Enhanced Channel Estimation for 6G Urban V2V Communication Using BPNN

With the sixth generation (6G) era approaching, the Internet of Vehicles (Io V) has attracted much attention as a key application. The future Vehicle-to-Vehicle (V2V) communication in 6G urban scenarios has a larger data volume, which requires faster data rate, lower latency, and more reliable communication quality. To meet these requirements, this paper conducts channel modeling for 6G urban V2V communication scenarios and proposes a channel estimator based on a three-layer back-propagation neural network (BPNN), where each BPNN estimates the channel response at a single frequency point. Simulation results show that the performance of BPNN in 6G urban environment is better than that of traditional channel estimation algorithm.