Abstract
Although the random forest (RF) model is a powerful machine learning tool that has been utilized in many wind speed/power forecasting studies, there has been no consensus on optimal RF modeling strategies. This study investigates three basic questions which aim to assist in the discernment and quantification of the effects of individual model properties, namely: (1) using a standalone RF model versus using RF as a correction mechanism for the persistence approach, (2) utilizing a recursive versus direct multi-step forecasting strategy, and (3) training data availability on model forecasting accuracy from one to six hours ahead. These questions are investigated utilizing data from the FINO1 offshore platform and Atmospheric Radiation Measurement (ARM) Southern Great Plains (SGP) C1 site, and testing results are compared to the persistence method. At FINO1, due to the presence of multiple wind farms and high inter-annual variability, RF is more effective as an error-correction mechanism for the persistence approach. The direct forecasting strategy is seen to slightly outperform the recursive strategy, specifically for forecasts three or more steps ahead. Finally, increased data availability (up to ∼8 equivalent years of hourly training data) appears to continually improve forecasting accuracy, although changing environmental flow patterns have the potential to negate such improvement. We hope that the findings of this study will assist future researchers and industry professionals to construct accurate, reliable RF models for wind speed forecasting.
Highlights
Machine learning (ML) methods are becoming increasingly popular within the wind energy sector, especially for wind speed/power forecasting [1]
Standalone random forest (RF) models are outperformed by their hybrid counterparts, while direct forecasts show slight improvement over their recursive counterparts
The results show that, at the FINO1 site, hybrid persistence–RF models tend to outperform the standalone RF models
Summary
Machine learning (ML) methods are becoming increasingly popular within the wind energy sector, especially for wind speed/power forecasting [1]. Increased usage of ML, and statistical modeling in general, for forecasting purposes is due to a timescale gap in the utility of other conventional techniques. Numerical weather prediction (NWP) models struggle to predict highly variable small-scale atmospheric characteristics (e.g., surface wind speeds) and are typically limited to forecasts of six or more hours ahead due to high computational costs [2]. The naive persistence approach (i.e., Uτ +n = Uτ ; U is mean streamwise wind speed, τ a given time step, and n the number of timesteps in advance to be forecasted) is most useful for very short-term (
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
