Google Moving Workloads Between Data Centers to Use Greener Energy

Google is moving workloads between data centers to boost its use of renewable energy, shifting the data processing for YouTube videos and Google photos to locations where green power is plentiful. It’s a development that creates powerful new opportunities to green create cloud applications powered by solar, wind and geothermal energy.

Today’s news builds on Google’s carbon-aware computing strategy, and demonstrates how software and network connectivity can transcend traditional limitations on green computing. This is a growing priority for hyperscale cloud builders and their users, as climate-driven disasters bring new urgency to sustainability.

Last year Google began shifting the timing of workloads within data centers to match their energy use to the availability of renewable sources. That laid the foundation for the next step – moving the actual compute capacity to more favorable locations.

“Google can now shift moveable compute tasks between different data centers, based on regional hourly carbon-free energy availability,” said Ross Koningstein, co-founder, Carbon-Intelligent Computing at Google. “This includes both variable sources of energy such as solar and wind, as well as “always-on” carbon-free energy such as our recently announced geothermal project. This moves us closer to our goal of operating on carbon-free energy everywhere, at all times, by 2030.”

Moving data and applications between data centers in real time requires sophisticated software and LOTS of network capacity. As the world’s largest computing platform, Google has the resources to be a trailblazer in this effort, which aligns with its corporate commitments to reduce its climate impact.

As part of that commitment, Google will soon begin using geothermal energy to power its data centers in Nevada with carbon-free energy, teaming with energy startup Fervo to use fiber optic sensors to tap the earth’s own heat to power Google Cloud servers.

Addressing the Location Challenge

The recent growth of cloud computing has sharpened the focus on how data centers can retool the economy for a sustainable future. As the COVID-19 pandemic shifts more essential activities online, the carbon impact of the world’s IT infrastructure becomes even more critical in addressing climate change.

Google’s announcement brings the realization of a futuristic vision for workloads to “follow the sun” to create solar-powered IT applications. Google has added wind and geothermal power, creating a broader “follow the green” strategy that integrates a wider array of renewable sources.

Workload mobility addresses a number of challenges in matching green power to IT operations. Renewable electricity is linked to geography and weather, and most widely available in regions with sunny or windy conditions.  There’s also the intermittent nature of renewable energy – solar power is only available during daylight hours. Wind energy can be used at night, but not when the wind dies down.

“The amount of computing going on at any given data center varies across the world, increasing or decreasing throughout the day,” said Koningstein. “Our carbon-intelligent platform uses day-ahead predictions of how heavily a given grid will be relying on carbon-intensive energy in order to shift computing across the globe, favoring regions where there’s more carbon-free electricity. The new platform does all this while still getting everything that needs to get done, done — meaning you can keep on streaming YouTube videos, uploading Photos, finding directions or whatever else.”

The first workloads using this location shifting include media processing tasks, in which Google encodes, analyzes and processes millions of multimedia files like videos uploaded to YouTube, Photos and Drive.

“Like many computing jobs at Google, these can technically run in many places (of course, limitations like privacy laws apply,” said Koningstein. “Now, Google’s global carbon-intelligent computing platform will increasingly reserve and use hourly compute capacity on the most clean grids available worldwide for these compute jobs — meaning it moves as much energy consumption as possible to times and places where energy is cleaner, minimizing carbon-intensive energy consumption.”

Significantly, Google Cloud’s developers and customers can also prioritize cleaner grids, boosting their use of carbon-free energy by assigning apps to regions with better carbon-free energy (CFE) scores.

Where might workloads shift within Google’s global network? The regions with the highest current CFE ratings include Oregon (89%), Sao Paulo, Brazil (87%), Council Bluffs, Iowa (78%) and Hamina, Finland (77%). At the low end of the scale are Singapore (3%) and Sydney, Australia (11%).