Pub Date : 2025-12-17DOI: 10.1109/TCCN.2025.3645402
Shuang Li;Huimin Hu;Hong-Chuan Yang;Ke Xiong;Pingyi Fan;Khaled Ben Letaief
Age of information (AoI), quantifying the freshness of status information, is a vital performance metric for monitoring Internet of Things (IoT) applications. Transmission scheduling serves as a key technique for improving AoI performance. Meanwhile, the transmission parameter, e.g. data rate, will also influence the AoI performance. In this work, we propose a novel joint scheduling and transmission rate design approach to improve the AoI performance of wireless-powered IoT (WP-IoT) networks. Specifically, our design jointly optimizes sensor scheduling and blocklength selection decisions to minimize the expected sum AoI (ES-AoI). We formulate the joint design problem into a parameterized action Markov decision process (PAMDP). Considering the hybrid discrete-continuous action space of the resulting PAMDP, we employ parameterized deep $Q$ -network (PDQN) and double PDQN (DPDQN) algorithms to learn the optimal joint scheduling and blocklength selection (JSBS) policy during offline training. To mitigate model inaccuracies and environmental variations, we further develop a computationally efficient PDQN-based online tuning algorithm that fine-tunes the offline-trained JSBS policy during online operation. Simulation results demonstrate that the proposed JSBS policy significantly enhances ES-AoI performance compared to fixed-blocklength scheduling and benchmark blocklength selection policies. Furthermore, the JSBS policy trained with PDQN achieves performance close to that of DPDQN while surpassing standard deep reinforcement learning (DRL) training algorithms. Notably, the PDQN-based online tuning algorithm effectively reduces the ES-AoI by up to 30% compared to the untuned policy.
{"title":"AoI Minimization for WP-IoT With PDQN-Based Hybrid Offline/Online Learning: A Joint Scheduling and Transmission Design Approach","authors":"Shuang Li;Huimin Hu;Hong-Chuan Yang;Ke Xiong;Pingyi Fan;Khaled Ben Letaief","doi":"10.1109/TCCN.2025.3645402","DOIUrl":"https://doi.org/10.1109/TCCN.2025.3645402","url":null,"abstract":"Age of information (AoI), quantifying the freshness of status information, is a vital performance metric for monitoring Internet of Things (IoT) applications. Transmission scheduling serves as a key technique for improving AoI performance. Meanwhile, the transmission parameter, e.g. data rate, will also influence the AoI performance. In this work, we propose a novel joint scheduling and transmission rate design approach to improve the AoI performance of wireless-powered IoT (WP-IoT) networks. Specifically, our design jointly optimizes sensor scheduling and blocklength selection decisions to minimize the expected sum AoI (ES-AoI). We formulate the joint design problem into a parameterized action Markov decision process (PAMDP). Considering the hybrid discrete-continuous action space of the resulting PAMDP, we employ parameterized deep <inline-formula> <tex-math>$Q$ </tex-math></inline-formula>-network (PDQN) and double PDQN (DPDQN) algorithms to learn the optimal joint scheduling and blocklength selection (JSBS) policy during offline training. To mitigate model inaccuracies and environmental variations, we further develop a computationally efficient PDQN-based online tuning algorithm that fine-tunes the offline-trained JSBS policy during online operation. Simulation results demonstrate that the proposed JSBS policy significantly enhances ES-AoI performance compared to fixed-blocklength scheduling and benchmark blocklength selection policies. Furthermore, the JSBS policy trained with PDQN achieves performance close to that of DPDQN while surpassing standard deep reinforcement learning (DRL) training algorithms. Notably, the PDQN-based online tuning algorithm effectively reduces the ES-AoI by up to 30% compared to the untuned policy.","PeriodicalId":13069,"journal":{"name":"IEEE Transactions on Cognitive Communications and Networking","volume":"12 ","pages":"4547-4560"},"PeriodicalIF":7.0,"publicationDate":"2025-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145929370","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}
This paper investigates a cell-free massive multiple-input multiple-output enabled multi-access edge computing (termed CF-MEC) system, where multiple users are served by multiple central processing units (CPUs) and their connected access points (APs), both of which are equipped with computation resources. For this system, a dynamic user-centric task offloading scheme is designed to provide seamless and efficient computation services for users. Based on this scheme, the joint optimization of user-centric AP clustering, edge server selection, communication and computation resources is formulated as a long-term problem to minimize the average energy consumption. The formulated problem is complicated non-convex due to the highly coupled time-varying discrete and continuous variables, resulting in high complexity and non-real-time to obtain the optimal solution. To tackle this challenging problem, we propose a multi-layer hierarchical multi-agent deep reinforcement learning (ML-HMADRL) based resource allocation algorithm. Specifically, the proposed algorithm incorporates a hierarchical structure with high, middle, and low-level agents that iteratively train the actor-critic networks to obtain discrete and continuous variables of the formulated problem. To further enhance the training effectiveness by leveraging the CF-MEC system, we design distinct actor-critic networks for the agents at different levels to facilitate centralized training and distributed execution. Simulation results validate the training stability of the proposed algorithm at each level, and demonstrate the superiority of the proposed algorithm over benchmark schemes in terms of the average energy consumption, providing a stable distributed framework for practical implementation in dynamic environments.
