Reinforcement Learning-Based Routing With Infrastructure Node Data Dissemination In Vehicular Networks(RRIN)

Vehicular ad hoc networks(VANETs)create an advanced framework to support the intelligent transportation system and increase road safety by managing traffic flow and avoiding accidents.These networks have specific characteristics,including the high mobility of vehicles,sparse connectivity,road-side obstacles,shortage of road-side units,dynamic topology,and frequent link failures.VANETs routing protocols face many challenges,including intermittent connectivity,large delays,packet delivery ratio,throughput,and communication overhead.For this reason,providing an efficient and stable routing approach for VANETs is a challenging issue.Reinforcement learning(RL)can solve the various challenges and issues of vehicular ad hoc networks,including routing.RL algorithms are more favorable than other optimization techniques owing to their modest usage of memory and computational resources.Because a VANETs deals with passenger safety,any kind of flaw is intolerable in VANETs routing.Fortunately,RL-based algorithms have the potential to optimize the different quality-of-service parameters of VANETs routing,such as bandwidth,end-to-end delay,and packet delivery ratio.Most of the existing reinforcement learning-based routing methods are incompatible with the dynamic network environment and cannot prevent congestion in the network.Network congestion can be controlled by managing traffic flow.This thesis work presents a routing protocol called a novel Q-learning-based routing protocol named reinforcement learning-based routing with infrastructure node data dissemination in vehicular networks(RRIN).The main goal of this work aims to increase the packet delivery ratio and reduce the end-to-end delay,and minimize communication overhead.We suggested two Q-learning routing functions for Road Model Segment Selection(RMSS)and Intermediate vehicle Selection(IVS).Further,we propose the deployment of the Roadside Unit(RSU)on each road junction.RSUs can further assist the vehicles in data dissemination.The RMSS is the combination of two probability functions,Shortest distance and Higher connectivity distribution.On the other hand,the IVS is based on five quantities,vehicle’s speed difference,vehicle’s moving direction,number of packets on the vehicle,signal fading,and link reliability.The results show that our algorithm outperforms the existing methods in terms of network performance,such as endto-end delay,packet delivery ratio,communication overhead,packet drop rate,and high throughput.