Channel Estimation in C-V2X using Deep Learning

Channel estimation forms one of the central component in current OFDM systems that aims to eliminate the inter-symbol interference by calculating the CSI using the pilot symbols and interpolating them across the entire time-frequency grid. It is also one of the most researched field in the PHY with LS and MMSE being the two most used methods. In this work, we investigate the performance of deep neural network architecture based on CNN for channel estimation in vehicular environments used in 3GPP Rel.14 CV2X technology. To this end, we compare the performance of the proposed DL architectures to the legacy LS channel estimation currently employed in C-V2X. Initial investigations prove that the proposed DL architecture outperform the legacy CV2X channel estimation methods especially at high mobile speeds