Publication
Deep Learning-Based Signal-to-Noise Ratio Prediction for Realistic Wireless Communication
Qiuheng Zhou; Wei Jiang; Donglin Wang; Hans D. Schotten (Hrsg.)
IEEE Vehicular Technology Conference (VTC-2022), June 19-22, Helsinki, Finland, IEEE, 2022.
Abstract
Artificial intelligence (AI) based channel state information (CSI) prediction for frequency division duplexing (FDD) massive multiple-input multiple-output (MIMO) systems have attracted growing attention recently. Accurate channel prediction can effectively improve the quality of CSI and can help optimize system transmission schemes, such as throughput and transmission efficiency. The aim of this paper is to propose an efficient deep learning algorithm for signal-to-noise ratio (SNR) prediction in the real world, and a method for measuring SNR data from a universal software radio peripheral (USRP)-based software-defined radio platform. The results verify that the proposed channel measurement method is efficient for getting real-world channel data, and the deep learning-based algorithm has a strong ability for real-world channel prediction.