Towards Simple Models for Energy-Performance Trade-Offs in Data Centers

Boudewijn R.H.M. Haverkort, Björn Frits Postema

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    26 Downloads (Pure)

    Abstract

    In this paper we advocate the use of simple stochastic models to analyse the energy-performance trade-off in data centres. Recently such trade-offs have received increased attention, however, the tools used to make such trade-offs are largely based on simulation and real-life experiments. Although simulations studies are very helpful, we think that simple analytical models, or models based on stochastic Petri nets (or similar description techniques) can be very fruitful in guiding design processes in the early phases. Similarly, we do think that experimental work is very important, however, its results come "after the fact" in the sense that the system has been built already once the experiments are being performed. Our claim is that the use of simple models early in the design phase provides a very good return on investment. This short paper presents some preliminary models that can be used for early-in-design trade-off analyses.
    Original languageUndefined
    Title of host publicationMMB & DFT 2014 : Proceedings of the International Workshops SOCNET 2014 and FGENET 2014
    Place of PublicationBamberg
    PublisherUniversity of Bamberg Press
    Pages113-122
    Number of pages10
    ISBN (Print)978-3-86309-208-5
    Publication statusPublished - 19 Mar 2014

    Publication series

    NameSchriften aus der Fakultät Wirtschaftsinformatik und Angewandte Informatik der Otto-Friedrich-Universität Bamberg
    PublisherUniversity of Bamberg Press
    ISSN (Print)1867-7401

    Keywords

    • Performance
    • Stochastic Petri Nets
    • matrix-geometric methods
    • EWI-24676
    • IR-91065
    • Data centres
    • Energy
    • METIS-304073
    • Analytical models

    Cite this

    Haverkort, B. R. H. M., & Postema, B. F. (2014). Towards Simple Models for Energy-Performance Trade-Offs in Data Centers. In MMB & DFT 2014 : Proceedings of the International Workshops SOCNET 2014 and FGENET 2014 (pp. 113-122). (Schriften aus der Fakultät Wirtschaftsinformatik und Angewandte Informatik der Otto-Friedrich-Universität Bamberg). Bamberg: University of Bamberg Press.
    Haverkort, Boudewijn R.H.M. ; Postema, Björn Frits. / Towards Simple Models for Energy-Performance Trade-Offs in Data Centers. MMB & DFT 2014 : Proceedings of the International Workshops SOCNET 2014 and FGENET 2014. Bamberg : University of Bamberg Press, 2014. pp. 113-122 (Schriften aus der Fakultät Wirtschaftsinformatik und Angewandte Informatik der Otto-Friedrich-Universität Bamberg).
    @inproceedings{82eec08fe8ce4483a611a2941f716db2,
    title = "Towards Simple Models for Energy-Performance Trade-Offs in Data Centers",
    abstract = "In this paper we advocate the use of simple stochastic models to analyse the energy-performance trade-off in data centres. Recently such trade-offs have received increased attention, however, the tools used to make such trade-offs are largely based on simulation and real-life experiments. Although simulations studies are very helpful, we think that simple analytical models, or models based on stochastic Petri nets (or similar description techniques) can be very fruitful in guiding design processes in the early phases. Similarly, we do think that experimental work is very important, however, its results come {"}after the fact{"} in the sense that the system has been built already once the experiments are being performed. Our claim is that the use of simple models early in the design phase provides a very good return on investment. This short paper presents some preliminary models that can be used for early-in-design trade-off analyses.",
    keywords = "Performance, Stochastic Petri Nets, matrix-geometric methods, EWI-24676, IR-91065, Data centres, Energy, METIS-304073, Analytical models",
    author = "Haverkort, {Boudewijn R.H.M.} and Postema, {Bj{\"o}rn Frits}",
    year = "2014",
    month = "3",
    day = "19",
    language = "Undefined",
    isbn = "978-3-86309-208-5",
    series = "Schriften aus der Fakult{\"a}t Wirtschaftsinformatik und Angewandte Informatik der Otto-Friedrich-Universit{\"a}t Bamberg",
    publisher = "University of Bamberg Press",
    pages = "113--122",
    booktitle = "MMB & DFT 2014 : Proceedings of the International Workshops SOCNET 2014 and FGENET 2014",

