Deep Learning-Aided 5G Channel Estimation

• Published in: 2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM) pp. 1 - 7
• Main Authors: Ha, An Le, Van Chien, Trinh, Nguyen, Tien Hoa, Choi, Wan, Nguyen, Van Duc
• Format: Conference Proceeding
• Language: English
• Published: IEEE 04.01.2021
• Subjects: 5G mobile communication; Channel estimation; Deep learning; Deep Neural Networks; Estimation; Frequency Selective Channels; MIMO communication; Multiple-Input Multiple-Output; Signal to noise ratio; System performance
• DOI: 10.1109/IMCOM51814.2021.9377351

Deep learning has demonstrated the important roles in improving the system performance and reducing computational complexity for 5G-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.