Deep Learning-based Implicit CSI Feedback in Massive MIMO

TL;DR

This paper introduces a deep learning-based implicit CSI feedback method for massive MIMO systems that reduces overhead by replacing traditional encoding with neural networks, leveraging environment info and subband correlation.

Contribution

It proposes a novel DL-based implicit feedback architecture compatible with existing systems, improving feedback efficiency over traditional codebook methods.

Findings

Reduces feedback overhead by up to 48% compared to Type II codebook.

Uses environment information for more accurate PMI mapping.

Exploits subband correlation to further enhance feedback performance.

Abstract

Massive multiple-input multiple-output can obtain more performance gain by exploiting the downlink channel state information (CSI) at the base station (BS). Therefore, studying CSI feedback with limited communication resources in frequency-division duplexing systems is of great importance. Recently, deep learning (DL)-based CSI feedback has shown considerable potential. However, the existing DL-based explicit feedback schemes are difficult to deploy because current fifth-generation mobile communication protocols and systems are designed based on an implicit feedback mechanism. In this paper, we propose a DL-based implicit feedback architecture to inherit the low-overhead characteristic, which uses neural networks (NNs) to replace the precoding matrix indicator (PMI) encoding and decoding modules. By using environment information, the NNs can achieve a more refined mapping between the precoding matrix and the PMI compared with codebooks. The correlation between subbands is also used to further improve the feedback performance. Simulation results show that, for a single resource block (RB), the proposed architecture can save 25.0% and 40.0% of overhead compared with Type I codebook under two antenna configurations, respectively. For a wideband system with 52 RBs, overhead can be saved by 30.7% and 48.0% compared with Type II codebook when ignoring and considering extracting subband correlation, respectively.