    }

    Haverkort, BRHM & Postema, BF 2014, Towards Simple Models for Energy-Performance Trade-Offs in Data Centers. in MMB & DFT 2014 : Proceedings of the International Workshops SOCNET 2014 and FGENET 2014. Schriften aus der Fakultät Wirtschaftsinformatik und Angewandte Informatik der Otto-Friedrich-Universität Bamberg, University of Bamberg Press, Bamberg, pp. 113-122.

    Towards Simple Models for Energy-Performance Trade-Offs in Data Centers. / Haverkort, Boudewijn R.H.M.; Postema, Björn Frits.

    MMB & DFT 2014 : Proceedings of the International Workshops SOCNET 2014 and FGENET 2014. Bamberg : University of Bamberg Press, 2014. p. 113-122 (Schriften aus der Fakultät Wirtschaftsinformatik und Angewandte Informatik der Otto-Friedrich-Universität Bamberg).

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    TY - GEN

    T1 - Towards Simple Models for Energy-Performance Trade-Offs in Data Centers

    AU - Haverkort, Boudewijn R.H.M.

    AU - Postema, Björn Frits

    PY - 2014/3/19

    Y1 - 2014/3/19

    N2 - In this paper we advocate the use of simple stochastic models to analyse the energy-performance trade-off in data centres. Recently such trade-offs have received increased attention, however, the tools used to make such trade-offs are largely based on simulation and real-life experiments. Although simulations studies are very helpful, we think that simple analytical models, or models based on stochastic Petri nets (or similar description techniques) can be very fruitful in guiding design processes in the early phases. Similarly, we do think that experimental work is very important, however, its results come "after the fact" in the sense that the system has been built already once the experiments are being performed. Our claim is that the use of simple models early in the design phase provides a very good return on investment. This short paper presents some preliminary models that can be used for early-in-design trade-off analyses.

    AB - In this paper we advocate the use of simple stochastic models to analyse the energy-performance trade-off in data centres. Recently such trade-offs have received increased attention, however, the tools used to make such trade-offs are largely based on simulation and real-life experiments. Although simulations studies are very helpful, we think that simple analytical models, or models based on stochastic Petri nets (or similar description techniques) can be very fruitful in guiding design processes in the early phases. Similarly, we do think that experimental work is very important, however, its results come "after the fact" in the sense that the system has been built already once the experiments are being performed. Our claim is that the use of simple models early in the design phase provides a very good return on investment. This short paper presents some preliminary models that can be used for early-in-design trade-off analyses.

    KW - Performance

    KW - Stochastic Petri Nets

    KW - matrix-geometric methods

    KW - EWI-24676

    KW - IR-91065

    KW - Data centres

    KW - Energy

    KW - METIS-304073

    KW - Analytical models

    M3 - Conference contribution

    SN - 978-3-86309-208-5

    T3 - Schriften aus der Fakultät Wirtschaftsinformatik und Angewandte Informatik der Otto-Friedrich-Universität Bamberg

    SP - 113

    EP - 122

    BT - MMB & DFT 2014 : Proceedings of the International Workshops SOCNET 2014 and FGENET 2014

    PB - University of Bamberg Press

    CY - Bamberg

    ER -

    Haverkort BRHM, Postema BF. Towards Simple Models for Energy-Performance Trade-Offs in Data Centers. In MMB & DFT 2014 : Proceedings of the International Workshops SOCNET 2014 and FGENET 2014. Bamberg: University of Bamberg Press. 2014. p. 113-122. (Schriften aus der Fakultät Wirtschaftsinformatik und Angewandte Informatik der Otto-Friedrich-Universität Bamberg).