Peer selection in P2P file sharing systems over mobile cellular networks with consideration of downlink bandwidth limitation

Abstract

In P2P file sharing systems over mobile cellular networks, the bottleneck of file transfer speed is usually the downlink bandwidth of the receiver rather than the uplink bandwidth of the senders. In this paper we consider the impact of downlink bandwidth limitation on file transfer speed and propose two novel peer selection algorithms named DBaT-B and DBaT-N, which are designed for two different cases of the requesting peer's demand respectively. Our algorithms take the requesting peer's downlink bandwidth as the target of the sum of the selected peers' uplink bandwidth. To ensure load balance on cells, they will first choose a cell with the lowest traffic load before choosing each peer. We also provide a Fuzzy Cognitive Map that can be used to estimate peers' service ability in P2P systems over mobile cellular networks. Simulation results show that in respective cases DBaT-B and DBaT-N can both achieve much better load balance on cells than some traditional algorithms while ensuring favorable file transfer speed.