More Cooling

More Cooling With Less $$

My last post took a look at the maintenance savings possible through more efficient data center/facility cooling management.  You can gain further savings by increasing the capacity of your existing air handling/ air conditioning units.  It is even possible to add IT load without requiring new air conditioners or at the least, deferring those purchases.  Here’s how.

Data centers and buildings have naturally occurring air stratification.  Many facilities deliver cool air from an under floor plenum.  As the air heats and rises, cooling air is delivered low and moved about with low velocity.  Because server racks sit on the floor, they sit in a colder area on average.  The air conditioners however, draw from higher in the room – capturing the hot air from above and delivering it, once cooled down, to the under floor plenum. This vertical stratification creates an opportunity to deliver cooler air to servers and at the same time increase cooling capacity by drawing return air from higher in the room.

However, this isn’t easy to achieve.  The problem is that uncoordinated or decentralized control of air conditioners often causes some of the units to deliver uncooled air into the under floor plenum. There, the mixing of cooled and uncooled air results in higher inlet air temperatures of servers, and ultimately lower return-air temperatures, which reduces the capacity of the cooling equipment.

A cooling management system can establish a colder profile at the bottom of the rack and make sure that each air conditioner is actually having a cooling effect, versus working ineffectively and actually increasing heat through its operation. An intelligent cooling energy management system dynamically right-sizes air conditioning unit capacity loads, coordinating their combined operation so that all the units deliver cool air and don’t mix hot return air from some units with cold air from other units. This unit-by-unit but combined coordination squeezes the maximum efficiency out of all available units so that, even at full load, inefficiency due to mixing is avoided and significant capacity-improving benefits are gained.

Consider this example.  At one company, their 40,000 sq. foot data center appeared to be out of cooling capacity.  After deploying an intelligent energy management system, not only did energy usage drop, but the company was able to increase its data center IT load by 40% without adding additional air conditioners and, in fact,  after de-commissioning two existing units. As well, the energy management system maintained proper, desired inlet air temperatures under this higher load condition.

Consider going smarter before moving to an additional equipment purchase decision.  Savings become even larger if you consider avoided maintenance costs for new equipment, and energy reduction through more efficiently balanced capacity loads, year-over-year.

2011 Reflections

There is a saying in the MEP consulting business: “no one ever gets sued for oversizing.” That fear-driven mentality also affects the operation of mechanical systems in data centers, which accounts for why data centers are over-cooled at great expense.  But few facility managers know by how much.  The fact is that it has been easier – and to date –safer to over-cool a data center as the importance of the data it contains has increased and with that importance, the pressure to protect it.

Last year that changed.  With new technology, facility managers know exactly how much cooling is required in a data center, at any given time. And, perhaps more importantly, technology can provide warning – and reaction time – in the rare instances when temperatures increase unexpectedly. With this technology, data center cooling can now be “dynamically right-sized.”  The risk of dynamic management can be made lower than manual operation, which is prone to human error.

In our own nod to the advantages of this technology, we re-named the company I co-founded in 2004, from Federspiel Corporation to Vigilent Corporation.  As our technology increased in sophistication, we felt that our new name, denoting vigilance and intelligent oversight of facility heating and cooling operations, was more reflective of the new reality in data center cooling management.   Last year, through smart, automated management of data center energy consumption, Vigilent reduced carbon emissions and energy consumption of cooling systems by 30-40%.  These savings will continue year after year, benefiting not only those companies’ bottom line, but also their corporate sustainability objectives.   These savings have been accomplished while maintaining the integrity and desired temperatures of data centers of all sizes and configurations in North America, Canada and Japan.

I’m proud of what we have achieved last year.  And I’m proud of those companies who have stepped up to embrace technology that can replace fear with certainty, and waste with efficiency.

Unexpected Savings

Data Center Cooling Systems Return
Unexpected Maintenance Cost Savings

Advanced cooling management in critical facilities such as
data centers and telecom central offices can save tons of energy (pun
intended). Using advanced cooling management to achieve always-ready,
inlet-temperature-controlled operation, versus the typical always-on,
always-cold approach yields huge energy savings.

But energy savings isn’t the only benefit of advanced cooling management. NTT America recently took a hard look at some of the
direct, non-energy savings of an advanced cooling system. They quantified
savings from reduced maintenance costs, increased cooling capacity from
existing resources, improved thermal management and deferred capital
expenditures. Their analysis found that the non-energy benefits increased the total dollar savings by one-third.

Consider first the broader advantages of reduced maintenance costs. Advanced cooling management identifies when CRACs are operating
inefficiently. Turning off equipment that doesn’t need to be on reduces wear and tear. Equipment that isn’t running isn’t wearing out. Reducing wear and tear reduces the chance of an unexpected failure, which is always something to avoid in a mission-critical facility. One counter-intuitive result of turning off lightly provisioned CRACs is that inlet air temperatures are reduced by a few degrees. Reducing inlet air temperature also reduces the risk of IT equipment failure and increases the ride-through time in the event of a cooling system failure.

The maintenance and operations cost savings of advanced cooling
management is significant, but avoiding downtime is priceless.

Cooling Tips

Ten Tips For Cooling Your Data Center

Even as data centers grow in size and complexity, there are still relatively simple and straightforward ways to reduce data center energy costs. And, if you are looking at an overall energy cost reduction plan, it makes sense to start with cooling costs as they likely comprise at least 50% of your data center energy spend.  Start with the assumption that your data center is over-cooled and consider the following:

Turn Off Redundant Cooling Units.  You know you have them, figure out which are truly unnecessary and turn them off. Of course, this can be tricky. See my previous blog on Data Center Energy Savings.

Raise Your Temperature Setting. You can stay within ASHRAE limits and likely raise the temperature a degree or two.

Turn Off Your Humidity Controls. Unless you really need them, and most data centers do not.

Use Variable Speed Drives but don’t run them all at 100% (which ruins their purpose). These are one of the biggest energy efficiency drives in a data center.

Use Plug Fans for CRAH Units. They have twice the efficiency and they distribute air more effectively.

Use Economizers.  Take advantage of outside air when you can.

Use An Automated Cooling Management System. Remove the guesswork.

Use Hot and Cold Aisle Arrangements. Don’t blow hot exhaust air from some servers into the inlets of other servers.

Use Containment. Reduce air mixing within a single space.

Remove Obstructions. This sounds simple, but  a poorly placed cart can create a hot spot. Check every day.

Here’s an example of the effect use of an automated cooling management system can provide.

The first section shows a benchmark of the data center energy consumption prior to automated cooling. The second section shows energy consumption after the automated cooling system was turned on. The third section shows consumption when the system was turned off and manual control was resumed, and the fourth section shows consumption with fully automated control. Notice that energy savings during manual control were nearly completely eroded in less than a month, but resumed immediately after resuming automatic control.

Occam’s Razor

Data Center Energy Savings

The simplest approach to data center energy savings might suggest that a facility manager’s best option is to turn off a few air conditioners.  And there’s truth to this.  See the graph below, showing before and after energy usage, and the impact of turning off some of the cooling units.

Before & After Energy Management Software Started

But the simplicity suggested here is deceptive.

Which air conditioners?

How many?

How will this truly affect the temperature?

What’s the risk to uptime or ridethrough?

While turning things off or down is likely our greatest opportunity for significant, immediate savings, the science driving the decision of which device to turn off and when, is complex and dynamic.

Fortunately, a convergence of new technology – wireless sensors for continuous, real-time and location-specific data, along with predictive, adaptive software algorithms that take into account all immediate and known variables at any given moment – can predict the future impact of energy management decisions, taking on/off decision-making to a new level.  Now, for the first time, it’s possible – thanks to the latest AI technology – to automatically, constantly and dynamically manage cooling resources to reduce average temperatures across a facility and avoid hot and cold spots of localized temperature extremes. Simultaneously, overall cooling energy consumption is reduced by intelligently turning down, or off, the right CRACs at the right time. The result is continually optimized cooling with greater assurance that the overall integrity of the data center is preserved.

Bay Area Talks

Data Center Energy Management Presentations

Heads up on a couple of my upcoming presentations in the Bay Area on June 21!

TiE Silicon Valley

The Silicon Valley TiE office is hosting a panel discussion on energy alternatives for data center management.   I’ll join four executives from the industry to discuss and debate:

  • Load management
  • Replacement of existing infrastructure
  • Cooling Management

We’ll discuss trends, tradeoffs and the effects of options in these areas.

For details, click here: http://sv.tie.org/event/sig-energy-energy-management-data-centers

Stop by and say hello!

Environmental Defense Fund Climate Corps Program

The EDF sponsors a terrific program to place MBA fellows at large companies to collect energy data, analyze accordingly and provide
recommendations.  I will provide a private webinar to these interns on energy efficiency strategies for data centers.