David Wright, account manager at WhoIsHostingThis.com, is a passionate, self-proclaimed tech geek who loves all things IT.
Continuous monitoring of your data center efficiency is essential if you want to reduce your power cost. Reducing electrical consumption will allow your data center to be more sustainable and increase ROI.
This article is aimed at a wide variety of companies (or departments within companies) that want to learn how to manage data in a sustainable, ethical and efficient way by saving energy and at the same time increasing their ROI.
The increasing need for sustainability and efficiency
Data centers are popular in areas such as education, charity, the public sector and research organizations. There are also some pretty interesting and unusual data centers, such as Bahnhof located in a former military bunker in Sweden.
There are many factors that are forcing data centers to become more sustainable and run efficiently in terms of power usage. Business demand, cost and ROI, environmental pressure and security concerns are just a few of the influencing factors. These issues are targeted by governments all across the world and other organizations such as The Green Grid and even the European Union.
The first step to controlling the energy use of a data center is to have a good understanding of how the data center uses the energy. The best way to do this is by coming up with ways of measuring energy through energy efficiency metrics.
Determining your data center’s energy efficiency level will allow you to come up with a strategy. Benchmarking can be done by using data efficiency metrics. Below we’ll take a look at two of the most accepted benchmarking practices.
Power Usage Effectiveness
The most common energy efficiency metric is called Power Usage Effectiveness, widely known as PUE.
PUE is determined by using the following formula:
PUE = Total Facility Power/IT Equipment Power
Total Facility Power is the power measured at the utility meter. The IT Equipment Power includes all the actual load of IT equipment such as workstations, servers, storage, switches, printers and other service delivery equipment.
PUE is determined on a scale from 1 to 4, 1 being very efficient and 4 very inefficient.
PUE is a green computing principle promoted by The Green Grid, a global organization based in the US which aims to develop and promote data center energy efficiency.
The Green Grid is a non-profit association of technology providers, end users, facility architects, utilities companies and policy makers. They all work together toward improving the resource efficiency of data centers and information technology all around the world. The Green Grid is famous for creating efficiency metrics, PUE being their biggest hit so far.
Data Center Infrastructure Efficiency
Data Center Infrastructure Efficiency, more commonly known as DCIE, is another popular metric used to benchmark energy efficiency of a data center. It is used by many data centers throughout the world.
The most obvious difference between PUE and DCIE is that the latter is expressed as a percentage rather than a number. The higher the percentage the more efficient the data center.
DCIE can be worked out by using the following formula:
DCIE = IT Equipment Power/Total Facility Power x 100%
IT Equipment Power and Total Facility Power principles explained above apply to DCIE too.
Here’s a quick example that will help you understand how to work out your data center energy efficiency by using the two metrics explained above:
Total Facility Power = 320 kW
IT Equipment Power = 160 kW
PUE = 320/100 = 3.2
DCIE = 100/320 x 100% = 31.25%
You can now calculate your data center’s electrical efficiency and then use the spectrum below to determine whether or not you need to improve it.
We hope you found this article useful, please feel free to share your thoughts in the comments section below.
Industry Perspectives is a content channel at Data Center Knowledge highlighting thought leadership in the data center arena. See our guidelines and submission process for information on participating. View previously published Industry Perspectives in our Knowledge Library.