In their most recent attempt to develop and promote metrics that allow datacenter operators to quantify the costs and efficiencies of their datacenters, the Green Grid, working as part of the Global Metrics Harmonization Task Force has released three new measurement metrics for modeling the overall efficiency of your datacenters; the Green Energy Coefficient (GEC), Energy Reuse Factor (ERF) and Carbon Usage Effectiveness (CUE) metrics.
These metrics are not being developed in a vacuum; the members of the task force include the U.S. Department of Energy’s Advanced Manufacturing Office and Federal Energy Management Programs, U.S. Environmental Protection Agency’s ENERGY STAR Program, European Commission Joint Research Center Data Centers Code of Conduct, Japan’s Ministry of Economy, Trade and Industry, and Japan’s Green IT Promotion Council. This wide range of viewpoints and governmental agencies attitudes is clearly reflected in these three new metrics, which, in my opinion, reflect two “feel good” numbers and one useful piece of information.
The “feel good” metrics are the Green Energy Coefficient, which is designed to measure the percentage of energy being used that is derived from “green” power source, and the Carbon Usage Effectiveness, which is designed to measure the absolute carbon footprint of the datacenter relative to the IT workload. Now it’s not that there is anything wrong with having this information available, but these measurements, are at best, checklist items to show the stockholders or public that the company is working on being a good citizen by minimizing their overall impact on carbon emissions and renewable energy resources. The third metric, the Energy Reuse factor, is the one that will most directly impact the bottom line of a business, and one which datacenter operators can point to as a way to show how they are dealing with what are generally considered the waste products of datacenter operation.
The ERF is, on its surface, a simple metric; it identifies the portion of the energy the datacenter uses that is exported for reuse outside the datacenter. This means that operators will be able to supply an easily understood number that defines the energy pass through; that the energy used to handle the IT load of a datacenter is not just a factor in the more difficult to define amount of work that is being done for the energy expenditure, but also in the energy that is available after the workload for use in other tasks.
The simplest example of this are facilities that use water cooling and then route the heated water for use in controlling the temperature in the facility outside of the server rooms. If the cost for heating the facility was X prior to this use and Y after the facility made use of the already heated water being routed back to free air cooling, there is a direct correlation to the overall operational expenses of the facility. This is the kind of information that is easily understood by accountants; much more so than arcane measurements of IT workloads per kilowatt hour, and an item that will make it easier for IT to justify datacenter energy expenditures when projecting budgets.