Joint Fine Time Synchronization and Channel Estimation Using Deep Learning for Wireless Communication Systems

This paper presents a joint fine time synchronization and channel estimation scheme based on deep learning (DL) for wireless communication systems. The scheme adopts a specific training sequence structure with both cyclic prefixing and cyclic postfixing. It works excellently without setting a search range and a threshold as required by the conventional method based on the same training sequence structure. Simulation results demonstrate that the proposed DL-based scheme has significant performance gains for most cases as compared with the conventional method. With improved time synchronization, better channel estimation performance is achieved accordingly.