Google Deploys AI to Forecast Wind Energy Output

Google has announced that in association with its Britain-based Artificial Intelligence (AI) subsidiary DeepMind, it has developed a system to forecast wind power output 36 hours ahead of tangible generation.

Google believed that these type of forecasts can increase the value of wind energy and can reinforce the business case for wind power and drive further acceptance of carbon-free energy on electric grids globally.

"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 heaved," Sims Witherspoon, Programme Manager at DeepMind and Will Fadrhonc, Carbon Free Energy Programme Lead at Google penned in a blog post.

"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 understood.

In quest 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.

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 extensively available weather forecasts and historical turbine data, the researchers constituted the DeepMind system to forecast 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 penned.

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

Wind Power | News published on 04/03/2019 by Moulin

Next events


Last interview
 Energetica India is a publication from Editorial Omnimedia. No reproduction in whole or part of content posted on this website.