IEICE TRANSACTIONS on Communications
Internet Traffic Modeling: Markovian Approach to Self-Similar Traffic and Prediction of Loss Probability for Finite Queues
Summary :
It has been reported that IP packet traffic exhibits the self-similar nature and causes the degradation of network performance. Therefore it is crucial for the appropriate buffer design of routers and switches to predict the queueing behavior with self-similar input. It is well known that the fitting methods based on the second-order statistics of counts for the arrival process are not sufficient for predicting the performance of the queueing system with self-similar input. However recent studies have revealed that the loss probability of finite queuing system can be well approximated by the Markovian input models. This paper studies the time-scale impact on the loss probability of MMPP/D/1/K system where the MMPP is generated so as to match the variance of the self-similar process over specified time-scales. We investigate the loss probability in terms of system size, Hurst parameters and time-scales. We also compare the loss probability of resulting MMPP/D/1/K with simulation. Numerical results show that the loss probability of MMPP/D/1/K are not significantly affected by time-scale and that the loss probability is well approximated with resulting MMPP/D/1/K.
- Publication
- IEICE TRANSACTIONS on Communications Vol.E84-B No.8 pp.2134-2141
- Publication Date
- 2001/08/01
- Publicized
- Online ISSN
- DOI
- Type of Manuscript
- Special Section PAPER (Special Issue on Internet Technology)
- Category
- Traffic Measurement and Analysis
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Shoji KASAHARA, "Internet Traffic Modeling: Markovian Approach to Self-Similar Traffic and Prediction of Loss Probability for Finite Queues" in IEICE TRANSACTIONS on Communications,
vol. E84-B, no. 8, pp. 2134-2141, August 2001, doi: .
Abstract: It has been reported that IP packet traffic exhibits the self-similar nature and causes the degradation of network performance. Therefore it is crucial for the appropriate buffer design of routers and switches to predict the queueing behavior with self-similar input. It is well known that the fitting methods based on the second-order statistics of counts for the arrival process are not sufficient for predicting the performance of the queueing system with self-similar input. However recent studies have revealed that the loss probability of finite queuing system can be well approximated by the Markovian input models. This paper studies the time-scale impact on the loss probability of MMPP/D/1/K system where the MMPP is generated so as to match the variance of the self-similar process over specified time-scales. We investigate the loss probability in terms of system size, Hurst parameters and time-scales. We also compare the loss probability of resulting MMPP/D/1/K with simulation. Numerical results show that the loss probability of MMPP/D/1/K are not significantly affected by time-scale and that the loss probability is well approximated with resulting MMPP/D/1/K.
URL: https://global.ieice.org/en_transactions/communications/10.1587/e84-b_8_2134/_p
Copy
@ARTICLE{e84-b_8_2134,
author={Shoji KASAHARA, },
journal={IEICE TRANSACTIONS on Communications},
title={Internet Traffic Modeling: Markovian Approach to Self-Similar Traffic and Prediction of Loss Probability for Finite Queues},
year={2001},
volume={E84-B},
number={8},
pages={2134-2141},
abstract={It has been reported that IP packet traffic exhibits the self-similar nature and causes the degradation of network performance. Therefore it is crucial for the appropriate buffer design of routers and switches to predict the queueing behavior with self-similar input. It is well known that the fitting methods based on the second-order statistics of counts for the arrival process are not sufficient for predicting the performance of the queueing system with self-similar input. However recent studies have revealed that the loss probability of finite queuing system can be well approximated by the Markovian input models. This paper studies the time-scale impact on the loss probability of MMPP/D/1/K system where the MMPP is generated so as to match the variance of the self-similar process over specified time-scales. We investigate the loss probability in terms of system size, Hurst parameters and time-scales. We also compare the loss probability of resulting MMPP/D/1/K with simulation. Numerical results show that the loss probability of MMPP/D/1/K are not significantly affected by time-scale and that the loss probability is well approximated with resulting MMPP/D/1/K.},
keywords={},
doi={},
ISSN={},
month={August},}
Copy
TY - JOUR
TI - Internet Traffic Modeling: Markovian Approach to Self-Similar Traffic and Prediction of Loss Probability for Finite Queues
T2 - IEICE TRANSACTIONS on Communications
SP - 2134
EP - 2141
AU - Shoji KASAHARA
PY - 2001
DO -
JO - IEICE TRANSACTIONS on Communications
SN -
VL - E84-B
IS - 8
JA - IEICE TRANSACTIONS on Communications
Y1 - August 2001
AB - It has been reported that IP packet traffic exhibits the self-similar nature and causes the degradation of network performance. Therefore it is crucial for the appropriate buffer design of routers and switches to predict the queueing behavior with self-similar input. It is well known that the fitting methods based on the second-order statistics of counts for the arrival process are not sufficient for predicting the performance of the queueing system with self-similar input. However recent studies have revealed that the loss probability of finite queuing system can be well approximated by the Markovian input models. This paper studies the time-scale impact on the loss probability of MMPP/D/1/K system where the MMPP is generated so as to match the variance of the self-similar process over specified time-scales. We investigate the loss probability in terms of system size, Hurst parameters and time-scales. We also compare the loss probability of resulting MMPP/D/1/K with simulation. Numerical results show that the loss probability of MMPP/D/1/K are not significantly affected by time-scale and that the loss probability is well approximated with resulting MMPP/D/1/K.
ER -
English
