Deep Learning-Based Channel Estimation for Wideband Hybrid MmWave Massive MIMO

TLDR

Hybrid analog‑digital architectures reduce cost and energy in mmWave massive MIMO, but limited RF chains, power leakage, beam squint, and high‑complexity compressive sensing algorithms hinder accurate channel estimation. We propose a deep‑learning‑based channel estimation method that unfolds sparse Bayesian learning into a neural network to overcome these challenges. Each SBL layer updates Gaussian variance parameters via a tailored DNN, jointly optimizes the measurement matrix, and extends to multi‑block scenarios by exploiting temporal channel correlation to predict the matrix and refine variance updates. Simulation results demonstrate that the proposed approach surpasses existing methods in both estimation accuracy and computational complexity.

Abstract

Hybrid analog-digital (HAD) architecture is widely adopted in practical millimeter wave (mmWave) massive multiple-input multiple-output (MIMO) systems to reduce hardware cost and energy consumption. However, channel estimation in the context of HAD is challenging due to only limited radio frequency (RF) chains at transceivers. Although various compressive sensing (CS) algorithms have been developed to solve this problem by exploiting inherent channel sparsity and sparsity structures, practical effects, such as power leakage and beam squint, can still make the real channel features deviate from the assumed models and result in performance degradation. Besides, the high complexity of CS algorithms caused by a large number of iterations hinders their applications in practice. To tackle these issues, we develop a deep learning (DL)-based channel estimation approach where the sparse Bayesian learning (SBL) algorithm is unfolded into a deep neural network (DNN). In each SBL layer, Gaussian variance parameters of the sparse angular domain channel are updated by a tailored DNN, which is able to capture complicated channel sparsity structures in various domains effectively and efficiently. The measurement matrix is jointly optimized for performance improvement. Then, the proposed approach is extended to the multi-block case where channel correlation in time is further exploited to adaptively predict the measurement matrix and facilitate the update of variance parameters. Simulation results show that the proposed approaches outperform existing approaches in terms of both performance and complexity.