DCeP-tive Metrics Are Not Productive

4 comments

MARK MONROE<BR/>DLB AssociatesMARK MONROE
DLB Associates

Mark Monroe is Chief Technology Officer and VP of DLB Associates. He recently served as Executive Director of The Green Grid, an IT industry and end user consortium focused on resource efficient data centers and business computing environments.

Think back to a few weeks ago, when March Madness was gripping the U.S. with basketball playoff fever. The ultimate measure of basketball productivity–total points–was carefully measured and tallied, using transparent, standard methods and highly objective reviews of whether a production event (a “shot”) resulted in 0, 1, 2 or 3 points. No one argued about how to measure total productivity one had to measure how many times and how fast the teams moved the basketball up and down the court, or how many basketballs were stored on the racks behind each teams’ benches, not being used, but ready in case anyone needed quick access to them.

The teams totals were objectively compared on a public display (the scoreboard) using a simple standard that had been established 123 years ago. The team that was most productive in the time allotted is allowed to continue, while the less productive team has to go out of business.

This way of looking at the basketball competition puts it in terms similar to the business world, where companies must compete, mostly with less objective, less transparent, and less standard methods of measuring performance than sporting events.

Wouldn’t it be great if there was something as simple for the information technology industry: counting the number of times something happened, adding it up on a scoreboard, then having everyone be able to understand what had happened, what should be done to improve. And, that the measurement was able to do what everyone really wants to do, compare themselves to their competition to see who “won.”

Data Center energy Productivity (DCeP) Gets The Nod

The Green Grid released a memo from their Global Harmonization Taskforce (GHT) 1 in the middle of March, describing new agreements that the team of global experts had reached over the last 18 months of discussion and negotiation. (Side note: I am very familiar with the people and working of the Global Harmonization Taskforce: I was on the board of directors of The Green Grid for 5 years, and was Executive Director of the organization Jan 2011-Aug 2012. I attended GHT meetings and applaud their efforts to come to agreement on many aspects of data center metrics from Power Usage Effectiveness (PUE) to Green Energy Coefficient (GEC). It’s a venerable group and does great work.)

One of the metrics endorsed in the GHT memo of March 14, 2014 is Data Center energy Productivity, abbreviated DCeP.

DCeP was first described 6 years ago in The Green Grid’s publication, WP#13-A Framework for Data Center Energy Productivity, released in April 2008.2 The original paper, and the Mar 2014 memo, describes DCeP as a metric that “quantifies the amount of useful work a data center produces relative to the amount of energy it consumes.”

equation-DCeP

The paper and memo describe a complicated equation that takes into account the relative value of transactions, the time-based decay of that value, and a normalization factor for the transactions. These last three parameters are set arbitrarily based on each business’ understanding of their IT operations. A business can pick any measure of utility and value for any transaction in their IT infrastructure, and use that to develop a picture of their DCeP value that applies to their business.

Peter Judge, a London-based IT journalist and consultant, wrote a great piece in Techweek Europe 3 in response to the announcement. In it, Peter wonders if YouTube would be measuring productivity in terms of “Kitten videos per kWh,” which some interpretations of DCeP would lead you to agree. I’d even go so far as to say “Kittens per kWh” might be the right measure of productivity for YouTube!

The Necessity of Simplicity

Despite the constant flailing that PUE takes from critics, it is the most used, most effective efficiency metric in the IT industry today. Other contenders from CADE to FVER have not gained the coverage, reporting, or public improvement that PUE has.

PUE-chart

From the first study by LBNL in 2007 to Facebook’s and eBay’s real time, online meters, there has been real change in the industry because of the use of this measure. Since the first reports by Lawrence Berkeley National Labs in 2008 to the real-time Facebook display, reliably reported PUE has dropped from an average of 2.2 to 1.08, a 93 percent reduction in wasted energy.

Pages: 1 2

Add Your Comments

  • (will not be published)

4 Comments

  1. Mark- interesting comments. I can't disagree that issue with DCeP is that it's overly complex, requires much more intelligence/insight, and requires quantification techniques (not always available), even though it works. As you know, the complexity may be due to having to apply for all markets and users. I think that what you are alluding to at the end, is the need for simplification, such that the complexity and cost can be reduced. Simplification and/or revisiting formula(e) should probably be the industry call to action.

  2. The Global Harmonization Task Force was comprised of many organizations, not just The Green Grid Association: U.S. Department of Energy’s Save Energy Now and Federal Energy Management Programs (March 2009 – October 2012); U.S. Environmental Protection Agency’s ENERGY STAR Program; European Commission - Joint Research Centre, Data Centres Code of Conduct; Japan’s Ministry of Economy, Trade and Industry; and, Japan’s Green IT Promotion Council.

  3. thanks Henry. Agree, simplify and start measuring something. Just try reporting average CPU utilization for a sample of machines to the CEO and see what happens.

  4. good point, Judy. Thanks for providing the full list.