by Michael Bullock

5 Myths of Data Center Power Usage Optimization

Jun 26, 20097 mins
Data Center

Understanding and improving power usage effectiveness (PUE)

At a recent CIO / CFO conference, I saw why so many executives tune out when the topic turns to green IT and why they fail to make the “no-brainer” decisions that would immediately benefit their organizations.  At the root of their apathy is the frequency with which they’re bombarded by green claims from vendors that often are misleading and sometimes absolutely meaningless.

As a reader commented on my recent blog Green IT Hype vs. Real Deal:  “too many companies are running around hyping themselves as ‘the green solution’ while doing nothing more that re-advertising their same old products.”

And this, my friends, is a big part of the problem.  Despite valuable green innovations in the data center, the really good ideas are having trouble rising above the clatter of the vendors’ PR and sales machines.

Hopefully, data center executives can hear this: If you can improve your Power Usage Effectiveness (PUE) in ways that produce a fast payback, you will save money and reduce your carbon foot print.  This is like hitting the Daily Double: You conserve natural resources while making money. 

Think of it this way. What if you could instantly increase your car’s fuel efficiency by 35 percent via an upgrade that would pay for itself in the first year based on reduced fuel costs alone? You’d jump at the chance, right? So why is there so little interest in doing the same thing in data centers? Because it’s hard to tell which upgrades are real and which are only “the same old products” in new green wrapping.

I’m not going to dive into specific energy saving technologies; instead, I’m going to provide a framework that will allow you to get beyond the vendor hype and evaluate them on your own. (If you’re curious about what these technologies are, check out my recent blogs on built green / built right  and cool ways to save money). 

A quick refresh: A data center’s PUE is the total load required to operate the IT systems plus support systems such as power distribution, humidification, and cooling.  A PUE of 2.0 – which is typical of most data centers today – means that for every dollar spent on IT load you burn up another dollar on support. Some facilities have average annual PUEs over 3.0 (not good) and the best run data centers can sustain PUE levels around 1.3.

So here are five myths regarding PUE engineering that often get in the way of good data center optimization and design and prevent executives from making informed decisions for their data centers:

Myth 1 – PUE is a constant that applies 24/7/365

Not true.  PUE can fluctuate by season, and even by time of day.  For example, if the design leverages the free cooling of outside air, then that benefit will only be available when the outside temperature is optimal.  That’s why it’s important to determine average annual PUE and not best case – which may only apply on cool days and nights.  So when a vendor says that its technology will reduce your PUE to 1.3, take the time to find out if this claim is best case, steady state, or annual average.

Myth 2 – During data center design and construction, you should optimize PUE to full anticipated load.

Not only is this not true, it’s an approach that’s doomed from the start, almost guaranteed to leave you with an underutilized or oversubscribed data center for much of its life cycle. You’d be better served by thinking of your data center as a resource that will morph over time. This will guide you to make design decisions that emphasize flexibility.

For example, the power density in your data center will change over time and with it the demand for power and cooling. If you build for the target capacity, you’ll be spending money in the early years for more cooling capacity (and backup power) than you need. In other words, a half-full data center designed for an average annual PUE of 1.4 may run at 2.0 until it fills up, however long that may take.

Building a flexible environment means you might oversize pipes, raise your floor above three feet and use variable air handling options. In this way you can build a data center with a PUE that will provide more scalability (and efficiency) over an expected 10+-year life cycle.

Myth 3 – Alternative energy sources improve PUE

False.  Supply side technologies such as cogeneration and renewable energy sources do not improve PUE, which is a measure of consumption efficiency.  If anyone tells you that alternative energy sources will improve your PUE, keep asking them how they’ll improve power consumption efficiency. Eventually, they’ll shut up.

I’m not saying that renewable energy sources are bad; they simply don’t impact PUE.  And sometimes they don’t save much money, either. Once maintenance costs are factored in, the power company will still need to provision power to you in case the system fails. 

So you should evaluate these power sources on their own financial merit based on cost, reliability, and time-to-payback.  Don’t jump in thinking these alternatives will earn you efficiency rebates or future carbon credits, especially if they’re driving inefficient power and cooling.

Myth 4 – You can’t improve PUE for existing facilities

Luckily, this is also false. If your data center is operating above its designed power and cooling capacity, there are things you can do to improve your PUE. The biggest gain can be achieved by removing heat- creating support systems from the data center floor. You can leverage outside air economizers; turn off the steam-based humidification systems, or replace CRACs with roof-top units.  Anything that reduces heat generation or increases cooling can improve PUE, may have a fast payback, and can be subsidized through power company rebates. On the other hand, if you introduce a new technology that consumes electricity and adds heat to the system, you may be addressing one problem while creating another.  For example, floor fan tiles are a sure giveaway that a facility is operating in a suboptimum range.

Myth 5 – New servers & virtualization improve PUE

This is partly true and partly false.  By now, everyone should understand how server and storage virtualization can reduce the number of systems required to support your mission while lowering power consumption costs. Again, this alone does not improve PUE. If your data center is operating at the top 10 percent if capacity, simply removing load (i.e., heat generation) may reduce the duty cycle on the cooling system enough to improve PUE. But data centers operating below 80 percent of maximum capacity will not see PUE improvements through virtualization.

That said, these systems use less electricity and understanding how to leverage virtualization should be at the top of everyone’s green agenda.

Hopefully, dispelling these myths will allow you to ask the right questions of your architects, engineers, and vendors as you put together the data centers you’ll need to live with for 10 years or more.  By evaluating PUE for yourself, you’ll be ready to save greenbacks and the environment.

Michael Bullock is founder and CEO of Transitional Data Services (TDS) a Boston, MA, based consulting firm focusing on green data center design / optimization, data center relocations, enterprise applications and technical operations.