Spatio-Temporal Representation with Deep Neural Recurrent Network in MIMO CSI Feedback

TL;DR

This paper introduces a deep recurrent neural network approach for compressing and reconstructing MIMO channel state information, leveraging spatio-temporal features to improve accuracy and robustness in FDD systems.

Contribution

It proposes a novel deep RNN model with depthwise separable convolution for efficient CSI feedback in massive MIMO systems, emphasizing decoupled spatio-temporal feature learning.

Findings

Outperforms existing DL-based methods in recovery quality

Achieves high accuracy at low compression ratios

Demonstrates robustness in practical scenarios

Abstract

In multiple-input multiple-output (MIMO) systems, it is crucial of utilizing the available channel state information (CSI) at the transmitter for precoding to improve the performance of frequency division duplex (FDD) networks. One of the mainchallenges is to compress a large amount of CSI in CSI feedback transmission in massive MIMO systems. In this paper, we propose a deep learning (DL)-based approach that uses a deep recurrent neural network (RNN) to learn temporal correlation and adopts depthwise separable convolution to shrink the model. The feature extraction module is also elaborately devised by studyingdecoupled spatio-temporal feature representations in different structures. Experimental results demonstrate that the proposed approach outperforms existing DL-based methods in terms of recovery quality and accuracy, which can also achieve remarkable robustness at low compression ratio (CR).