Q-Learning Based Point to Point Data Transfer in Vanets

Vehicular ad hoc networks (VANETs) are highly mobile wireless network. Vehicular Ad-hoc Network (VANET) is becoming the most suitable solution for driving assistance and traffic monitoring in the current scenario. A VANET provides vehicle to vehicle connectivity and can be used as an alert system in the vehicles. However, due to vehicle mobility, limited wireless resources, and the lossy characteristics of a wireless channel, achieving a reliable multi hop communication in VANETs is particularly challenging. In this paper, we propose PP-AODV, which is a portable VANET routing protocol that learns the optimal route by employing a fuzzy constraint Q-learning algorithm based on ad hoc on-demand distance vector (AODV) routing. With the help of fuzzy logic it is estimated whether a link is good or not by considering multiple metrics which are specifically the available Bandwidth, Delay, packet collision probability. The protocol can understand vehicle movement based on neighbour information when position information is unavailable. Simulations show that the proposed protocol showed good performance with a rise in packet delivery ratio, decreased end-to-end delay, and low overhead.