Deep Reinforcement Learning Based Joint Cooperation Clustering and Downlink Power Control for Cell-Free Massive MIMO

作     者：Du Mingjun Sun Xinghua Zhang Yue Wang Junyuan Liu Pei Du Mingjun;Sun Xinghua;Zhang Yue;Wang Junyuan;Liu Pei

作者机构：School of Electronics and Communication EngineeringSun Yat-sen UniversityShenzhen 518107China Department of Electronic and Information EngineeringShantou UniversityShantou 515063China College of Electronic and Information EngineeringTongji UniversityShanghai 201804China School of Information EngineeringWuhan University of TechnologyWuhan 430070China Zhongshan Institute of Advanced Engineering Technology of Wuhan University of TechnologyZhongshan 528437China 

出 版 物：《China Communications》 (中国通信（英文版）)

年 卷 期：2024年第21卷第11期

页      面：1-14页

核心收录：

学科分类：080904[工学-电磁场与微波技术] 12[管理学] 0809[工学-电子科学与技术（可授工学、理学学位）] 08[工学] 0810[工学-信息与通信工程] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 080402[工学-测试计量技术及仪器] 0804[工学-仪器科学与技术] 0835[工学-软件工程] 081001[工学-通信与信息系统] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by Guangdong Basic and Applied Basic Research Foundation under Grant 2024A1515012015 supported in part by the National Natural Science Foundation of China under Grant 62201336 in part by Guangdong Basic and Applied Basic Research Foundation under Grant 2024A1515011541 supported in part by the National Natural Science Foundation of China under Grant 62371344 in part by the Fundamental Research Funds for the Central Universities supported in part by Knowledge Innovation Program of Wuhan-Shuguang Project under Grant 2023010201020316 in part by Guangdong Basic and Applied Basic Research Foundation under Grant 2024A1515010247 

主　　题：cell-free massive MIMO clustering deep reinforcement learning power control 

摘      要：In recent times,various power control and clustering approaches have been proposed to enhance overall performance for cell-free massive multipleinput multiple-output(CF-mMIMO)*** the emergence of deep reinforcement learning(DRL),significant progress has been made in the field of network optimization as DRL holds great promise for improving network performance and *** this work,our focus delves into the intricate challenge of joint cooperation clustering and downlink power control within CF-mMIMO *** the potent deep deterministic policy gradient(DDPG)algorithm,our objective is to maximize the proportional fairness(PF)for user rates,thereby aiming to achieve optimal network performance and resource ***,we harness the concept of“divide and conquerstrategy,introducing two innovative methods termed alternating DDPG(A-DDPG)and hierarchical DDPG(H-DDPG).These approaches aim to decompose the intricate joint optimization problem into more manageable sub-problems,thereby facilitating a more efficient resolution *** findings unequivo-cally showcase the superior efficacy of our proposed DDPG approach over the baseline schemes in both clustering and downlink power ***,the A-DDPG and H-DDPG obtain higher performance gain than DDPG with lower computational complexity.