A Lightweight Deep Network for Efficient CSI Feedback in Massive MIMO Systems

TL;DR

This paper introduces ENet, a lightweight neural network architecture designed for efficient CSI compression and feedback in massive MIMO systems, leveraging the correlation in channel responses to reduce feedback overhead.

Contribution

The paper presents a novel neural network architecture, ENet, that significantly reduces network size while maintaining high performance for CSI feedback in massive MIMO systems.

Findings

ENet outperforms existing neural network solutions in CSI feedback accuracy.

ENet reduces network size by nearly an order of magnitude.

Experimental results confirm the effectiveness of ENet in practical scenarios.

Abstract

To fully exploit the advantages of massive multiple-input multiple-output (m-MIMO), accurate channel state information (CSI) is required at the transmitter. However, excessive CSI feedback for large antenna arrays is inefficient and thus undesirable in practical applications. By exploiting the inherent correlation characteristics of complex-valued channel responses in the angular-delay domain, we propose a novel neural network (NN) architecture, namely ENet, for CSI compression and feedback in m-MIMO. Even if the ENet processes the real and imaginary parts of the CSI values separately, its special structure enables the network trained for the real part only to be reused for the imaginary part. The proposed ENet shows enhanced performance with the network size reduced by nearly an order of magnitude compared to the existing NN-based solutions. Experimental results verify the effectiveness of the proposed ENet.