Date Added: Mar 2013
Top-k query is widely used in the search engine and gains great success, which perform the cooperative query by aggregating the database objects' degree of match for each different query predicate and returning the best k matching objects only. It's also applied to P2P file-sharing systems. However, top-k query processing in P2P systems is very challenging because the potentially large number of peers may contribute to the query results, which may induce a huge amount of network traffic and high latency. In this paper, the authors develop a framework that can effectively satisfy the demands. Two algorithms are used for local peer query processing and hierarchical join query processing, and two schemes are proposed to deal with the problem of peer's dynamicity and further reduce communication cost.