate an uplink scenario where a broadband user coexists with multiple latency-constrained IoT devices employing grant-free access. We formulate IoT access policy optimisation as a decentralised, model-free MARL problem, enabling devices to learn their transmission strategies under finite frame length structures and strict latency requirements. Under both RAN Slicing and RAN Sharing regimes, the proposed scheme outperforms baseline decentralised approaches; in each regime it achieves substantial IoT latency gains while sustaining broadband throughput and energy efficiency (EE). Furthermore, the results highlight and compare regime-specific trade-offs.","PeriodicalId":13343,"journal":{"name":"IEEE Wireless Communications Letters","volume":"15 ","pages":"1050-1054"},"PeriodicalIF":5.5,"publicationDate":"2025-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145777904","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-18DOI: 10.1109/LWC.2025.3645925
Zhiqiang Dan;Qi Li;Yuxin Fang;Wenjun Wu;Zhipeng Wang;Jingjing Wang
This letter proposes an intelligent cross-layer handoff management framework for hybrid low Earth orbit (LEO)-terrestrial aeronautical networks. By integrating LEO and ground base stations under software-defined networking control, a unified architecture enables robust and coordinated access for airborne user equipments. The handoff process is formulated as a Markov decision process, and a deep double Q-network (DDQN)-based method is developed to jointly optimize base station selection and subchannel allocation while meeting heterogeneous quality-of-service demands. Simulation results verify that the proposed method significantly increases service rate and lowers interruption probability compared with baselines, demonstrating its effectiveness for reliable in-flight connectivity.
{"title":"Intelligent Cross-Layer Handoff for Hybrid LEO-Terrestrial Aeronautical Networks","authors":"Zhiqiang Dan;Qi Li;Yuxin Fang;Wenjun Wu;Zhipeng Wang;Jingjing Wang","doi":"10.1109/LWC.2025.3645925","DOIUrl":"10.1109/LWC.2025.3645925","url":null,"abstract":"This letter proposes an intelligent cross-layer handoff management framework for hybrid low Earth orbit (LEO)-terrestrial aeronautical networks. By integrating LEO and ground base stations under software-defined networking control, a unified architecture enables robust and coordinated access for airborne user equipments. The handoff process is formulated as a Markov decision process, and a deep double Q-network (DDQN)-based method is developed to jointly optimize base station selection and subchannel allocation while meeting heterogeneous quality-of-service demands. Simulation results verify that the proposed method significantly increases service rate and lowers interruption probability compared with baselines, demonstrating its effectiveness for reliable in-flight connectivity.","PeriodicalId":13343,"journal":{"name":"IEEE Wireless Communications Letters","volume":"15 ","pages":"1030-1034"},"PeriodicalIF":5.5,"publicationDate":"2025-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145778021","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-18DOI: 10.1109/LWC.2025.3645940
Yuxian Hua;Lv Ye;Mujun Qian;Yunchao Song;Chen Liu
Driven by the low-power and low-cost requirements of 6G communications, dynamic scattering array (DSA), which leverages the strong near-field mutual coupling effects between the active antenna and passive scatterers, offers a novel approach for flexible beam control. Existing studies have not yet established a complete physically consistent model that incorporates the circuit parameters of both the DSA and the receiving antenna, along with the wireless channel. Furthermore, corresponding optimization algorithms are also lacking. To address these issues, this letter proposes an end-to-end physically consistent model and an optimization method for DSA-based systems. Specifically, a more comprehensive end-to-end channel model is constructed by jointly considering the mutual coupling among the active antenna, passive scatterers, and the receiving antenna. Based on this model, the performance of the DSA-based system is formulated as an achievable rate maximization problem, which is solved using a tailored gradient ascent (GA) algorithm. Numerical results demonstrate that the achievable rate of the system is significantly improved by effectively leveraging the mutual coupling effect.
