NCTM - SLIIT 2012 >

Please use this identifier to cite or link to this item:

Title: Optimization of Adaptive Routing Algorithm for Cognitive Packet Network Infrastructure Based on Neural Networks
Authors: Madubashitha, D.K.D.
Wijesinghe, W.M.S.S.
Kamaladiwela, K.A.S.R
Ranaweera, M.G.P.
Wijekoon, J.
Abeygunawardhana, P.K.W.
Keywords: Artificial intelligence
Neural Network
Reinforced Learning
Issue Date: Jan-2012
Publisher: SLIIT
Citation: NCTM 2012
Series/Report no.: SLIIT/LIB/;
Abstract: This paper examines the possibility of optimizing an intelligent routing protocol to the Internet, based on the cognitive packet network architecture with respect to the QoS (Quality of Service) delivered to the end users. The major reason for the initial introduction and subsequent improvements carried out in this research is the inability of current Internet infrastructure to cater the ever increasing Internet community and deliver the expected level of service to the end users. Because of this there is an eminent threat looming Internet becoming less productive. As a measure of countering this phenomenon the research team focuses on provide an improved routing algorithm which is an extension of the previously introduced algorithm based on the new & upcoming Cognitive Packet Network (CPN) network architecture which would improve the QoS, provide reliable and efficient service which can fulfill the ever growing Internet usage demand. CPN’s underlying technology will be a neural network which will be learning the changes in the network and adapt to the situation through the knowledge gathered. The packets travelling in the network collectively learns about the network thus the load on the routers will be minimized and it will completely replaces the need of a routing table which result in more efficient and reliable routing when compared to current routing protocols like Open Shortest Path First (OSPF). This research proves that the future of the Internet is with the neural network based intelligent, dynamically adapting and learning cognitive packet network infrastructure instead of current packet switched network.
ISSN: 1800-3591
Appears in Collections:NCTM - SLIIT 2012

Files in This Item:

File Description SizeFormat
View Statistics

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.


Valid XHTML 1.0! DSpace Software Copyright © 2002-2010  Duraspace - Feedback