Energy-efficiency virtual machine placement based on binary gravitational search algorithm
- PDF / 1,184,125 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 60 Downloads / 201 Views
(0123456789().,-volV)(0123456789(). ,- volV)
Energy-efficiency virtual machine placement based on binary gravitational search algorithm Foudil Abdessamia1 • Wei-Zhe Zhang1,2
•
Yu-Chu Tian3
Received: 5 August 2019 / Revised: 28 October 2019 / Accepted: 20 November 2019 Ó Springer Science+Business Media, LLC, part of Springer Nature 2019
Abstract Cloud computing is a remarkable growing paradigm for hosting and offering services through the Internet. It attracted the most notorious business companies and resulted to an exponential increase of its users from simple end users to companies that deploy more and more of their system over the cloud. The amount of resources to provide the demand became tremendous. therefore, a great need energy supply. The world as we know is highly concerned about the environment and the energy-efficiency in all aspect of life and the domain of IT is one them. To deal with energy wastage in data centers, researches use Virtual machine placement as a main key to assure cloud consolidation and reduce power wastage. Several approaches were proposed for Virtual machine placement. This paper proposes a solution based on Binary gravitational search algorithm (BGSA) for the virtual machine placement in the heterogeneous data center. In this work, we compared the BGSA method to fit with virtual machines in data centers with particle swarm optimization, First-fit, Best-fit, and worst-fit. results showed significant difference of energy save comparing to other strategies. The results obtained gave the advantage to our approach and its better response with the increase of number of virtual machines. Keywords Cloud computing Green computing Energy-efficiency Optimization
1 Introduction The world of technology and internet gained a huge success in the recent years, it allowed the emergence of the cloud computing as new model for scalable computing resources and on demand services model or also called ‘‘pay as you go’’ model. These services are provided to users, and access to them through the internet in three levels, Infrastructure-as-a-Service (IaaS), Platform-as-aService (PaaS) and Software-as-a-Service (SaaS) [1]. In & Wei-Zhe Zhang [email protected] Foudil Abdessamia [email protected] Yu-Chu Tian [email protected] 1
School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China
2
Peng Cheng Laboratory, Shenzhen, China
3
School of Electrical Engineering and Computer Science, QUT, Brisbane, QLD, Australia
one hand, computing resources are way cheaper than before and in the other hand they are more powerful and with high performance. In this case, the end users or consumers are provided with computing resources such as CPU run time and storage over the internet. The providers manage the allocation of these resources to consumers following a pricing model. The information technology IT was impacted by this change, the big names in the industry of IT rapidly invested this business. They compete, offer and provide more powerful platforms, less expen
Data Loading...
