• DocumentCode
    1910713
  • Title

    Discrete event simulation model for analysis of horizontal scaling in the cloud computing model

  • Author

    Idziorek, Joseph

  • Author_Institution
    Iowa State Univ., Ames, IA, USA
  • fYear
    2010
  • fDate
    5-8 Dec. 2010
  • Firstpage
    3004
  • Lastpage
    3014
  • Abstract
    One of the distinguishing characteristics of the cloud model is the ability for the service users to horizontally scale computing resources to match customer demand. Because the cloud model is offered in a pay-as-you-go scheme, it is in the service user´s best interest to maximize utilization while still providing a high quality of service to the customer. This paper describes a discrete event simulation model that is used to explore the relationship between the horizontal scaling profile configurations and the functionality of the cloud model. Initial results show that both a state-aware load distribution algorithm and the parameters that dictate the elasticity of the horizontal scaling ability are essential to achieving high rates of utilization. Through modeling and simulation, this paper presents both a framework and initial results to further explore the cloud model.
  • Keywords
    cloud computing; discrete event simulation; cloud computing model; customer demand; discrete event simulation model; horizontal scaling analysis; horizontal scaling profile configurations; pay-as-you-go scheme; state-aware load distribution algorithm; Biological system modeling; Cloud computing; Clouds; Computational modeling; Load modeling; Web server;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Simulation Conference (WSC), Proceedings of the 2010 Winter
  • Conference_Location
    Baltimore, MD
  • ISSN
    0891-7736
  • Print_ISBN
    978-1-4244-9866-6
  • Type

    conf

  • DOI
    10.1109/WSC.2010.5678994
  • Filename
    5678994