Deep learning in channel estimation and signal detection in OFDM systems

• Main Author: Wang, Zefan
• Other Authors: Teh Kah Chan
• Format: Thesis-Master by Coursework
• Language: English
• Published: Nanyang Technological University 2022
• Subjects: Engineering::Electrical and electronic engineering::Wireless communication systems
• Online Access: https://hdl.handle.net/10356/158355
• Institution: Nanyang Technological University

This dissertation presents the results of channel estimation and signal detection using deep learning in Orthogonal Frequency Division Multiplexing (OFDM) system. In this dissertation, deep learning is used to deal with wireless OFDM channel. In the existing method, the channel state information is estimated first, and then the estimated channel state information is used to detect / recover the OFDM receiver of the transmission symbol. The method based on deep learning proposed in this dissertation implicitly estimates the channel state information and directly recovers the transmission symbols. In order to solve the channel distortion, the deep learning model first uses the data generated by the simu- lation based on channel statistics for offline training, and then directly restores the data transmitted online. From the simulation results, the method based on deep learning is more robust than the traditional method. In conclusion, deep learning is a useful method in signal detection and channel estimation in complex channel with distortion.