Proactive Replication for Rare Objects in Unstructured Peer-to-Peer Networks
出版社：
- 出版社：Elsevier
- 页数：：85-96
- 出版年：2012
摘要内容：
Unstructured peer-to-peer (P2P) networks have become a very popular architecture for contentdistribution in large-scale and dynamic environments. The search ef?ciency problem in unstructuredP2P networks has not been adequately addressed so far, especially concerning search for rare objects. Inthis paper, we propose a proactive replication strategy to improve search ef?ciency for rare objects. Ituses an object-probing technique for peers to decide whether or not to establish replications for theirobjects when they join the network. This strategy can effectively increase the popularity of rare objectsin order to enhance search ef?ciency. We also present a rare object search algorithm to reduce theoverhead caused by the replication strategy. When a peer forwards a search request, the forwardprobability is calculated according to its neighbors’ degrees and the number of neighbors’ objects.Therefore, the search request is forwarded to the peers more likely containing target objects.Simulations show that our proactive replication strategy greatly improves search ef?ciency for rareobjects with moderate communication overhead. The rare object search algorithm not only improvessearch ef?ciency for rare objects, but also achieves load balance in search.
关键词：
- Peer-to-peer network,Rare object,Replication,Search,Object popularity
