Logo image
A neural network shortest path algorithm for routing in packet-switched communication networks
Conference paper   Open access

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

M.W. Dixon, G.R. Cole and M.I. Bellgard
Proceedings IEEE International Conference on Communications ICC '95, Vol.3, pp.1602-1606
1995 International Conference on Communications (ICC '95): Gateway to Globalization (Seattle, Washington, USA, 18/06/1995–22/06/1995)
1995
pdf
neural_network_shortest_path.pdfDownloadView
Published (Version of Record) Open Access
url
Link to Published Version *Subscription may be requiredView

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.

Details

Metrics

189 File views/ downloads
112 Record Views
Logo image