Propagation routing for hybrid bandwidth allocation with reinforcement learning in VANET infrastructure analysis

Advances in Vehicular Ad Hoc Networks (VANETs) require better security protocols to give automobiles and other VANET components impenetrable security. VANETs have several security challenges due to the openness of their communication architecture. The security and privacy issues related to vehicle-to-vehicle (V2V) communication have been addressed through various mutual authentication systems that researchers have recently put out. The investigation of the VANET infrastructure using artificial intelligence is proposed in this paper as a unique approach to smart V2V data transfer. The infrastructure study uses a hybrid multi-channel technique based on bandwidth allocation. The data are sent using reinforcement Q-learning techniques in conjunction with propagation routeing. The experimental investigation focuses on throughput, delay, QoS, computational cost and data transmission rate.