Network Traffic Load Balancing in Hierarchical Peer-to-Peer Systems

The management of huge amounts of data distributed across multiple sites has become a necessity more and more demanding. Peer-to-peer systems (P2P) can afford the requirements of managing, indexing, searching and analyzing data with scalability and self-organization. Until now, most efforts have focused primarily on improving the number of hops and structure maintenance messages. However, the non-uniform distribution of data and the hierarchical structures, together with heavy load, can cause unbalanced traffic load. In this paper we improve our previous work on the overlay structure G-Grid, merging it with a Small World network. The Small World networks make a compromise between order and randomness, they are derived from social networks and show an almost uniform traffic distribution. Experiments show how this new hybrid structure obtains the best performance in traffic distribution.