{"title":"Resource Allocation in Cell-Free MEC Networks: A Hierarchical MADRL-Based Algorithm","authors":"Mengmeng Ren;Long Yang;Yuchen Zhou;Lu Lv;Jian Chen;Pei Xiao;Cicek Cavdar;Rahim Tafazolli","doi":"10.1109/TCCN.2025.3645433","DOIUrl":"https://doi.org/10.1109/TCCN.2025.3645433","url":null,"abstract":"This paper investigates a cell-free massive multiple-input multiple-output enabled multi-access edge computing (termed CF-MEC) system, where multiple users are served by multiple central processing units (CPUs) and their connected access points (APs), both of which are equipped with computation resources. For this system, a dynamic user-centric task offloading scheme is designed to provide seamless and efficient computation services for users. Based on this scheme, the joint optimization of user-centric AP clustering, edge server selection, communication and computation resources is formulated as a long-term problem to minimize the average energy consumption. The formulated problem is complicated non-convex due to the highly coupled time-varying discrete and continuous variables, resulting in high complexity and non-real-time to obtain the optimal solution. To tackle this challenging problem, we propose a multi-layer hierarchical multi-agent deep reinforcement learning (ML-HMADRL) based resource allocation algorithm. Specifically, the proposed algorithm incorporates a hierarchical structure with high, middle, and low-level agents that iteratively train the actor-critic networks to obtain discrete and continuous variables of the formulated problem. To further enhance the training effectiveness by leveraging the CF-MEC system, we design distinct actor-critic networks for the agents at different levels to facilitate centralized training and distributed execution. Simulation results validate the training stability of the proposed algorithm at each level, and demonstrate the superiority of the proposed algorithm over benchmark schemes in terms of the average energy consumption, providing a stable distributed framework for practical implementation in dynamic environments.","PeriodicalId":13069,"journal":{"name":"IEEE Transactions on Cognitive Communications and Networking","volume":"12 ","pages":"4593-4609"},"PeriodicalIF":7.0,"publicationDate":"2025-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145929377","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}
In the context of high-dynamic satellite scenarios, the orthogonal time frequency space (OTFS) modulation demonstrates superior performance compared to conventional waveforms. Furthermore, the channel estimation results of OTFS can be directly utilized for navigation. Therefore, OTFS is considered as a promising waveform for blue the 6G satellite integrated communication and navigation (ICAN) internet. Traditional OTFS is limited to integer channel estimation, and conventional methods incur computational overhead to improve estimation accuracy. However, the estimation accuracy is gradually approaching its theoretical limits, making further breakthroughs difficult. To address these challenges, a high-resolution channel estimation method based on Artificial Perturbation (AP)-OTFS is proposed, which treats the receiver DD-grid detector as a rounding quantiser whose resolution is enhanced by zero-mean dithering and achieves estimation performance close to Cramér-Rao lower bound. Based on this, we derive the analytical solution for the constraints of unbiased estimation and the blue minimum number of accumulation pilots, providing guidance for ICAN system. In addition, we conduct detailed analysis and experiments of various AP distributions. Results indicate that uniform AP-OTFS achieves the highest accumulation efficiency, which enhances delay resolution by 2–3 orders and improves pilot efficiency by approximately 5–10 dB compared to the no-perturbation case.
