Fully connected layer‐shared network architecture for massive MIMO CSI feedback

Abstract

In frequency division duplex (FDD) massive multiple-input multipleoutput (MIMO) system, deep learning-based channel state information (CSI) feedback approach improves CSI reconstruction accuracy. However, different models need to be trained and stored for different scenarios, which causes huge memory cost, especially at the user equipment (UE) side. In this letter, a fully connected layer-shared (FCS) feedback architecture is proposed to simplify the feedback network at the UE. As a case study, the FCS architecture is applied on CsiNet and CRNet in the indoor and outdoor scenarios. Experimental results indicate that the network using the FCS architecture is able to achieve comprehensive performance with impressive storage saving.