Abstract
In this paper we propose a two-step expectation-maximization (EM) algorithm to fit parameters of a Markovian arrival process (MAP) according to measured data traces. The first step of the EM algorithm performs fitting of the empirical distribution function to a phase type (PH) distribution, and the second step transforms the PH distribution into a MAP and modifies the MAP matrices to capture the autocovariance of the trace. In the first step of the algorithm a compact presentation of the distribution function is used and in the second step statistical properties of measured data traces are exploited to improve the efficiency of the algorithm. Numerical examples show that even compact MAP models yield relatively good approximations for the distribution function and the autocovariance.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
The internet traffic archive, http://ita.ee.lbl.gov/html/traces.html
Andersen, A.T.: Modelling of Packet Traffic With Matrix Analytic Methods. PhD thesis, Technical University of Denmark (1995)
Andersson, S.: Hidden Markov Models - traffic modeling and subspace methods. PhD thesis, Lund University, Centre for Mathematical Sciences (2002)
Asmussen, S., Nerman, O., Olsson, M.: Fitting phase type distributions via the EM algorithm. Scandinavian Journal of Statistics 23, 419–441 (1996)
Buchholz, P.: An EM-algorithm for MAP fitting from real traffic data. In: Kemper, P., Sanders, W.H. (eds.) TOOLS 2003. LNCS, vol. 2794, pp. 218–236. Springer, Heidelberg (2003)
Fox, B.L., Glynn, P.W.: Computing Poisson probabilities. Communications of the ACM 31(4), 440–445 (1988)
Klemm, A., Lindemann, C., Lohmann, M.: Modeling IP Traffic Using the Batch Markovian Arrival Process (extended version). Perf. Eval. 54, 149–173 (2003)
Mitchell, K., van de Liefvoort, A.: Approximation models of feed-forward G/G/1/N queueing networks with correlated arrivals. Performance Evaluation 51(1) (2003)
Neuts, M.F.: Structured Stochastic Matrices of M/G/1 Type and Their Applications. Marcel Dekker, Inc., New York (1989)
Nogueira, A., Salvador, P., Valadas, R., Pacheco, A.: A hierarchical approach based on MMPP’s for modelling self-similar traffic over multiple time scales. In: HET-NETs 2003 Technical Proceedings (2003)
Resnick, S.: Modeling data networks. Tr-1345, School of Operations Research and Industrial Engineering, Cornell University (August 2002)
Riska, A., Diev, V., Smirni, E.: An EM-based technique for approximating long-tailed data sets with ph distributions. Performance Evaluation 55, 147–164 (2004)
Ryden, T.: An EM algorithm for estimation in Markov-modulated Poisson processes. Computational Statistics and Data Analysis 21, 431–447 (1996)
Yoshihara, T., Kasahara, S., Takahashi, Y.: Practical Time-scale Fitting of Self-similar Traffic with MMPP. Telecommunication Systems 17, 185–211 (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Buchholz, P., Panchenko, A. (2004). A Two-Step EM Algorithm for MAP Fitting. In: Aykanat, C., Dayar, T., Körpeoğlu, İ. (eds) Computer and Information Sciences - ISCIS 2004. ISCIS 2004. Lecture Notes in Computer Science, vol 3280. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30182-0_23
Download citation
DOI: https://doi.org/10.1007/978-3-540-30182-0_23
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23526-2
Online ISBN: 978-3-540-30182-0
eBook Packages: Springer Book Archive