DocumentCode
1967684
Title
Replacement policies for super-peer in unstructured P2P network
Author
Min, Soohong ; Holliday, JoAnne
Author_Institution
Dept. of Comput. Eng., Santa Clara Univ., Santa Clara, CA, USA
fYear
2009
fDate
14-16 Sept. 2009
Firstpage
715
Lastpage
720
Abstract
For the last few years, there has been a large volume of research on peer-to-peer (P2P) systems, resulting in many hybrid P2P models. In the hybrid model, all P2P overlay traffic will be routed via the SP. In this model, the SP selection and replacement are important to accomplishing high scalability and reliable service in P2P network. Main purpose of this paper is to provide highly available SP (super-peer) by reducing the replacement of SPs in the network. In this paper, we present a variety of replacement policies and discuss replacement of SPs in a P2P system. We manage SPs by dividing the selected group and the candidate SP group and use a lazy replacement concept to distinguish SP´s status between unavailable and available. Finally, we choose new SPs using proposed replacement policies. Through experiments, we can provide the reliable SP by reducing the number of replacements using a timeout value and presented replacement policy. Also, we can improve the resilience of the system by improving the availability of SPs selected by OPs (ordinary-peer). Finally, we present the points to be considered for analysis of past behavior of peers and discuss which factors affect the performance of the system.
Keywords
peer-to-peer computing; telecommunication traffic; ordinary-peer; peer-to-peer systems; replacement policies; super-peer; unstructured P2P network; Availability; Computer networks; Costs; Peer to peer computing; Performance analysis; Query processing; Resilience; Scalability; Telecommunication traffic; Traffic control; Lifetime; Peer-to-Peer; Replacement; Super-Peer;
fLanguage
English
Publisher
ieee
Conference_Titel
Computer and Information Sciences, 2009. ISCIS 2009. 24th International Symposium on
Conference_Location
Guzelyurt
Print_ISBN
978-1-4244-5021-3
Electronic_ISBN
978-1-4244-5023-7
Type
conf
DOI
10.1109/ISCIS.2009.5291911
Filename
5291911
Link To Document