基于联邦学习的毫米波大规模MIMO的混合波束赋形和资源分配  

Hybrid Beamforming and Resource Allocation for mm-Wave Massive MIMO Based on Federated Learning

作　　者：孙艳华 乔兰[1,2] 杨睿哲 司鹏搏 张延华[1,2] SUN Yanhua;QIAO Lan;YANG Ruizhe;SI Pengbo;ZHANG Yanhua(Faculty of Information Technology,Beijing University of Technology,Beijing 100124,China;Beijing Laboratory of Advanced Information Networks,Beijing University of Technology,Beijing 100124,China)

机构地区：[1]北京工业大学信息学部,北京100124 [2]北京工业大学先进信息网络北京实验室,北京100124

出　　处：《北京工业大学学报》2023年第8期851-861,共11页Journal of Beijing University of Technology

基　　金：北京市自然科学基金资助项目(L202016)。

摘　　要：针对大规模毫米波(millimeter wave,mm-Wave)多输入多输出(multiple input multiple output,MIMO)系统中的混合波束赋形在中心式机器学习(centralized machine learning,CML)中导致的通信开销过大问题,提出了分层联邦学习(federated learning,FL)框架下的混合波束赋形与基于合同理论的资源分配优化方法。首先,在分层系统中对多用户计算系统开销,并通过优化分配资源实现系统的效益最大化;然后,用户利用分配的资源对信道数据和相应的预编码数据进行反向传播神经网络(back propagation neural network,BPNN)模型训练,利用边缘服务器(edge server,ES)收集用户训练的权值和参数进行边缘聚合,达到一定精度后上传到云服务器(cloud server,CS)进行云聚合,直到取得最优的模型。实验结果表明,资源优化极大地降低了通信开销,并且基于FL的混合波束赋形不仅取得了和CML类似的和速率,而且其和速率要优于基于正交匹配追踪(orthogonal matching pursuit,OMP)的混合波束赋形以及全数字波束赋形方案。Aiming at the problem that the hybrid beamforming in millimeter wave(mm-Wave) massive multiple input multiple output(MIMO) system leads to excessive communication overhead in centralized machine learning(CML),a hybrid beamforming and resource allocation optimization method based on contract theory under hierarchical federated learning(FL) was proposed.First,the system overhead was calculated for multiple users in a hierarchical system,and the maximum benefit of the system was realized by optimizing the allocation of resources.Then,the allocated resources were used to train the channel data and corresponding precoder data in the back propagation neural network(BPNN).The model was aggregated at the edge server(ES) by collecting weights and parameters from users and uploaded to the cloud server(CS) to aggregate after reaching a certain accuracy until obtaining an optimal model.The simulation results show that the resource optimization greatly reduces the communication overhead,and hybrid beamforming based on FL not only achieves almost the same sum rate as to CML,but also outperforms orthogonal matching pursuit(OMP) hybrid beamforming and fully digital beamforming.

关 键 词：联邦学习(federated learning FL) 毫米波(millimeter wave mm-Wave) 多输入多输出(multiple input multiple output MIMO) 资源分配 混合波束赋形 合同理论 

分 类 号：TN929[电子电信—通信与信息系统]