Google recently announced that an artificial intelligence software has made energy produced from wind farms more feasible.
Google teamed up with its London-based subsidiary, DeepMind to make this feat possible. DeepMind’s machine learning algorithm will help predict the wind-output from the farms Google uses for its green initiatives. According to Google, “This software has improved the value of the wind energy which these farms are providing by 20% over a baseline where no such time-based predictions are being performed.” Google mainly works in wind farms in the Midwest, however the exact location where this technology is being deployed is still unclear.
Google further commented that due to the variable nature of wind power, using renewable resources may not be as easy. This is mainly because it is difficult to predict how much power a specific farm will generate, or how to best store it. “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,” write Sims Witherspoon, a product manager at DeepMind, and Will Fadrhonc, Google’s Carbon Free Energy program lead, in a co-authored blog post.
The team concluded that this approach is advantageous 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. Additionally, this sort of work benefits both Google and DeepMind since the latter has previously shown exceptional expertise but is still to find substantial revenue streams.