AI Case Study
DeepMind increases value of wind power by 20% by predicting supply 36 hours in advance
Researchers from DeepMind and Google develop a neural network machine learning system to better predict availability of wind power 36 hours in the future. This is based on weather forecasts and historic turbine data, allowing for better grid scheduling of wind power supply a day in advance.
Industry
Energy
Renewable Energy
Project Overview
In order to mitigate for the unpredictability of wind power, "DeepMind and Google started applying machine learning algorithms to 700 megawatts of wind power capacity in the central United States. 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, we 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. "
Reported Results
"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."
Technology
Details undisclosed
Function
Operations
General Operations
Background
From DeepMind: "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."
Benefits
Data
Weather forecasts and historic turbine data