ATM Connection Admission Control Using Traffic Parameters Compression


The KIPS Transactions:PartC, Vol. 8, No. 3, pp. 311-318, Jun. 2001
10.3745/KIPSTC.2001.8.3.311,   PDF Download:

Abstract

This paper proposes a connection admission control method based on the compression of traffic parameters. We evaluate and compare the performance of the proposed method according to typical compression methods, K-means, CL (Competitive Learning), Fuzzy ISODATA and FNC (Fuzzy Neural Clustering) algorithm. These algorithms are used to compress a number of traffic parameters (variance and mean of observed cell stream). The proposed CAC first estimates the characteristics of input traffic pattern using Fuzzy Mapping Function, and then it decides whether input traffic should be accepted or rejected, using a feedforward Neural Network. We simulate to compare the performance of connection admission control according to used compression methods. The simulation results show that the CAC using FNC algorithm outperforms other methods. To more improve CAC performance, we also found that, if variance of a frame is high, fuzziness value(F) should be small ; otherwise, if variance of a frame is low, fuzziness value should be large.


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]
J. Y. Lee, "ATM Connection Admission Control Using Traffic Parameters Compression," The KIPS Transactions:PartC, vol. 8, no. 3, pp. 311-318, 2001. DOI: 10.3745/KIPSTC.2001.8.3.311.

[ACM Style]
Jin Yi Lee. 2001. ATM Connection Admission Control Using Traffic Parameters Compression. The KIPS Transactions:PartC, 8, 3, (2001), 311-318. DOI: 10.3745/KIPSTC.2001.8.3.311.