Blog Environment Science Technology Top Stories

Google and DeepMind Are Using AI to Predict How Much Energy Wind Turbines Will Produce

Written by Scott Colon

DeepMind, British artificial intelligence Company, which was acquired by Alphabet in 2014 has been developing artificial-intelligence programs since 2010 to solve complex problems. One of the company’s latest projects has cantered around the predictability of wind power, a recent Google post said.

While the giant wind turbines produce power, only when they’re moving this poses a problem for the grid: in the absence of expensive energy storage, it’s difficult to analyze how much power these turbines will be able to provide.

And for this, the industry has been using AI techniques for years to try to come closer and closer to real wind predictions. However, the wind is still difficult to predict.

But the Alphabet owned AI Company says that the AI programs it has developed over the last year can help bring the “wind output” line even closer to the “expected wind output” line. “The algorithms developed by us were trained on historical weather data. In addition, we also tested a year’s worth of wind power output recorded by 700 megawatts’ worth of wind turbines owned by Google, the company says.

The company along with Google wanted to be able to predict wind output 36 hours 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,” Google wrote today. The model that DeepMind developed helps wind-farm owners to tell almost accurate expected power to the regional power grid manager “a full day in advance.”

Google says this will enable the researcher’s ability to accurately tell the local grid manager: how much wind a farm will produce. The model has also boosted the value of the wind energy by roughly 20%, compared to the baseline scenario of no time-based commitments to the grid. Google has also released a GIF showing how its predictions track actual wind output. “We hope that our machine-learning approach can strengthen the business case for wind power. Also, it will drive further adoption of carbon-free energy on electric grids worldwide,” Google wrote.

Leave a Comment