For the first time ever Google has deployed artificial intelligence (AI) tools to increase the value of wind energy production.
The AI division of Google, known as DeepMind, claims its technology will boost the value of energy generated by onshore wind farms by 20%.
Google purchases 2.6GW of renewable energy a year, close to 100% of its operational needs, and has agreements with 20 different wind and solar projects which could benefit from similar DeepMind analysis.
Using a neural network (computer system inspired by the structure of biological networks) that was trained using weather forecasts and historical turbine data, DeepMind engineers configured their AI to predict power output of wind turbines 36 hours ahead of time.
The benefits from using the AI in the management of the windfarm are threefold; better prediction of production, better prediction of power demands, and operational cost savings.
Source: Google DeepMind
DeepMind has been experimenting by applying its AI-led analysis to onshore turbines in the United States, on projects such as the Great Western Wind project in Oklahoma. In total, DeepMind has optimised 700MW of generation so far.
DeepMind has already been used to optimise power use in Google’s datacenters, and there were reports in 2017 that DeepMind was in discussions with the National Grid in the UK to help balance power supply and demand.
Writing on Google’s blog, Google carbon free energy program lead, Will Fadrhonc and DeepMind program manager Sims Witherspoon said that while the research cannot fully predict the weather, using AI does make the output of wind farms more predictable.
“We can’t eliminate the variability of the wind, but our early results suggest that we can use machine learning to make wind power sufficiently more predictable and valuable,” they said.
Alphabet, the parent company of Google, has recently expressed significant interest in upping its involvement in infrastructure projects, with Google sister company SideWalk showing interest in developing a light railway system extension in Toronto as part of wider ‘Smart City’ development.
DeepMind has been approached for comment.
Like what you’ve read? To receive New Civil Engineer’s daily and weekly newsletters click here.