Abstract
Abstract. The extrapolation of wind speeds measured at a meteorological mast to wind turbine rotor heights is a key component in a bankable wind farm energy assessment and a significant source of uncertainty. Industry-standard methods for extrapolation include the power-law and logarithmic profiles. The emergence of machine-learning applications in wind energy has led to several studies demonstrating substantial improvements in vertical extrapolation accuracy in machine-learning methods over these conventional power-law and logarithmic profile methods. In all cases, these studies assess relative model performance at a measurement site where, critically, the machine-learning algorithm requires knowledge of the rotor-height wind speeds in order to train the model. This prior knowledge provides fundamental advantages to the site-specific machine-learning model over the power-law and log profiles, which, by contrast, are not highly tuned to rotor-height measurements but rather can generalize to any site. Furthermore, there is no practical benefit in applying a machine-learning model at a site where winds at the heights relevant for wind energy production are known; rather, its performance at nearby locations (i.e., across a wind farm site) without rotor-height measurements is of most practical interest. To more fairly and practically compare machine-learning-based extrapolation to standard approaches, we implemented a round-robin extrapolation model comparison, in which a random-forest machine-learning model is trained and evaluated at different sites and then compared against the power-law and logarithmic profiles. We consider 20 months of lidar and sonic anemometer data collected at four sites between 50 and 100 km apart in the central United States. We find that the random forest outperforms the standard extrapolation approaches, especially when incorporating surface measurements as inputs to include the influence of atmospheric stability. When compared at a single site (the traditional comparison approach), the machine-learning improvement in mean absolute error was 28 % and 23 % over the power-law and logarithmic profiles, respectively. Using the round-robin approach proposed here, this improvement drops to 20 % and 14 %, respectively. These latter values better represent practical model performance, and we conclude that round-robin validation should be the standard for machine-learning-based wind speed extrapolation methods.
Highlights
Both the preconstruction and operational phases of wind farm projects require an accurate assessment of the wind resource at the heights of the rotor-swept area to forecast generated power (Brower, 2012)
Neither law is capable of representing specific phenomena that typically occur in the nocturnal stable boundary layer in some regions, such as low-level jets (Sisterson et al, 1983), whose strong winds are of great benefit for wind energy production (Cosack et al, 2007)
The random forest provides the most accurate results when it is tested at the site where it is trained
Summary
Both the preconstruction and operational phases of wind farm projects require an accurate assessment of the wind resource at the heights of the rotor-swept area to forecast generated power (Brower, 2012). Conventional extrapolation approaches do not have nor require knowledge of rotor-height wind speeds and can generalize to any location where measurements are available at a single level near the surface (for the logarithmic law) or at two levels in the lower part of the boundary layer (for the power law). To more fairly and practically validate machine-learningbased vertical extrapolation of wind speeds against conventional methods, a “round-robin” approach should be used Such an approach involves training the model at a given site and assessing its performance at other sites where rotor-height wind speeds are unknown to the model. We implement a round-robin validation approach to assess the performance of machine-learning-based vertical extrapolation of wind speeds against conventional methods. Data recorded at the two lowest heights (13 and 39 m a.g.l.) could not be used because of their poor quality, as they lie in the lidar blind zone
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.
