AbIx: An Approach to Content-Based Approximate Query Processing in Peer-to-Peer Data Systems

In recent years there has been a significant interest in peer-to-peer(P2P) environments in the community of data management. However, almostall work, so far, is focused on exact query processing in current P2P datasystems. The autonomy of peers also is not considered enough. Inaddition, the system cost is very high because the informationpublishing method of shared data is based on each document instead ofdocument set.In this paper, abstract indices (AbIx) are presented to implementcontent-based approximate queries in centralized, distributed andstructured P2P data systems. It can be used to search as few peers aspossible but get as many returns satisfying users' queries as possibleon the guarantee of high autonomy of peers. Also, abstract indices havelow system cost, can improve the query processing speed, and supportvery frequent updates and the set information publishing method.In order to verify the effectiveness of abstract indices, a simulator of10,000 peers, over 3 million documents is made, and several metrics areproposed. The experimental results show that abstract indices work wellin various P2P data systems.