Energy efficient VM scheduling in Reservation supported Cloud Data Centers under availability constraints

The exponential surge in digital usage is resulting in a significant need for computational resources. This has led to businesses migrating to the cloud for benefits like usage of resources as a service, scalability, etc. Infrastructures supporting these businesses will need to conserve energy in th...

Full description

Saved in:
Bibliographic Details
Published in2021 International Conference on Intelligent Technologies (CONIT) pp. 1 - 8
Main Authors Charan, Bhavya, Goutham, K S, Mampilli, Ruben John, Kempaiah, Bharani Ujjaini, Phalachandra, H L
Format Conference Proceeding
LanguageEnglish
Published IEEE 25.06.2021
Subjects
availability
cloud computing
data center
Data centers
DVFS
Dynamic scheduling
Energy efficiency
Heuristic algorithms
network overhead
Performance evaluation
Processor scheduling
resource reservation
Scalability
VM migration
Online AccessGet full text

Cover

More Information
Summary:The exponential surge in digital usage is resulting in a significant need for computational resources. This has led to businesses migrating to the cloud for benefits like usage of resources as a service, scalability, etc. Infrastructures supporting these businesses will need to conserve energy in the context of the ever-increasing size of the data centers and provide a highly available environment with mechanisms for business continuity, disaster recovery, etc. These would need to be supported at minimal costs while meeting the expected performance along with conformance to the SLAs. This paper considers a cost-efficient resource reservation based environment and evolves an approach to perform energy-efficient VM scheduling with migrations, while factoring in the network Overheads, having Availability as a constraint, and orchestrating the devices in terms of Dynamic Voltage Frequency Scaling, for optimal energy usage. Two novel algorithms are proposed: the Power and Availability Aware Best Fit Decreasing (PAABFD) allocation policy and the Power Availability Network DVFS Aware (PANDA) migration policy, when combined achieving up to 82.35% improvement in data center energy while offering an availability of 99.999% when compared with other scheduling policies.
DOI:10.1109/CONIT51480.2021.9498421