Paper Info
Title
A method for managing green power of a virtual machine cluster in cloud.
Abstract
A green power management scheme is proposed to determine how many physical machines should be run or turned off based on the gross occupied resource weight ratio of the virtual machine cluster. The gross occupied resource weight ratio is defined as the ratio of the sum of resource weights of all virtual machines over the sum of available resource weights of all running physical machines. When the gross occupied resource weight ratio is greater than the maximum tolerant occupied resource weight ratio, preset to ensure quality of service, a standby physical machine in the non-running physical machines is selected and wakened up to join as one of the running physical machines. On the other hand, when the gross occupied resource weight ratio is less than the minimum critical occupied resource weight ratio, preset to trigger energy saving algorithms, one of the running physical machines, selected as a migration physical machine with the virtual machines therein removed after live migration, is moved from other running physical machines, and then turned off. As a result, a resource allocation process is realized to distribute loads of the running physical machines such that the total number of the running physical machines can be flexibly dispatched to achieve the objective of green power management.
Year
DOI
Venue
2014
10.1016/j.future.2014.03.001
Future Generation Computer Systems
Keywords
Field
DocType
Green power management,Resource allocation,Live migration,Virtual machine cluster
Virtual machine,Computer science,Live migration,Quality of service,Real-time computing,Resource allocation,Green power,Operating system,Cloud computing,Distributed computing
Journal
Volume
ISSN
Citations 
37
0167-739X
17
PageRank 
References 
Authors
0.73
28
4
Name
Order
Citations
PageRank
Chao-Tung Yang11196139.50
Jung-Chun Liu223333.10
Kuan-Lung Huang3443.97
Fuu-Cheng Jiang411113.62