The Hot Aisle Logo
Fresh Thinking on IT Operations for 100,000 Industry Executives

A key management principle is that you can’t manage what you can’t measure. So if we want to manage the energy efficiency of our data center estate, then we had better be in a position to baseline where we are today so that we can identify the value of the changes that we implement.

The problem with measuring anything is deciding what to measure. Measuring data center efficiency is particularly difficult, where do you start and what do you measure? A good starting point is looking at what others do in this space.

A common measure is PUE – Power Usage Effectiveness a simple measure of the total power delivered to the facility divided by the IT Equipment Power. So how, then do we measure or calculate PUE?

To get the Total Power Delivered to the Facility, and if we had instrumentation in our data center, we could measure the instantaneous power entering the building through the high voltage feed (often this feed has other uses including ancillary buildings, offices and other non-data center assets which will need to be excluded). We could alternatively look at an average and use the utility electricity meter to count the number of MW hours over a fixed period (dividing the MW hour value by the number of hours we measure over gets us to an average power value).

To get to the IT Equipment Power value we have two approaches, we could use the boilerplate values (vendor supplied power rating usually attached to the equipment on a label) for each piece of equipment and simply add them up or we could (if we are lucky to have them) use our iPDU devices to measure the total power delivered to the racks. Both of these approaches have weaknesses. In the former case, we will find that boilerplate values are very poor measures of the real power consumed as that will be often dependent on the number of accessories attached or the loading of the device (e.g. a network switch). Getting the values from the PDU is much better but will tend to be too large as often rack mounted fans and other non IT Equipment load will be hanging off the PDU feeds.

An alternative simple measure to PUE is DCE – Data Center Effectiveness, the reciprocal of PUE i.e. IT Equipment Power divided by Total Equipment Power delivered to the facility. (Another term for the same measure is DCiE – Data Center infrastructure Effectiveness).

The main weakness with these measures is that they focus exclusively on the building M&E effectiveness and fail to address efficiency in terms of computing, network and storage. In other words a good PUE does not mean that you have an effective data center if the servers are all running at 2% utilization and the storage is mostly empty. Nevertheless highly efficient M&E plant is a great place to start.

A fuller measure that is sensitive to more of the initiatives we can take to being energy efficient is CPE – Compute Power Efficiency. This is IT Equipment Utilization divided by PUE.

A facility with IT Equipment running at 5% utilization will have a much lower CPE than another with a better PUE but a 15% IT Equipment Utilization. This is a much more realistic measure of what has been achieved. Plainly equipment running at 100% utilization with a PUE of 1 is the target that we will never get to but nevertheless it should be an aspiration.

Even CPE is a rather one dimensional measure as it focusses on Servers, there are many other areas of efficiency that we could bring into the equation:

  • Network Utilization
  • Storage Utilization
  • Data Center Utilisation

Where we need to get to is a meaningful measure that is possible to calculate repeatedly (better still in real time) that we can use to compare our performance with other Data Center operators.

Is it too fanciful to imagine the CPE measure being adopted by government to regulate data center operators in an energy constrained world?

There Are 11 Responses So Far. »

  1. Steve

    This is a really thought provoking article and one that I intend to use to start baselining my data centers. Have you any advice about where I might get help in pulling these numbers together?

    It seems evident to me that taking this measure, manage, measure approach will lead to us getting a much better understanding of how our behavior impacts energy efficiency.

    Anyone out there got any comparative values?

    Bill

  2. Bill

    A good place to start is with The Green Grid (see Industry Bodies on this Blog for URL). They are pretty theoretical and spend a lot of time looking at and developing standards such as PUE etc.. Then you need a decent Electrical Engineer to follow the basic instructions in this post. You might consider getting in touch with Martin Williams at Glasshouse to see if using their Reflector product might get you closer to real time measurement of your KPIs.

    Anyway very good luck and let me know how you get on.

    Steve

  3. [...] like BT’s 21st Century Data Center use 100% Fresh Air cooling and have a significantly better PUE. Switch has spent years banging away on a data center design that runs contrary to conventional [...]

  4. [...] data center. If I was you I would not be publicizing it in a press release. (My earlier article How Efficient is my Data Center? explains the math behind calculating data center efficiency). Now if you get down to a PUE of 1.3 [...]

  5. [...] a victim of heroism via unexpected consequences. Pretty much single handed VMWare has raised the CPE – Compute Power Efficiency of the average Intel based server out of all recognition. Whenever I have had the guys pull [...]

  6. [...] a staggering 2.1 KW extra power load from a similar sized competitive product. Depending on the PUE of your Data Center (say an average modern one at 1.6) this is a total annual energy saving of nearly 30 MW hours. [...]

  7. I like the approach, but I’m worried about how it gets to be misused by the inexperienced as it still doesn’t tie together the resource used (electricity) with the business’ operations that drive revenues/cost (business applications/processes or transactions).

    I’ve had really naive questions from people in large businesses charged with ‘improving utilisation’ whose targets could be met by either swapping out new kit for old (sic), or running SETI@home on all of their servers.

    I think that there’s often too large a gap between front and back ends of IT delvery (App Dev -> Operations), leading to local optimisation and global dysfunction.

  8. Hi Tim,

    Thanks for the comment. You are absolutely right that the measure we need is much more about measuring business value against electricity used. How many unnecessary or underused applications are deployed in our data centers and how mush do they cost the business to run for zero benefits?

    I started looking at the implications of this in Asset Management is a Green Issue – an earlier article. Methinks I need to develop this theme around how we measure value of IT from a business perspective.

    Steve

  9. I HAVE A GREEN DATA CENTER COOLING SYSTEM THAT USES 50% LESS TONNAGE.YOU CAN VIEW DRAWINGS AND SPECD AT THE DATA CENTER JOURNAL BLOG FROM APRIL HAS LINK.

  10. Our experience in providing design, build and support to computer rooms is that many organisations cannot yet measure power consumption either in the rack or in the room but either add up the labels on the back of their kit or look at bills.

    Even worse, we have found that companies interested in doing this have had budget cuts (recession – what recession?) because these exercises 'can wait'

  11. Our experience in providing design, build and support to computer rooms is that many organisations cannot yet measure power consumption either in the rack or in the room but either add up the labels on the back of their kit or look at bills.

    Even worse, we have found that companies interested in doing this have had budget cuts (recession – what recession?) because these exercises 'can wait'

Post a Response