Cloud virtual machine scheduling: Modelling the cloud virtual machine instantiation

S. Sotiriadis, N. Bessis, F. Xhafa, N. Antonopoulos

Research output: Chapter in Book/Report/Conference proceedingConference proceeding (ISBN)peer-review

19 Citations (Scopus)

Abstract

Cloud computing provides an efficient and flexible means for various services to meet the diverse and escalating needs of IT end-users. It offers novel functionalities including the utilization of remote services in addition to the virtualization technology. The latter feature offers an efficient method to harness the cloud power by fragmenting a cloud physical host in small manageable virtual portions. As a norm, the virtualized parts are generated by the cloud provider administrator through the hyper visor software based on a generic need for various services. However, several obstacles arise from this generalized and static approach. In this paper, we study and propose a model for instantiating dynamically virtual machines in relation to the current job characteristics. Following, we simulate a virtualized cloud environment in order to evaluate the model's dynamic-ness by measuring the correlation of virtual machines to hosts for certain job variations. This will allow us to compute the expected average execution time of various virtual machines instantiations per job length.
Original languageEnglish
Title of host publicationProceedings - 2012 6th International Conference on Complex, Intelligent, and Software Intensive Systems, CISIS 2012
DOIs
Publication statusPublished - 23 Jul 2012

Keywords

  • Cloud
  • Virtualization
  • Virtual Machine instantiation
  • Static and dynamic Virtual Machine scheduling

Fingerprint

Dive into the research topics of 'Cloud virtual machine scheduling: Modelling the cloud virtual machine instantiation'. Together they form a unique fingerprint.

Cite this