International Conference on Computer and Knowledge Engineering

Home / 11th International Conference on Computer and Knowledge Engineering

Virtual machine consolidation using SLA-aware genetic algorithm placement for data centers with non-stationary workloads

Authors :

Hossein Monshizadeh Naeen¹

1- Department of Computer and Information Technology Engineering, Neyshabur Branch, Islamic Azad University, Neyshabur, Iran

Keywords :

Cloud Computing; Green IT; SLA violation; VM Consolidation; Genetic Algorithms; Stochastic Proccess

Abstract :

Cloud computing is a computing model based on computer networks such as the Internet that provides a new model for the provision, use and delivery of computing services (including infrastructure, software, and platform) using network facilities. In fact, Cloud service providers provide services to cloud users based on user demand, and users pay as much as they need to use cloud resources. Until recently, efficiency was one of the most important concern in the problem of data center resources provisioning, but now, due to high energy costs, the issue of reducing energy consumption has also become very important. Dynamic virtual machine (VM) consolidation is one of the technologies that has been considered for green computing in cloud data centers. In this paper, we present a service level agreement aware system based on genetic algorithms for consolidation of VMs in an Infrastructure as a Service (IaaS) Cloud environment. The proposed approach considers workloads as non-stationary stochastic processes, and automatically models workloads as stationary processes using a dynamic sliding window method. Simulation results in the CloudSim confirms that the proposed VM consolidation algorithms in this paper provides significant cost savings.