Autonomous topology optimization for unstructured peer-to-peer networks

The topology of a peer-to-peer overlay network is usually constructed randomly without considering the characteristics of underlying physical links. Thus searching and routing between peer nodes is often inefficient. This paper proposes a mechanism that a peer node autonomously optimizes the topology of a peer-to-peer network based on the metrics of underlying networks. The simulation results show that this mechanism optimizes the topology of a peer-to-peer network and significantly decreases the average hop count between any pair of peer nodes.