Ulster University Logo

Energy Aware Scheduling across ‘Green’ Cloud Data Centres

Peoples, Cathryn, Parr, Gerard, McClean, Sally, Morrow, PJ and Scotney, BW (2013) Energy Aware Scheduling across ‘Green’ Cloud Data Centres. In: IFIP/IEEE Integrated Network Management Symposium, Ghent, Belgium. IEEE. 4 pp. [Conference contribution]

[img]
Preview
PDF
428kB

Abstract

Data centre energy costs are reduced when virtualisation is used as opposed to physical resource deployment to a degree sufficient to accommodate all application requests.Nonetheless, regardless of the hardware provisioning approach, opportunities remain with regard to the way in which resources are made available and workload is scheduled, particularly for improved efficiency objectives. In previous work, we propose the e-CAB as an architecture which captures real-time network state in data centres for improved efficiency. In this paper, we extend the discussion with consideration of a server selection mechanism integrated into the e-CAB which takes into account server utilisation and operational cost attributes. We recognise that cost incurred at a server is a function of its hardware characteristics. The objective of our approach is therefore to pack workload intodevices, selected as a function of their cost to operate, to achieve (or as close to) the maximum recommended capacity utilisation in a cost-efficient manner and help to avoid instances where devices are under-utilised and management cost is incurredinefficiently. This is based on principles behind queuing theory and the relationship between packet arrival rate, service rate and response time, and recognises a similar exponential relationship between power cost and server utilisation to drive its intelligentselection for improved efficiency. There is a subsequent opportunity to power redundant devices off to exploit power savings through avoiding their management.

Item Type:Conference contribution (Paper)
Keywords:Cloud data centre, cost-benefit balance, green policy-based management, operational efficiency, workload scheduling.
Faculties and Schools:Faculty of Computing & Engineering
Faculty of Computing & Engineering > School of Computing and Information Engineering
Research Institutes and Groups:Computer Science Research Institute
Computer Science Research Institute > Information and Communication Engineering
ID Code:24223
Deposited By: Dr Cathryn Peoples
Deposited On:13 Sep 2013 13:48
Last Modified:09 Dec 2015 11:09

Repository Staff Only: item control page