Approximate Aggregations in Structured P2P Networks

• Published in: IEEE transactions on knowledge and data engineering Vol. 23; no. 11; pp. 1748 - 1752
• Main Authors: Sun, Dalie, Wu, Sai, Jiang, Shouxu, Li, Jianzhong
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.11.2011; IEEE Computer Society; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Agglomeration; Aggregates; Applied sciences; approximate query processing; Approximation; BATON; Business; Computer science; control theory; systems; Computer systems and distributed systems. User interface; Estimation; Exact sciences and technology; Indexes; Information systems. Data bases; Memory organisation. Data processing; Networks; Peer to peer computing; Peer-to-Peer; Queries; Query processing; Random numbers; Servers; Software; Studies; High performance; Peer to peer; approximate query processing; Probabilistic approach; Database query; Distributed system; Peer-to-Peer; Distributed computing; Random number; Aggregation; Query processing; BATON; Database; Random access
• ISSN: 1041-4347; 1558-2191
• DOI: 10.1109/TKDE.2010.198

In corporate networks, daily business data are generated in gigabytes or even terabytes. It is costly to process aggregate queries in those systems. In this paper, we propose PACA, a probably approximately correct aggregate query processing scheme, for answering aggregate queries in structured Peer-to-Peer (P2P) network. PACA retrieves random samples from peers' databases and applies the samples to process queries. Instead of scanning the entire database of each peer, PACA only accesses a small random number of data. Moreover, based on the query distribution,PACA publishes a precomputed synopsis and uses the synopsis to answer future queries. Most queries are expected to be answered by the precomputed synopsis partially or fully. And the synopsis is adaptively tuned to follow the query distribution. Experiments on the PlanetLab show the effectiveness of the approach.