An intelligent clustering algorithm based on hybrid RF/VLC communication model for VANET

With the increasing density of vehicles and the increasing demand for high data rates, Visible Light Communication(VLC) has been added to the traditional VANET communication based on Radio Frequency (RF) as a new green communication technology. In order to improve the communication quality between vehicles, this paper presents a hybrid communication model of RF and VLC, and then proposes an intelligent cluster head(CH) selection algorithm based on reinforcement learning(RL). In this algorithm, the communication mode is judged and selected according to the relative position of the CH and its members, and the vehicles are divided into clusters by the relative position and the relative speed, and the total signal-to-noise ratio(SNR) in the cluster is taken as the reward to select the CH intelligently. Simulation results show that compared with the Stable Clustering Algorithm for vehicular ad hoc networks (SCalE), the proposed algorithm has higher SNR and lower power consumption.