A two-stage uncertainty forecasting method for offshore wind power based on FEDformer and SDCDM

Accurate forecasting of offshore wind power output is particularly challenging owing to the resource's stochasticity and instability. Uncertainty modeling in wind power forecasting not only reveals output volatility but also underpins safe grid operation. For the first time, this paper presents a novel two-stage framework for offshore wind power uncertainty forecasting, combining deterministic point forecasts with probabilistic scenario generation. The proposed method combines Frequency Enhanced Decomposed Transformer (FEDformer) for deterministic prediction and Seasonally Conditional Decomposed Diffusion Model (SDCDM) for scenario generation. FEDformer enhances multi-scale feature extraction through frequency decomposition, while SDCDM applies seasonal decomposition and conditional diffusion to generate diverse probabilistic scenarios. The model demonstrates strong performance in MRAE, NAPS, and CRPS metrics, indicating excellent predictive accuracy and reliable uncertainty quantification.