Collaborative Probabilistic Wind Power Forecasting Using Adaptive Flow Matching Enhanced Neural Process

Abstract

With the large‐scale integration of wind power, its inherent intermittency and uncertainty pose significant challenges to power system operation. Existing probabilistic forecasting methods often struggle with capturing spatiotemporal correlations among multiple turbines as well as generalizing to unseen turbines or future time steps. To address these issues, we propose a novel multi‐turbine collaborative probabilistic forecasting framework based on the flow matching enhanced neural process. By formulating wind power forecasting as a conditional stochastic process, our method naturally enables cross‐turbine knowledge sharing through a Transformer‐based encoder. The introduction of flow matching allows efficient single‐ or few‐step sampling while avoiding the usage of variational lower bounds, and hence is more effective. Experiments on a real‐world dataset comprising 134 turbines over 245 days demonstrate that the proposed framework achieves superior performance, significantly outperforming existing neural process variants and deep learning baselines in terms of RMSE, MAE, and continuous ranked probability score.