SUBSCRIBE TO TMCnet
TMCnet - World's Largest Communications and Technology Community

CHANNEL BY TOPICS


QUICK LINKS




The Effect of Weather on Data Centers
Green Technology Featured Articles
August 07, 2012

The Effect of Weather on Data Centers


Discussions of extreme weather are back in the news after the release of NOAA’s 2011 State of the Climate Report this month. The report, filled with evidence supporting long-term climate warming trends, should prompt us to rethink our data center strategies as extreme weather can severely impact data center power and cooling – two of the three capacity parameters (power, cooling and space) that data center managers balance to keep everything running without interruption. A number of large companies, Amazon included, did not expect such widespread weather-related outages, but then Netflix and major sites went offline.  Even worse, outages of a couple of days or more can impact fuel supplies and other services when access to roads is restricted. Major natural disasters can even destroy a data center itself. There are several ways organizations can prepare.  


At a minimum, every organization should upgrade and routinely test its disaster recovery and/or business continuity strategies. The average data center in the U.S. already experiences about five power outages over a two-year period, according to a detailed study by the Ponemon Institute (News - Alert). And the increase in severe weather events (heavy snow and rain, and high winds that bring down power lines) will undoubtedly cause these outages to occur more frequently and last longer. 

Power is precious during an outage because the UPS may not have sufficient capacity to run the air conditioning and if the generator fails to come on, the servers can overheat quickly. Even when the generator works, fuel is usually limited and with extended outages may not be available. To reduce the risk and stretch the fuel supply should make power efficiency a critical aspect of any business continuity strategy. The best way to improve efficiency is to address poor server utilization, which is normally the biggest source of wasted energy in most data centers. Consolidating and virtualizing the servers can increase overall utilization from around 10 percent (typical of dedicated servers) to between 20 and 30 percent, and over 50 percent with dynamic capacity management systems. AOL (News - Alert), for example, recently reported annual savings of $5 million from “decommissioning” about one-fourth of its servers worldwide, including $2.2 million in OS licenses and $1.65 million in energy bills. 

The efficiency of the servers themselves is also important. The key metric here is the transactions per second per Watt or TPS/Watt. The PAR4 Efficiency Rating system used in the Underwriters Laboratories’ (News - Alert) UL2640 standard is the most accurate means for IT managers to compare the transactional efficiency of legacy servers with newer ones, and newer models of servers with one another. Indeed, assessing the energy efficiency of servers should now be considered a best practice during every hardware refresh cycle and whenever adding capacity.  

To mitigate against more destructive disasters, every organization should operate multiple, geographically-dispersed data centers, and the greater the separation the better the protection against widespread events (e.g. a major hurricane or an outbreak of tornados). Virtualization and load-balancing enable organizations to have a flexible and fully redundant infrastructure where all applications can run in any data center at any time. Furthermore, automated power capping during outages can keep servers running without much cooling, while slower, the reduced clock speed will reduce power consumption and heat output dramatically. Runbooks can be used to automate the general operating procedures and specific steps involved in shifting and shedding the workloads. Runbooks also make it easier to do something very few organizations currently do: test and perfect the disaster recovery response to various failure scenarios. They can also be used to adjust the number of physical servers in a cluster providing further flexibility during outages or cooling issues. 

Regularly shifting loads across a fully redundant data center configuration can help minimize the cost of such an infrastructure by keeping each facility at least partially utilized 24x7. But there are other ways the ability to shift and shed loads can help pay for itself. One way is through participation in demand response programs and/or ancillary energy markets where electric utilities and aggregators offer financial incentives to organizations to reduce power consumption during peak periods (usually in the late afternoon and evening during the summer months). 

Having multiple, strategically-located data centers also enables loads to be shifted to where power is currently the most stable and the least expensive. Because power is invariably the most abundant and least expensive at night, such a “follow the moon” strategy can result in considerable savings. In addition, because outside air temperature is always at its lowest at night, this strategy can also save substantially on cooling costs. In fact, a well-designed data center operated with a full workload exclusively at night during a finite “shift” may not even need to use its power-hungry air-conditioning system. But it should still have one, of course, because it may be called into service during the day in response to an extreme weather or other disaster occurring on the other side of the globe. 



Clemens Pfeiffer is the CTO of Power Assure and is a 25-year veteran of the software industry, where he has held leadership roles in process modeling and automation, software architecture and database design, and data center management and optimization technologies.




Want to learn more about the latest in communications and technology? Then be sure to attend ITEXPO West 2012, taking place Oct. 2-5, in Austin, TX. ITEXPO (News - Alert) offers an educational program to help corporate decision makers select the right IP-based voice, video, fax and unified communications solutions to improve their operations. It's also where service providers learn how to profitably roll out the services their subscribers are clamoring for – and where resellers can learn about new growth opportunities. For more information on registering for ITEXPO click here.

Stay in touch with everything happening at ITEXPO. Follow us on Twitter.




Edited by Brooke Neuman


Green Technology Related Articles






Technology Marketing Corporation

2 Trap Falls Road Suite 106, Shelton, CT 06484 USA
Ph: +1-203-852-6800, 800-243-6002

General comments: [email protected].
Comments about this site: [email protected].

STAY CURRENT YOUR WAY

© 2024 Technology Marketing Corporation. All rights reserved | Privacy Policy