Posted by Eric Kraieski on Mon, Feb 15, 2010
Latest PUE Standards News from Green Grid
The Green Grid recently announced agreement by global world governments on using PUE as the primary measurement of data center efficiency:
"A group of global leaders met on February 2, 2010 to agree on data center energy efficiency measurements, metrics, and reporting conventions. Organizations represented were the U.S. Department of Energy's Save Now and Federal Energy Management Programs, U.S. Environmental Protection Agency's ENERGY STAR Program, European Commission JRC Code of Conduct, Japan's Ministry of Economy, Trade and Industry, Japan's Green IT Promotion Council, and The Green Grid."
"The collective groups are in agreement on the following guiding principles, as an interim step toward the desired outcomes (1. b.). It is recommended that data centers begin to measure PUE according to these principles... "
Here is the announcement from Green Grid:
Posted by Michael Bullock on Fri, Jun 26, 2009
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 CIO.com 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.
Posted by Michael Bullock on Mon, Mar 23, 2009
The role of PUE, DCiE and new performance metrics
According to the EPA’s 2007 report to Congress on server and data center energy efficiency,the two largest consumers of electricity in the data center are the support systems (50% of total) and general servers (34%). Last week I wrote about Energy Star Servers which over time will drive down the electrical demands of the servers. Today I’d like to focus on overall data center efficiency and productivity and the efforts of the Green Grid industry alliance.
For the most part, being green in the data center is about increasing power efficiency and thereby reducing greenhouse gas emissions. From a purely environmental and ecological perspective, higher levels of green could be achieved by examining the entire life cycle of technology systems— from production and supply chain all the way to the disposal of toxic components. But for now let’s stick with the power efficiency theme.
Here are some Green Grid developed metrics for evaluating data center facility efficiency:
- PUE—Power Usage Effectiveness represents how much total power you need to drive your IT systems when you take into account power distribution, cooling, humidification, lighting, etc. If you need 1MW to run your IT systems, a PUE of 1.8 means that you are consuming 1.8MW to get this usable level of power.
- DCiE—Data Center Infrastructure Efficiency represents the ratio of IT equipment power to total facility power. Using the same example, a facility with a PUE of 1.8 has a DCiE of about 55%, meaning a little more than half of the power used by the data center is making its way to the IT systems (no mystery here; DCiE is simply the inverse of PUE).
From a planning perspective, I’ve personally found PUE to be a more useful tool than DCiE because it gives you a simple multiplier you can use to estimate your increasing facility requirements as you add new servers, storage and the like. While PUEs generally fall into the 1.7 (more efficient) to 3.0 range (less efficient), I have seen PUEs approach 1.3 when a holistic, facility-wide approach is taken regarding power efficiency.
Keep in mind, the PUE and DCiE numbers tell you how efficiently your data center is operating from a power distribution and cooling perspective. They do not tell you how efficiently your IT group is delivering useful value per kW of total power consumed.
This is exactly what Green Grid is trying to do next: define ways to measure overall Data Center Productivity (DCP). That is, Green Grid is attempting to help you quantify how well the energy you’re using is being applied to useful work. Since this is very complicated and will vary by application and industry, the Grid is hoping to define useful “proxies” or indicators that can provide some normalized measurement and useful insight.
Here are some of the types of measurement proxies being considered by the Green Grid (read the Green Grid Proxy White Paper for more details):
- Server productivity.Because you need a greater number of older servers to get the job done, and because older servers consume a lot more electricity per instruction executed than newer ones, you could come up with a productivity measurement based on MCUPS (million compute units per second) per kW consumed by the data center (the more, the better). This, of course, ignores the value of stored data which may be considerable, or even required for regulatory compliance. However, it provides a measure worth consideration.
- Server utilization and virtualization. Running high-end servers at 20% capacity means they are being used inefficiently.The idea here is that running servers at higher utilization rates is good and a highly virtualized environment has the
- (server utilization continued) potential to produce more useful work per kWh consumed. Of course, this would not be good way to measure efficiency for applications that are seasonal or “bursty”— like those used by retailers (for, say, the Christmas rush), financial brokerages (with sudden floods of transactions) and even national security applications that are built for peak loads to guarantee performance in any eventuality.
- Bits out per kWh. The idea here is that it may be possible to measure useful work simply based on output. This may in fact be a great proxy for data intensive applications like websites, VoIP and video where the name of the game is moving bits efficiently. On the other hand, this would be a poor measurement for applications that aggregate and analyze data, then report out digestible, concise information, such as in business intelligence applications.
My purpose here is not to disparage the efforts of the Green Grid regarding DCP. I do believe, however, that the DCP models could use more input from the user community. That’s right: I mean you. Please post any comments here or, if you prefer, you can get involved with the Green Grid directly and provide feedback to the DCP survey.
At the same time, I encourage you to not lose sight that optimizing your PUE offers low hanging fruit in achieving improved efficiency, reducing carbon emissions and saving money. Modern facility technologies such as ultrasonic humidification, high efficiency harmonic mitigating transformers and variable frequency drives (VFDs) can be effective in dropping your PUE into the more efficient 1.3-1.5 range.
In fact, let’s compare IT server and storage upgrades with facility infrastructure improvements (PUE):
- For a baseline, let’s assume your IT equipment consumes 2MW with a PUE of 2.5. By investing in more efficient servers and storage, let’s say you are able to cut IT power demand by 30%. If the cooling and power systems scale down as well, you will cut your total power from 5MW to 3.5MW. Not bad— but also not really a quick fix as you migrate apps to your new servers and retire old systems.
- Now, using the same scenario, let’s say we improve facility efficiency instead (the support systems—cooling, humidification, distribution, etc.), driving PUE from 2.5 to 1.5 with changes that are invisible to the applications, servers and storage systems. In this scenario, you could reduce total electricity by 40% to 3MW and do it with a lot less migration expense and pain.
There’s no doubt that replacing older,inefficient computers and storage systems with more energy efficient models is a good idea. Clearly, ENERGY STAR servers and storage will help through natural technology refresh cycles. Virtualization will reduce the number of servers you need, allowing your systems to run at higher operational efficiency.
However, if you want to make an immediate impact that will continue to pay dividends as you refresh your servers, storage and network systems over time, improve your PUE first.