基于分布式联邦学习的毫米波通信系统波束配置方法  

Beam Configuration for Millimeter Wave Communication Systems Based on Distributed Federated Learning

作　　者：薛青 来东 徐勇军[1] 闫莉[3] XUE Qing;LAI Dong;XU Yongjun;YAN Li(School of Communication and Information Engineering,Chongqing University of Posts and Telecommunications,Chongqing 400065,China;State Key Laboratory of Internet of Things for Smart City,University of Macao,Macao 999078,China;School of Information Science and Technology,Southwest Jiaotong University,Chengdu 610031,China)

机构地区：[1]重庆邮电大学通信与信息工程学院,重庆400065 [2]澳门大学智慧城市物联网国家重点实验室,中国澳门999078 [3]西南交通大学信息科学与技术学院,成都610031

出　　处：《电子与信息学报》2024年第1期138-145,共8页Journal of Electronics & Information Technology

基　　金：国家自然科学基金(62001071,62101460,62271094);澳门青年学者计划(AM2021018);重庆市教委科学技术研究项目(KJZDK202200601);中国博士后科学基金(2022MD723725)。

摘　　要：针对超密集组网中毫米波通信系统复杂的波束配置问题,该文提出一种基于分布式联邦学习(DFL)的波束配置算法(BMDFL),旨在利用有限的波束资源实现用户覆盖率最大化。考虑到传统集中式学习存在用户数据安全问题,基于分布式联邦学习框架构建系统模型,从而减少用户隐私信息的泄露。为了实现波束的智能化配置,引入双深度Q学习算法(DDQN)训练系统模型,并通过马尔可夫决策过程将长期的动态优化问题转化为相应的数学模型进行求解。仿真结果从系统的网络吞吐量和用户覆盖率方面验证了该方法的有效性和鲁棒性。Considering the complex beam configuration problem of ultra-dense millimeter wave communication systems,a Beam management Method based on Distributed Federation Learning(BMDFL)is proposed to maximize the beam coverage by using the limited beam resources.To solve the problem of user data security in traditional centralized learning,the system model is constructed based on DFL,which can reduce the leakage of user privacy information.In order to realize intelligent configuration of beams,Double Deep Q-Network(DDQN)is introduced to train the system model,and the long-term dynamic optimization problem is transformed into the corresponding mathematical model through the Markov decision process.Simulation results demonstrate the effectiveness and robustness of the proposed method in terms of network throughput and user coverage.

关 键 词：毫米波通信 波束配置 超密集组网 分布式联邦学习 强化学习 

分 类 号：TN92[电子电信—通信与信息系统]