A neural network approach for routing in computer networks

Author

Pierre, Samuel ; Said, Hassane ; Probst, Wilfried G.

Author_Institution

LICEF Res. Center, Quebec Univ., Montreal, Que., Canada

Volume

2

fYear

1998

fDate

24-28 May 1998

Firstpage

826

Abstract

This paper presents a new approach based on artificial neural networks to solve the routing problem in a context of computer network design. This approach is based on a network representation enabling one to match each network configuration with a Hopfield (1984) neural network in order to find the best path between any node pair by minimizing an energy function. It is suitable to be integrated into an overall topological design process of moderate-speed and high-speed networks subject to quality of service constraints as well as to changes in configuration and link costs

Keywords

Hopfield neural nets; computer networks; network topology; packet switching; telecommunication computing; telecommunication network routing; Hopfield neural network; artificial neural networks; computer network design; computer networks routing; configuration costs; energy function minimisation; high-speed networks; link costs; moderate-speed networks; network configuration; network nodes; packet switching network; quality of service constraints; routing problem solution; topological design; Algorithm design and analysis; Artificial neural networks; Clocks; Computer networks; Hopfield neural networks; Informatics; Intelligent networks; Neural networks; Neurons; Routing;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical and Computer Engineering, 1998. IEEE Canadian Conference on

Conference_Location

Waterloo, Ont.

ISSN

0840-7789

Print_ISBN

0-7803-4314-X

Type

conf

DOI

10.1109/CCECE.1998.685625

Filename

685625