Google's AI subsidiary DeepMind has developed a machine learning algorithm to predict the productivity of wind farms up to 36 hours in advance.
The system is currently used across 700MW of wind power capacity the company uses to run its data centers and offices in the US.
No more wondering whether the weather will be windy or wither and wane
"Using a neural network trained on widely available weather forecasts and historical turbine data, we configured the DeepMind system to predict wind power output 36 hours ahead of actual generation," DeepMind's Sims Witherspoon and Google's Will Fadrhonc wrote in a blog post.
"Based on these predictions, our model recommends how to make optimal hourly delivery commitments to the power grid a full day in advance.
"This is important, because energy sources that can be scheduled (i.e. can deliver a set amount of electricity at a set time) are often more valuable to the grid."
To date, the company claims, it has "boosted the value of our wind energy by roughly 20 percent," but said it would continue to refine the algorithm. DCD asked DeepMind whether the algorithm will be used outside of the US, and whether the company has any plans to open source the technology or commercialize it - it has declined to comment.
The algorithm is just one of Google's approaches to improving the stability of the grid - in 2014, the company partnered with TAE Technologies (formerly Tri Alpha Energy), the world's largest private fusion reactor company, to explore using machine learning in this space. Three years later, the two companies announced the Optometrist Algorithm to accelerate the pace of plasma research.
X, the research arm of Google's parent company Alphabet, is also experimenting with grid storage. Project Malta aims to store energy from intermittent renewable sources using molten salt and antifreeze.