Deep unfolding based channel estimation for wideband terahertz near-field massive MIMO systems

The combination of terahertz and massive multiple-input multiple-output (MIMO) is promising for meeting the increasing data rate demand of future wireless communication systems thanks to the significant bandwidth and spatial degrees of freedom. However, unique channel features, such as the near-field beam split effect, make channel estimation particularly challenging in terahertz 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 study, 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 terahertz massive MIMO channel estimation algorithm is proposed. In each iteration of the approximate message passing-sparse Bayesian learning algorithm, the optimal update rule is learned by a deep neural network (DNN), whose architecture is customized to effectively exploit the inherent channel patterns. Furthermore, a mixed training method based on novel designs of the DNN architecture 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.