Multi-task neural diffusion processes for uncertainty-quantified wind power prediction
This work addresses uncertainty quantification for wind farm operations, offering incremental improvements in predictive modeling for renewable energy integration.
The paper tackled uncertainty-aware wind power prediction by extending neural diffusion processes to a multi-task framework (MT-NDP) for wind turbines, resulting in improved point accuracy and calibration, especially for turbines deviating from the fleet average.
Uncertainty-aware wind power prediction is essential for grid integration and reliable wind farm operation. We apply neural diffusion processes (NDPs)-a recent class of models that learn distributions over functions-and extend them to a multi-task NDP (MT-NDP) framework for wind power prediction. We provide the first empirical evaluation of NDPs in real supervisory control and data acquisition (SCADA) data. We introduce a task encoder within MT-NDPs to capture cross-turbine correlations and enable few-shot adaptation to unseen turbines. The proposed MT-NDP framework outperforms single-task NDPs and GPs in terms of point accuracy and calibration, particularly for wind turbines whose behaviour deviates from the fleet average. In general, NDP-based models deliver calibrated and scalable predictions suitable for operational deployment, offering sharper, yet trustworthy, predictive intervals that can support dispatch and maintenance decisions in modern wind farms.