Dependency Analysis based Approach for Virtual Machine Placement in Software-Defined Data Center

In data centers, cloud-based services are usually deployed among multiple virtual machines (VMs), and these VMs have data traffic dependencies on each other. However, traffic dependency between VMs has not been fully considered when the services running in the data center are expanded by creating ad...

Full description

Saved in:
Bibliographic Details
Published in:Applied sciences 2019-08, Vol.9 (16), p.3223
Main Authors: Narantuya, Jargalsaikhan, Ha, Taejin, Bae, Jaewon, Lim, Hyuk
Format: Article
Language:English
Subjects:
Automation
Clustering
Computer centers
Computer programs
Cost control
Customer services
Data centers
dependency analysis
Gravity
Infrastructure
Network security
Principal components analysis
scalable VM placement
Software
software-defined data center
Traffic congestion
traffic dependency
Traffic volume
Virtual environments
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In data centers, cloud-based services are usually deployed among multiple virtual machines (VMs), and these VMs have data traffic dependencies on each other. However, traffic dependency between VMs has not been fully considered when the services running in the data center are expanded by creating additional VMs. If highly dependent VMs are placed in different physical machines (PMs), the data traffic increases in the underlying physical network of the data center. To reduce the amount of data traffic in the underlying network and improve the service performance, we propose a traffic-dependency-based strategy for VM placement in software-defined data center (SDDC). The traffic dependencies between the VMs are analyzed by principal component analysis, and highly dependent VMs are grouped by gravity-based clustering. Each group of highly dependent VMs is placed within an appropriate PM based on the Hungarian matching method. This strategy of dependency-based VM placement facilitates reducing data traffic volume of the data center, since the highly dependent VMs are placed within the same PM. The results of the performance evaluation in SDDC testbed indicate that the proposed VM placement method efficiently reduces the amount of data traffic in the underlying network and improves the data center performance.
ISSN:2076-3417
2076-3417
DOI:10.3390/app9163223