A Novel Learning based Algorithm for Resource Searching in Peer-to-Peer over Mobile Ad-hoc Networks

Peer to peer network is a set of self-adaptive and identic nodes that cooperate together without the central coordinator. Mobile peer to peer network is caused from the implementation of peer to peer network over mobile Ad-hoc networks’ platform. The distributed structure of these networks reinforces the resource searching. The requests in these networks are often propagated randomly and broadcast. Thus, designing a self- adavptive mechanism that sends the request intentionally to the network is crucial, to be able to discover the demanded source of the request with the maximum amount of success rate and minimum amount of energy and traffic load. In this research is presented solution with the aim of improving serach on the mobile peer to peer network. Learning automata are adaptive decision making units which run in random environments that learn the optimal action through repeated interaction with its environment.In the proposed algorithm, each node having a message sends a search request to some more useful neighbors. Correspondingly the best route from the source node will transmit the requested resource. Moreover Because of saving result in neighbourse cache table, Neighbourse experince are effective in future forwards. The simulation results of the proposed algorithm and comparison with the “Gossiping Load Balancing alghorithm” algorithm and “Imporoved Adaptive Probablitistic Search”, show that avoiding selecting random neighbors for forward request and considering the history of each node using the results stored in cache tables, reduce energy consumption, the number of sended and droped network packets , and the networkload. Since, due to the influence of neighboring nodes in proceeding, the request message is sent to the neighbors who have been more successful in previous searches, the success rate of the network also increases.