Enhancement of BARTERCAST using reinforcement learning to effectively manage freeriders

Abstract

Efficient searching and quality services are offered by prevailing infrastructure of Peer-to-Peer(P2P)networks. P2P applications are more and more wide spreading with good scope. Though the advantages are still existing the P2P system is vulnerable to some security issues. One of the important issues that threatens the subsistence of P2P system is freeriding. Freeriders are peers(nodes) which only utilize the system but not contribute anything to the system. Freeriders affect the system in a drastic manner. Freeriders mainly download the contents without uploading anything. So the contents will be concentrated in few peers and that will increase the congestion and reduce the quality of the system. This reduces the popularity of the system. This paper compares different approaches for managing freeriders and finally a solution is suggested which is an extension to existing protocol known as BARTERCAST and the enhancement is done through Q-learning. Application of reinforcement learning approach in BARTERCAST results in more accurate results. © 2011 Springer-Verlag.