CoCopula: Conformal Calibration and Copula Aggregation for Reliable Renewable Energy Forecasting
The framework combines Copula-based dependence modeling with Context-Aware Conformal Prediction (CACP) to create reliable fleet-level forecasts from site-level data. This method successfully captures cross-site correlations and corrects miscalibration at the aggregated level, outperforming existing aggregation techniques and matching the accuracy of direct system forecasts.