Learned Trimmed-Ridge Regression for Channel Estimation in Millimeter-Wave Massive MIMO

TL;DR

This paper introduces a novel deep learning-based channel estimation method for millimeter-wave massive MIMO systems, leveraging a trimmed-ridge regression model to improve accuracy and enable real-time processing.

Contribution

It proposes a new unfolded trimmed-ridge regression model integrated into deep learning for fast, accurate channel estimation in challenging MIMO scenarios.

Findings

Outperforms existing deep learning models in accuracy

Supports higher downlink sum rates

Enables real-time channel reconstruction

Abstract

Channel estimation poses significant challenges in millimeter-wave massive multiple-input multiple-output systems, especially when the base station has fewer radio-frequency chains than antennas. To address this challenge, one promising solution exploits the beamspace channel sparsity to reconstruct full-dimensional channels from incomplete measurements. This paper presents a model-based deep learning method to reconstruct sparse, as well as approximately sparse, vectors fast and accurately. To implement this method, we propose a trimmed-ridge regression that transforms the sparse-reconstruction problem into a least-squares problem regularized by a nonconvex penalty term, and then derive an iterative solution. We then unfold the iterations into a deep network that can be implemented in online applications to realize real-time computations. To this end, an unfolded trimmed-ridge regression model is constructed using a structural configuration to reduce computational complexity and a model ensemble strategy to improve accuracy. Compared with other state-of-the-art deep learning models, the proposed learning scheme achieves better accuracy and supports higher downlink sum rates.