Catalog Home Page

A neural network shortest path algorithm for routing in packet-switched communication networks

Dixon, M.W., Cole, G.R. and Bellgard, M.I. (1995) A neural network shortest path algorithm for routing in packet-switched communication networks. In: 1995 International Conference on Communications (ICC '95): Gateway to Globalization, 18 - 22 June 1995, Seattle, Washington, USA pp. 1602-1606.

[img]
Preview
PDF - Published Version
Download (417kB)
Link to Published Version: http://dx.doi.org/10.1109/ICC.1995.524472
*Subscription may be required

Abstract

This paper presents a Hopfield neural network that solves the routing problem in a communication network. It uses mean field annealing to eliminate the constraint terms in the energy function. Since there are no penalty parameters this approach should avoid the problems of scaling. Computer simulations of the neural network algorithm have shown that it can find optimal or near-optimal valid routes for all origin destination pairs in a fourteen node communication network.

Publication Type: Conference Paper
Murdoch Affiliation: School of Mathematical and Physical Sciences
URI: http://researchrepository.murdoch.edu.au/id/eprint/17456
Item Control Page Item Control Page

Downloads

Downloads per month over past year