Fitting Markovian Arrival Processes by Incorporating Correlation into Phase Type Renewal Processes

This paper presents a novel MAP fitting method. As many recent fitting methods, it is based on the separate fitting of the distribution of the inter-arrival times and the correlation structure of the arrival process. We assume that a Phase-type(PH) distribution representing the inter-arrival times is available. Our procedure obtains a MAP featuring the prescribed PH distributed inter-arrival times and capturing several correlation measures as accurately as possible. The correlation measures being used during the fitting are the joint moments of two inter-arrival times (including higher order ones). Contrary to other available MAP fitting methods, the proposed method does not only fit the lag-1, but also higher lag joint moments. The special MAP structure used for fitting enables to formulate the fitting problem as a non-negative least-squares problem for which efficient numerical implementations exist. Several numerical examples are presented to demonstrate that our method can be used in various practical applications.

[1]  Peter Buchholz,et al.  A novel approach for fitting probability distributions to real trace data with the EM algorithm , 2005, 2005 International Conference on Dependable Systems and Networks (DSN'05).

[2]  A. Horváth,et al.  Matching Three Moments with Minimal Acyclic Phase Type Distributions , 2005 .

[3]  Anja Feldmann,et al.  Fitting mixtures of exponentials to long-tail distributions to analyze network performance models , 1997, Proceedings of INFOCOM '97.

[4]  Peter Buchholz,et al.  A Two-Step EM Algorithm for MAP Fitting , 2004, ISCIS.

[5]  Charles L. Lawson,et al.  Solving least squares problems , 1976, Classics in applied mathematics.

[6]  R. Hanson.  On the constrained linear least-squares problem: a personal view , 1987 .

[7]  Peter Buchholz,et al.  An EM-Algorithm for MAP Fitting from Real Traffic Data , 2003, Computer Performance Evaluation / TOOLS.

[8]  Gábor Horváth,et al.  A minimal representation of Markov arrival processes and a moments matching method , 2007, Perform. Evaluation.

[9]  Miklós Telek,et al.  PhFit: A General Phase-Type Fitting Tool , 2002, Computer Performance Evaluation / TOOLS.

[10]  Gábor Horváth,et al.  On the canonical representation of phase type distributions , 2009, Perform. Evaluation.

[11]  F. Bause,et al.  Doubly Stochastic and Circulant Structured Markovian Arrival Processes , 2009 .

[12]  Ren Asmussen,et al.  Fitting Phase-type Distributions via the EM Algorithm , 1996 .

[13]  Peter Buchholz,et al.  A Heuristic Approach for Fitting MAPs to Moments and Joint Moments , 2009, 2009 Sixth International Conference on the Quantitative Evaluation of Systems.

[14]  Gábor Horváth,et al.  A Joint Moments Based Analysis of Networks of MAP/MAP/1 Queues , 2008, QEST.

[15]  Ramin Sadre,et al.  Fitting World Wide Web request traces with the EM-algorithim , 2001, SPIE ITCom.

[16]  Sally Floyd,et al.  Wide area traffic: the failure of Poisson modeling , 1995, TNET.

[17]  Vaidyanathan Ramaswami,et al.  Introduction to Matrix Analytic Methods in Stochastic Modeling , 1999, ASA-SIAM Series on Statistics and Applied Mathematics.

[18]  Peter Buchholz,et al.  A MAP fitting approach with independent approximation of the inter-arrival time distribution and the lag correlation , 2005, Second International Conference on the Quantitative Evaluation of Systems (QEST'05).

[19]  T. Rydén.  An EM algorithm for estimation in Markov-modulated Poisson processes , 1996 .