Improving data sharing in practice – power curve benchmarking case study

Abstract

In this work, a data sharing case study is presented, aiming to investigate and demonstrate how data sharing can be improved in practice in the wind energy sector. The case study is part of the WeDoWind framework, which creates tangible incentives to motivate different types of people to actually share data in practice. For this, a WeDoWind “challenge” on the topic of wind turbine power curve benchmarking is created and implemented within the framework. The results allow five different data-driven power curve prediction methods to be compared. The best method reduces the model error by as much as 70% in terms of mean absolute error and 45% in terms of root mean squared error compared to the standard industry method of binning. The results of a survey filled out by the participants show that data sharing could be improved compared to previous WeDoWind case studies, by providing more clear comparison and evaluation criteria, as well as by better integrating students into the WeDoWind framework. Overall, we find that “challenge”-based collaborations can help the industry become more innovative, by providing a motivation and basis for sharing data, as well as for comparing and benchmarking different methods. Finally, our experience in doing this as part of the present work allows us to make some suggestions for improving data sharing in practice.