Exactly how much energy is available depends on factors such as farm layout and site wind conditions. However, when tested on a commercial farm in India, the algorithm increased energy output by 1% to 3%, depending on wind speed, which is equivalent to powering 3 million homes if the software were deployed on existing farms around the world, The study’s authors estimate.
Getting to this point isn’t as far-fetched as it sounds. One of the benefits of this approach is its potential for real-world scalability. Xavi Vives, a controls engineer at wind turbine manufacturer Siemens Gamesa, said: “Usually adding a production unit requires either installing a larger rotor or a more powerful generator, or changing some hardware.” (Vives was not involved in the study, although Employees at Siemens Gamesa participated in the study.) “But it’s pure software, so it’s very promising, and the cost is very low.”
Testing the technology in India was also important for one of the study’s co-authors, Varun Sivaram, who was then CTO of ReNew Power, India’s leading renewable energy company. “I want to find a way to turn lab-scale technologies into real-world experiments. I also want to do this in emerging economies, because that’s where the real need for clean energy solutions is going to be—where these energy demands continue to grow growing emerging economies,” he said.
In addition to increasing the power output of the turbines, the algorithm can also help wind farms by extending the life of the turbines and reducing wear and tear that can reduce their output over time. “I think the most important takeaway from their study is that if you can balance the load, if you can really get more wind through the subsequent turbines, then you’re going to have less wear and tear on the first turbine,” said Mark Z. Jacobson , Professor of Civil and Environmental Engineering at Stanford University. Vives agrees: “The higher the turbulence, the more wear… If you can reduce or direct the wake, then you can also make the turbines more slack so they can run longer.”
While the research shows promise, Jacobson believes further experiments are needed before the software can be rolled out, as initial testing focused on a setup involving three turbines under specific conditions. In reality, the potential configurations of turbines, wind speeds and terrain are limitless, he explained. “I think they need to test more complex configurations and try to come up with general rules that apply to any configuration,” he said. “You don’t want to try and optimize every turbine and farm.”
As wind energy scales, Sivaram believes such algorithms are needed to generate as much electricity as possible. The ideal wind farm site requires a specific environment – a place where the wind is very fast and there is enough land to place the turbines far away. The future is likely to see turbines placed close together as land becomes less available.