On the topology maintenance of dynamic P2P overlays through self-healing local interactions

Abstract

Abstract-This paper deals with the use of self-organizing protocols to improve the reliability of dynamic Peer-to-Peer (P2P) overlay networks. We present two approaches, that employ local knowledge of the 2nd neighborhood of nodes. The first scheme is a simple protocol requiring interactions among nodes and their direct neighbors. The second scheme extends this approach by resorting to the Edge Clustering Coefficient (ECC), a local measure that allows to identify those edges that connect different clusters in an overlay. A simulation assessment is presented, which evaluates these protocols over uniform networks, clustered networks and scale-free networks. Different failure modes are considered. Results demonstrate the viability of the proposal.

Self-healing protocols for connectivity maintenance in unstructured overlays

“…The calculation of these metrics usually involves a full (or partially full) knowledge about the whole network. Conversely, the aim of this work is to preserve connectivity without such a global knowledge [19], [20], [34], [49].…”