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

Björn Frits Postema, Boudewijn R.H.M. Haverkort, Marta Beltrán (Editor), William Knottenbelt, Jeremy Bradley (Editor)

Research output: Other contributionOther research output

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 languageEnglish
PublisherSpringer International Publishing AG
Number of pages15
Place of PublicationSwitzerland
ISBN (Print)978-3-319-23266-9
DOIs
Publication statusPublished - Aug 2015
Externally publishedYes

Fingerprint

Servers
Numerical models
Power management

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

Postema, B. F., Haverkort, B. R. H. M., Beltrán, M. (Ed.), Knottenbelt, W., & Bradley, J. (Ed.) (2015, Aug). An AnyLogic simulation model for power and performance analysis of data centres. Switzerland: Springer International Publishing AG. https://doi.org/10.1007/978-3-319-23267-6_17
Postema, Björn Frits ; Haverkort, Boudewijn R.H.M. ; Beltrán, Marta (Editor) ; Knottenbelt, William ; Bradley, Jeremy (Editor). / An AnyLogic simulation model for power and performance analysis of data centres. 2015. Switzerland : Springer International Publishing AG. 15 p.
@misc{8e116a984ae74aeab1aee4bba8fc4a6a,
title = "An AnyLogic simulation model for power and performance analysis of data centres",
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.",
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",
author = "Postema, {Bj{\"o}rn Frits} and Haverkort, {Boudewijn R.H.M.} and Marta Beltr{\'a}n and William Knottenbelt and Jeremy Bradley",
note = "eemcs-eprint-26243",
year = "2015",
month = "8",
doi = "10.1007/978-3-319-23267-6_17",
language = "English",
isbn = "978-3-319-23266-9",
publisher = "Springer International Publishing AG",
address = "Switzerland",
type = "Other",

}

Postema, BF, Haverkort, BRHM, Beltrán, M (ed.), Knottenbelt, W & Bradley, J (ed.) 2015, An AnyLogic simulation model for power and performance analysis of data centres. Springer International Publishing AG, Switzerland. https://doi.org/10.1007/978-3-319-23267-6_17

An AnyLogic simulation model for power and performance analysis of data centres. / Postema, Björn Frits; Haverkort, Boudewijn R.H.M.; Beltrán, Marta (Editor); Knottenbelt, William; Bradley, Jeremy (Editor).

15 p. Switzerland : Springer International Publishing AG. 2015, .

Research output: Other contributionOther research output

TY - GEN

T1 - An AnyLogic simulation model for power and performance analysis of data centres

AU - Postema, Björn Frits

AU - Haverkort, Boudewijn R.H.M.

AU - Knottenbelt, William

A2 - Beltrán, Marta

A2 - Bradley, Jeremy

N1 - eemcs-eprint-26243

PY - 2015/8

Y1 - 2015/8

N2 - 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.

AB - 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.

KW - EWI-26243

KW - Steady state analysis

KW - Performance analysis

KW - Power Management

KW - Power-performance trade-off

KW - Data centres

KW - METIS-314949

KW - Transient analysis

KW - Simulation

KW - IR-98113

KW - Cascading effect

KW - Agent-based models

KW - Discrete-event models

U2 - 10.1007/978-3-319-23267-6_17

DO - 10.1007/978-3-319-23267-6_17

M3 - Other contribution

SN - 978-3-319-23266-9

PB - Springer International Publishing AG

CY - Switzerland

ER -