A Deep Learning Based Channel Estimation Scheme for IEEE 802.11p Systems

In this paper, we propose a novel deep learning based channel estimation scheme for IEEE 802.11p vehicle-to-everything (V2X) communication systems. A major challenge in the V2X system is to grasp complicated variations and distortion of the channels due to high mobility. To address the issue, the data-pilot aided (DPA) channel estimation schemes have been investigated, but the performance is still unsatisfactory due to the error propagation issue. To tackle the problem, in this paper, we introduce a machine learning technique based on an artificial neural network so called autoencoder (AE) to the conventional DPA process. To reduce the size of the neural network, thereby minimizing the receiver complexity, we design the AE such that it learns the channel frequency characteristics only. Then, we use the trained AE for updating the channel estimates obtained from the DPA process. The trained AE is capable of recovering estimation errors based on the channel frequency correlation, and thus help us attenuate the error propagation issue of the DPA process. The proposed scheme is scalable from the conventional systems, because we can simply put or remove the AE in the middle of the DPA process. In addition, it is verified from simulation results that the proposed scheme exhibits a dramatic performance gain over the conventional V2X channel estimation schemes.