Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces a domain adaptation approach for transferring power curve models from existing wind farms to new sites, challenging traditional reliance on distance and terrain characteristics. By leveraging temporal environmental variates and spatial terrain variables, the authors establish a more effective similarity metric for cross-farm power curve modeling. Empirical results demonstrate that their method significantly enhances the accuracy of site-planning power predictions compared to existing techniques.
Traditional methods for cross-farm power curve transfer fall short, but a domain adaptation approach reveals a more accurate way to forecast wind energy potential at new sites.
The wind energy industry relies on accurate power curve models to make power forecast, evaluate turbine performance, quantify upgrade, or support site-planning decisions. In this paper, we focus on site-planning power curves, i.e., we investigate how power curve models trained using turbine data on an operating wind farm can be transferred to a new, undeveloped farm. The traditional wisdom in the wind energy literature relies on distance, layout, or terrain characteristics for making cross-farm power curve transfer. Through the lens of domain adaptation, we propose a more reliable transfer learning approach for cross-farm power curve modeling. In the cross-farm applications, a domain is specified by the temporal environmental variates and spatial terrain variables. Domain adaptation is to find a capable similarity metric to adapt the domain on the new farm to that on the existing farm. Empirical results show that our domain adapted power curve consistently outperforms competing approaches by an appreciable margin for site-planning power predictions.