Artificial intelligence (AI) policy: ASHRAE prohibits the entry of content from any ASHRAE publication or related ASHRAE intellectual property (IP) into any AI tool, including but not limited to ChatGPT. Additionally, creating derivative works of ASHRAE IP using AI is also prohibited without express written permission from ASHRAE.

logoShaping Tomorrow's Built Environment Today

Data Centers: Where and How Should PUE Be Improved?

Nick Casale, P.E.

Share This

©2021 This excerpt taken from the article of the same name which appeared in ASHRAE Journal, vol. 63, no. 6, June 2021.

About the Author
Nick Casale, P.E., is principal at kW Mission Critical Engineering, Troy, N.Y.

Power usage effectiveness (PUE) is the overall building power (or energy) divided by the IT power within the building. This metric for benchmarking efficiency is regularly used in the data center industry. However, questions persist regarding how it is calculated, measured and communicated to peers, owners, laypeople and end users. So, where and how should it be improved? This article proposes a standardized methodology for how to use PUE for system and component comparisons and for infrastructure design.


In 2012 ASHRAE Technical Committee 9.9, Mission Critical Facilities, Data Centers, Technology Spaces and Electronic Equipment, established Special Project Committee 90.4 to develop ANSI/ASHRAE Standard 90.4, Energy Standard for Data Centers. Originally published in 2016 and updated in 2019, the standard supplements existing energy codes with tools and requirements better suited to data centers.

In 2013 ASHRAE Technical Committee 9.9, in conjunction with The Green Grid Association, published PUE: A Comprehensive Examination of the Metric, which is part of the ASHRAE Datacom Series. While this book covers a lot of information on basis and theory behind PUE and how it is to be applied, challenges remain in applying the metric consistently across the many sectors of the data center industry.

The PUE book serves primarily to benchmark new and existing facilities, while Standard 90.4 is used to validate that engineering designs meet baseline efficiencies. The book focuses on existing facilities and the measurement of PUE. While this is one application in which PUE is used, existing facilities are not the only means by which the metric is applied in common practice:

Industry professionals use PUE as a means of validating existing facilities and also as a means of predicting the theoretical efficiency of new facility designs.

Equipment manufacturers often illustrate the efficiencies of their equipment by using a term designated by the book as partial power usage effectiveness (pPUE). Per the definition of partial PUE as described by the book, this application is often misapplied by the manufacturers.

Colocation providers use PUE to compare themselves to one another for marketing purposes as well as a basis of the contracts they sign with their customers.

Enterprise data centers use PUE to drive energy efficiency in their business, for energy rebates and incentive programs and for public relations purposes.

Regardless of how the metric is used, for the industry to truly benchmark and compare facilities there must be consistency across calculations and the method with which they are approached.

PUE: A Comprehensive Examination of the Metric

The book’s introduction states, “As there are various ways to calculate PUE, stakeholders in the industry have expressed concerns around the consistency and repeatability of publicly reported measurements.” This indicates that the calculation of PUE is one challenge and that its measurement is another. In theory (calculation) and in practice (measurement) the two efforts should be approached as similarly as possible. Despite the book’s being centered around the measurement aspect, most of its information can be directly applied to the respective calculation for peak or annual PUE (shown in the next section).

Chapter 3 states, “To further enable equitable comparison of PUE results among data centers, additional attributes such as age, geographic location, capacity loading, size of facility, infrastructure resiliency and the like should be taken into consideration.” An interpretation of this could be that the age of a facility needs to be accounted for to level-set comparisons between facilities of significant age and newer facilities.

Read the Full Article

ASHRAE Members have free access to the full-text PDF of this article as well as the complete ASHRAE Journal archives back to 1997 in the Free Member Access Area.

Non-members can purchase features from the ASHRAE Bookstore. Or, Join ASHRAE!

Return to Featured Article Excerpts

Return to ASHRAE Journal Featured Article Excerpts