Affiliations: Department of Business Computing and Law, University of Derby, Kedleston Road, Derby, DE22 1GB, UK, e-mail: n.bessis@derby.ac.uk, eleana.asimakopoulou@googlemail.com | Intelligent Systems Laboratory (InteLLigence), Department of Electronic & Computer Engineering, Technical University of Crete (TUC), Chania, Crete, GR-73100, Greece, e-mail: s.sotiriadis@intelligence.tuc.gr | Departament de Llenguatges i Sistemes Informàtics, Universitat Politècnica de Catalunya, Campus Nord, Ed. Omega, C/Jordi Girona 1-3, 08034 Barcelona, Spain, e-mail: fatos@lsi.upc.edu
Note: [] Corresponding author.
Abstract: This study proposes a model for supporting the decision making process of the cloud policy for the deployment of virtual machines in cloud environments. We explore two configurations, the static case in which virtual machines are generated according to the cloud orchestration, and the dynamic case in which virtual machines are reactively adapted according to the job submissions, using migration, for optimizing performance time metrics. We integrate both solutions in the same simulator for measuring the performance of various combinations of virtual machines, jobs and hosts in terms of the average execution and total simulation time. We conclude that the dynamic configuration is prosperus as it offers optimized job execution performance.
