Deriving multivariate probabilistic solar generation forecasts based on hourly imbalanced data

Accurate forecasting of solar PV generation is critical for integrating renewable energy into power systems. This paper presents a multivariate probabilistic forecasting model that addresses the challenges posed by imbalanced data resulting from day and night-time periods in solar photovoltaic (PV) generation. The proposed approach offers a robust and accurate method for predicting solar PV output by incorporating forecast updates and modeling the temporal interdependencies. The methodology is applied to a case study in France, demonstrating effectiveness across different spatial granularities and forecast horizons. The model uses advanced data handling methods combined with copula models, resulting in improved Energy Scores and Variogram-based Scores. These improvements underscore the importance of addressing imbalanced data and utilizing multivariate models with repeated updates to enhance solar forecasting accuracy. This work contributes to advancing forecasting techniques essential for integrating renewable energy into power grids, supporting the global transition to a sustainable energy future.