Dynamic Virtual Machines Placement in a Cloud Environment by Multi-Objective Programming

Abstract

Recently, cloud services and cloud computing have revolutionized both academic research and industrial practices.A corresponding focus on how to improve the performance of cloud computing is growing apace.It is a significant approach to allocate virtual machines (VMs) on a set of physical machines (PMs).Computing resources can be utilized effectively with the optimal distribution of the virtual machines among the physical machines.This study aims to establish the dynamic placement model of VMs by multi-objective programming (MOP) for minimizing energy consumption, maximizing effectiveness of physical machine, and minimizing the task waiting time.The genetic algorithm (GA) is used to solve the multi-objective programming models and compared with the greedy method (GM).Experiments are implemented to verify the effectiveness of the proposed methods.