GRU-Based Deep Learning Channel Estimation Scheme for the IEEE 802.11p Standard
Jun Hou, Huaijie Liu, Yang Zhang, Wei Wang, Jiaqian Wang
Abstract
In the IEEE 802.11p standard, channel estimation is quite challenging in the presence of high mobility due to rapid channel variations. Extensive research has been conducted on data pilot aided (DPA) channel estimation to address this issue. Nonetheless, the estimation performance of state-of-the-art DPA schemes is unsatisfactory because of error propagation. In this letter, a channel estimation technique is proposed using a gated recurrent unit (GRU) based deep learning scheme for extracting time and frequency domain features to suppress error propagation of the DPA process applied to IEEE 802.11p. Simulation results demonstrate that the proposed scheme outperforms other deep-learning-based channel estimation schemes without increasing the computational complexity.