ASPEN: an adaptive spatial peer-to-peer network

  • Authors:
  • Haojun Wang;Roger Zimmermann;Wei-Shinn Ku

  • Affiliations:
  • University of Southern California, Los Angeles, CA;University of Southern California, Los Angeles, CA;University of Southern California, Los Angeles, CA

  • Venue:
  • Proceedings of the 13th annual ACM international workshop on Geographic information systems
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

Geographic Information Systems (GIS) are increasingly managing very large sets of data and hence a centralized data repository may not always provide the most scalable solution. Here we introduce a novel approach to manage spatial data by leveraging structured Peer-to-Peer (P2P) systems based on Distributed Hash Tables (DHTs). DHT algorithms provide efficient exact-match object search capabilities without requiring global indexing and as a result they are extremely scalable. Furthermore, the adoption of uniform hash functions ensures excellent load balancing. However, range queries -- which are very common with spatial data -- cannot be executed efficiently because the hash functions unfortunately destroy any existing data locality. Here we report on the design of an Adaptive Spatial Peer-to-pEer Network (ASPEN) that extends Content Addressable Networks (CAN) to preserve spatial locality information while also retaining many of the load balancing properties of DHT systems. We introduce the concept of scatter regions, which are spatial data distribution units that optimize both load balancing and spatial range query processing at the same time. We present a data object key generation function and algorithms for spatial range queries. We rigorously evaluate our technique with both synthetic and real world data sets and the results demonstrate the efficient execution of spatial range queries in the ASPEN system.