Metrics and Measurements

White Paper

Return to Main

Comment Policy

The comment option is to provide feedback on this particular deliverable. Any advertisement of products will be removed.


White Paper #49-PUE: A Comprehensive Examination of the Metric

Posted In:

Metrics and Measurements



Download

Share

Editors:
Victor Avelar, Schneider Electric
Dan Azevedo, The Walt Disney Company
Alan French, Emerson Network Power

Contributors: 
Hugh Barrass, Cisco
Christian Belady, Microsoft
Stephen Berard, Microsoft
Mark Bramfitt, PG&E
Tahir Cader, Hewlett-Packard
Henry Coles, Lawrence Berkeley National Laboratory
Jud Cooley, Oracle
Lex Coors, Interxion
Tommy Darby, Texas Instruments
Jamie Froedge, Emerson Network Power
Nick Gruendler, IBM
Jon Haas, Intel
Eric Jewitt, Nationwide
Christine Long, Schneider Electric
Bob MacArthur, EMC
Phil Morris, Sun Microsystems
Zeydy Ortiz, IBM
John Pflueger, Dell
Andy Rawson, AMD
Jim Simonelli, Schneider Electric
Harkeeret Singh, BT
Roger Tipley, Hewlett-Packard
Robert Tozer, Hewlett-Packard
Gary Verdun, Dell
John Wallerich, Intel
Randall Wofford, Dell 

[Please note: Contributors are listed with The Green Grid member company they worked for at the time of their contribution.]

Power usage effectiveness (PUE™) has become the industry-preferred metric for measuring infrastructure energy efficiency for data centers. The PUE metric is an end-user tool that helps boost energy efficiency in data center operations. Since its original publication, PUE has been globally adopted by the industry. Over the past years, The Green Grid has continued to refine the metric measurement methodology with collaborative industry feedback. This collective work has been brought together here to simplify the absorption and use of the PUE metric. To produce this document, The Green Grid consolidated all its previously published material related to PUE and included new material as well. This document supersedes prior white papers and consolidates all things that The Green Grid has developed and published relating to PUE. As such, this document is recommended by The Green Grid to those implementing, using, and reporting PUE. Quick access to various levels of information is provided via the links embedded throughout the document. This document allows executives to gain a high level of understanding of the concepts surrounding PUE, while providing in-depth application knowledge and resources to those implementing and reporting data center metrics.

PUE: A Comprehensive Examination of the Metric supersedes all prior white papers and consolidates all of the new and previously published content that The Green Grid has developed related to PUE. The definition and measurement guidelines included in this book have been harmonized globally, with a primary focus on energy.

Using mobile computing to monitor PUE

e-mail fwd to TGG: I believe that mobile computing is the way to go to collect, filter/validate & help to analyze PUE data on both local & global scales (i.e., within an organization & worldwide). Since PUE is a very sensitive metric that can be influenced by a lot of factors, mobiles will help to gather a max of information to improve the statistic/machine learning procedure. Meaning that mobiles would be used as intermediate devices between various servers. Meaning TGG and data centers need to develop their own APIs. For instance, an organization would have its own API that employees could use to load local data and perform some analysis in the background of an app (e.g. data filtering), while TGG would have its own server/API to globally collect the filtered data from mobiles to build : **a world's map of the energy consumption of supercomputing center/data center **a world's map of the reused energy per supercomputing center **country energy supercomputing profile **daily-real time energy profile This way you uniformed how the data are manipulated, as well as it will help to globally report, register and certify PUE measurement – sort of global standardization. It is also much less energy for data centers to put in regarding the analysis burden that it involves. Another very important point: Mobile device could help to detect malfunction within a data center (e.g., if the PUE does not fall in a bell shape → send alert to employees). Our phones will become PUE monitoring devices for TGG and data/supercomputing centers to reinforce quality control. I believe that you can monetize such app via in-app purchase. Since the app will help an organization to monitor their real-time PUE, the organization will have to pay for each employee willing to use this functionality. Obviously, this has to be a collaborative work between TGG / data centers / academia / national labs / private companies etc.

Posted at 01:22 PM on October 05, 2012 by kavi\barbara.collignon

Comment On This Document


Rate This

survey

Thanks for visiting The Green Grid website! We are always working to improve our site and would appreciate your input.

Please click here to take a brief website survey.

No Thanks