When Data Demand Tops Data Center Efficiency

Arthur Cole

The enterprise has made great strides in curbing its appetite for energy over the past decade, but will this ultimately be a losing battle as demand for data continues to rise?

According to a recent report from the Lawrence Berkeley National Laboratory, the number of data centers coming online has seen a dramatic uptick in the past few years as organizations struggle to meet the always-on demands of an increasingly connected population. But the good news is that due to virtualization, low-power/high-density architectures and other developments, actual energy consumption has been flat. This is in stark contrast to the first decade of the new century, which saw energy demand jumping as high as 90 percent per year.

Still, leaders in the data center industry are concerned that the big gains in energy efficiency are over but the relentless demand for data, fueled in part by rapidly falling costs that are themselves the result of more efficient infrastructure, will put the industry on the fast track to dramatically higher consumption in relatively short order. At a meeting sponsored by DCD Energy this week, Donald Paul, of the University of Southern California’s Energy Institute, noted that once data centers approach a PUE of 1.0, there are no more gains to be had, since you cannot achieve more than 100 percent efficiency. And programs that encourage enterprises to reduce demands on the local grid also encourage the use of mostly diesel-power backup systems.

Still, it isn’t entirely certain that efficiency has run its course. Increased use of the cloud increases consumption by centralized, hyperscale facilities, but it generally lowers consumption-per-bit far more than thousands of privately held facilities each running highly underutilized systems. And the U.S. Department of Energy is looking to keep the technology ball rolling with a number of research initiatives, such as the $25 million ARPA-E program designed to incorporate photonics into chip-level interconnects, which is then expected to foster increasingly dense architectures that produce less heat and draw less energy for data operations.


At the same time, the IT industry has only just started to turn Big Data technology, which is currently driving the Internet of Things, on its own data infrastructure. As Raritan International’s Sanjay Motwani points out, temperature sensors in equipment racks and throughout the data center can help drill down to trouble spots and provide information to implement more affective air-flow. Meanwhile, contact closure sensors and other alerting devices can ping managers the instant something has gone wrong in the data environment, while workflow monitoring tools and DCIM (Data Center Infrastructure Management) systems can ensure that data loads are properly balanced across available resources at all times.

Although it is theoretically possible that data infrastructure will run out of room on the efficiency scale someday, as a practical matter there is no reason to believe this will happen any time soon. Even after more than 100 years of development, the automobile is still making strides – even to the point of replacing gas-powered engines with electric ones. In the data center, we may very well be on the verge of something similar as research into quantum computing starts to bear fruit.

In the meantime, the quest for greater efficiency should not be allowed to wane just because most of the major gains have already been implemented. As data infrastructure becomes more connected and economies of scale become more pronounced, even relatively small improvements can still translate into big dollars.

Arthur Cole writes about infrastructure for IT Business Edge. Cole has been covering the high-tech media and computing industries for more than 20 years, having served as editor of TV Technology, Video Technology News, Internet News and Multimedia Weekly. His contributions have appeared in Communications Today and Enterprise Networking Planet and as web content for numerous high-tech clients like TwinStrata and Carpathia. Follow Art on Twitter @acole602.


Subscribe to our Newsletters

Sign up now and get the best business technology insights direct to your inbox.


 



Add Comment      Leave a comment on this blog post

Post a comment

 

 

 

 


(Maximum characters: 1200). You have 1200 characters left.

 

null
null

 

Subscribe to our Newsletters

Sign up now and get the best business technology insights direct to your inbox.


 
Subscribe to our Newsletters

Sign up now and get the best business technology insights direct to your inbox.