{"title":"Physically Consistent Modeling and Achievable Rate Optimization of Wireless Systems Using Dynamic Scattering Array","authors":"Yuxian Hua;Lv Ye;Mujun Qian;Yunchao Song;Chen Liu","doi":"10.1109/LWC.2025.3645940","DOIUrl":"10.1109/LWC.2025.3645940","url":null,"abstract":"Driven by the low-power and low-cost requirements of 6G communications, dynamic scattering array (DSA), which leverages the strong near-field mutual coupling effects between the active antenna and passive scatterers, offers a novel approach for flexible beam control. Existing studies have not yet established a complete physically consistent model that incorporates the circuit parameters of both the DSA and the receiving antenna, along with the wireless channel. Furthermore, corresponding optimization algorithms are also lacking. To address these issues, this letter proposes an end-to-end physically consistent model and an optimization method for DSA-based systems. Specifically, a more comprehensive end-to-end channel model is constructed by jointly considering the mutual coupling among the active antenna, passive scatterers, and the receiving antenna. Based on this model, the performance of the DSA-based system is formulated as an achievable rate maximization problem, which is solved using a tailored gradient ascent (GA) algorithm. Numerical results demonstrate that the achievable rate of the system is significantly improved by effectively leveraging the mutual coupling effect.","PeriodicalId":13343,"journal":{"name":"IEEE Wireless Communications Letters","volume":"15 ","pages":"950-954"},"PeriodicalIF":5.5,"publicationDate":"2025-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145777903","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-18DOI: 10.1109/LWC.2025.3645939
Yeqing Zheng;Liang Lv;Yi Fang;Pingping Chen;Guojun Han
This letter proposes a novel multilevel polar-coded differential spatial modulation (MLP-DSM) scheme. Specifically, the proposed structure intelligently integrates the polar coding and DSM by cascading signal polarization and channel polarization to establish the MLP-DSM system with a more significant overall polarization effect. Furthermore, we put forward the concept of matrix Hamming distance (MHD) to quantify the intrinsic difference between antenna activation order matrices (AAOMs). Based on the MHD metric, we design a novel set partitioning order (SPO) constellation tailored for MLP-DSM systems. The designed SPO constellation exploits the reduced Latin rectangles (RLRs) to increase the structural difference among AAOMs, thereby improving the constellation-constrained capacity. Moreover, the set partitioning (SP) mapping criterion is adopted to further strengthen the system polarization effect. Simulation results demonstrate that the proposed MLP-DSM schemes obtain excellent error performance gains over the conventional DSM system and other counterparts.
{"title":"Set Partitioning Order Constellation Design for Multilevel Polar-Coded Differential SM Systems","authors":"Yeqing Zheng;Liang Lv;Yi Fang;Pingping Chen;Guojun Han","doi":"10.1109/LWC.2025.3645939","DOIUrl":"10.1109/LWC.2025.3645939","url":null,"abstract":"This letter proposes a novel multilevel polar-coded differential spatial modulation (MLP-DSM) scheme. Specifically, the proposed structure intelligently integrates the polar coding and DSM by cascading signal polarization and channel polarization to establish the MLP-DSM system with a more significant overall polarization effect. Furthermore, we put forward the concept of matrix Hamming distance (MHD) to quantify the intrinsic difference between antenna activation order matrices (AAOMs). Based on the MHD metric, we design a novel set partitioning order (SPO) constellation tailored for MLP-DSM systems. The designed SPO constellation exploits the reduced Latin rectangles (RLRs) to increase the structural difference among AAOMs, thereby improving the constellation-constrained capacity. Moreover, the set partitioning (SP) mapping criterion is adopted to further strengthen the system polarization effect. Simulation results demonstrate that the proposed MLP-DSM schemes obtain excellent error performance gains over the conventional DSM system and other counterparts.","PeriodicalId":13343,"journal":{"name":"IEEE Wireless Communications Letters","volume":"15 ","pages":"875-879"},"PeriodicalIF":5.5,"publicationDate":"2025-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145777902","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-18DOI: 10.1109/LWC.2025.3646113
Nils Pachler;Bruce G. Cameron
The proliferation of cost-effective, highly capable satellites opens opportunities and poses challenges in the quest for efficient constellation designs. While existing literature explores the design of Low and Medium Earth Orbit constellations, hybrid systems combining satellites at different altitudes hold promise in exploiting the advantages of both. To find efficient hybrid designs, we propose a two-phased strategy: a surrogate model to filter the design space, and a detailed model to provide insight into system performance. Results show that while hybrid systems are appealing in theory, operational considerations such as inter-satellite interference make them undesirable for practical implementation.
{"title":"The Best of Both Worlds? Why Satellite Constellations Are Unlikely to Span Both LEO and MEO","authors":"Nils Pachler;Bruce G. Cameron","doi":"10.1109/LWC.2025.3646113","DOIUrl":"10.1109/LWC.2025.3646113","url":null,"abstract":"The proliferation of cost-effective, highly capable satellites opens opportunities and poses challenges in the quest for efficient constellation designs. While existing literature explores the design of Low and Medium Earth Orbit constellations, hybrid systems combining satellites at different altitudes hold promise in exploiting the advantages of both. To find efficient hybrid designs, we propose a two-phased strategy: a surrogate model to filter the design space, and a detailed model to provide insight into system performance. Results show that while hybrid systems are appealing in theory, operational considerations such as inter-satellite interference make them undesirable for practical implementation.","PeriodicalId":13343,"journal":{"name":"IEEE Wireless Communications Letters","volume":"15 ","pages":"900-904"},"PeriodicalIF":5.5,"publicationDate":"2025-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145778022","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Device-to-device (D2D) communication, when combined with non-orthogonal multiple access (NOMA), holds promise for enhanced spectral efficiency. However, it demands careful radio resource allocation, particularly under topology changes. In this letter, we propose a fast one-shot beamforming adaptation scheme based on a graph neural network (GNN) integrated with meta-learning. The approach computes meta-gradients to derive general meta-parameters optimized for rapid adaptation, rather than direct deployment, thereby enabling effective adaptation to target network conditions. Evaluation results show that the proposed solution achieves sum-rate gains of up to 27% over GNN-based schemes and up to 86% over the multi-agent reinforcement learning (MARL) baseline.
{"title":"Fast Beamforming Adaptation for Distributed NOMA in D2D Communication Using MetaGNN","authors":"Giang Minh Nguyen;Derek Kwaku Pobi Asiedu;Ji-Hoon Yun","doi":"10.1109/LWC.2025.3645242","DOIUrl":"10.1109/LWC.2025.3645242","url":null,"abstract":"Device-to-device (D2D) communication, when combined with non-orthogonal multiple access (NOMA), holds promise for enhanced spectral efficiency. However, it demands careful radio resource allocation, particularly under topology changes. In this letter, we propose a fast one-shot beamforming adaptation scheme based on a graph neural network (GNN) integrated with meta-learning. The approach computes meta-gradients to derive general meta-parameters optimized for rapid adaptation, rather than direct deployment, thereby enabling effective adaptation to target network conditions. Evaluation results show that the proposed solution achieves sum-rate gains of up to 27% over GNN-based schemes and up to 86% over the multi-agent reinforcement learning (MARL) baseline.","PeriodicalId":13343,"journal":{"name":"IEEE Wireless Communications Letters","volume":"15 ","pages":"945-949"},"PeriodicalIF":5.5,"publicationDate":"2025-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145770908","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-17DOI: 10.1109/LWC.2025.3645637
Yushi Lei;Shuyuan Hu;Yusha Liu;Kun Yang
Low Earth orbit (LEO) satellite communication enhances global network coverage and has gained significant attention. However, accurate downlink channel state information (CSI) acquisition under severe Doppler shifts and fast fading remains challenging. This letter proposes HyperTransformer, an end-to-end channel estimation (CE) framework based on the transformer and hypernetwork architecture. By first designing the attention mechanism, we extract channel features over time and utilize fading correlations for improved tracking in dynamic environments. Additionally, a hypernetwork is introduced to exploit partial uplink reciprocity to refine downlink CE network, reducing pilot overhead. Simulations demonstrate that the proposed HyperTransformer achieves a lower normalized mean square error (NMSE) than state-of-the-art deep learning (DL)-based methods.
{"title":"Transformer-Aided Channel Estimation for LEO Satellite Communications","authors":"Yushi Lei;Shuyuan Hu;Yusha Liu;Kun Yang","doi":"10.1109/LWC.2025.3645637","DOIUrl":"10.1109/LWC.2025.3645637","url":null,"abstract":"Low Earth orbit (LEO) satellite communication enhances global network coverage and has gained significant attention. However, accurate downlink channel state information (CSI) acquisition under severe Doppler shifts and fast fading remains challenging. This letter proposes HyperTransformer, an end-to-end channel estimation (CE) framework based on the transformer and hypernetwork architecture. By first designing the attention mechanism, we extract channel features over time and utilize fading correlations for improved tracking in dynamic environments. Additionally, a hypernetwork is introduced to exploit partial uplink reciprocity to refine downlink CE network, reducing pilot overhead. Simulations demonstrate that the proposed HyperTransformer achieves a lower normalized mean square error (NMSE) than state-of-the-art deep learning (DL)-based methods.","PeriodicalId":13343,"journal":{"name":"IEEE Wireless Communications Letters","volume":"15 ","pages":"1155-1159"},"PeriodicalIF":5.5,"publicationDate":"2025-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145770910","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：