PUE is defined by the total data center energy consumption or power divided by the IT energy consumption or power. So, the lower the resulting variable, the higher the energy efficiency of the data center because more of the total energy is being used for its intended function – to power the IT equipment – rather than to cool the servers, provide lighting, support infrastructure, etc.

The PUE standards have been updated recently to account for the  loopholes that several companies had exploited to lower their PUE value (these abuses were reported on Forbes.com and InfoWorld.com, among other places). As a result of these considerations, new standards such as including a weighted measure of different types of source energy (not just electricity but natural gas, fuel oil, other fuels, district chilled water, district hot water, and district steam) and a requirement to take readings from energy meters over a 12-month period (rather than over one 24-hour duration and extrapolating for the entire year).

The new recommendations are definitely worth a read for those involved with data centers. There are a few important points to keep in mind about Version 1 of the new PUE standards:

1. Dedicated data centers – the new standards are limited to data centers which are located in a building where the power, cooling, lighting, and support infrastructure are devoted exclusively to them. An update to the current document will include guidelines for measuring PUE in mixed-use facilities.
2. Report PUE with subscript – there are four categories of PUE (0-3), depending on how energy consumption or power is measured. PUE₃ is rated the highest standard because the energy consumption reading is taken at the point of connection of the IT devices to the electrical system, not at less accurate locations. PUE₀, the most generic category, can not be used when source energy includes types other than electricity. PUE must always be reported with the subscript of the category used, and the eventual goal is for PUE₃ to become the industry standard of data center efficiency measurement.
3. Must subtract non-IT equipment power use – Categories 0 and 1 measure IT energy at the UPS output location. According to the white paper, “If there is non-IT equipment supported by the UPS system (e.g., CRAC, CRAH, In-row coolers, etc.) it must be metered out and subtracted from the UPS Output reading”.
4. Energy sources are weighted – See the white paper for a table of the different factors by which source energy types are weighted.
5. Heating nearby homes doesn’t count – A trend in data centers has been to use excess energy generated from cooling the server rooms to heat other buildings (for example, a data center in Zurich heats nearby homes). These efforts to improve overall energy efficiency do not lower the PUE score in any of the categories because PUE is defined as an efficiency measurement of only the dedicated data center itself. According to the report, though, “currently there are on-going industry efforts to define a metric that could be used to account for this beneficial use, but it is specifically excluded from PUE.”

According to an article on GreenBiz.com, billions of dollars are wasted a year worldwide to run and maintain servers that sit on racks unused. Hopefully increased standards for energy management in data centers, such as the PUE metric, will help us be more mindful of how energy is used (or misused) in our IT hardware hubs.

Check out these related posts:

1. IPMI – How to Manage Your Data Center from the Golf Course Malfunctioning servers are more than a nuisance — they often...

Related posts brought to you by Yet Another Related Posts Plugin.

While this blog was operational, it was an emerging resource for IT people (and also those not so knowledgeable in electronics) to learn more about computers, have their questions answered, and their server problems solved.

I have taken over for the former blogmaster, Alex Pyatetsky, and will continue the good work that he has begun here. My name is Alex as well (confusing, yes).

I’ll begin by linking to a few posts in our other blog, the International Computer Concepts (ICC) company blog. The idea behind running two blogs simultaneously is that our company blog will be for general current events pertaining to servers, HPC, new technologies and the like. This blog, ServerProblemsSolved.com, will be more for introductions to new technology (like the introduction to IPMI post below) and issues related to, well, solving server problems.

So, without further adieu, I invite you to check out our introduction to InfiniBand post on the ICC blog. Also, if you are interested about how GPU (graphics-processing unit) servers are making supercomputers affordable for everybody, see that post as well.

No related posts.

Related posts brought to you by Yet Another Related Posts Plugin.

This is how we pick teams at ICC. Image by Groovyguru @ Flickr

The Official Launch

I know you’ve all been waiting for a long time, asking yourselves, “when will this damn blog be up? I have soooo many server problems!” Well, I have good news for you, fellow Nerds – today is your day.

Today, we celebrate the launch of Sever Problems Solved, your new favorite publication dedicated to finding practical solutions to frustrating server problems!

Who are you guys? What are you doing here?

We’re glad you asked.

This blog is presented on behalf of the good folks at International Computer Concepts (aka. ICC). Since 1993, we’ve been building servers and supporting a wide variety of clients including hosters, government, research/universities, start ups, end ups, and everybody in between.

This blog is our opportunity to hit many birds with 1 stone:

1. Give the IT community a reliable and thorough resource for answers relating to the most frustrating and relevant hardware problems.
2. Engage our readers to uncover and resolve community wide concerns as they crop up.
3. And hopefully, by using this resource, you’ll come to like us, and will consider us for future IT hardware purchases. If not, that’s ok too. We appreciate your eyeballs.

You Mentioned an Internship?

You bet. And its paid!

In order to deliver quality content on a consistent basis, we want to build a team of trusty interns who will help synthesize the collective wisdom of our company into a stream of articles.

Are you always tinkering with computers and technology? Are you the go-to guy/girl for all of your friends’ computer problems? Do you find yourself thinking “Damn, that’s dumb,” when you see technology being misused? If so, we may need to talk.

See the complete job description and instructions on how to apply.

Before you leave!

Thanks for checking out the very first post on this blog. We’re really excited to help you solve your server problems.

Please subscribe to our RSS feed or follow us on Twitter to keep up with our articles. Also, if you click the “Tweet This” button below and help us spread the word, we would be unspeakably thankful.

Having server problems? Want to request an article? Let us know in the comments below. If not, just say “hi” so we know you’re out there.

Check out these related posts:

1. Introductions to GPU and Infiniband Wow, it’s been so long since this blog was updated...

Related posts brought to you by Yet Another Related Posts Plugin.