Deep Learning-Based Radio Map for MIMO-OFDM Downlink Precoding  

作　　者：Wei Wang Bin Yang Wei Zhang 

机构地区：[1]Peng Cheng Laboratory,Shenzhen 518055,China [2]The School of Electrical Engineering and Telecommunications,the University of New South Wales,Sydney,NSW 2052,Australia

出　　处：《Journal of Communications and Information Networks》2023年第3期203-211,共9页通信与信息网络学报（英文）

基　　金：This work was supported in part by the Key Area Research and Development Program of Guangdong Province under Grant 2020B0101110003;in part by the National Natural Science Foundation of China under Grant 62201309.The associate editor coordinating the review of this paper and approving it for publication was L.Bai。

摘　　要：Radio map is an advanced technology that mitigates the reliance of multiple-input multiple-output(MIMO)beamforming on channel state information(CSI).In this paper,we introduce the concept of deep learning-based radio map,which is designed to be generated directly from the raw CSI data.In accordance with the conventional CSI acquisition mechanism of MIMO,we first introduce two baseline schemes of radio map,i.e.,CSI prediction-based radio map and throughput predictionbased radio map.To fully leverage the powerful inference capability of deep neural networks,we further propose the end-to-end structure that outputs the beamforming vector directly from the location information.The rationale behind the proposed end-to-end structure is to design the neural network using a task-oriented approach,which is achieved by customizing the loss function that quantifies the communication quality.Numerical results show the superiority of the task-oriented design and confirm the potential of deep learning-based radio map in replacing CSI with location information.

关 键 词：radio map deep learning MIMO taskoriented approach 

分 类 号：TN9[电子电信—信息与通信工程]