Distributed Multi-Source Transmission in Wireless Mobile Peer-to-Peer Networks: A Restless Bandit Approach

In wireless mobile peer-to-peer (P2P) networks, multiple sources can provide multimedia file sharing at the same time. The selection of multiple sources is one of the key issues in the design of a multi-source transmission system in wireless mobile P2P networks. In this paper, we propose a distributed multi-source sender selection scheme to maximize the receiving data rate and minimize the energy consumption. Our scheme is based on recent advances in restless bandit algorithms. The proposed sender selection scheme has an indexability property that dramatically simplifies the computation and implementation of the policy. In addition, there is no need for a centralized control point, and senders can join and leave from the wireless mobile P2P network freely. Simulation results show that the proposed scheme improves the receiving data rate and energy consumption performance significantly compared to the existing scheme.