Deep Unfolding-Based Channel Estimation for Wideband TeraHertz Near-Field Massive MIMO Systems

TL;DR

This paper introduces a deep unfolding-based channel estimation method for wideband THz massive MIMO systems that effectively addresses near-field beam split effects by using frequency-dependent dictionaries and learned iterative updates.

Contribution

It proposes a novel deep unfolding algorithm with frequency-dependent dictionaries and a mixed training approach for improved THz MIMO channel estimation.

Findings

Outperforms existing algorithms in accuracy and robustness.

Reduces computational complexity significantly.

Effectively handles near-field beam split effects.

Abstract

The combination of Terahertz (THz) and massive multiple-input multiple-output (MIMO) is promising to meet the increasing data rate demand of future wireless communication systems thanks to the huge bandwidth and spatial degrees of freedom. However, unique channel features such as the near-field beam split effect make channel estimation particularly challenging in THz massive MIMO systems. On one hand, adopting the conventional angular domain transformation dictionary designed for low-frequency far-field channels will result in degraded channel sparsity and destroyed sparsity structure in the transformed domain. On the other hand, most existing compressive sensing-based channel estimation algorithms cannot achieve high performance and low complexity simultaneously. To alleviate these issues, in this paper, we first adopt frequency-dependent near-field dictionaries to maintain good channel sparsity and sparsity structure in the transformed domain under the near-field beam split effect. Then, a deep unfolding-based wideband THz massive MIMO channel estimation algorithm is proposed. In each iteration of the unitary approximate message passing-sparse Bayesian learning algorithm, the optimal update rule is learned by a deep neural network (DNN), whose structure is customized to effectively exploit the inherent channel patterns. Furthermore, a mixed training method based on novel designs of the DNN structure and the loss function is developed to effectively train data from different system configurations. Simulation results validate the superiority of the proposed algorithm in terms of performance, complexity, and robustness.