DocumentCode :
2097853
Title :
Distributed Hot Spots Caching Mechanism for Queries with Popular Distribution
Author :
Chen, Jianyong ; Long, Haijian ; Liang, Leijuan
Author_Institution :
Coll. of Inf. Eng., Shenzhen Univ., Shenzhen, China
Volume :
2
fYear :
2008
fDate :
20-22 Dec. 2008
Firstpage :
418
Lastpage :
421
Abstract :
Peer-to-peer (P2P) systems have gained considerable attention in the past few years. Since the popularity distribution of queries follows a zipf-like distribution in a P2P network, the performance can get significant improvement if a simple and effective caching mechanism called hot spots caching mechanism (HSCM) is used, which stores the IP address and port number of the successor node of the key. Simulations also show that the HSCM is basically independent of particular P2P algorithms and can be easily combined with other improved methods to further improve the performance of P2P search capabilities.
Keywords :
IP networks; cache storage; file organisation; peer-to-peer computing; IP address; P2P network; distributed hash table; distributed hot spots caching mechanism; port number; zipf-like distribution; Computer science; Distributed computing; Educational institutions; Floods; Frequency; Gaussian distribution; Large-scale systems; Peer to peer computing; Telecommunication traffic; Web and internet services; Chord; Distributed Hash Table (DHT); Peer-to-peer (P2P);
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Science and Computational Technology, 2008. ISCSCT '08. International Symposium on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4244-3746-7
Type :
conf
DOI :
10.1109/ISCSCT.2008.110
Filename :
4731654
Link To Document :
بازگشت