As facility managers are often faced with the challenges posed by their IT departments’ excessive energy appetites, they need to make an honest effort to understand power consumption if they hope to promote overall facility-wide energy efficiency. In modern buildings, IT equipment contributes to a significant portion of power consumption and thus, operating costs. In order for facility managers to implement an effective green building strategy, IT departments need management and measurement tools capable of telling them which actions will have the biggest impact to use power more efficiently.

While facilities staff is usually responsible for paying the electric bill, it is the IT department that consumes most of the building’s power. For example, data centers account for up to 50 percent of the energy used in commercial buildings and consume 10 times more energy per square foot than the rest of the building. With best practices instituted by the facility to optimize the “shell” of the data center, IT equipment often consumes more than half of the power bill.

Historically, facility management teams have approached IT energy demands as unavoidable operating costs. Instead, facility management teams must jointly work with IT managers to put in place tools that establish a dialogue around effective energy efficiency strategies.

By treating energy as an asset, facilities and IT can jointly address pressing energy issues: ensuring continuous operation and preventing power outages, reducing energy consumption and costs, and provisioning for future growth or consolidation. Power and environmental conditions affect both facilities and IT. Air temperature and humidity feed back into the building management system (BMS) to control chillers, air handlers, CRAC units, and humidification systems, but temperature also impacts the mortality of IT equipment and placement within a rack. Power is distributed from switchgear to IT equipment, but facilities typically only measure at the highest levels, whereas IT staff aims to get the most computing done per Watt down at the equipment level.

Given the significant overlap of data used by facilities and IT, why are the two organizations still operating in silos, with unconnected tools? Facilities management is missing out on data that IT has; and IT is missing out on data from facilities. The data center of the future is one where energy and environmental conditions are managed holistically and jointly.

The data center is there to run applications and provide services. While facilities (and in many cases, IT) would like to treat IT systems as a black box that consumes power uniformly, advances in virtualization and cloud computing are changing this view of the world. In periods of low utilization, applications can be moved (physically and virtually) to a corner of the data center, shutting down parts of the server and storage pools that are not in use. Now, only this segment needs to be cooled. Joint management enables this scenario, and this is just one of many improvements possible in today’s data centers.

To work together, the key is following and then repeating a proven set of three steps, jointly undertaken: measure, analyze and act. By implementing the right system and following these steps, IT managers can significantly reduce energy usage while optimizing use of the assets they have in the data center. And by working with IT managers to implement this process, facility management can gain control over ever-increasing energy costs. Here is a summary of the three steps as they relate to data center energy management.

Measure

A recent McKinsey report shows that the average data center only utilizes 6 percent of its servers and only 50 percent of its facilities. It’s amazing how much opportunity there is to better manage power in the data center.

First and foremost, the organization must figure out exactly how much energy it is currently using, where it is being used, and for what purpose. The joint IT/facilities team must arm itself with as much information as possible, measuring where and when power is consumed to set a baseline whereby progress can be evaluated. Also, it is important to keep in mind that the power coming into a data center is not the same as the power being used by the equipment. By measuring every step that the power takes along the way to the equipment, whether it’s through the uninterruptible power supply (UPS) or the power distribution system, the IT/facilities team can get an accurate read on what needs to be fixed. This process is true for any industry that consumes power—data centers, commercial buildings, industrial facilities, and so on.

It is also critical to make sure measurements are thorough and detailed and to avoid taking shortcuts. If the organization wants to reduce power operating costs, the IT/facilities team has to know exactly how much power it is using and how it’s being used.

Analyze

In the Analyze phase, the team dives into the details to find precise remedies for saving power, lowering risk or freeing up capacity. Analysis involves two major components: consolidating all of the data collected into meaningful actions, and strategizing about which actions are best to employ. Start by determine which areas are consuming the most power. There are potential energy leaks and losses throughout the data center. Data center technology has evolved rapidly in the last 10 years; if the IT/facilities team hasn’t upgraded the data center, it is likely that less than half of the power is actually being delivered to the IT loads to perform useful computing functions.

