Deep Learning-Aided 5G Channel Estimation

TL;DR

This paper introduces a deep learning-assisted channel estimation method for 5G MIMO systems that enhances accuracy while supporting low-cost least squares estimation, especially under Doppler effects.

Contribution

The paper proposes a novel deep learning-based approach to improve 5G channel estimation accuracy while maintaining low computational cost, supporting existing least squares methods.

Findings

Outperforms previous methods in mean square error metrics

Effective under Doppler effects in 5G MIMO channels

Supports low-cost least squares estimation with improved accuracy

Abstract

Deep learning has demonstrated the important roles in improving the system performance and reducing computational complexity for $5$G-and-beyond networks. In this paper, we propose a new channel estimation method with the assistance of deep learning in order to support the least squares estimation, which is a low-cost method but having relatively high channel estimation errors. This goal is achieved by utilizing a MIMO (multiple-input multiple-output) system with a multi-path channel profile used for simulations in the 5G networks under the severity of Doppler effects. Numerical results demonstrate the superiority of the proposed deep learning-assisted channel estimation method over the other channel estimation methods in previous works in terms of mean square errors.