DocumentCode
2385148
Title
A neural approach to performance evaluation for teletraffic system
Author
Okuda, Takashi ; Anthony, Manimaran ; Tadokoro, Yoshiaki
Author_Institution
Sch. of Bus. Adm., Asahi Univ., Gifu, Japan
fYear
1994
fDate
1-5 May 1994
Firstpage
774
Abstract
For traffic management of the ISDN and BISDN, it is necessary to evaluate the performance of the GI/G/s teletraffic system. The GI/G/s means s homogeneous parallel servers with general independent interarrival times and the general service times. We propose a method of performance evaluation for the GI/G/s by using a simple neural network. In order to train the network, the proposed method uses the parameters and corresponding exact values of well-known systems. Using the trained network, we can evaluate the performance of GI/G/s in a simple calculation
Keywords
ISDN; backpropagation; feedforward neural nets; multilayer perceptrons; performance evaluation; queueing theory; telecommunication network management; telecommunication traffic; BISDN; ISDN; back propagation algorithm; feed forward three layer network; general independent interarrival times; general service times; homogeneous parallel servers; performance evaluation; system parameters; teletraffic system; traffic management; trained network; Education; Feedforward neural networks; Feeds; ISDN; Impedance matching; Information processing; Neural networks; Telecommunication traffic; Testing; Traffic control;
fLanguage
English
Publisher
ieee
Conference_Titel
Communications, 1994. ICC '94, SUPERCOMM/ICC '94, Conference Record, 'Serving Humanity Through Communications.' IEEE International Conference on
Conference_Location
New Orleans, LA
Print_ISBN
0-7803-1825-0
Type
conf
DOI
10.1109/ICC.1994.368816
Filename
368816
Link To Document