A pragmatic approach to location-aware service organization and discovery

Abstract

In this paper, we propose a pragmatic approach for location-aware service organization and discovery in structured peer-to-peer networks. To achieve local administration, the geographical space is divided into autonomous "local areas". The local areas and service providers within each area are then organized in two separate tiers using Hilbert Space Filling Curve. Furthermore, the locality-preserving property of the Hilbert curve is exploited to ease the maintenance and to make location-based range searches feasible. Besides, we adapt the Small World Model in our novel Source Sampling method to make the resulting network model navigable. As shown in preliminary experiments, our framework performs better in terms of routing efficiency, when compared with early approaches. In addition, it reduces the workload of superpeers and mitigates the negative effect of the failure of the superpeers. © 2009 IEEE.