By Sam Prudhomme, Vice President of Sales & Marketing
Recently, I was interviewed by a Computer Weekly journalist, Fleur Doidge, who was writing an article focusing on the quick wins when it comes to improving systems performance in the data center. Inspired by our discussion, I’ve come up with Subzero’s top 5 ways to boost data center utilization.
The data center industry, quite rightly, has an ongoing, major focus on how it can improve both the performance and energy efficiency of its facilities. That’s partly down to the perception that our industry are major consumers of energy and contribute a high volume of carbon emissions each year.
According to an article published in Science Magazine, data centers account for around 1% of global energy use. It’s clear that we need to improve our environmental performance and to ensure we never forget we’re part of the sustainability solution, but we should also remember that data center performance and energy efficiency improvements make great business sense.
While there are many, many issues to consider as part of a comprehensive, long-term strategy to both improve data center performance as well as to achieve carbon neutral status, this article focuses on the ‘low hanging fruit’ – relatively simple actions, which will have an immediate positive impact on your facility, and with an ROI measured in months rather than years.
Step 1 – As Easy as (free) CFD
Those of you who know Subzero Engineering well will not be surprised that Step 1 involves a Environmental Impact Evaluation (CFD) of your data center. We believe it all starts with the data and offer this service for free. It is a simple, efficient, and super-fast way of discovering just how your data center is performing right now – where the power is, where the heat is, and isn’t, hence where the cold air does or doesn’t need to be.
Step 2 – Using the Data
Once the Environmental Impact Evaluation (CFD) has been carried out, you’ll be armed with a large quantity of data about how your data center is performing. It’s highly likely that you’ll be presented with some really quick wins. For example, you’ll discover where the hotspots (points of efficiency leakage) are; and part of the solution may be something as simple as installing any necessary blanking panels.
Then again, the CFD data may highlight that Row 5 in Rack 6 is running 15 degrees hotter than anywhere else in the data center. You’ll be able to decide whether you need to move this stack to a better location where more cooling is available, or maybe you just need to open up the grate to optimize or increase the airflow.
Step 3 – The 3 ms: Measuring, monitoring & Modulation
A data center is a live environment. So, although the CFD analysis can identify and help to resolve what we might call any ‘permanent’ power and cooling issues, it’s essential that you monitor and measure the performance of the power and cooling plant in real-time. This is because data center variables such as the IT load and operating temperatures are in constant flux. With the right system you are able to modulate the airflow accordingly. For example, if the cooling needs to react to the load inside each rack and cabinet, as well as respond to the impact of, say, an extremely hot outside temperature.
Rather than blast a load of cold air into the data center and ‘hope’ that it keeps the IT hardware within operating tolerances, with the right monitoring solution, you can be confident that you can modulate the cold air as required right down to the rack level. This ensures that the cooling usage is as effective and energy efficient as possible.
Step 4 – Contain Your Excitement
How would you like to reduce your PUE by 0.4? Or to achieve a 29% reduction in data center energy consumption? Well, these are the average savings we achieve for our customers when they deploy one of our containment solutions.
The initial Environmental Impact Evaluation (CFD) we carry out also proves how this can be achieved – it compares and contrasts hot vs cold aisle containment and containment vs no containment. Furthermore, a containment solution ensures that Steps 1-3 really do achieve the maximum performance and energy efficiency improvements within the data center.
Without containment, you’ll still have hotspots – separating hot and cold air will be hit and miss and far from being optimized.
With containment, you can bring down the power consumption to cooling ratio close to a 1:1 match in KW consumed – that’s how the energy consumption/utility bill reduction is achieved.
As for the PUE reduction? Well, that’s achieved by smarter, more efficient use of an optimized combination of chilled water and the air conditioning fans. The US Environmental Protection Agency (EPA) estimates that containment can reduce fan energy consumption by up to 25% and deliver 20% savings at the cold water chiller.1
One final containment benefit – we supplied a containment solution to a colo customer and by separating the hot and cold air in their facility, we helped them to not only eliminate hotspots, but also to increase rack density by an average of 14%.
Step 5 – Turn the Lights out
This breadth of knowledge brings me to my final data center performance and energy efficiency improvement: turn out the lights. By that, I actually mean remove anything incandescent and go with an LED retrofit kit within your existing tray system. And then automate the lighting system.
It may be a while before a true lights out data center becomes the norm, if ever, but that’s no excuse not to ensure that your lighting system is as energy efficient as possible. By using LEDs and only using the lights when needed you’ll improve your energy efficiency as well as your bank balance.
While Subzero Engineering’s major focus is data center consultancy, using CFD analysis and containment solutions, to help drive performance and efficiency improvements we can also help owners/operators with their critical power infrastructure, DCIM and other solutions as required.
Download the 5 Steps to Improving Data Center Performance & Energy Efficiency pdf here.
1Recalibrating global data center energy-use estimates – Science Magazine 2018