Tech Giant Google Using AI to Predict Wind Energy Output

This is important, because energy sources that can be scheduled, or can deliver a set amount of electricity at a set time, are often more valuable to the grid

Google
The Google logo is seen at a start-up campus in Paris, France, Feb. 15, 2018. VOA

In collaboration with its Britain-based Artificial Intelligence (AI) subsidiary DeepMind, Google has developed a system to predict wind power output 36 hours ahead of actual generation.

Google said that these type of predictions can boost the value of wind energy and can strengthen the business case for wind power and drive further adoption of carbon-free energy on electric grids worldwide.

“Over the past decade, wind farms have become an important source of carbon-free electricity as the cost of turbines has plummeted and adoption has surged,” Sims Witherspoon, Programme Manager at DeepMind and Will Fadrhonc, Carbon Free Energy Programme Lead at Google wrote in a blog post this week.

“However, the variable nature of wind itself makes it an unpredictable energy source – less useful than one that can reliably deliver power at a set time,” they said.

In search of a solution to this problem, DeepMind and Google started applying machine learning algorithms to 700 megawatts of wind power capacity in the central US.

Google, smart compose
The Google name is displayed outside the company’s office in London, Britain. VOA

These wind farms – part of Google’s global fleet of renewable energy projects – collectively generate as much electricity as is needed by a medium-sized city.

Using a neural network trained on widely available weather forecasts and historical turbine data, the researchers configured the DeepMind system to predict wind power output 36 hours ahead of actual generation.

“Based on these predictions, our model recommends how to make optimal hourly delivery commitments to the power grid a full day in advance,” Witherspoon and Fadrhonc wrote.

Also Read- Apple to Empower Over 90,000 US Girls in Coding

This is important, because energy sources that can be scheduled, or can deliver a set amount of electricity at a set time, are often more valuable to the grid.

“To date, machine learning has boosted the value of our wind energy by roughly 20 per cent, compared to the baseline scenario of no time-based commitments to the grid,” the post said. (IANS)