Learning to Estimate RIS-Aided mmWave Channels

TL;DR

This paper introduces a deep unfolding neural network approach for estimating RIS-aided mmWave channels, leveraging channel sparsity to improve accuracy and reduce training overhead in SIMO systems.

Contribution

The paper proposes a novel deep unfolding neural network architecture tailored for RIS-aided mmWave channel estimation, outperforming traditional LS methods with less training.

Findings

Deep unfolding network outperforms LS method in accuracy.

Reduced training overhead achieved with the proposed method.

Efficient online computation demonstrated.

Abstract

Inspired by the remarkable learning and prediction performance of deep neural networks (DNNs), we apply one special type of DNN framework, known as model-driven deep unfolding neural network, to reconfigurable intelligent surface (RIS)-aided millimeter wave (mmWave) single-input multiple-output (SIMO) systems. We focus on uplink cascaded channel estimation, where known and fixed base station combining and RIS phase control matrices are considered for collecting observations. To boost the estimation performance and reduce the training overhead, the inherent channel sparsity of mmWave channels is leveraged in the deep unfolding method. It is verified that the proposed deep unfolding network architecture can outperform the least squares (LS) method with a relatively smaller training overhead and online computational complexity.