A Study on The Real-time Prediction of Traffic Flow in the ATM Network


The Transactions of the Korea Information Processing Society (1994 ~ 2000), Vol. 7, No. 10, pp. 3195-3200, Oct. 2000
10.3745/KIPSTE.2000.7.10.3195,   PDF Download:

Abstract

This paper is a study on the production of multi-media traffic flow for the realization of optimum ATM congestion control. In ATM network it is expected that the characteristic of multi-media traffic flow is varied slowly with a time. For the simulation, time-variable multi-media traffic is generated using poisson distribution(connect calls per process time), gamma distribution(transmission rate per a call) and exponential distribution(holding time per a call). And using back-propagation neural network and proposed tripple neural network, the simulation to predict generated traffic is executed. From the result, it`s capability is shown that the proposed neural network model can be used in the prediction of ATM traffic flow.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
Y. S. Kim and Y. O. Chin, "A Study on The Real-time Prediction of Traffic Flow in the ATM Network," The Transactions of the Korea Information Processing Society (1994 ~ 2000), vol. 7, no. 10, pp. 3195-3200, 2000. DOI: 10.3745/KIPSTE.2000.7.10.3195.

[ACM Style]
Yun Seok Kim and Yong Ohk Chin. 2000. A Study on The Real-time Prediction of Traffic Flow in the ATM Network. The Transactions of the Korea Information Processing Society (1994 ~ 2000), 7, 10, (2000), 3195-3200. DOI: 10.3745/KIPSTE.2000.7.10.3195.