In a collaboration with sister alphabet company, Deepmind, Google was able to achieve 20% increase in energy value. Machine learning was able to accurately forecast power output 36 hours in advance.
Wind and solar are inherently intermittent and the challenge has been incorporating renewables into the energy mix is a predictable and reliable way, without the use of fossil fuels to support the base load around the clock.
Deepmind trained their neural network on weather forecasts and historic turbine data from Google’s 700MW wind portfolio to predict wind power generation 36 hours in advance of generation.
“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, machine learning has boosted the value of our wind energy by roughly 20 percent, compared to the baseline scenario of no time-based commitments to the grid.”
Source and images – deepmind
