Deep Learning-based Path loss Prediction for Fifth-generation New Radio Vehicle Communications

Fifth-generation (5G) technology is rapidly spreading to vehicle-to-vehicle (V2V) communication, which requires high reliability, data transmission rate, and low latency meet service requirements through a new frequency band called millimeter wave (mmWave). However, mmWave bands are difficult utilize in dynamically changing vehicle environment because of the propagation attenuation against obstacles. Various studies underway predict path loss on roads with many it still challenging accurately various environments existing prediction models either generalize solely based measurement or only use specific parameters. Recently, investigations artificial intelligence have been conducted using techniques that different from heuristic methods. Following this trend, we propose deep learning-based considers obstacles weather conditions V2V communication mmWave. To consider affecting measurement, constructed realistic simulation collected used train our learning models. Our proposed approach achieves accurate predictions for loss.