Reinforcement learning-based parameter tuning for a broadcast protocol In VANETs

摘要

It is particularly challenging to design an intelligent multi-hop broadcast protocol for vehicular ad hoc networks (VANETs) due to the dynamic environment. Existing protocols are optimized for a specific scenario, and are not capable of working in various scenarios. In this paper, we present a broadcast protocol which is able to make forwarding decision based on a self-learning mechanism. The protocol employs a fuzzy logic-based relay node selection approach to take into account multiple metrics for the forwarding algorithm. The parameters used for the fuzzy logic are tuned online using a reinforcement learning approach. The combination of reinforcement learning and fuzzy logic can provide an intelligent solution for broadcasting in VANETs. We conduct computer simulations to evaluate the proposed protocol.