Cooperative reinforcement learning approach for routing in ad hoc networks

Abstract

Most of the routing algorithms over ad hoc networks are based on the status of the link (up or down). They are not capable of adapting the run time changes such as traffic load, delay and delivery time to reach to the destination etc, thus though provides shortest path, these shortest path may not be optimum path to deliver the packets. Optimum path can only be achieved when quality of links within the network is detected on continuous basis instead of discrete time. Thus for achieving optimum routes we model ad hoc routing as a cooperative reinforcement learning problem. In this paper, agents are used to optimize the performance of a network on trial and error basis. This learning strategy is based work in swarm intelligence: those systems whose design is inspired by models of social insect behaviour. This paper describes the algorithm used in cooperative reinforcement learning approach and performs the analysis by comparing with existing routing protocols.