Distributed Neural Precoding for Hybrid mmWave MIMO Communications with Limited Feedback

TL;DR

This paper introduces a distributed neural network approach for hybrid precoding in mmWave MIMO systems, effectively compressing CSI and enhancing precoding performance with limited feedback.

Contribution

It proposes a novel distributed neural network architecture, DNet, for efficient CSI compression and hybrid precoding design tailored to matrix data structures.

Findings

DNet achieves nearly 50% performance improvement over traditional methods.

The distributed architecture reduces training parameters and network complexity.

DNet effectively handles various CSI compression ratios.

Abstract

Hybrid precoding is a cost-efficient technique for millimeter wave (mmWave) massive multiple-input multiple-output (MIMO) communications. This paper proposes a deep learning approach by using a distributed neural network for hybrid analog-and-digital precoding design with limited feedback. The proposed distributed neural precoding network, called DNet, is committed to achieving two objectives. First, the DNet realizes channel state information (CSI) compression with a distributed architecture of neural networks, which enables practical deployment on multiple users. Specifically, this neural network is composed of multiple independent sub-networks with the same structure and parameters, which reduces both the number of training parameters and network complexity. Secondly, DNet learns the calculation of hybrid precoding from reconstructed CSI from limited feedback. Different from existing black-box neural network design, the DNet is specifically designed according to the data form of the matrix calculation of hybrid precoding. Simulation results show that the proposed DNet significantly improves the performance up to nearly 50% compared to traditional limited feedback precoding methods under the tests with various CSI compression ratios.