Underwriters Laboratories Announces New Power Measurement Standard
The demand for data center capacity continues to grow at an 11 percent CAGR, driven by business trends in data-driven decision making, digitization of information, complex algorithms, and automation of more processes. (IDC, 2007) The US Department of Energy estimates that the cost to power a server over its useful life now exceeds the original capital expenditure.
PAR4 factors in the age of IT equipment and a measure of server transaction performance, providing a unique way to compare efficiency between servers regardless of age or capacity. PAR4 is a rating that represents transactions per Watt-second of energy consumption. This number will be higher with every generation of equipment as their capacity, performance and capabilities increase. A higher number represents a higher level of performance per watt. This can then be used to better forecast server utilization and power consumption, thus optimizing the efficiency of the data center.
“UL is giving data centers a powerful new view into measuring and rating a core part of its infrastructure: server performance,” said Kevin Ravo, general manager, technology and regulations, high tech business, UL. “Encouraging industry usage of a universal measurement and reporting methodology for evaluating server efficiency is a significant step in helping to reduce data center costs and improve equipment quality.”
“Now data centers can quickly and effectively monitor, measure and report on server efficiency,” said Brad Wurtz, president and CEO, Power Assure. “For the first time, IT professionals can make valid comparisons between servers, better calculate total cost of server ownership, and make better decisions about the life and management of their servers. Only with accurate metrics can a data center operator optimize the efficiency of their data center.”
To calculate server performance using the UL standard, a series of standardized tests must be performed with the equipment. These tests include Power On Spike Test, Boot Cycle Test, and a Benchmark Test. The Power On Spike test is used to characterize the initial power surge that occurs when a device is first turned on or plugged in. The Boot Cycle test is used to measure the time from the power off state until the device is fully functional and has stabilized at an idle state. The Benchmark test is used to determine and classify the overall performance of the server and grant the PAR4certification in one of the following categories: Green (most efficient), Gold (very efficient), Silver (fairly efficient), or Black (low efficiency).