CAse Study REPORT

PUE DATA CENTER EFFICIENCY MEASUREMENT

Introduction

One of the metrics used for measuring datacenter efficiency is Power Usage Effectiveness, or PUE. PUE compares the power consumption for the entire facility with the power consumed by the core IT components—servers, storage and network equipment. This ratio illustrates how effectively the power being consumed translates into net compute capacity. Mathematically, the calculation is straightforward:

For example, if one watt is being consumed by the servers and one watt is being consumed for the supporting cooling, power back up and other administrative use, the ratio would be 2.0—which is where most datacenters operate. The theoretical ideal PUE is 1.0, where the only energy consumed is for computation. The value of this metric is that it focuses on the non-value added use of power, which in a datacenter is anything that doesn’t compute or store information.

PUE = Total Facility Power/ IT Equipment Power

Below is an Example to calculate the PUE:

Having a facility that uses 100,000 kW of total power of which 80,000 kW is used to power your IT equipment, would generate a PUE of 1.25. The 100,000 kW of total facility power divided by the 80,000 kW of IT power

Total Facility Power is defined to be “power as measured at the utility meter”. IT Equipment Power is defined as “the load associated with all of the IT equipment”. Stated simply, PUE is the ratio of the power delivered to the facility divided by the power actually delivered to the servers, storage, and networking gear. It gives us a measure of what percentage of the power actually gets to the servers with the rest being lost in the infrastructure. These infrastructure losses include power distribution (switch gear, uninterruptable power supplies, Power Distribution Units, Remote Power Plugs, etc.) and mechanical systems (Computer Room Air Handlers/Computer Room Air Conditioners, cooling water pumps, air moving equipment outside of the servers, chillers, etc.). The inverse of PUE is called Data Center Infrastructure Efficiency (DCIE): DCiE = IT Equipment Power / Total Facility Power * 100% So, if we have a PUE of 1.7 that’s a DCIE of 59%. In this example, the data center infrastructure is dissipating 41% of the power and the IT equipment the remaining 59%. This is useful to know in that allows us to compare different infrastructure designs and understand their relative value. Unfortunately, where money is spent, we often see metrics games and this is no exception. Let’s look at some of the issues with PUE and then propose a partial solution.

PROPORTIONAL DATA CENTER POWER: SCALABILITY Ideally, a data center’s Total Facility Power (Power total) would scale linearly to zero as the IT Equipment Power (Power IT) scales to zero. These lines are not asymptotes but are ideal guides for how Power total would optimally scale if Power total scaled proportionally to changes in Power IT

Below shows examples of PUE curves for various hypothetical data centers, wherein mPUE is the linear slope of proportional scalability for a given statistical mean PUE value.

[pic]
Understanding the center energy consumption and estimating the energy efficiency savings

Data Center Efficiency Savings Calculator helps IT Professionals and C-level management understand the short term and long-term savings that can be achieved by improving the energy efficiency of their data center infrastructure. Efficiency savings are both financial (Capital expense (CAPEX) and operating expense (OPEX) as well as the environmental savings in carbon emissions (the carbon given off by the electricity used to power the equipment in their data centers). Also important to consider but beyond the scope of this calculator are the substantial CAPEX savings in reducing assets and deferred data center construction and savings in other green house gasses other than CO2. The Efficiency Savings Calculator is designed to be useful for determining savings for any size data center, computer room, server room, or wiring closet.

• Data Center Efficiency CAPEX versus OPEX Savings A more efficient data center eliminates many power and cooling capacity issues thus reducing the need to add additional power and cooling equipment assets, and potentially eliminating the need to either build a new data center or move to a larger data center space. Additional efficiency measures such as asset retirement, virtualization and consolidation reduce the floor square required by IT and infrastructure equipment. Though not illustrated in the savings shown by this calculator, the CAPEX costs savings in not have to build, design, and equip a new data center have been shown to be as much as 5-6 times the OPEX savings shown here for makings your data center more efficient. In addition to the financial CAPEX savings, any new equipment that doesn't have to be manufactured, and any data center facility that doesn't need to be built saves the unnecessary production of tons of CO2 & Green House Gases (GHG) emissions.

• Using the Efficiency Savings Calculator

o Current Efficiency Level If you are just getting started in understanding your data center's efficiency, PUE and DCIE are key efficiency benchmarks proposed by the Green Grid and widely accepted and adopted by the data center industry. Even without having your data center's PUE/DCIE calculations, you can estimate. The Uptime Institute approximates an industry average PUE of 2.5. But if you haven't yet focused on improving your data center's efficiency, your benchmarks may be less efficient.

o Efficiency Goal Not everyone is going to be able to achieve the impressive efficiency levels of a Google, Yahoo, or Microsoft (all have PUE's of 1.15 to 1.21), but most data centers can make substantial efficiency improvements. The following chart showing data detailed by the EPA and presented by the Green Grid can help give you some ideas of achievable goals. After calculating your current PUE/DCIE, it is recommend to set a realistic team efficiency improvement objective, to determine the potential savings of achieving that improved level, and keeping in mind the environmental and goodwill benefits, weight the savings against the costs of your efficiency efforts. It is also recommended is implementing some low cost /no cost/ no costs efficiency strategies

|PUE |DCiE |Level of Efficiency |
|3.0 |33% |Very Inefficient |
|2.5 |40% |Inefficient |
|2.0 |50% |Average |
|1.5 |67% |Efficient |
|1.2 |83% |Very Efficient |

Summary:

We have defined tPUE to be: tPUE =Total Facility Power / Productive IT Equipment Power We defined total facility power to be measured before all UPS and power conditioning at medium voltage. And we defined Productive IT Equipment Power to be server power not including PSU, VRD and other conversion losses nor including fan or cooling power consumption. Please consider helping to evangelize tPUE and use tPUE. And, for you folks designing and building commercial servers, if you can help by measuring the Productive IT Equipment Power for one or more of your SKUs, I would love to publish your results. If you can supply Productive IT Equipment Power measurement for one of your newer servers, I’ll publish it here with a picture of the server.

Conclusion:

The Data center manager to strive to keep the tPUE value less than 1.0 in order to have an efficient system.

Reference:
1 - The Green Grid Power Effi ciency Metrics: PUE and DCiE, September 2007, http://www.thegreengrid.org/

gg_content/TGG_Data_Center_Power_Effi ciency_Metrics_PUE_and_DCiE.pdf.

2 - “Measurement Period” is described in The Green Grid Metrics: Data Center Infrastructure Effi ciency (DCiE)

Detailed Analysis, whitepaper #14 from The Green Grid Association. Briefl y stated, the Measurement Period is

The total interval of time over which many periodic samples are taken.

3 - CRC Standard Mathematical Tables, 26th Edition, pp509, 1981 CRC Press