Unrivaled reliability and highly efficient. Mitsubishi Electric Uninterruptible Power Supply systems for maximum critical infrastructure protection.
Purpose-built and highly efficient. Mitsubishi Electric Cooling Systems for IT and electrical equipment.
PUE (power usage effectiveness) describes how well a data center delivers energy to IT load and supports it. PUE can be leveraged to identify opportunities to improve operational efficiency within the data center.
Power usage effectiveness (PUE) is a data center metric developed by The Green Grid Association (TGG) in 20071 and defined as the ratio of the total facility energy to the IT equipment energy.
While PUE does not measure the computational efficiency of the IT load, it can help identify where power is utilized to improve data center energy efficiency.
Let’s assume the PUE in your data center was calculated to be 2.0.
50% of its energy would be consumed by IT equipment and 50% by the overhead associated with running the data center and supporting the IT load.
Every watt used for IT load will require an additional watt of overhead. Figure 1 depicts a hypothetical breakdown of the total data center energy consumption.
In the PUE calculation above, the majority of the power being used to support the IT load comes from cooling and HVAC. The rest of the energy is being used by electrical equipment, lighting, and other sources, such as fire suppression systems and security. This means the biggest gains can be made by decreasing the energy used for cooling. The next best area to optimize is the power distribution infrastructure.
Operation cannot improve without an understanding of the current state of the data center’s energy efficiency. With proper PUE calculation, the least efficient areas of the data center can be targeted and optimizations evaluated. This requires taking specific measurements throughout the data center.
Figure 1: Total Data Center Energy Breakdown (U.S. Environmental Protection Agency, 2007)
TGG defines a basic (Level 1), intermediate (Level 2), and advanced (Level 3) measurement for PUE calculations2. All three levels require the total facility energy to be measured at the utility input, although each level recommends additional measurement points and requires different IT load measurement.
A basic indication of the data center PUE by means of measuring the IT load at the Uninterruptible Power Supply (UPS) outputs.
A more accurate data center PUE figure by measuring the IT load from the Power Distribution Unit (PDU) outputs.
The most accurate data center PUE figure by measuring the IT load at the input of the IT equipment. This can be accomplished through metered rack PDUs.
Additional metering locations can provide more insight into your data center’s energy efficiency and used to predict the effects of various changes. Beneficial locations would be on the outputs of automatic transfer switches (ATS), inputs of UPS, or inputs of mechanical equipment. Branch circuit monitoring can also provide power usage at the rack level. Measuring at these different locations not only provides additional granularity for insight but can be used as inputs for a computational fluid dynamics (CFD) model.
A CFD model uses numerical methods and algorithms to provide an accurate picture of the cooling capabilities of a data center as well as opportunities for improvement. This includes determining where hot spots have been created, where hot/cold air is mixing, and how to right size the cooling. It reviews power usage, equipment details and airflow measurements on perforated tiles. Once complete, it’s much easier to identify cooling and airflow management improvements.
When your layout allows hot and cold air to mix, it’s more difficult – and takes more energy – to cool the data center. If a CFD study has been done, you’ll be able to identify key problem areas, and with a few basic strategies, you can isolate hot and cold air to optimize cooling throughout the data center.
The electrical infrastructure is the second largest overhead associated with the data center. The distribution system can be optimized by making runs as short as possible, bringing higher voltages to the equipment and using more efficient equipment, all of which minimize resistance and power losses. Given the integral nature of a UPS for your data center, it makes sense to choose a high-efficiency model.
While old UPS installations use transformers and large filters due to 6 pulse and 12 pulse converter sections, new technology has allowed UPS systems to become more efficient and create less heat. The latest advancement (the use of silicon carbide (SiC) transistors) allows for operational efficiencies up to 98% (from a previous efficiency of 90% to 95%).
The elimination of transformers increases efficiencies and reduces cooling requirements, and thus upgrading your UPS can have a major impact on your data center PUE.
Efficient lighting can play a large part in lowering the PUE, even though it makes up only a small percentage of the total load. The goal is to have the lights off when not needed and use less energy when they are. LED bulbs, motion sensors, and lighting control are key components to optimize lighting.
LED lighting (particularly in conjunction with a central power-conversion module) will use less energy than the common fluorescent lighting typically found in a data center, eliminating electrical losses and decreasing heat.
You may also want to consider establishing a sensor network tied into the central control system that dynamically changes the lighting so it’s only on where the technician is working. This centralized control system can also collect data for insight into energy usage.
Siloed improvements in efficiencies can result in a higher PUE. If updates are not balanced (for example, failing to adjust cooling to account for a more efficient UPS or computing equipment that uses less energy), you won’t see a positive impact on your data center’s PUE. Your infrastructure updates should work in concert so that overhead energy can decrease when IT load decreases. If your PUE is still high after making some updates, it may be that you’re not using your conserved energy efficiently.
Machine learning and neural networks may be able to help you more accurately analyze a complex infrastructure by looking at the systemic impact of a single change. Establishing governance of best practices will help lower PUE and maintain efficiencies on a regular basis. You may even want to consider a containerized system that would house all cooling and power.
Ready to take a step towards reducing your data center's energy consumption? Mitsubishi Electric can help you upgrade to a more efficient UPS.
1 The Green Grid. (2007, February 20). Green Grid Metrics: Describing DataCenter Power Efficiency. Retrieved February 18, 2015, from www.thegreengrid.org: http://www.thegreengrid.org/en/Global/Content/white-papers/Green-Grid-Metrics
The TGG white paper #49, “PUE: A Comprehensive Examination of the Metric”, is an invaluable resource for any data center wanting to report and use PUE.
2 The Green Grid. (2012). PUE: A Comprehensive Examination of the Metric. Retrieved February 18, 2015, from www.thegreengrid.org: http://www.thegreengrid.org/en/Global/Content/white-papers/WP49-PUEAComprehensiveExaminationoftheMetric
uptimeinstitute. (2011, June 1). Google Data Center Efficiency Lessons that apply to all Data Centers. Retrieved February 20, 2015, from https://www.youtube.com/watch?v=0m-yRYEMZVY
Sean Evanuik, EIT, Mitsubishi Electric Power Products, Inc., UPS Division, Application Engineer
U.S. Environmental Protection Agency. (2007, August 2). Report to Congress on Server and Data Center Energy Efficiency Public Law 109-431. Retrieved February 24, 2015, from www.energystar.gov: http://www.energystar.gov/ia/partners/prod_development/downloads/EPA_Datacenter_Report_Congress_Final1.pdf
ASHRAE TC 9.9. (2011). 2011 Thermal Guidelines for Data Processing Environments - Expanded Data Center Classes and Usage Guidance. Retrieved March 4, 2015