Economics
Successful data center energy management projects typically marry engineering and economic assessment. Engineering improvements can be identified using the information in the Best Practices section, while this section offers perspectives on evaluating the cost-benefit tradeoffs for energy saving measures, and other business-relevant factors to take into consideration.
Real-world efforts to implement energy-efficiency upgrades in data centers have proven highly cost effective. This is illustrated by a collection of 36 examples [chart] from a major telecommunications company. Note that the total one-time investment of over $500,000 million yielded $2,000,000 per year in energy savings, for an average payback time of only three months. In ten of the cases, the improvements were made at no cost (e.g. changes in operations and maintenance procedures). Individual measures, such as specifying more efficient power supplies can yield large savings [chart].
The U.S. Department of Energy provides an overview of cost-benefit analysis methods useful for evaluating energy efficiency projects. Lifecycle cost analysis is perhaps the most common technique for evaluating cost-effectiveness. The U.S. Department of Energy's Federal Energy Management Program offers a good compilation of software, training resources, and publications on the topic. The Whole Building Design Guide also provides a methodology. The National Institute for Standards and Technology also offers training materials.
Equally important are the so-called "non-energy benefits" associated with many energy-efficiency measures. Following are a few examples:
- Capital-cost savings: Key among these are the enormous capital expenditures in mechanical cooling required to service every more powerful (and heat-producing) servers. An article in the Wall Street Journal [download] presented several case studies in which tens or even hundreds of thousands of dollars had to be invested to upgrade the cooling equipment in data centers as servers were upgraded. Fortunately, such investments (and their associated operating costs) can be reduced if premium-efficiency equipment is specified all around.
- Maintaining uptime: In design, as well as operations, commissioning [download] and retrocommissioning [download] (respectively) can not only help secure and maximize energy savings but also help maintain facility uptime.
- Protecting equipment: Excessive heat is a rising problem [download] in data centers, and has been associated with equipment failure. Heat is a result of energy inefficiency. Selection of premium efficiency servers and smart design of heat-removal systems can serve to reduce thermal stress on the IT equipment.
- Maximizing productivity: The results of a 2002 study [download] indicate that although a data center had expanded its operations by roughly 33% from the previous year and increased the electricity demand associated with the computer equipment by 55%, the total computer room power density—which includes cooling and auxiliary equipment!—remained the same as the previous year at 355 W/m2. The facility's efforts to improve energy efficiency offset the energy demand from an increased, electrically active, computer room area. The energy-efficiency measures included better optimization of power distribution units, power management modules, computer room air-conditioning units, alterations to operating conditions, facility-wide reductions in lighting, and improved facility controls.
Our essays [short | full - downloads] on the overall "business case" for energy efficiency in data centers and other high-tech facilities are designed to assist facility managers in explaining the rationale for efficiency projects to upper management.
[top]