According to the National Resources Defense Council (NRDC), data center electricity consumption is projected to increase to approximately 140 billion kilowatt-hours annually by 2020, the equivalent annual output of 50 power plants. The cost to American businesses? A tidy $13 billion annually.
Make no mistake, many enterprises and data center providers are striving to reduce their carbon footprint. Switch recently announced that, as of the first of this year, all of its SUPERNAP data centers are powered by 100% renewable energy through its new solar facilities operating in Nevada. Across the pond, Apple is developing two new 100% renewable energy data centers in Ireland and Denmark. And Facebook just launched a massive new data center in Lulea, a town located in a remote corner of northern Sweden, that requires 70% less mechanical cooling capacity than the average data center because of the cool climate.
But what if your data center is located in Houston or Rio de Janeiro? Fortunately there exists a viable solution to achieve improved Power Usage Effectiveness (PUE), and reduce costs associated with cooling and power while mitigating a facility’s carbon footprint. Data Center Infrastructure Management (DCIM) are software and technology products that converge IT and building facilities functions to provide engineers and administrators with a holistic view of a data center's performance to ensure that energy, equipment and floor space are used as efficiently as possible.
In large data centers, where electrical energy billing comprises a large portion of the cost of operation, the insight these software platforms provide into power and thermal management accrue directly to an organization’s bottom line.
In order to take appropriate actions, data center managers need accurate intel concerning power consumption, thermals, airflow and utilization. One wouldn’t think this is the realm of MS Excel spreadsheets and Stanley tape measures. However, a recent study by Intel DCM and Redshift Research found that four in 10 data center managers in 200 facilities surveyed in the U.S. and the UK still rely on these Dark Age tools to initiate expansion or layout changes.
The good news is that DCIM provides increased levels of automated control that empowers data center managers to receive timely information to manage capacity planning and allocations, as well as cooling efficiency. By deploying thermal-management middleware, for example, improvements in airflow management can reduce energy consumption by 40%. Data center managers can also drive a stake through the problem of zombie servers by consolidating servers to reduce energy consumption from 10% to 40%.
Modern data centers maintain a stable operating environment for servers by implementing stringent temperature controls, which, paradoxically, also makes it possible to apply various energy-saving and eco-friendly measures in a centralized manner. A DCIM system that offers simulations integrating real-time monitoring information to allow for continuous improvements and validation of cooling strategy and air handling choices can have a direct impact on the bottom line.
Somewhat counter-intuitively, raising internal temperatures in data centers can save annually upwards of 100K per temperature degree without degrading service levels or reducing hardware lifespan. And by deploying various other innovative cooling technologies, facilities can expend up to 95% less energy.
Utilizing DCIM real-time data analysis tools, along with maintaining an active server refresh schedule, can effectively combat runaway energy consumption. The combination of processor improvement with feature rich intuitive dashboards that recognize imbalances in cooling and identify underutilized servers, can sometimes reveal a profligate energy consumer right under an administrator’s nose.
Replacing an older server with today’s advanced technology and using DCIM to identify underutilized systems can reduce energy need by 30%. Considering the four-year life expectancy of a server, this will save up to $480. While that figure might not seem too significant, the numbers get significant if you have thousands of servers.