QLAR: A Q-learning based adaptive routing for MANETs
Recently mobile ad-hoc networks (MANET) have found widespread applications. In this infrastructure-less networks the routes have to be refreshed often due to mobility of nodes which also acting as routers. Many ad-hoc routing protocols have been proposed, of which on-demand routing protocols are very popular. To meet the scarce of network resources, the need of the time is to develop a protocol which makes efficient use of resources. In this paper we propose a mobility adaptive cross layer design to enhance the performance of ad-hoc on-demand distance vector (AODV) routing protocol by establishing stable routes. The adaptive decision making according to the speed of mobile nodes on route request (RREQ) packet forwarding results in stable routes. Comparing with the basic AODV protocol, the new cross layer algorithm has better performance as shown with the simulation results obtained using the network simulator, GloMoSim.