Relay selection algorithm based on social network combined with Q‐learning for vehicle D2D communication

Abstract

A relay selection algorithm was proposed to improve a communication rate of D2D (device-to-device) users in-vehicle networking communication systems based on social network combined with Q-learning. The scheme was divided into two steps. Firstly, a social threshold was introduced to filter the potential relay nodes to reduce the number of probing times based on the user's interest similarity in D2D communication network. Then, an optimal relay selection algorithm was proposed to maximise the total rate of D2D links based on a Q-learning algorithm. This method can provide the optimal relay selection scheme to meet the requirements of vehicle networking communication. The simulation results showed that the proposed scheme could reduce the number of probing relays and improve the communication speed of the system on the basis of ensuring communication security.