There are approximately 4.75 million servers worldwide being run, managed and upgraded without being actively used on a daily basis. Those unused servers cost $20.7 billion to run, plus consume another $3.7 billion in energy costs. Furthermore, around $21.4 billion is wasted each year on hardware, maintenance, management, energy and cooling for unused servers. This is roughly equal to the cost of the Apollo space program.
Managing energy actively results in 40 percent or more energy savings in the data center. When you consider that a data center can consume 10 to 100 times more energy per square foot than the average office building, and in some cases up to 40 percent of an organization's carbon footprint, it is clear that managing energy in the data center is of paramount importance.
Data center executives generally do not have comprehensive management tools for monitoring and controlling energy. As a result, there's a lack of systematic analysis of energy strategies to determine which will yield the greatest benefits or pose the greatest risk to ongoing operations. This impedes the decision making process, leaving many guessing or adopting ad-hoc strategies. Once you begin measuring the energy in your data center, you can expose the biggest offenders (high energy consumers), come up with a plan to reach your goals, implement this plan and document your progress.
These are some of the most common ways data center energy management reduces energy consumption:
1. Detecting unused equipment and turning it off or recommissioning it. 15-20 percent of all servers are never used. Idle servers still consume about three-quarters of the energy of a server at 100 percent utilization. However, most data centers do not have tools to uncover unused equipment. Look for an energy management solution that enables you to detect all idle or rogue machines and make decisions using a per-asset cost analysis.
2. Virtualization. A recent survey found that among data centers that claimed to have completed their virtualization process, only about 35 percent of their servers had been virtualized. In other words, this survey revealed that picking servers that are suitable for virtualization is still a very ad-hoc process. An energy management solution can profile assets and give data center executives a per-asset cost and utilization picture of the data center. Virtualization can then be geared toward assets with low-utilization or high energy consumption in a planned effort.