A Swarm based Adaptive Routing Protocol for Real Time Transmission in MANETs

The Mobile ad hoc networks are highly dynamic in nature and their having limited bandwidth. Due to these reasons the routing is more difficult than other networks. The various kinds of multimedia applications such as video, audio with diverse traffic characteristics and require Quality of Service (QoS) at very high rates, leads to significant traffic problems such as packet losses, transmission delay, routing overhead caused by congestion in the networks. The prediction of these problems in real time environment is difficult and making the effectiveness of existing routing protocols based on analytical models questionable. We have proposed a new adaptive routing protocol in this paper, a state of the art of this problem followed by a solution based on reinforcement learning paradigm that we find more optimal for this kind of problems. We have implemented this protocol in NS2 and compared with DSR and AODV. Our proposed protocol performed well in all cases over DSR and AODV routing protocols.