Deep Learning-based Channel Estimation for Beamspace mmWave Massive MIMO Systems

TL;DR

This paper introduces a deep learning approach using LDAMP neural networks for effective channel estimation in beamspace mmWave massive MIMO systems with limited RF chains, outperforming traditional methods.

Contribution

It proposes a learned denoising-based approximate message passing network tailored for channel estimation, with an analytical performance framework and superior results over existing algorithms.

Findings

LDAMP outperforms compressed sensing algorithms in simulations.

Deep learning effectively captures channel structure in mmWave MIMO.

The approach works well with few RF chains.

Abstract

Channel estimation is very challenging when the receiver is equipped with a limited number of radio-frequency (RF) chains in beamspace millimeter-wave (mmWave) massive multiple-input and multiple-output systems. To solve this problem, we exploit a learned denoising-based approximate message passing (LDAMP) network. This neural network can learn channel structure and estimate channel from a large number of training data. Furthermore, we provide an analytical framework on the asymptotic performance of the channel estimator. Based on our analysis and simulation results, the LDAMP neural network significantly outperforms state-of-the-art compressed sensingbased algorithms even when the receiver is equipped with a small number of RF chains. Therefore, deep learning is a powerful tool for channel estimation in mmWave communications.