Google's Carbon-Intelligent Computing Platform matches data centre demand with renewable supply

Approach mirrors the growing use of time-of-use energy tariffs and demand response platforms

Google has unveiled a Carbon-Intelligent Computing Platform designed to match data centre energy use with peaks in renewable power generation.

In a blog post entitled Our data centers now work harder when the sun shines and wind blows, published to coincide with Earth Day, technical lead for carbon-intelligent computing at Google, Ana Radovanovic, said the internet and cloud giant has just completed the third year in a row when it matched total energy usage with 100 per cent renewable energy purchases.

To ensure it uses zero emission power from now on, Google has now developed software to help ensure its data centres "work more closely with carbon-free energy sources like solar and wind".

The "first-of-its-kind" platform has been deployed at Google's hyperscale data centres, allowing them to "shift the timing of many compute tasks to when low-carbon power sources, like wind and solar, are most plentiful".

The platform has been developed without any requiring additional hardware and without impacting the performance of Google services, said Radovanovic.

"Shifting the timing of non-urgent compute tasks - like creating new filter features on Google Photos, YouTube video processing, or adding new words to Google Translate - helps reduce the electrical grid's carbon footprint, getting us closer to 24x7 carbon-free energy."

The platform works by ingesting forecasts provided by energy data specialist Tomorrow that provides day-ahead information on predicted grid carbon intensity. Meanwhile, a complementary Google internal forecast predicts the hourly power resources that a data centre needs to carry out compute tasks over the same period, allowing the system to shift tasks to minimise emissions and essentially deliver a localised demand response system.

The approach mirrors the growing use of time-of-use energy tariffs and demand response platforms, which incentivise households and businesses to use power when renewables supplies are peaking.

"Early results demonstrate carbon-aware load shifting works," Radovanovic said. "Results from our pilot suggest that by shifting compute jobs we can increase the amount of lower-carbon energy we consume."

Google is now looking to not just shift tasks to different times of the day within the same data centre, but also move flexible compute tasks between different data centres, so that more work is completed when and where doing so is more environmentally friendly.

"Our plan for the future is to shift load in both time and location to maximise the reduction in grid-level CO2 emissions," Radovanovic said.

"Our methodology, including performance results of our global rollout, will be shared in upcoming research publications. We hope that our findings inspire other organisations to deploy their own versions of a carbon-intelligent platform, and together, we can continue to encourage the growth of carbon-free electricity worldwide."

A version of this article first appeared on our sibling site BusinessGreen