Artificial intelligence group DeepMind has developed a set of machine learning algorithms that can raise the value of wind energy.
The company, owned by Google parent Alphabet, recently applied a system of algorithms to 700MW of wind power in central USA to predict wind power output 36 hours ahead of actual generation.
DeepMind’s neural network looked at weather forecasts and historical turbine data to make optimal hourly delivery commitments to the grid a day in advance.
Researchers said this boosted the value of the energy generated by around 20 percent against having no time-based commitments to the grid.
“We can’t eliminate the variability of the wind, but early results suggest that we can use machine learning to make wind power sufficiently more predictable and valuable,” DeepMind said.
The AI experts are continuing to refine the algorithm.
“This development from Google’s DeepMind is the latest proof for operators that modern data use can bring substantial benefits to the renewable energy industry,” head of technology at predictive maintenance experts Onyx Insight Xiaoquin Ma said.
“AI is crucial to streamlining power production and asset maintenance, allowing renewable energy to thrive in a post-subsidy world.”