Sung Ho Jin, Jae Hong Yim, Dong Il Kim

The KIPS Transactions:PartC, Vol. 8, No. 3, pp. 327-334, Jun. 2001
10.3745/KIPSTC.2001.8.3.327,   PDF Download:

Abstract

One of the most important matters in designing network and realizing service, is to grip on the traffic characteristics. However, we used the models which based on the Poisson or Markovian such as conventional traffic prediction and analysis. Recently, experimental research on the LAN, WAN and VBR traffic properties have been pointed out that they weren't able to display actual real traffic specificities because the models which based on the Poisson assumption had been underestimated the long range dependency of network traffic and self-similar peculiarities. Therefore, it has been lately presented that the new approach method using self-similarity characteristics as similar as the real traffic models. In this paper, we are going to discuss the definition of self-similarity traffic. Moreover, we collected the real traffics and applied to the queue on the ATM switch after compared artificial self-similarity traffics with the traffics which were applied Poisson model. So, we estimated the probability of buffer overflows on the low-bound and the cell losses in the case of appling the self-similarity traffic to the queue on the ATM switch.

Statistics
Cite this article