XMGM: performance modeling using matrix geometric techniques

Boudewijn R.H.M. Haverkort; Aad P.A. van Moorsel; Dirk-Jan Speelman

doi:10.1109/MASCOT.1994.284430

XMGM: performance modeling using matrix geometric techniques

Boudewijn R.H.M. Haverkort, Aad P.A. van Moorsel, Dirk-Jan Speelman

Research output: Contribution to conference › Paper

6 Citations (Scopus)

354 Downloads (Pure)

Abstract

Over the last two decades a considerable amount of effort has been put in the development and application of matrix geometric techniques for the analysis of queueing systems of which the (embedded) Markov chain exhibits a regular structure. Most of this work however has been presented in either a mathematical context or an a purely application-oriented context. In this paper we present XMGM, a performance analysis tool which allows its users to easily specify queueing systems in terms of interarrival and service time distributions. XMGM then takes care of the translation of this description to an underlying Markov chain that exhibits a matrix geometric solution. Subsequently, it takes care of the derivation of the measures specified by the user. With XMGM models are specified via C procedure calls. This turns out to be a very flexible approach for modelling queueing systems; it also allows for the easy evaluation of models over parameter ranges

Original language	English
Pages	152-157
DOIs	https://doi.org/10.1109/MASCOT.1994.284430
Publication status	Published - 1994
Event	2nd International Workshop on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, MASCOTS 1994 - Durham, United States Duration: 31 Jan 1994 → 2 Feb 1994 Conference number: 2

Workshop

Workshop	2nd International Workshop on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, MASCOTS 1994
Abbreviated title	MASCOTS
Country/Territory	United States
City	Durham
Period	31/01/94 → 2/02/94

Keywords

IR-56051

Access to Document

10.1109/MASCOT.1994.284430

00284430

Cite this

@conference{668df92b27e24f7da172d94a54d4557a,

title = "XMGM: performance modeling using matrix geometric techniques",

abstract = "Over the last two decades a considerable amount of effort has been put in the development and application of matrix geometric techniques for the analysis of queueing systems of which the (embedded) Markov chain exhibits a regular structure. Most of this work however has been presented in either a mathematical context or an a purely application-oriented context. In this paper we present XMGM, a performance analysis tool which allows its users to easily specify queueing systems in terms of interarrival and service time distributions. XMGM then takes care of the translation of this description to an underlying Markov chain that exhibits a matrix geometric solution. Subsequently, it takes care of the derivation of the measures specified by the user. With XMGM models are specified via C procedure calls. This turns out to be a very flexible approach for modelling queueing systems; it also allows for the easy evaluation of models over parameter ranges",

keywords = "IR-56051",

author = "Haverkort, \{Boudewijn R.H.M.\} and \{van Moorsel\}, \{Aad P.A.\} and Dirk-Jan Speelman",

year = "1994",

doi = "10.1109/MASCOT.1994.284430",

language = "English",

pages = "152--157",

note = "2nd International Workshop on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, MASCOTS 1994, MASCOTS ; Conference date: 31-01-1994 Through 02-02-1994",

}

XMGM: performance modeling using matrix geometric techniques. / Haverkort, Boudewijn R.H.M.; van Moorsel, Aad P.A.; Speelman, Dirk-Jan.
1994. 152-157 Paper presented at 2nd International Workshop on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, MASCOTS 1994, Durham, North Carolina, United States.

Research output: Contribution to conference › Paper

TY - CONF

T1 - XMGM: performance modeling using matrix geometric techniques

AU - Haverkort, Boudewijn R.H.M.

AU - van Moorsel, Aad P.A.

AU - Speelman, Dirk-Jan

N1 - Conference code: 2

PY - 1994

Y1 - 1994

N2 - Over the last two decades a considerable amount of effort has been put in the development and application of matrix geometric techniques for the analysis of queueing systems of which the (embedded) Markov chain exhibits a regular structure. Most of this work however has been presented in either a mathematical context or an a purely application-oriented context. In this paper we present XMGM, a performance analysis tool which allows its users to easily specify queueing systems in terms of interarrival and service time distributions. XMGM then takes care of the translation of this description to an underlying Markov chain that exhibits a matrix geometric solution. Subsequently, it takes care of the derivation of the measures specified by the user. With XMGM models are specified via C procedure calls. This turns out to be a very flexible approach for modelling queueing systems; it also allows for the easy evaluation of models over parameter ranges

AB - Over the last two decades a considerable amount of effort has been put in the development and application of matrix geometric techniques for the analysis of queueing systems of which the (embedded) Markov chain exhibits a regular structure. Most of this work however has been presented in either a mathematical context or an a purely application-oriented context. In this paper we present XMGM, a performance analysis tool which allows its users to easily specify queueing systems in terms of interarrival and service time distributions. XMGM then takes care of the translation of this description to an underlying Markov chain that exhibits a matrix geometric solution. Subsequently, it takes care of the derivation of the measures specified by the user. With XMGM models are specified via C procedure calls. This turns out to be a very flexible approach for modelling queueing systems; it also allows for the easy evaluation of models over parameter ranges

KW - IR-56051

U2 - 10.1109/MASCOT.1994.284430

DO - 10.1109/MASCOT.1994.284430

M3 - Paper

SP - 152

EP - 157

T2 - 2nd International Workshop on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, MASCOTS 1994

Y2 - 31 January 1994 through 2 February 1994

ER -

XMGM: performance modeling using matrix geometric techniques

Abstract

Workshop

Keywords

Access to Document

Fingerprint

Cite this