An AnyLogic simulation model for power and performance analysis of data centres

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

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

    9 Citations (Scopus)
    2454 Downloads (Pure)

    Abstract

    In this paper we propose a simulation framework that allows for the analysis of power and performance trade-offs for data centres that save energy via power management. The models are cooperating discrete-event and agent-based models, which enable a variety of data centre configurations, including various infrastructural choices, workload models, (heterogeneous) servers and power management strategies. The capabilities of our modelling and simulation approach is shown with an example of a 200-server cluster. A validation that compares our results, for a restricted model with a previously published numerical model is also provided.
    Original languageUndefined
    Title of host publicationProceedings of the 12th European Workshop on Computer Performance Engineering, EPEW 2015
    EditorsMarta Beltrán, William Knottenbelt, Jeremy Bradley
    Place of PublicationSwitzerland
    PublisherSpringer
    Pages258-272
    Number of pages15
    ISBN (Print)978-3-319-23266-9
    DOIs
    Publication statusPublished - Aug 2015
    Event12th European Workshop on Computer Performance Engineering, EPEW 2015 - Madrid, Spain
    Duration: 31 Aug 20151 Sept 2015

    Publication series

    NameLecture Notes in Computer Science
    PublisherSpringer International Publishing
    Volume9272
    ISSN (Print)0302-9743
    ISSN (Electronic)1611-3349

    Conference

    Conference12th European Workshop on Computer Performance Engineering, EPEW 2015
    Period31/08/151/09/15
    Other31 August - 1 September 2015

    Keywords

    • EWI-26243
    • Steady state analysis
    • Performance analysis
    • Power Management
    • Power-performance trade-off
    • Data centres
    • METIS-314949
    • Transient analysis
    • Simulation
    • IR-98113
    • Cascading effect
    • Agent-based models
    • Discrete-event models

    Cite this