Traffic Modeling of IP Networks Using the Batch Markovian Arrival Process
- 595 Downloads
In this paper, we identify the batch Markovian arrival process (BMAP) as an analytically tractable model of choice for aggregated traffic modeling of IP networks. The key idea of this aggregated traffic model lies in customizing the batch Markovian arrival process such that the different lengths of IP packets are represented by rewards (i.e., batch sizes of arrivals) of the BMAP. The utilization of the BMAP is encouraged by the observation that IP packet lengths follow to a large extent a discrete distribution. A comparative study with the MMPP and the Poisson process illustrates the effectiveness of the customized BMAP for IP traffic modeling by visual inspection of sample paths over four different time-scales, by presenting important statistical properties, and by analysis of traffic burstiness using R/S statistics. Additionally, we show that the BMAP model outperforms MMPP and Poisson traffic models by comparison of queuing performance.
KeywordsPoisson Process Sample Path Batch Size Internet Service Provider Packet Length
Unable to display preview. Download preview PDF.
- 1.Andersson, S., Ryden, T.: Maximum Likelihood Estimation of a Structured MMPP with Applications to Traffic Modeling. Proc. 13th ITC Specialist Seminar on Measurement and Modeling of IP Traffic, Monterey CA (2000) 20.1–20.10Google Scholar
- 2.Ash, G.R.: Traffic Engineering & QoS Methods for IP-, ATM-, & TDM-Based Multiservice Networks. Internet Draft draft-ietf-tewg-qos-routing-01.txt (2001)Google Scholar
- 6.Kilpi, J., Norros, I.: Call Level Traffic Analysis of a Large ISP. Proc. 13th ITC Specialist Seminar on Measurement and Modeling of IP Traffic, Monterey CA (2000) 6.1–6.9Google Scholar
- 7.Kruse, H., Allman, M., Griner, J., Ostermann, S., Helvey, E.: Satellite Network Performance Measurements Using Simulated Multi-User Internet Traffic. Proc. 7th Int. Conf. on Telecommunication Systems (1999)Google Scholar
- 10.McCreary, S., Claffy K.C.: Trends in Wide Area IP Traffic Patterns: A View from Ames Internet Exchange. Proc. 13th ITC Specialist Seminar on Measurement and Modeling of IP Traffic, Monterey CA (2000) 1.1–1.12Google Scholar
- 11.Nuzman, C.J., Saniee, I., Sweldens, W., Weiss, A.: A Compound Model for TCP Connection Arrivals. Proc. 13th ITC Specialist Seminar on Measurement and Modeling of IP Traffic, Monterey CA (2000) 1–9Google Scholar
- 15.Willinger, W., Paxson, V., Taqqu, M.S.: Self-similarity and Heavy Tails: Structural Modeling of Network Traffic. In: A Practical Guide to Heavy Tails. Chapman & Hall (1998) 27–53Google Scholar