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.
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.
Machine learning is quickly becoming a commonly used technique for wind speed and power forecasting. Many machine learning methods utilize exogenous variables as input features, but there remains the question of which atmospheric variables are most beneficial for forecasting, especially in handling non-linearities that lead to forecasting error. This question is addressed via creation of a hybrid model that utilizes an autoregressive integrated moving-average (ARIMA) model to make an initial wind speed forecast followed by a random forest model that attempts to predict the ARIMA forecasting error using knowledge of exogenous atmospheric variables. Variables conveying information about atmospheric stability and turbulence as well as inertial forcing are found to be useful in dealing with non-linear error prediction. Streamwise wind speed, time of day, turbulence intensity, turbulent heat flux, vertical velocity, and wind direction are found to be particularly useful when used in unison for hourly and 3 h timescales. The prediction accuracy of the developed ARIMA–random forest hybrid model is compared to that of the persistence and bias-corrected ARIMA models. The ARIMA–random forest model is shown to improve upon the latter commonly employed modeling methods, reducing hourly forecasting error by up to 5 % below that of the bias-corrected ARIMA model and achieving an R2 value of 0.84 with true wind speed.
Machine learning is quickly becoming a commonly used technique for wind speed and power forecasting. Many of these methods utilize exogenous variables as input features, but there remains the question of which atmospheric variables provide the most predictive power, especially in handling non-linearities that lead to forecasting error. This investigation addresses this question via creation of a hybrid model that utilizes an autoregressive integrated moving average (ARIMA) model to make an initial wind speed forecast followed by a random forest model that attempts to predict the ARIMA forecasting error using knowledge of exogenous atmospheric variables. Variables conveying information about atmospheric stability and turbulence as well as inertial forcing are found to be useful in dealing with non-linear error prediction. Wind direction (θ) and temperature (T) are found to be the most beneficial individual input features. Streamwise wind speed (U), time of day (t), turbulence intensity (TI), turbulent heat flux (w'T'), θ, and T are found to be particularly useful when used in conjunction.The prediction accuracy of the ARIMA-RF hybrid is compared to that of the persistence and bias-corrected ARIMA models. The ARIMA-RF model is shown to improve upon these commonly employed modeling methods, reducing hourly forecasting error by approximately 30 % below that of the bias-corrected ARIMA model.
Model uncertainty is a significant challenge in the wind energy industry and can lead to mischaracterization of millions of dollars' worth of wind resource. Machine learning methods, notably deep artificial neural networks (ANNs), are capable of modeling turbulent and chaotic systems and offer a promising tool that can be used to produce high-accuracy wind speed forecasts and extrapolations. This paper quantifies the role of domain knowledge on ANN wind speed extrapolation accuracy using data collected using profiling lidars over three field campaigns. A series of 11 meteorological features are used as ANN inputs and the resulting output accuracy is compared with that of a simple power law extrapolation. It is found that normalized inputs, namely turbulence intensity, normalized current wind speed, and normalized previous wind speed, are the features that most reliably improve ANN accuracy, providing up to a 52 % increase in extrapolation accuracy over the power law predictions. The volume of input data is also deemed important for achieving robust results. One test case is analyzed in-depth using dimensional and non-dimensional features, showing that feature normalization drastically improves network accuracy and robustness for uncommon atmospheric cases.