June 5, 10:15am
Location: Santa Clara II

Data Driven Models for Wind Farm Performance Optimization

The power generated by a wind turbine is dependent on the atmospheric conditions, such as wind speed, air density, turbulence intensity and shear, as well as by the wakes of upstream wind turbines. Better understanding of these effects is important for optimising the total power output of a wind farm. In this talk, I will discuss how data-driven models are used in the wind energy industry to predict (i) the effects of atmospheric conditions on single wind turbine performance, and (ii) wakes within wind farms. The advantage of data-driven models is their efficiency and the incorporation of field data of actual wind farms. I will give examples of some of our work with Swiss industry partners, including a recent project applying graph neural networks (GNNs), which combine recursive neural networks and Markov Chains for the use on graph structures and allow for node-level applications, to predict wake interactions.

Sarah Barber is Head of the Wind Energy Innovation Division at the Eastern Switzerland University of Applied Sciences and is founder and president of the Swiss Wind Energy R&D Network. She is a lecturer in wind energy at the universities of St. Gallen and Graubünden. As well as this, she is a qualified Business Coach and runs leadership workshops for engineers in her spare time. She recently become Chair of the Diversity Committee at the European Academy of Wind Energy. Sarah has a joint M.Eng. in Aerospace Engineering from the University of Cambridge (UK) and MIT (USA) and a Ph.D. in Aerodynamics from the University of Sheffield (UK). She has been active in the R&D of wind energy since 2007, as a Postdoc and Lecturer at ETH Zurich, Wind Energy Expert at BKW Energie AG, Chief Technology Officer at Agile Wind Power AG (CH) and Group Manager at Fraunhofer IWES (DE).