An Effective Training Pattern Processing Method for ATM Connection Admission Control Using the Neural Network 


Vol. 9,  No. 2, pp. 173-180, Apr.  2002
10.3745/KIPSTB.2002.9.2.173


PDF
  Abstract

The virtual cell loss rate was introduced for the training pattern of the neural network in the VOB(Virtual Output Buffer) model. The VOB model shows that the neural network can find the connection admisson boundary without the real cell loss rate. But the VOB model tends to overestimate the cell loss rate, so the utilization of network is low. In this paper, we uses the reference curve of the cell loss rate, which contains the information about the cell loss rate at the connection admission boundary. We process the patterns of the virtual cell loss rate using the reference curve. We performed the simulation with two major ATM traffic classes. One is On-Off traffic class that has the traffic characteristic of LAN data and the other is Auto-Regressive traffic class that has the traffic characteristic of a video image communication.

  Statistics
  Cite this article

[IEEE Style]

O. J. Kwon, H. G. Jeon, S. K. Kwon, T. S. Kim, J. B. Lee, "An Effective Training Pattern Processing Method for ATM Connection Admission Control Using the Neural Network," The KIPS Transactions:PartB , vol. 9, no. 2, pp. 173-180, 2002. DOI: 10.3745/KIPSTB.2002.9.2.173.

[ACM Style]

Oh Jun Kwon, Hyoung Goo Jeon, Soon Kak Kwon, Tai Suk Kim, and Jeong Bae Lee. 2002. An Effective Training Pattern Processing Method for ATM Connection Admission Control Using the Neural Network. The KIPS Transactions:PartB , 9, 2, (2002), 173-180. DOI: 10.3745/KIPSTB.2002.9.2.173.

Forms

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)

Old Journals

Indexing

All publications of TKIPS is indexed in DOI, EBSCO, Google Scholar, Crossref, and CrossCheck.

TKIPS is also selected as the Journal for Accreditation by NRF (National Research Foundation of Korea).

Related Journals