Optimizing virtual machine placement in IaaS data centers: taxonomy, review and open issues
- Publisher:
- Springer
- Publication Type:
- Journal Article
- Citation:
- Cluster Computing, 2020, 23, (2), pp. 837-878
- Issue Date:
- 2020
Closed Access
| Filename | Description | Size | |||
|---|---|---|---|---|---|
| Talebian2020_Article_OptimizingVirtualMachinePlacem.pdf | Published version | 2.16 MB |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
© 2019, Springer Science+Business Media, LLC, part of Springer Nature. The unprecedented growth of energy consumption in data centers created critical concern in recent years for both the research community and industry. Besides its direct associated cost; high energy consumption also results in a large amount of CO2 emission and incurs extra cooling expenditure. The foremost reason for overly energy consumption is the underutilization of data center resources. In modern data centers, virtualization provides a promising approach to improve the hardware utilization level. Virtual machine placement is a process of mapping a group of virtual machines (VMs) onto a set of physical machines (PMs) in a data center with the aim of maximizing resource utilization and minimizing the total power consumption by PMs. An optimal virtual machine placement algorithm substantially contributes to cutting down the power consumption through assigning the input VMs to a minimum number of PMs and allowing the dispensable PMs to be turned off. However, VM Placement Problem is a complex combinatorial optimization problem and known to be NP-Hard problem. This paper presents an extensive review of virtual machine placement problem along with an overview of different approaches for solving virtual machine placement problem. The aim of this paper is to illuminate challenges and issues for current virtual machine placement techniques. Furthermore, we present a taxonomy of virtual machine placement based on various aspects such as methodology, number of objectives, operation mode, problem objectives, resource demand type and number of clouds. The state-of-the-art VM Placement techniques are classified in single objectives and multi-objective groups and a number of prominent works are reviewed in each group. Eventually, some open issues and future trends are discussed which serve as a platform for future research work in this domain.
Please use this identifier to cite or link to this item: