Searching using Probabilistic Hints in Unstructured Peer-to-Peer Networks

X. Li, Jie Wu, and J. Xu (USA)


Bloom filter, hint-based, peer-to-peer, search.


Peer-to-peer (P2P) networking is designed for sharing re sources at the edge of the Internet. Searching in file-sharing P2P networks has been an important research topic, and it has drawn significant attention recently. Hints can be uti lized to improve query success rates. Determining how to efficiently and effectively propagate hints is a challenging issue. In this paper, we propose a searching protocol called HS-SDBF (Hint-based Search by Scope Decay Bloom Fil ter) that addresses this issue. HS-SDBF uses a data struc ture named SDBF (Scope Decay Bloom Filter) to repre sent and propagate probabilistic hints. Compared to exist ing proactive schemes, HS-SDBF can answer many more queries successfully at a lower amortized cost considering both the query traffic and hint propagation traffic. The ex perimental results support the performance improvement of our protocol.

Important Links:

Go Back