Mean field calculation for optical grid dimensioning

Benny Van Houdt, Chris Develder, Juan F. Pérez, Mario Pickavet, Bart Dhoedt

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

For traditional optical network dimensioning, a plethora of algorithms exists to design the amount of network resources required to accommodate a given amount of traffic, expressed as a (source, destination)-based traffic matrix. In optical Grid dimensioning, however, the anycast principle applies: Grid users do not really care where exactly their tasks (Grid jobs) end up being executed. Thus, the destination of traffic is not known beforehand and traditional dimensioning algorithms are not applicable. In this paper we propose a mean field calculation method to analytically derive the traffic matrix for given job arrival intensities at the originating Grid sites (the sources). We also indicate how it can be integrated in a stepwise dimensioning approach to compute not only the amount of network resources, but also Grid resources (computational and/or storage). Hence it forms part of a solution for Grid dimensioning: determining how many servers to provide, where to place them, and which network to install for interconnecting server sites and users generating Grid jobs.

Original languageEnglish (US)
Article number5465052
Pages (from-to)355-367
Number of pages13
JournalJournal of Optical Communications and Networking
Volume2
Issue number6
DOIs
StatePublished - Jun 1 2010
Externally publishedYes

Fingerprint

Servers
Fiber optic networks

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications

Cite this

Van Houdt, Benny ; Develder, Chris ; Pérez, Juan F. ; Pickavet, Mario ; Dhoedt, Bart. / Mean field calculation for optical grid dimensioning. In: Journal of Optical Communications and Networking. 2010 ; Vol. 2, No. 6. pp. 355-367.
@article{01723d38b6dc4c78bc763088ee0a603f,
title = "Mean field calculation for optical grid dimensioning",
abstract = "For traditional optical network dimensioning, a plethora of algorithms exists to design the amount of network resources required to accommodate a given amount of traffic, expressed as a (source, destination)-based traffic matrix. In optical Grid dimensioning, however, the anycast principle applies: Grid users do not really care where exactly their tasks (Grid jobs) end up being executed. Thus, the destination of traffic is not known beforehand and traditional dimensioning algorithms are not applicable. In this paper we propose a mean field calculation method to analytically derive the traffic matrix for given job arrival intensities at the originating Grid sites (the sources). We also indicate how it can be integrated in a stepwise dimensioning approach to compute not only the amount of network resources, but also Grid resources (computational and/or storage). Hence it forms part of a solution for Grid dimensioning: determining how many servers to provide, where to place them, and which network to install for interconnecting server sites and users generating Grid jobs.",
author = "{Van Houdt}, Benny and Chris Develder and P{\'e}rez, {Juan F.} and Mario Pickavet and Bart Dhoedt",
year = "2010",
month = "6",
day = "1",
doi = "10.1364/JOCN.2.000355",
language = "English (US)",
volume = "2",
pages = "355--367",
journal = "Journal of Optical Communications and Networking",
issn = "1943-0620",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "6",

}

Van Houdt, B, Develder, C, Pérez, JF, Pickavet, M & Dhoedt, B 2010, 'Mean field calculation for optical grid dimensioning', Journal of Optical Communications and Networking, vol. 2, no. 6, 5465052, pp. 355-367. https://doi.org/10.1364/JOCN.2.000355

Mean field calculation for optical grid dimensioning. / Van Houdt, Benny; Develder, Chris; Pérez, Juan F.; Pickavet, Mario; Dhoedt, Bart.

In: Journal of Optical Communications and Networking, Vol. 2, No. 6, 5465052, 01.06.2010, p. 355-367.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Mean field calculation for optical grid dimensioning

AU - Van Houdt, Benny

AU - Develder, Chris

AU - Pérez, Juan F.

AU - Pickavet, Mario

AU - Dhoedt, Bart

PY - 2010/6/1

Y1 - 2010/6/1

N2 - For traditional optical network dimensioning, a plethora of algorithms exists to design the amount of network resources required to accommodate a given amount of traffic, expressed as a (source, destination)-based traffic matrix. In optical Grid dimensioning, however, the anycast principle applies: Grid users do not really care where exactly their tasks (Grid jobs) end up being executed. Thus, the destination of traffic is not known beforehand and traditional dimensioning algorithms are not applicable. In this paper we propose a mean field calculation method to analytically derive the traffic matrix for given job arrival intensities at the originating Grid sites (the sources). We also indicate how it can be integrated in a stepwise dimensioning approach to compute not only the amount of network resources, but also Grid resources (computational and/or storage). Hence it forms part of a solution for Grid dimensioning: determining how many servers to provide, where to place them, and which network to install for interconnecting server sites and users generating Grid jobs.

AB - For traditional optical network dimensioning, a plethora of algorithms exists to design the amount of network resources required to accommodate a given amount of traffic, expressed as a (source, destination)-based traffic matrix. In optical Grid dimensioning, however, the anycast principle applies: Grid users do not really care where exactly their tasks (Grid jobs) end up being executed. Thus, the destination of traffic is not known beforehand and traditional dimensioning algorithms are not applicable. In this paper we propose a mean field calculation method to analytically derive the traffic matrix for given job arrival intensities at the originating Grid sites (the sources). We also indicate how it can be integrated in a stepwise dimensioning approach to compute not only the amount of network resources, but also Grid resources (computational and/or storage). Hence it forms part of a solution for Grid dimensioning: determining how many servers to provide, where to place them, and which network to install for interconnecting server sites and users generating Grid jobs.

UR - http://www.scopus.com/inward/record.url?scp=77953690371&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77953690371&partnerID=8YFLogxK

U2 - 10.1364/JOCN.2.000355

DO - 10.1364/JOCN.2.000355

M3 - Article

AN - SCOPUS:77953690371

VL - 2

SP - 355

EP - 367

JO - Journal of Optical Communications and Networking

JF - Journal of Optical Communications and Networking

SN - 1943-0620

IS - 6

M1 - 5465052

ER -