By Topic

A New Congestion Control Model Based on Fuzzy Neural Networks

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)
Lixiang-Liu ; Inst. of Software, Chinese Acad. of Sci., Beijing ; Junsuo-Zhao ; Wenjun-Zhang ; Fanjiang-Xu

In this paper, a new congestion control model based on fuzzy neural networks (FNNs) is proposed for P2P network, which considers the practical status of data buffer and P2P traffic. The proposed model divides buffer into two queues which store P2P data packets and non-P2P data packets respectively. It predicts and evaluates conditions of buffer queues through FNN, and directs space allocation of each queue through constructing an evaluation function. Thus, this model is able to control congestion condition of each queue and resize allocation of queues in the buffer automatically, and then it can avoid lock-out of the buffer by dropping packets actively before the buffer is overflow. Simulation results show the model is good both ensuring equitable network resource allocation and decreasing the delay of packet queuing and the dropping ratio, thus improving the ability of routers in dealing with network congestion

Published in:

Computational Engineering in Systems Applications, IMACS Multiconference on  (Volume:1 )

Date of Conference:

4-6 Oct. 2006