Channel Estimation under Hardware Impairments: Bayesian Methods versus Deep Learning

TL;DR

This paper compares Bayesian and deep learning methods for channel estimation in multi-antenna systems affected by hardware impairments, demonstrating that neural networks can better exploit impairment features for improved accuracy.

Contribution

It introduces a neural network-based channel estimator that outperforms traditional Bayesian LMMSE methods under hardware impairments in uplink scenarios.

Findings

Deep learning improves channel estimation accuracy.

Neural network exploits hardware impairment characteristics.

Bayesian methods treat impairments as noise.

Abstract

This paper considers the impact of general hardware impairments in a multiple-antenna base station and user equipments on the uplink performance. First, the effective channels are analytically derived for distortion-aware receivers when using finite-sized signal constellations. Next, a deep feedforward neural network is designed and trained to estimate the effective channels. Its performance is compared with state-of-the-art distortion-aware and unaware Bayesian linear minimum mean-squared error (LMMSE) estimators. The proposed deep learning approach improves the estimation quality by exploiting impairment characteristics, while LMMSE methods treat distortion as noise.