Key questions to be answered are: What are the costs associated with those areas? Are there any significant trends? In the Analyze phase, the goal is to take the massive amount of data gathered and put it into a succinct and understandable context.

Analysis is not just about the power distribution and flow, but also how power is used by IT equipment. Continuous, real time measurements provide insight into when the IT equipment is in use, and how much of its power and computing capacity is utilized. Tracking idle periods and usage patterns identifies candidates for virtualization, improperly configured equipment, equipment that is no longer being used, and gross offenders of power relative to their peers.

There are many options for improving energy efficiency, but they each have different pros and cons. To put these options into context, if a virtualization strategy has a proposed 10:1 consolidation ratio for 20 percent of the IT equipment, the team can calculate the total energy savings the organization will gain. If IT is 50 percent of the total data center energy consumption, that virtualization project saves 9 percent of the total bill. Similarly, power distribution architectures can be updated to save up to 80 percent, but distribution losses only account for 10 percent of most data center facilities, and thus yield only an 8 percent savings. It is important to figure out the return on investment (ROI), as well as the total cost of ownership (TCO), based on these calculations, and then put in place a strategy that’s backed by the actual characteristics of the organization’s data center.

Act

Once the IT/facilities team has completed the measurements and analyzed and identified a strategy, the next step is to mobilize, plan and act on energy measures.

By putting policies and strategies in place, IT managers can measure every tier of the data center—servers, storage, racks, cooling systems—and analyze and identify equipment that’s not being used in an efficient manner. Once they’ve identified the things that aren’t performing up to their specifications, they can act by employing new policies, by consolidating equipment using new techniques such as virtualization, and by rescheduling jobs to run more efficiently.

While the previous example may be IT-focused, the end result has a tremendous impact on facilities management. To put it in perspective, saving one Watt at the server component level can save up to another 1.84 Watts in cooling and power distribution without doing anything else—a total saving of 2.84 Watts.

And it’s not just about optimizing the facilities and equipment. Adjusting how people perform their jobs can result in energy reduction as well. Day-to-day operations management determines what applications run where. IT can adjust where applications run to take advantage of the most efficient servers for that task. IT can also incorporate new software, replace faulty equipment, and turn off equipment that isn’t being used. Facilities can help by identifying the most efficient space for new equipment, and pinpoint where power and cooling capacity can be best utilized.

Here’s another reason to act. According to the Environmental Protection Agency (EPA), enterprises can save up to $4 billion annually in their data centers by becoming more efficient. Furthermore, many utilities are offering incentives for every kilowatt-hour saved, as long as reductions can be proven.

Technology Has the Answer

Today there are non-invasive software solutions for managing energy in the data center. Performance and efficiency can be improved, downtime reduced, and expansion or consolidation can be rationalized with real data. By finding an energy management solution that bridges the IT and facilities gap, organizations are armed with a comprehensive picture of where, when and why energy is used. With one view into the energy profile of a data center and leveraging a common console, increased cooperation between facilities and IT is attainable, resulting in significant energy savings.

About the Author
Joe Polastre is co-founder and chief technology officer at Sentilla, a company that provides enterprise software for managing power in the data center. Joe is responsible for defining and implementing the company’s global technology and product strategy.

Winner of the 2009 Silicon Valley/San Jose Business Journal 40 Under 40 award and named one of BusinessWeek’s Best Young Tech Entrepreneurs, Joe often speaks about energy management and the role of physical computing -- where information from the physical world is used to make energy efficiency decisions. Before joining Sentilla, Joe held software development and product manager positions with IBM, Microsoft and Intel. Joe is active in numerous organizations, including The Green Grid, US Green Building Council, ACM and IEEE.

Joe holds M.S. and Ph.D. degrees in Computer Science from University of California, Berkeley, and a B.S. in Computer Science from Cornell University.

[Click Banner To Learn More]

[Home Page]  [The Automator]  [About]  [Subscribe ]  [Contact Us]