A peer-to-peer overlay for context information search

Abstract

The widespread use of context information necessitates an efficient wide-area lookup service in pervasive computing. In this paper, we present semantic context space (SCS), a semantic overlay network that facilitates efficient search for context information in distributed environments. Peers in SCS are grouped based on the semantics of their local data and self-organized into a one-dimensional ring space. Context search requests are only routed to the appropriate semantic clusters, reducing unnecessary search cost on peers that have irrelevant context data, and increasing the chances that the context data will be found quickly. By exploring parallelism in a semantic cluster, search request can be found quickly. Our simulation studies demonstrate the effectiveness of SCS.