{"title":"A High-Resolution Channel Estimation Method for ICAN Systems Based on Artificial Perturbation-OTFS","authors":"Jiyang Liu;Xiaomei Tang;Feixue Wang;Xin Chen;Wenbo Xu","doi":"10.1109/TCCN.2025.3644028","DOIUrl":"10.1109/TCCN.2025.3644028","url":null,"abstract":"In the context of high-dynamic satellite scenarios, the orthogonal time frequency space (OTFS) modulation demonstrates superior performance compared to conventional waveforms. Furthermore, the channel estimation results of OTFS can be directly utilized for navigation. Therefore, OTFS is considered as a promising waveform for blue the 6G satellite integrated communication and navigation (ICAN) internet. Traditional OTFS is limited to integer channel estimation, and conventional methods incur computational overhead to improve estimation accuracy. However, the estimation accuracy is gradually approaching its theoretical limits, making further breakthroughs difficult. To address these challenges, a high-resolution channel estimation method based on Artificial Perturbation (AP)-OTFS is proposed, which treats the receiver DD-grid detector as a rounding quantiser whose resolution is enhanced by zero-mean dithering and achieves estimation performance close to Cramér-Rao lower bound. Based on this, we derive the analytical solution for the constraints of unbiased estimation and the blue minimum number of accumulation pilots, providing guidance for ICAN system. In addition, we conduct detailed analysis and experiments of various AP distributions. Results indicate that uniform AP-OTFS achieves the highest accumulation efficiency, which enhances delay resolution by 2–3 orders and improves pilot efficiency by approximately 5–10 dB compared to the no-perturbation case.","PeriodicalId":13069,"journal":{"name":"IEEE Transactions on Cognitive Communications and Networking","volume":"12 ","pages":"4561-4576"},"PeriodicalIF":7.0,"publicationDate":"2025-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145759626","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}
Ultra-reliable low-latency communication (URLLC) supports services that require stringent low latency and high reliability, as well as finite block transmission. The goal of the future sixth-generation (6G) networks is to implement the internet-of-everything, where the number of URLLC users is expected to reach the order of millions. Intelligent reflective surfaces (IRS) and non-orthogonal multiple access (NOMA) technologies can enhance the performance of URLLC communications by adjusting wireless channels and allowing multiple users in the same resource block, respectively. In this paper, to manage massive users in IRS-aided NOMA URLLC networks, the resource assignment strategy (including sub-channel allocation, transmitting power selection, and the phases of IRS units) is optimized using a proposed multi-agent reinforcement learning (MARL)-based algorithm, while meeting the reliability and latency demands of URLLC services. In addition, transfer learning is introduced to reduce learning overheads and enhance the probability of successful access. Our simulation results indicate that the proposed MARL-based approach significantly outperforms baseline methods in terms of the successful access probability for scenarios with massive users.
