Title :
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
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;
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
DOI :
10.1109/COMSIG.1997.629993
