A hybrid neural expert system for traffic estimation and failure detection in communication networks

Author

Lo, Z.-P. ; Kang, C. ; Bavarian, B. ; Tan, H.

Author_Institution

Dept. of Electr. & Comput. Eng., California Univ., Irvine, CA, USA

fYear

1991

fDate

14-17 May 1991

Firstpage

541

Abstract

The authors address a novel methodology to estimate user traffic demand and to detect topological changes in a large-scale communication network by using a hybrid neural expert system. They develop a framework for hierarchical acquisition and estimation using multiple supervised learning neural network modules augmented in a distributed tree structure. Simulation results are presented, and possible future developments are discussed

Keywords

expert systems; learning systems; neural nets; telecommunication networks; telecommunication traffic; telecommunications computing; communication networks; distributed tree structure; failure detection; hierarchical acquisition; hybrid neural expert system; multiple supervised learning neural network modules; topological changes; traffic estimation; user traffic demand; Communication networks; Communication system traffic control; Computer networks; Expert systems; Intelligent networks; Large-scale systems; Neural networks; Routing; Telecommunication traffic; Traffic control;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1991., Proceedings of the 34th Midwest Symposium on

Conference_Location

Monterey, CA

Print_ISBN

0-7803-0620-1

Type

conf

DOI

10.1109/MWSCAS.1991.252104

Filename

252104