By Topic

M-Ring: A Distributed, Self-Organized, Load-Balanced Communication Method on Super Peer Network

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

4 Author(s)
Tsung-Han Lin ; Dept. of Comput. Sci., Nat. Tsing-Hua Univ., Hsinchu ; Tsung-Hsuan Ho ; Yu-Wei Chan ; Yeh-Ching Chung

Many peer-to-peer file sharing systems have been proposed to take the locality and heterogeneity into account. The two-layered architecture is one of the most widespread systems with abilities by classifying peers into groups and serving some powerful peers as the super peers. In order to communicate with other sets of super peers, each super peer has to connect with all the other super peers within its neighboring group or other groups by some gateway-like super peers. However, it may be the problem of the single-point-of-failure if using peers as the gateway-like peers. In this paper, we propose a distributed, self-organized and load-balanced communication method - M-Ring. In this method, each super peer connects with other sets of super peers within its neighboring group by constructing its link table. Also, each super peer in the different groups has a unique identity within the same identity space. Besides, we notice a "overlap handle scope" feature while all super peers who are in the different groups are in the same identity space. We use this feature to enhance the efficiency of query of super peers. Our method can reduce the total requirements of storage space and bandwidth by storing different portion of metadata. The simulation results show that our approach efficiently reduces the overhead of connections among super peers within their neighboring groups.

Published in:

Parallel Architectures, Algorithms, and Networks, 2008. I-SPAN 2008. International Symposium on

Date of Conference:

7-9 May 2008