By Topic

The Study of How to Reduce the Content Delivery Time and the System Load in P2P System

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
$33 $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)
Aya Takekawa ; R&D Center, Nippon Telegraph & Telephone West Corp., Osaka, Japan ; Naohiko Imaeda ; Hiroyuki Tanaka ; Tsuyoshi Kitagawa

In recent years, large-volume contents have delivery has been growing, so network traffic and content delivery time has increased. To solve the problem, Peer to Peer technology has been on the rise in content delivery systems. In addition, P4P system, which can tell a peer its adequate upload peers so as to reduce network traffic and to accelerate the content delivery speed, has been coming to the forefront. However, existing P4P systems have a problem that they cannot notify delivery routes minutely and accurately e.g. in units of routers or of peers. Therefore the hop counts between a download peer and an upload peer is not sufficiently reduced, then the network traffic is not satisfactorily decreased. For details, some existing P4P systems cannot satisfactorily reduce the hop counts, and the other existing P4P method which can reduce the hop counts has a restriction that IP addresses must be hierarchically assigned. To solve the problem, we propose a new P4P method reducing hop counts, which is free from the restriction. For this purpose, we use network structure information to search the hop counts, and utilize the hint server to manage the information. We evaluated the effect of our system by experiments in the lab. As a result, our method gives the best performance on the network traffic and the content delivery time among the existing methods. Additionally, we found that decreasing the hop count reduces the network traffic and the content delivery time. We researched the causes that the content delivery time is reduced by reduction of the hop counts. The most probable cause is the load balance of upload peers by decreasing the hop counts.

Published in:

Complex, Intelligent and Software Intensive Systems (CISIS), 2010 International Conference on

Date of Conference:

15-18 Feb. 2010