A two-step machine learning approach to statistical post-processing of weather forecasts for power generation

Abstract

By the end of 2021, the renewable energy share of the global electricity capacity reached 38.3% and the new installations are dominated by wind and solar energy, showing global increases of 12.7% and 18.5%, respectively. However, both wind and photovoltaic energy sources are highly volatile making planning difficult for grid operators, so accurate forecasts of the corresponding weather variables are essential for reliable electricity predictions. The most advanced approach in weather prediction is the ensemble method, which opens the door for probabilistic forecasting; though ensemble forecast are often underdispersive and subject to systematic bias. Hence, they require some form of statistical post-processing, where parametric models provide full predictive distributions of the weather variables at hand. We propose a general two-step machine learning-based approach to calibrating ensemble weather forecasts, where in the first step improved point forecasts are generated, which are then together with various ensemble statistics serve as input features of the neural network estimating the parameters of the predictive distribution. In two case studies based of 100m wind speed and global horizontal irradiance forecasts of the operational ensemble pre diction system of the Hungarian Meteorological Service, the predictive performance of this novel method is compared with the forecast skill of the raw ensemble and the state-of-the-art parametric approaches. Both case studies confirm that at least up to 48h statistical post-processing substantially improves the predictive performance of the raw ensemble for all considered forecast horizons. The investigated variants of the proposed two-step method outperform in skill their competitors and the suggested new approach is well applicable for different weather quantities and for a fair range of predictive distributions.

arXiv comment25 pages, 12 figures, 4 tables

References in corpus (10)

• Neural networks for post-processing ensemble weather forecasts
• Uncertainty Quantification in Complex Simulation Models Using Ensemble Copula Coupling
• Statistical Postprocessing for Weather Forecasts -- Review, Challenges and Avenues in a Big Data World
• Probabilistic Quantitative Precipitation Forecasting Using Ensemble Model Output Statistics
• Log-normal distribution based EMOS models for probabilistic wind speed forecasting
• Censored and shifted gamma distribution based EMOS model for probabilistic quantitative precipitation forecasting
• Post-processing numerical weather prediction ensembles for probabilistic solar irradiance forecasting
• Comparison of multivariate post-processing methods using global ECMWF ensemble forecasts
• Truncated generalized extreme value distribution based EMOS model for calibration of wind speed ensemble forecasts
• Calibration of wind speed ensemble forecasts for power generation

Cited by in corpus (5)

• Machine learning-based probabilistic forecasting of solar irradiance in Chile
• Clustering-based spatial interpolation of parametric post-processing models
• A Composite-Loss Graph Neural Network for the Multivariate Post-Processing of Ensemble Weather Forecasts
• Post-processing of ensemble photovoltaic power forecasts with distributional and quantile regression methods
• Parametric model for post-processing visibility ensemble forecasts