The use of neural networks in ATM

Author

Kotze, N.J.H. ; Pauw, Christoff K.

Author_Institution

Dept. of Electr. & Electron. Eng., Pretoria Univ., South Africa

fYear

1997

fDate

9-10 Sep 1997

Firstpage

115

Lastpage

119

Abstract

This paper is an introduction to static flow control in ATM and the application of neural networks at the different levels of control. Network resource management, call admission control and rate based control form the three main levels of ATM flow control. The QoS (quality of service), which includes call-blocking probability, cell delay, cell delay variations, cell loss rate and allocated bandwidth is used as a measure of performance for these flow control functions

Keywords

asynchronous transfer mode; delays; neural nets; telecommunication computing; telecommunication congestion control; telecommunication network management; ATM networks; QoS; bandwidth allocation; call admission control; call-blocking probability; cell delay variations; cell delay,; cell loss rate; network resource management; neural networks; performance; quality of service; rate based control; static flow control; Circuits; Communication system traffic control; Fluid flow measurement; Intelligent networks; Loss measurement; Neural networks; Performance loss; Resource management; Routing; Shape control;

fLanguage

English

Publisher

ieee

Conference_Titel

Communications and Signal Processing, 1997. COMSIG '97., Proceedings of the 1997 South African Symposium on

Conference_Location

Grahamstown

Print_ISBN

0-7803-4173-2

Type

conf

DOI

10.1109/COMSIG.1997.629993

Filename

629993