Wind Speed Forecast Based on Post-Processing of Numerical Weather Predictions Using a Gradient Boosting Decision Tree Algorithm

Abstract

With the large-scale development of wind energy, wind power forecasting plays a key role in power dispatching in the electric power grid, as well as in the operation and maintenance of wind farms. The most important technology for wind power forecasting is forecasting wind speed. The current mainstream methods for wind speed forecasting involve the combination of mesoscale numerical meteorological models with a post-processing system. Our work uses the WRF model to obtain the numerical weather forecast and the gradient boosting decision tree (GBDT) algorithm to improve the near-surface wind speed post-processing results of the numerical weather model. We calculate the feature importance of GBDT in order to find out which feature most affects the post-processing wind speed results. The results show that, after using about 300 features at different height and pressure layers, the GBDT algorithm can output more accurate wind speed forecasts than the original WRF results and other post-processing models like decision tree regression (DTR) and multi-layer perceptron regression (MLPR). Using GBDT, the root mean square error (RMSE) of wind speed can be reduced from 2.7–3.5 m/s in the original WRF result by 1–1.5 m/s, which is better than DTR and MLPR. While the index of agreement (IA) can be improved by 0.10–0.20, correlation coefficient be improved by 0.10–0.18, Nash–Sutcliffe efficiency coefficient (NSE) be improved by −0.06–0.6. It also can be found that the feature which most affects the GBDT results is the near-surface wind speed. Other variables, such as forecast month, forecast time, and temperature, also affect the GBDT results.

Estimation of Soil Nutrient Content Using Hyperspectral Data

“…GBDT: The gradient boosting decision tree is a boosting algorithm that calculates the information gain during the branching of the decision tree to determine the spectral variable to be split and the corresponding split value. Once all decision trees are constructed, the feature importance (FI) is obtained by calculating the information gain of the decision tree feature and dividing by the total frequency of the feature in all trees of the GBDT strong learner [28]:…”

Wind power forecasting for the Villonaco wind farm

“…Another approach use neural networks with random weights (NNRW) and linear combiner (Musikawan et al, 2020), in this approach the original time-series is decomposed into a collection of subseries by different decomposition techniques, each sub-series is modeled and predicted separately using (NNRW). Anthers authors uses the WRF model to obtain the numerical weather forecast and the gradient boosting decision tree (GBDT) algorithm to improve the near-surface wind speed post-processing results of the numerical weather model (Xu et al, 2020).…”

Wind Speed Forecasts of a Mesoscale Ensemble for Large-Scale Wind Farms in Northern China: Downscaling Effect of Global Model Forecasts

“…In responding to atmospheric long-and short-wave radiative forcing, model forecast errors often exhibit diurnal and seasonal variations [44][45][46][47]. Some other researchers focused on revising model forecast results through post-processing by using statistical and machine learning methods [48]. However, the errors of the model initial and boundary conditions derived from different global model background fields are often large [49,50], but very little attention has been paid to this issue [51].…”