Scalable spatial information discovery over Distributed Hash Tables
Faraz Memon, Daniel Tiebler, Frank Dürr, Kurt Rothermel, Marco Tomsu, Peter Domschitz · 2009
In this paper, we present a Peer-to-Peer (P2P) spatial information discovery system that enables spatial range queries over Distributed Hash Tables (DHTs). Our system utilizes a less-distorting octahedral map projection in contrast to the quadrilateral projections used by majority of the previously proposed systems, to represent the spatial information. We also introduce a Space-Filling Curve (SFC)-based data placement strategy that reduces the probability of data hot-spots in the network. Moreover, we show that our system achieves scalable resolution of location-based range queries, by utilizing a tree-based query optimization algorithm. Compared to the basic query resolution algorithm, the query optimization algorithm reduces the average number of parallel messages used to resolve a query, by a factor of 96%.