Teaching “selfish” wind turbines to share can increase productivity

Exactly how much energy is generated depends, among other things, on the farm layout and the wind conditions at the location. However, when tested on a commercial farm in India, the algorithm boosted energy output by 1 to 3 percent depending on wind speed, which would be equivalent to powering 3 million homes if the software were deployed to the world’s existing farms. Estimate of the study authors.

And getting to that point isn’t as far-fetched as it might sound. One of the advantages of the approach is its potential for real-world scalability. “To increase the production unit, you usually have to either add a larger rotor or a more powerful generator, or change some hardware,” says Xavi Vives, controls engineer at wind turbine manufacturer Siemens Gamesa. (Vives was not involved in the study, although employees from Siemens Gamesa were involved in the research.) “But this is pure software, so very promising at a very low price.”

Testing the technology in India was also significant for Varun Sivaram, one of the study’s co-authors, who at the time was serving as Chief Technology Officer at ReNew Power, India’s leading renewable energy company. “I wanted to find a way to transfer a lab scale technology to a real experiment. And I also wanted to do it in an emerging market because that’s where the real need for clean energy solutions is – in these emerging countries where the demand for energy is growing,” he says.

In addition to increasing the power output of turbines, the algorithm could also help wind farms by extending turbine life and reducing wear and tear that can reduce their performance over time. “I think the most important takeaway from their study is that if you can actually let more wind pass to downstream turbines, if you can actually let more wind pass through to downstream turbines, you’re going to reduce wear on the first turbine, if you can balance the loads,” says Mark Z. Jacobson, professor of Civil and Environmental Engineering from Stanford University. Vives agrees, “The higher the turbulence, the higher the wear…if you can reduce wake or steer it away, you also give the turbines more wiggle room to run longer.”

Although the study has shown promise, Jacobson believes more experimentation is needed before the software can be rolled out, as initial testing focused on a three-turbine setup under specific conditions. In reality, there are an infinite number of possible configurations of turbines, wind speeds and topographies, he explains. “I think they need to test more complex configurations and try to come up with general rules that apply regardless of the configuration,” he says. “You don’t want to try to optimize every single turbine and every park.”

As wind energy is scaled up, Sivaram believes algorithms like this will be needed to generate as much electricity as possible. Ideal land locations for wind farms require certain circumstances – locations with very high wind speeds and plenty of land to place turbines far apart. In the future, turbines will likely be close together as land becomes less available.

Leave a Comment

Your email address will not be published.