Sprungmarken

Servicenavigation

Hauptnavigation

Sie sind hier:

Hauptinhalt

Publications

PH and MAP Fitting with Aggregated Traffic Traces

Jan Kriege, Peter Buchholz

Proc. of the 17th International GI/ITG Conference on Measurement, Modelling and Evaluation of Computing Systems and Dependability and Fault Tolerance (MMB & DFT 2014), Springer, 2014.

 

Abstract

Phase Type Distributions (PHDs) and Markovian Arrival Processes (MAPs) are versatile models for the modeling of timing behavior in stochastic models. The parameterization of the models according to measured traces is often done using Expectation Maximization (EM) algorithms, which have long runtimes when applied to realistic datasets. In this paper, new versions of EM algorithms are presented that use only an aggregated version of the trace. Experiments show that these realizations of EM algorithms are much more efficient than available EM algorithms working on the complete trace and the fitting quality remains more or less the same.

 

Keywords
Phase-type distributions, Markovian Arrival Processes, Expectation Maximization Algorithm, Trace Aggregation

 

BibTeX
@incollection{KBu14, 
	 author = {Jan Kriege and Peter Buchholz}, 
	 title = {{PH and MAP Fitting with Aggregated Traffic Traces}}, 
	 Booktitle = {Proceedings of the 17th International GI/ITG Conference on Measurement,  
		 Modelling and Evaluation of Computing Systems and Dependability and Fault Tolerance (MMB \& DFT 2014)}, 
	 year = {2014}, 
	 isbn = {978-3-319-05358-5}, 
	 series = {Lecture Notes in Computer Science}, 
	 volume = {8376}, 
	 editor = {Fischbach, Kai and Krieger, Udo R.}, 
	 doi = {10.1007/978-3-319-05359-2_1}, 
	 url = {http://dx.doi.org/10.1007/978-3-319-05359-2_1}, 
	 publisher={Springer}, 
	 pages = {1-15} 
}

 

Links