Microsoft Azure: Microsoft shares data center PUE and WUE data for the first time

May 02, 2022 | Posted by MadalineDunn

Microsoft has shared its data center power usage effectiveness (PUE) and water usage effectiveness (WUE) data for the first time. Overall, the giant achieved a high level of efficiency with regards to PUE, while when it came to WUE, it didn't quite meet its target, and there was room for improvement. This publishing of efficiency data is part of Microsoft's efforts to make its sustainability data more transparent. 

Noelle Walsh, Microsoft's VP of cloud operations and innovation, outlined these sustainability gains in a blog post. She said that, although the giant's global PUE design goal was 1.22, it achieved a PUE of 1.18, while in EMEA, it achieved a 1.185 PUE, and in the Asia-Pacific region, where the designed PUE was 1.32, Microsoft hit a higher actual PUE of 1.405 - this was reportedly down to higher ambient temperature in the region which it said: "necessitates additional cooling."

On the other hand, it didn't meet its global design goal for WUE. WUE is calculated by dividing the "number of liters of water used for humidification and cooling by the total annual amount of power (measured in kWh) required for operation, and while it aimed for 0.39 L/kWh, it reported an actual global WUE of 0.49 L/kWh. Again, in the Asia-Pacific region, according to Walsh due to high ambient temperatures, it didn't meet its design goal of 0.99 L/kWh. Its actual WUE was 1.65 L/kWh.

In Walsh's post, she also acknowledged Microsoft's annual sustainability report, published in March, which revealed that it had seen a rise in its Scope 3 emissions, which increased about 23 percent year over year. Commenting on this, Walsh wrote: "We know that Scope 3 emissions (representing the total emissions across a company's entire value chain) are the most difficult to control and reduce, because we can often only influence change. We know this is a long-term effort and this year we have increased our focus on operational discipline that is rooted in reliable data."

{{ commentCount }} Comments