Proficient Decision Making on Virtual Machine

Creation in IaaS Cloud Environment

Radhakrishnan Ayyapazham and Kavitha Velautham

Department of Computer Science, Anna University, India

Abstract: Cloud computing is a most fascinated technology that is being utilized by IT companies to reduce their infrastructure setup cost by outsourcing data and computation on demand. Cloud computing offer services in three basic models such as SaaS, PaaS and Infrastructure as a Service (IaaS). Where IaaS is one of the fundamental cloud service model in which cloud provider offers Virtual Machines (VMs) as resources to cloud customers through virtualization. The VMs act as dedicated computer system to consumers which are created on physical hosts of cloud provider. Making decision of physical host selection for VMs creation is a challenging task for cloud provider. Any deficiency of this selection causes VMs migration in middle of computation or restart computation from the scratch; these would sternly affect profit and trust of cloud provider. In this paper, we proposed a novel methodology to handle VMs creation and allocation for IaaS service. The proposed methodology employs a genetically weight optimized neural network component in each host to predict their near future availability during VMs creation. We analyses the host load prediction performance of various neural networks through real time host load values. Also we proposed a proficient decision making algorithm named Future Load Based Virtual machine Creation (FLBVC) to choose appropriate launching hosts for VMs. The performance of our methodology is validated using CloudAnalyst tool. The results demonstrated that our proposed approach reduces response time of cloud customers and rental cost of VMs. 

Keywords: IaaS, VMs, jordon neural network, genetic algorithm, service level agreements, FLBVC.

Recieved October 20, 2013; accepted July 2, 2014