A mobile ad-hoc network is an infrastructure less, a self configuring network connected by wireless links. No central administration is needed for these types of networks. Therefore, they are suitable only for temporary communication links. An important issue in computer network is to design the network in such a way to cope up with the speed required today. Routing is the process of selecting paths in a network along which to send data or physical traffic. Routing directs the passing of logically addressed packets from their source toward their ultimate destination through intermediary nodes. In any network, the data packets have to be routed to the destination with minimum loss, minimum delay and maximum packet delivery ratio. Therefore, there must be an efficient routing algorithm which satisfies all these Quality of Service requirements and it must also be robust and adaptive. The algorithm Multi Agent Ant Based Routing Algorithm is designed from the ACO framework, inspired by the behavior of biological ants. The algorithm consists of both reactive and proactive components. This technique increases node connectivity and decreases average end-to-end delay and increase packet delivery ratio. Since node connectivity increases, packet loss is reduced. The simulations are carried out by NS-2 and the results prove that Multi Agent Ant Based Routing Algorithm outperformsAntHocNet,AODVandDSRin terms of average end-to-end delay and packet delivery ratio.

Key words: MANETs, QoS, Routing,AntHocNet,ACO,AODV, DSR.