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

This paper presents a Hopfield (1986) neural network that solves the routing problem in 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 sim...

Full description

Saved in:
Bibliographic Details
Published inProceedings IEEE International Conference on Communications ICC '95 Vol. 3; pp. 1602 - 1606 vol.3
Main Authors Dixon, M.W., Cole, G.R., Bellgard, M.I.
Format Conference Proceeding
LanguageEnglish
Published IEEE 1995
Subjects
Annealing
Communication networks
Computational modeling
Computer architecture
Computer science
Computer simulation
Hopfield neural networks
Intelligent networks
Neural networks
Routing
Online AccessGet full text

Cover

More Information
Summary:This paper presents a Hopfield (1986) neural network that solves the routing problem in 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.
ISBN:0780324862
9780780324862
DOI:10.1109/ICC.1995.524472