Research promises to slash data centre energy consumption

Market

University of Sydney researchers have found a way of simultaneously optimising the energy consumption and completion time of computationally intensive processes.

Dr Young Choon Lee and Professor Albert Zomaya of the University of Sydney's Centre for Distributed and High Performance Computing have patented a scheme that is said to reduce CPU power consumption by as much as 60%.

Lee and Zomaya's patented Energy Conscious Scheduling algorithm (ECS) is aimed at computationally intensive tasks such as those performed in areas such as astronomy, chemistry, life sciences and financial forecasting.

The basic idea appears to be to take advantage of the dynamic voltage scaling (DVS) feature of modern processors. Reducing the voltage supply and clock frequency means a process takes longer to complete but uses less energy.

ECS uses this to adjust the speed of various processes to reduce the need for one to wait for another to complete.

"Computations are typically comprised of interdependent tasks, so the need to wait for a parent task to complete can create slack and therefore wastage," said Zomaya.

"When ECS is employed with the help of DVS capability, mapping decisions between processors, supply voltages, and tasks are streamlined to significantly lower the amount of energy required at any given time," he added.

Reducing the slack time (when processors are not usefully employed) in this way can cut energy consumption by between 10 and 60%, Zomaya claimed.

Lee and Zomaya are developing an ECS prototype, which they hope to commercialise by 2011.

"ECS will work well on cloud systems as they mature but will give a more immediate means for organisations to reduce their data centre's energy consumption. With demand for computing and data storage capacities growing exponentially, this world first will make a valuable contribution to both the environment to and organisations' bottom line," said Zomaya.

Power consumption by servers has more than doubled since 2000, according to University of Sydney officials.

The availability and price of electricity has become a significant factor in choosing sites for large data centres. In addition to cost, there is growing social pressure for organisations to reduce their energy consumption or at least make more efficient use of what they use.

Please enable JavaScript in your browser to post your comment!

SPONSORED PRESS RELEASES

Independent Research Shows High Customer Satisfaction for NetSuite
NetSuite Inc. (NYSE: N), a leading vendor of cloud computing business management software suites, today announced that technology advisory firm Nucleus Research has completed an independent survey of NetSuite customers and concluded that NetSuite customers are highly satisfied, l...

Featured IT jobs

Senior Software consultant responsible for providing support on a unique enterprise level software solution for various customers, Melbourne based!
Skills Tags:   IT  ITIL  Linux  Management  RFP  Unix
This financial client has an excellent opportunity for an experienced Database Developer. SQL 2005 Some Schema design + SSIS & SSRS - 80k+super
Skills Tags:   Design  Development  SQL  SQL Server
Massive Hyperion Project requires a Hyperion Planning Architect / Lead Developer - drive home a huge Hyperion solution.
Skills Tags:   Architect  Design  Development  Hyperion
OBIEE Consultant to work on a very large greenfield OBIEE implementation to date to work end-to-end with excellent modelling & BI Server skills
Skills Tags:   Business Intelligence  Cognos  Hyperion  Informatica  Oracle  SQL

Editors Picks

Stories you may have missed 

What iTWire offers for free

E - mail News SMS Headlines Desktop Alerts News Feeds Job Alerts Technology Events Press-Releases