jPhase: an object-oriented tool for modeling phase-type distributions

  title={jPhase: an object-oriented tool for modeling phase-type distributions},
  author={Juan F. P{\'e}rez and Germ{\'a}n Ria{\~n}o},
  booktitle={SMCtools '06},
Phase-Type distributions are a powerful tool in stochastic modeling of real systems. In this paper, we describe an object-oriented tool used to represent and manipulate these distributions as computational objects. It allows the computation of multiple closure properties that can be used when modeling large systems with multiple interactions. The tool also includes procedures for fitting the parameter of a distribution from a data set and capabilities for generating random numbers from a… 

Figures and Tables from this paper

jMarkov: an object-oriented framework for modeling and analyzing Markov chains and QBDs

This paper describes jMarkov, an object-oriented framework designed to facilitate the construction and analysis of large-scale Markov Chains. The object-oriented design allows a natural translation

PHASE: A Stochastic Formalism for Phase-Type Distributions

A stochastic process calculus named PHASE is introduced which operates with phase-type distributions, and a step-by-step description of how PHASE processes can be translated into models supported by the probabilistic model checker PRISM is provided.

Algorithm 972

Markov chains (MC) are a powerful tool for modeling complex stochastic systems. Whereas a number of tools exist for solving different types of MC models, the first step in MC modeling is to define

HyperStar: Phase-Type Fitting Made Easy

HyperStar is presented, an extensible tool with a graphical user-interface that enables simple and efficient fitting of phase-type distributions to data sets and can be optimised using intuitive graphical selection of important features of the density.

Cluster-based fitting of phase-type distributions to empirical data

Formal Methods Laboratory Romanian Academy FML Technical Report TR no . FML-1401 Printed : June 2014 Phase-Type Approximations for Non-Markovian Systems

We introduce a novel stochastic process algebra, called PHASE, which directly supports phase-type distributions, useful for approximating the dynamics of non-Markovian HCI systems. In order to

mapfit: An R-Based Tool for PH/MAP Parameter Estimation

A tool for estimating parameters of phase-type distribution PH and Markovian arrival process MAP on the statistical analysis package R to reduce non-Markovian models to continuous-time Markov chains CTMCs that can be solved by analytical approaches.

On capturing dependence in point processes : Matching moments and other techniques

Providing probabilistic analysis of queueing models can be difficult when the input distributions are non-Markovian. In response, a plethora of methods have been developed to approximate a general

Generalizations of the ‘Linear Chain Trick’: incorporating more flexible dwell time distributions into mean field ODE models

Analytical results are provided that enable modelers to more efficiently construct ODE models using the LCT or related extensions and formulations of these LCT extensions that bypass the need to derive ODEs from integral equations are provided.

Assessing the Impact of Concurrent Replication with Canceling in Parallel Jobs

  • Z. QiuJuan F. Pérez
  • Computer Science
    2014 IEEE 22nd International Symposium on Modelling, Analysis & Simulation of Computer and Telecommunication Systems
  • 2014
This paper proposes a stochastic model that explicitly considers parallel job processing, replication at both the job and the task level, and handles general arrival processes, and develops a numerically-efficient algorithm to solve large-scale instances of the model and compute key performance metrics.



jMarkov: an object-oriented framework for modeling and analyzing Markov chains and QBDs

This paper describes jMarkov, an object-oriented framework designed to facilitate the construction and analysis of large-scale Markov Chains. The object-oriented design allows a natural translation

Matching Three Moments with Minimal Acyclic Phase Type Distributions

Abstract A number of approximate analysis techniques are based on matching moments of continuous time phase type (PH) distributions. This paper presents an explicit method to compose minimal order

An EM-based technique for approximating long-tailed data sets with PH distributions

Efficient fitting of long-tailed data sets into hyperexponential distributions

A new technique for fitting long-tailed data sets into hyperexponential distributions that allows one to apply existing analytic tools to analyze the behavior of queueing systems that operate under workloads that exhibit long-tail behavior, such as queues in Internet-related systems.

Generating random variates from a distribution of phase type

An algorithm for generating phase type random variates is presented because the exponential sojourn times allow us to record only the number of visits to each state before absorption and then generate appropriate Erlang-k random Variates.

Acyclic discrete phase type distributions: properties and a parameter estimation algorithm

A novel approach for fitting probability distributions to real trace data with the EM algorithm

A novel approach is presented that fits a restricted class of phase-type distributions, namely mixtures of Erlang distributions, to trace data and an algorithm of the expectation maximization type is developed, which yields phase- type approximations for a wide range of data traces that are as good or better than approximation computed with other less efficient and less stable fitting methods.

Matching moments to phase distributions: density function shapes

We study density-function shapes of distributions selected by phase-distribution-selection methods developed in Johnson and Taaffe [2, 3]. In Johnson and Taaffe [2], analytic results for matching

Necessary and Sufficient Conditions for Representing General Distributions by Coxians

This paper formally characterize the set of distributions G which are well-represented by an n-phase Coxian distribution, in the sense that the Coxian distributions matches the first three moments of G.