Reinforcement learning based on routing with infrastructure nodes for data dissemination in vehicular networks (RRIN)

Vehicular-Ad hoc Networks are extremely important due to the potential for improving road safety, traffic monitoring, and in-vehicle infotainment services. A novel Q-learning-based routing protocol named Reinforcement learning-based Routing with Infrastructure Node Data Dissemination in Vehicular Network (RRIN) is proposed to efficiently address such a dynamic network. RRIN is a routing protocol that aims to achieve low end-to-end communication latency and a high data delivery ratio. To meet the objectives, we proposed two Q-routing functions for Road Model Segment Selection (RMSS) and Intermediate Vehicle Selection (IVS). The network environment is separated into road model segments, and Road Side Units at each road junction to assist nodes in data dissemination was deployed. The exploration feature of the Q-learning algorithm allowed the vehicles to randomly explore and interact with the dynamic environment in the vehicular network. Our findings show that the proposed RRIN routing protocol is highly beneficial compared to other efficient routing protocols with high packet delivery, high throughput, and low end-to-end communication latency. Due to the exploration and exploitation phases of Q-learning, the proposed RRIN routing protocol enhances the reliability and the efficiency of the vehicular network in terms of high throughput, low communication latency, and low packet and high packet delivery ratio. For RMSS, the shortest distance and higher connectivity distribution are considered parameters; whereas, the parameters for IVS are vehicle speed difference, link reliability, moving direction, and buffer size.