An Efficient Network with Novel Quantization Designed for Massive MIMO CSI Feedback

TL;DR

This paper introduces CsiConformer, a novel neural network combining convolutional and self-attention mechanisms with a new quantization module, significantly improving CSI feedback accuracy and efficiency for massive MIMO systems.

Contribution

The paper presents a new network architecture and quantization method that enhance CSI feedback accuracy and reduce computational overhead in massive MIMO systems.

Findings

CsiConformer achieves 17.67% higher accuracy than previous methods.

The proposed quantization module improves encoding efficiency.

CsiConformer reduces computational overhead compared to state-of-the-art networks.

Abstract

The efficacy of massive multiple-input multiple-output (MIMO) techniques heavily relies on the accuracy of channel state information (CSI) in frequency division duplexing (FDD) systems. Many works focus on CSI compression and quantization methods to enhance CSI reconstruction accuracy with lower feedback overhead. In this letter, we propose CsiConformer, a novel CSI feedback network that combines convolutional operations and self-attention mechanisms to improve CSI feedback accuracy. Additionally, a new quantization module is developed to improve encoding efficiency. Experiment results show that CsiConformer outperforms previous state-of-the-art networks, achieving an average accuracy improvement of 17.67\% with lower computational overhead.