Estimating power demand is the biggest challenge for data center designers, with no absolute answer and no simple...
When designing for total server power consumption, a kW per rack approach is more useful than Watts per square foot, which hasn't been a valid measurement for years. The right methodology to develop a good estimate depends on how much you know about your existing operation, and its probable growth trends.
Create representative equipment groupings as capacity units, but don't get too granular. A large, stand-alone big iron system can be a single capacity unit, but for normal cabinets in a sub-10,000 square foot data center, eight to 12 capacity unit definitions should be plenty. You aren't developing a capacity unit for every cabinet since you won't install IT equipment exactly this way. The intent is to develop realistic, generic requirements you can extrapolate for the entire space.
Don't overestimate power draws. Nameplate numbers on IT equipment are useless and they lead to outrageous overestimates. Use the hardware manufacturers' online configurators if possible. As a last resort, use the server's power supply rating -- a server with a 300-Watt power supply can never draw 800 Watts. Size the power systems based on real demand loads.
Dual-corded equipment adds redundancy to IT hardware, and the lines share power load. If a dual-corded server has two 300-Watt power supplies, it can still draw no more than 300 Watts in your power design, because each power supply has to be able to handle the server's full load (not including power supply efficiency calculations).
The other way to estimate total server power consumption is to use industry norms. Unless you're hosting high performance computing, you can probably figure groupings in three levels of density: Low density cabinets run 3.5 to 5 kW; medium density run 5 to 10 kW; high density run 10 to 15 kW. The amount of each rack type to allocate depends on your operation. Generally, data centers operate with about 50% low density cabinets, 35% medium and 15% high density.
Download this form to estimate your server power consumption in capacity units.
When you've used either of these methods, do a sanity check by dividing the existing uninterruptible power supply reading by the existing cabinet count to get an average. Do the same for your projected cabinet count and total estimated server power load in the deployment. Be aware that very few server deployments actually operate anywhere near the designer's initial load estimate maximums.
If your projected average is more than 1.5 times your existing average, take a closer look at the numbers. This result is fine if you expect a significant density increase, due to new business requirements or increased virtualization onto blade servers. But if there's no apparent reason for such a density growth, re-examine your assumptions.
About the author:
Robert McFarlane is a principal in charge of data center design at Shen Milsom and Wilke LLC, with more than 35 years of experience. An expert in data center power and cooling, he helped pioneer building cable design and is a corresponding member of ASHRAE TC9.9. McFarlane also teaches at Marist College's Institute for Data Center Professionals.
Most server cabinets today are rated at 2,500 to 3,000 lbs. capacity. With data center densities generally increasing, plan the building to support close to capacity loads. Thoroughly research cabinet and raised floor loading to avoid critical design errors.
Dig Deeper on Data center design and facilities
Related Q&A from Robert McFarlane
Our latest firewall/VPN firmware upgrade left CPU usage at 100%. A malfunctioning DHCP-Server means people aren't getting IPs. I have to pull the ... Continue Reading
Do battery cooling cabinets save money over cooling batteries within the whole data center? Continue Reading
We are looking at a building surrounded by several acres of land for a new data center. Should we consider geothermal horizontal loops for cooling? Continue Reading