Machine Learning for Disseminating Cooperative Awareness Messages in Cellular V2V Communications

This paper develops a novel Machine Learning (ML)-based strategy to distribute aperiodic Cooperative Awareness Messages (CAMs) through cellular Vehicle-to-Vehicle (V2V) communications. According it, an ML algorithm is employed by each vehicle forecast its future CAM generation times; then, the autonomously selects radio resources for message broadcasting on basis of provided algorithm. action combined with wise analysis available transmission, that identifies subchannels where collisions might occur, avoid selecting them. Extensive simulations show accuracy in prediction CAMs’ temporal pattern excellent. Exploiting this knowledge resource assignment, and carefully identifying idle resources, allows outperform legacy LTE-V2X Mode 4 all respects.