Energy Efficiency, Sourcing Renewables, Wind - February 27, 2019
Google uses AI to predict wind output
Google has partnered with DeepMind to apply machine learning algorithms to 700 megawatts of wind power capacity in the central U.S. that are part of Google’s global fleet of renewable energy projects, with the goal of strengthening the business case for wind power and driving further adoption of carbon-free energy on electric grids worldwide.
According to a posting on Google’s The Keyword blog, using a neural network trained on widely available weather forecasts and historical turbine data, the DeepMind system was configured to predict wind power output 36 hours ahead of actual generation. Based on these predictions, a model then recommends how to make optimal hourly delivery commitments to the power grid a full day in advance. The post explained, “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.”
While the blog noted that the algorithm is still being refined, the model has produced positive results. “To date, machine learning has boosted the value of our wind energy by roughly 20%, compared to the baseline scenario of no time-based commitments to the grid.” Early results, they say, suggest that they can make wind power sufficiently more predictable and valuable. “This approach also helps bring greater data rigor to wind farm operations, as machine learning can help wind farm operators make smarter, faster and more data-driven assessments of how their power output can meet electricity demand.”
Check out some of the key moments at SED's Innovation Summit!
- A Comparison of Fuel Choice for Backup Generators
- Capturing the Full Value of Renewable Energy for Businesses in ERCOT
- Benchmarking and Transparency: Resources for State and Local Leaders
- Establishment Labs Deploys Microgrid to Maintain Manufacturing Operations During Grid Outages
- EV100 Progress and Insights Annual Report