Multi-Objective Mixed Integer Linear Programming Model for VM Placement to Minimize Resource Wastage in a Heterogeneous Cloud Provider Data Center

Abstract

Ahstract- Virtual Machine Placement (VMP) is one of the pressing issues encountered in cloud computing data centers. VMP is the process of selecting the most suitable physical machine (PM) to host the virtual machines (VMs). Typically, the placement goal falls under one of the following optimization criteria: the maximization of the PM usage or power consumption efficiency. In this paper, we propose a Multi-Objective Mixed Integer Linear Programming model (MOMILP) aiming at simultaneously minimizing the VM rejection ratio, the resource wastage and the number of used PMs. To the best of our knowledge, this is the first work which combines such objectives in a Multi-Objective model. We also assume heterogeneous configuration for the data center which has been proven, through recent research work and industrial experience, to be more cost-effective for some applications especially those with intensive Input/Output (I/O) operations. To assess the performance of the proposed model, a comparative study has been curried out. Through the simulation results, it was observed that the proposed model achieves total gains reaching 35 % and 10% in terms of resource wastage and power consumption respectively. It was also reported that the power consumption is not only impacted by the number of used PMs but also by the selected PM configurations.