Ensemble Machine Learning-Based Wind Forecasting to Combine NWP Output With Data From Weather Station

Wind generation resources are the fastest growing energy resources throughout the world. An accurate wind forecasting is critical to the integration of a large amount of wind generation units into the grid operations. This paper presents an ensemble machine learning-based method to forecast wind power production, which uses both the wind generation forecasted by a numerical weather prediction (NWP) model and the meteorological observation data from weather stations. In this way, it takes advantage of the atmosphere models while capturing spatial and temporal correlation between meteorological observations at different locations. Three machine learning algorithms (artificial neural network, support vector regression, Gaussian process) are proposed to synthesize the meteorological data and the prediction from NWP. An ensemble forecast is then created by blending the results derived from three algorithms through a Bayesian model average. The performance of this ensemble forecast has been validated by the 2-year operational data collected at Electricity Reliability Council of Texas.