I can hear my mother telling me this like it was yesterday, “It’s the little things that make a big difference.” So often do we get caught up in the big picture that this can be all but forgotten. As I walk around the raised floor I am reminded of this by the sight of one and two open U spaces appearing sporadically throughout the center. The saying, “It’s the little things,” could not be more true for this scenario. Considered best practice throughout the data center industry, blanking, more often than not becomes an afterthought at best. Open spaces left within racks allow the hot isle air to recirculate to the cold isle leading to a number of problems from placing operating equipment at risk of overheating to the added energy costs. Now rack blanking and the use of various types of blanking panels is nothing new to the personnel that work at a data center. To get the most out of this “little thing that makes a big difference” though, a new approach or deliberate effort, to blanking could go a long way. Continue reading The Raised Floor Perspective- Blanking
Monthly Archives: February 2014
ROI – a misunderstood metric
Right now there’s a phone commercial. A guy is building a birdhouse and he says to someone else “I’m thinking of renting it out to get a better return on investment”. Now this guy understands what ROI is. He has an investment. He understands what it means. It’s how much he makes relative to what he put into it.
Investopedia defines ROI as the amount of net income returned as a percentage of shareholder equity. It further amplifies this definition to allow for different organizations to calculate ROI differently. ROI can be a cash amount, it can be a ratio, a percentage, or an annual yield. One thing clearly absent from this list of possible ways to calculate a return on investment is a time period.
Maximizing Utilization by Revisiting SLAs
First, let me define SLA as it relates to this discussion. SLA is service level agreement and for the facility minded individual is how we guarantee conditions at the server. We guarantee uptime and with properly corded devices we guarantee customers will not lose power. We also have temperature and humidity SLAs. They might be do not exceed 60-89 degrees f and 20-80% relative humidity for more than 4 hrs, for example. Now we have a target band tighter than that but that is our promise.
With that understood, we can start the discussion. Let’s say we have 2 MW busses with 4 primary and 1 redundant bus using static transfer switches to transfer to the reserve (redundant) bus. Let’s say that each bus has 1400 kW of UPS power, requires 100 kW for house loads, 100 kW for UPS losses, 40 KW for lighting, and 760 kW reserved for design day cooling. As we can see we will not be able to use about 400 kW of installed UPS capacity. Continue reading Maximizing Utilization by Revisiting SLAs
House loads / PUE
Right now we’re having a bit of a debate on how to calculate PUE. We are all familiar with the GreenGrid definitions of PUE 1, 2, 3 etc but our debate is which is most valid. As a colocation provider we lease data center space. We also lease data center adjacent office space. Should this space count against our PUE? Some of our sites don’t have offices while some do. Comparing them to identify opportunities would require a similar metric wouldn’t it? The office really isn’t supporting the center, it’s its own entity. At the same time, we have been including office, so the historical readings will no longer be as relevant if we change PUE. I’d like to open up a discussion here if anyone is interested.
I’m not as obsessed with conforming to an industry standard as I am with providing useful standards for comparison and progress. Of course us in the know are looking at so much more than just PUE, we break down the load path, find out where our power is and where it should be, and look for opportunities or solve issues. Yet PUE is an important tool for executive level reporting.
Metrics for goals – PUE, kWh, or $$
What’s the best measurement of success in an organization when your talking about energy savings? Cash savings is great because it’s quantified in the most important business metric. Unfortunately it does not correct for changes in IT load and utility pricing. kWh gets at what is most controllable by efforts of the group trying to save energy, but again needs to be calibrated for IT loads. If we benchmark against expected energy spend (vice previous spend or trended spend) then we can use the actual IT load and the results can represent what the energy efforts actually accomplished. PUE doesn’t need any calibration, but it isn’t quantified. The statement PUE went from 1.77 to 1.65 is meaningless to a income statement. And those are the results with impact ( save $400,000 a year with a net present value of $2,500,000 and a first cost of $300,000 for improvement is a great victory to anyone in corporate finance). It’s a juggling act, maybe it depends more on who is seeing it. But when your getting evaluated for year end performance, which is most important?
Kilawhat?
Many people make the mistake of confusing a Kilowatt (a unit of power) and a Kilowatt-hour (A unit of energy). The same could be said about Watts and Watt-hours, but the Kilowatt is much more commonly applied.
A kilowatt is power. Think of it as a rate of consumption. This is how fast you are gobbling up electrons from the grid.
A kilowatt-hour is energy. This represents the amount of electrons you have gobbled from the grid since your last utility bill, for example. (not really electrons, but you get the picture) Continue reading Kilawhat?
VFDs Spend a little Save a LOT
So one of the big things I have been pushing for in my job has been VFDs on every motor >2 horsepower. VFDs can be incredibly useful tools. First of all, without considering energy implications, they give you finite control of the motor. Just being able to modulate capacity is huge, especially if you have a control system that can handle the input.
Energy savings, however, are really where its at. Most of our motors in the data center are connected to a fan or a pump. For the most part, fans and pumps are variable torque loads and (with the exception of some oddball positive displacement pumps) vary their consumption with the cube of the speed, per the fan laws. Continue reading VFDs Spend a little Save a LOT
Welcome to PUElink
Thanks for visiting my site. I plan to discuss my thoughts and ideas regarding effective and efficient operation of data centers. In particular, I want to focus on existing infrastructure and how to maximize the utilization (Install more server power) while at the same time improving efficiency.
PUElink - Saving Energy and Maximizing Capacity 