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

Author

Dixon, Michael W. ; Cole, Graeme R. ; Bellgard, Matthew I.

Author_Institution

Sch. of Math. & Phys. Sci., Murdoch Univ., WA, Australia

Volume

3

fYear

1995

fDate

18-22 Jun 1995

Firstpage

1602

Abstract

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

Keywords

Hopfield neural nets; packet switching; telecommunication network routing; Hopfield neural network; computer simulations; energy function; mean field annealing; near-optimal valid routes; network routing; neural network algorithm; optimal valid routes; origin-destination pairs; packet switched communication networks; shortest path algorithm; Annealing; Communication networks; Computational modeling; Computer architecture; Computer science; Computer simulation; Hopfield neural networks; Intelligent networks; Neural networks; Routing;

fLanguage

English

Publisher

ieee

Conference_Titel

Communications, 1995. ICC '95 Seattle, 'Gateway to Globalization', 1995 IEEE International Conference on

Conference_Location

Seattle, WA

Print_ISBN

0-7803-2486-2

Type

conf

DOI

10.1109/ICC.1995.524472

Filename

524472