10th EAI International Conference on Performance Evaluation Methodologies and Tools

Research Article

BuTools 2: a Rich Toolbox for Markovian Performance Evaluation

  • @INPROCEEDINGS{10.4108/eai.25-10-2016.2266400,
        author={Gabor Horvath and Miklos Telek},
        title={BuTools 2: a Rich Toolbox for Markovian Performance Evaluation},
        proceedings={10th EAI International Conference on Performance Evaluation Methodologies and Tools},
        publisher={ACM},
        proceedings_a={VALUETOOLS},
        year={2017},
        month={5},
        keywords={markovian performance analysis toolbox},
        doi={10.4108/eai.25-10-2016.2266400}
    }
    
  • Gabor Horvath
    Miklos Telek
    Year: 2017
    BuTools 2: a Rich Toolbox for Markovian Performance Evaluation
    VALUETOOLS
    ACM
    DOI: 10.4108/eai.25-10-2016.2266400
Gabor Horvath1,*, Miklos Telek2
  • 1: Budapest University of Technology and Economics
  • 2: MTA-BME Information Systems Research Group
*Contact email: ghorvath@hit.bme.hu

Abstract

BuTools 2 is collection of computational methods that are useful for Markovian and non-Markovian matrix analytic performance analysis. It consists of various packages. There are packages to obtain, analyze, transform and minimize discrete and continuous time phase-type (PH) distributions and Markovian arrival processes (MAP); to fit empirical measurement data and to evaluate the result; to solve many performance measures of various Markovian queueing systems; and to solve block-structured Markov chains. All three major mathematical frameworks are supported: BuTools is released for MATLAB, Mathematica and NumPy/IPython as well, with the same features, with the same call interfaces. Every function is documented, the documentation is supplemented by many examples and the related citations. BuTools uses the state-of-the art algorithms and apart of the basic functionalities it contains several unique, difficult to implement procedures as well.