Abstract | ||
---|---|---|
Efficient service discovery in dynamic, cross-organizational is one of the challenge aspects in ChinaGrid. Network overlay and search algorithms are two important considerations to the problem. Tree topology of organizations is easily managed but the root is a single point of failure; P2P structure tends to be conversed. To merge the advantages of both, we present a hybrid system with two layers: tree layer and peer layer. This structure is practical because organizations targeting at sub objects of a subject are inclined to be organized hierarchically as a superpeer; and all these superpeers construct an unstructured P2P network that adapts to peer's interest by learn neighbor algorithm. Experimental evaluation shows that our mechanism exhibits better search performance than fully hierarchical or fully distributed system |
Year | DOI | Venue |
---|---|---|
2006 | 10.1109/AINA.2006.263 | AINA (1) |
Keywords | Field | DocType |
tree topology,p2p structure,better search performance,tree searching,grid computing,hybrid system,service discovery,telecommunication network topology,learn neighbor algorithm,hybrid peer-to-peer overlay,search algorithm,p2p network,network overlay,chinagrid,peer-to-peer computing,peer-to-peer overlay network,tree layer,unstructured p2p network,challenge aspect,peer layer,resource management,distributed system,p2p,high performance computing,clustering algorithms,robustness,scalability,network topology | Single point of failure,Grid computing,Search algorithm,Computer science,Computer network,Network topology,Service discovery,Hybrid system,Overlay network,Distributed computing,Scalability | Conference |
Volume | ISSN | ISBN |
1 | 1550-445X | 0-7695-2466-4 |
Citations | PageRank | References |
0 | 0.34 | 9 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jing Tie | 1 | 17 | 2.83 |
Hai Jin | 2 | 6544 | 644.63 |
Shengli Li | 3 | 5 | 2.52 |
Xuanhua Shi | 4 | 571 | 57.87 |
Hanhua Chen | 5 | 350 | 37.92 |
Xiaoming Ning | 6 | 5 | 0.88 |