The ever-increasing demand for high data rates and high connection densities in the vehicle communication network, along with the widespread adoption of radio access over the Third Generation Partnership Project (3GPP) standard, has been a major driver of a large amount of research on cellular vehicle-to-everything (C-V2X) communication. Additionally, Wi-Fi and other wireless communication technology work on the unlicensed band has undergone booming development due to the proliferation of handheld devices over the years. It is, therefore, likely that C-V2X users dedicated band on the 5.9 GHz spectrum may suffer from both co-channel and adjacent channel interference, which cannot be negligible, especially in urban scenarios. To this end, 3GPP has standardized relay technology in New Radio (NR) V2X sidelink to confront such engineering concerns. Placing relay nodes on vehicles is a promising approach to save power and energy, as well as extend the transmission range under interference. In this paper, through a link-level and system-level simulation study, we implement parameter optimization and performance evaluation in relaying scenarios. Motivated by the recent success of deep learning, a novel neural network is further introduced to detect and classify interference signals of different protocols so that the sidelink transceiver can adopt specific schemes to mitigate interference respectively. Simulation results provide direct insight into the system performance in relay-assisted cases and reveal that the interference incurred by NR on unlicensed spectrum (NR-U) signal is the most intractable which may bring potential challenges in future works.