Weather-informed probabilistic forecasting and scenario generation in power systems

The integration of renewable energy sources (RES) into power grids presents significant challenges due to their intrinsic stochasticity and uncertainty, necessitating the development of new techniques for reliable and efficient forecasting. This paper proposes a method combining probabilistic forecasting and Gaussian copula for day-ahead prediction and scenario generation of load, wind, and solar power in high-dimensional contexts. By incorporating historical weather data and weather forecasts as covariates and restoring spatio-temporal correlations, the proposed method enhances the reliability of probabilistic forecasts in RES. Extensive numerical experiments compare the effectiveness of different time series models, with performance evaluated using comprehensive metrics on a real-world and high-dimensional dataset from Midcontinent Independent System Operator (MISO). The results highlight the importance of weather information and demonstrate the efficacy of the Gaussian copula in generating realistic scenarios, with the proposed weather-informed Temporal Fusion Transformer (WI-TFT) model showing superior performance, achieving 49% reduction in load forecasting error, 40% improvement in wind energy prediction, and 34% enhancement in solar energy prediction at individual asset levels compared to non-weather-informed approaches. The integration of copula further improves scenario generation quality, with 2%–7% reduction in energy scores. • A weather-informed deep learning method with a Gaussian copula is proposed. • Different forecasting models are evaluated with and without weather data integration. • Methods tested on a large dataset from MISO for 48-hour ahead predictions. • Results show weather data improves accuracy, especially for long horizons. • Gaussian copula captures spatial and temporal correlations for scenario generation.