{"title":"A MARL-Based Approach for Massive Access in IRS-Aided NOMA-URLLC Networks","authors":"Huimei Han;Hongyang Wang;Weidang Lu;Wenchao Zhai;Ying Li;Celimuge Wu;Mohsen Guizani","doi":"10.1109/TCCN.2025.3643938","DOIUrl":"10.1109/TCCN.2025.3643938","url":null,"abstract":"Ultra-reliable low-latency communication (URLLC) supports services that require stringent low latency and high reliability, as well as finite block transmission. The goal of the future sixth-generation (6G) networks is to implement the internet-of-everything, where the number of URLLC users is expected to reach the order of millions. Intelligent reflective surfaces (IRS) and non-orthogonal multiple access (NOMA) technologies can enhance the performance of URLLC communications by adjusting wireless channels and allowing multiple users in the same resource block, respectively. In this paper, to manage massive users in IRS-aided NOMA URLLC networks, the resource assignment strategy (including sub-channel allocation, transmitting power selection, and the phases of IRS units) is optimized using a proposed multi-agent reinforcement learning (MARL)-based algorithm, while meeting the reliability and latency demands of URLLC services. In addition, transfer learning is introduced to reduce learning overheads and enhance the probability of successful access. Our simulation results indicate that the proposed MARL-based approach significantly outperforms baseline methods in terms of the successful access probability for scenarios with massive users.","PeriodicalId":13069,"journal":{"name":"IEEE Transactions on Cognitive Communications and Networking","volume":"12 ","pages":"5176-5191"},"PeriodicalIF":7.0,"publicationDate":"2025-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145759620","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}
Pub Date : 2025-12-15DOI: 10.1109/tccn.2025.3644040
Jian Gu, Yin Wang, Wen Ji, Zhongxiang Wei, Jingjing Wang
{"title":"LLM-Based Dynamic Event-Triggered Communication for Multi-UAV Formation Control in Urban Environments","authors":"Jian Gu, Yin Wang, Wen Ji, Zhongxiang Wei, Jingjing Wang","doi":"10.1109/tccn.2025.3644040","DOIUrl":"https://doi.org/10.1109/tccn.2025.3644040","url":null,"abstract":"","PeriodicalId":13069,"journal":{"name":"IEEE Transactions on Cognitive Communications and Networking","volume":"77 1","pages":""},"PeriodicalIF":8.6,"publicationDate":"2025-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145759615","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}
Pub Date : 2025-12-15DOI: 10.1109/TCCN.2025.3644303
Jin Xie;Yunzhe Jiang;Ke Zhang;Fan Wu;Yin Zhang;Xiaoyan Huang;Shujiang Xu;Chau Yuen;Yan Zhang
In the forthcoming 6G paradigm, billions of endpoint devices will benefit from the widespread availability of network services. Given the unique characteristics of spectrum access across numerous and geographically dispersed devices, blockchain-based spectrum sharing (BSS) presents a compelling solution for enabling dynamic and decentralized spectrum allocation. However, the performance of blockchain, specifically the transaction throughput and block interval, directly impacts the efficiency of spectrum sharing. This aspect is often overlooked in current research. Furthermore, the decentralized nature of blockchain presents challenges for interference management due to the absence of centralized transmission power and channel coordination. To address these issues, we propose the Directed Acyclic graph and SHarding-based blockchain (DASH) for spectrum sharing, which improves transaction throughput while accounting for block interval effects in spectrum sharing scenarios. Additionally, we delve into a blockchain-assisted multi-agent deep reinforcement learning (MADRL) approach to tackle interference management in a decentralized manner. Finally, we evaluate our method taking into account the time delay associated with blockchain updates. The numerical results demonstrate the effectiveness of our proposed approach.
{"title":"High-Throughput DAG Blockchain for Efficient Spectrum Sharing in 6G Networks","authors":"Jin Xie;Yunzhe Jiang;Ke Zhang;Fan Wu;Yin Zhang;Xiaoyan Huang;Shujiang Xu;Chau Yuen;Yan Zhang","doi":"10.1109/TCCN.2025.3644303","DOIUrl":"10.1109/TCCN.2025.3644303","url":null,"abstract":"In the forthcoming 6G paradigm, billions of endpoint devices will benefit from the widespread availability of network services. Given the unique characteristics of spectrum access across numerous and geographically dispersed devices, blockchain-based spectrum sharing (BSS) presents a compelling solution for enabling dynamic and decentralized spectrum allocation. However, the performance of blockchain, specifically the transaction throughput and block interval, directly impacts the efficiency of spectrum sharing. This aspect is often overlooked in current research. Furthermore, the decentralized nature of blockchain presents challenges for interference management due to the absence of centralized transmission power and channel coordination. To address these issues, we propose the Directed Acyclic graph and SHarding-based blockchain (DASH) for spectrum sharing, which improves transaction throughput while accounting for block interval effects in spectrum sharing scenarios. Additionally, we delve into a blockchain-assisted multi-agent deep reinforcement learning (MADRL) approach to tackle interference management in a decentralized manner. Finally, we evaluate our method taking into account the time delay associated with blockchain updates. The numerical results demonstrate the effectiveness of our proposed approach.","PeriodicalId":13069,"journal":{"name":"IEEE Transactions on Cognitive Communications and Networking","volume":"12 ","pages":"4865-4881"},"PeriodicalIF":7.0,"publicationDate":"2025-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145759614","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}
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：