Reinforcement Learning for Quality of Service in Mobile Ad Hoc Network (MANET)

It is very difficult to find feasible QoS (Quality of service) routes in the mobile ad hoc networks (MANETs), because of the nature constrains of it, such as dynamic network topology, wireless communication link and limited process capability of nodes. In order to reduce average cost in flooding path discovery scheme of the traditional MANETs routing protocols and increase the probability of success in finding QoS feasible paths and It proposed a heuristic and distributed route discovery new method supports QoS requirement for MANETs in this study. This method integrates a distributed route discovery scheme with a Reinforcement Learning (RL) method that only utilizes the local information for the dynamic network environment; and the route expand scheme based on Cluster based Routing Algorithms (CRA) method to find more new feasible paths and avoid the problem of optimize timing in previous smart net Quality of service in MANET. In this paper proposed method Compared with traditional method, the experiment results shoItd the network performance is improved optimize timing, efficient and effective.