Abstract
Abstract. Model uncertainty is a significant challenge in the wind energy industry and can lead to mischaracterization of millions of dollars' worth of wind resources. Machine learning methods, notably deep artificial neural networks (ANNs), are capable of modeling turbulent and chaotic systems and offer a promising tool to produce high-accuracy wind speed forecasts and extrapolations. This paper uses data collected by profiling Doppler lidars over three field campaigns to investigate the efficacy of using ANNs for wind speed vertical extrapolation in a variety of terrains, and it quantifies the role of domain knowledge in ANN extrapolation accuracy. A series of 11 meteorological parameters (features) are used as ANN inputs, and the resulting output accuracy is compared with that of both standard log-law and power-law extrapolations. It is found that extracted nondimensional inputs, namely turbulence intensity, current wind speed, and previous wind speed, are the features that most reliably improve the ANN's accuracy, providing up to a 65 % and 52 % increase in extrapolation accuracy over log-law and power-law predictions, respectively. The volume of input data is also deemed important for achieving robust results. One test case is analyzed in depth using dimensional and nondimensional features, showing that the feature nondimensionalization drastically improves network accuracy and robustness for sparsely sampled atmospheric cases.
Highlights
Challenges to the prediction of microscale atmospheric flows are well-documented, especially for complex terrain and forested regions (Baklanov et al, 2011; Krishnamurthy et al, 2013; Fernando et al, 2015, 2019; Sfyri et al, 2018; Yang et al, 2017; Berg et al, 2019; Wilczak et al, 2019; Pichugina et al, 2019)
Large extrapolation errors are detrimental for wind farms, which rely on accurate wind speed extrapolation to estimate available wind resource and forecast output power
With the industry currently bracing for turbines up to 260 m tall, vertical extrapolation accuracy has become important for the generation of wind farms
Summary
Challenges to the prediction of microscale atmospheric flows are well-documented, especially for complex terrain and forested regions (Baklanov et al, 2011; Krishnamurthy et al, 2013; Fernando et al, 2015, 2019; Sfyri et al, 2018; Yang et al, 2017; Berg et al, 2019; Wilczak et al, 2019; Pichugina et al, 2019). Every location has unique flow features with variability that warrants a dedicated field campaign to develop and validate parameterization schemes befitting local forecasting This process can still result in poor spatial representation of the site due to limitations in measurement technology, area covered by the field campaign, and site complexity. The current industry standard of 1 % uncertainty per 10 m vertical extrapolation (Langreder and Jogararu, 2017) must be improved in order to increase the viability of such largescale, powerful turbines. This would likely be difficult to accomplish by using numerical models. Model results must be scaled down to the desired finer resolutions, which can result
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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.
