DBFP-Net: Dynamic Graph and Bidirectional Temporal-Frequency Fusion Network for Wind Power Prediction with Physics Constraints
Open Access
- 1 April 2026
- journal article
- research article
- Published by MDPI AG in Information
- Vol. 17 (4) , 338
Abstract
High-precision wind power prediction improves grid stability and reduces curtailment losses. Existing methods face three limitations: static graphs cannot capture dynamic spatial correlations under weather changes, time series models miss multi-scale temporal features, and frequency-domain analyses lack physical constraints. We propose: (1) a dynamic distance correlation weighted graph that adaptively combines geographic and power correlations for weather–terrain coupling; (2) a spatio-temporal-frequency fusion framework integrating graph networks, bidirectional GRUs, and a patchwise sparse time–frequency module; (3) a turbine power curve-constrained frequency mixer for physical consistency. On the SDWPF dataset, our model achieves MAE reductions of 37.47–43.32% and RMSE reductions of 37.93–42.70% versus baselines, outperforming state-of-the-art methods. The approach demonstrates superior performance in complex spatio-temporal scenarios.Keywords
Funding Information
- State Grid Corporation of China (52170025002A- 285 380-ZN)
This publication has 35 references indexed in Scilit:
- A novel frequency-domain physics-informed neural network for accurate prediction of 3D spatio-temporal wind fields in wind turbine applicationsApplied Energy, 2025
- Review of several key processes in wind power forecasting: Mathematical formulations, scientific problems, and logical relationsApplied Energy, 2024
- A novel BiGRU multi-step wind power forecasting approach based on multi-label integration random forest feature selection and neural network clusteringEnergy Conversion and Management, 2024
- Wind power prediction using optimized MLP-NN machine learning forecasting modelElectrical Engineering, 2024
- An enhanced feature extraction based long short-term memory neural network for wind power forecasting via considering the missing data reconstructionEnergy Reports, 2023
- Spatio-temporal wind speed forecasting using graph networks and novel Transformer architecturesApplied Energy, 2022
- Short-term prediction for wind power based on temporal convolutional networkEnergy Reports, 2020
- Corrected multi-resolution ensemble model for wind power forecasting with real-time decomposition and Bivariate Kernel density estimationEnergy Conversion and Management, 2020
- Wind Power Forecasting Using Parallel Random Forest Algorithm2019
- Wind speed forecasting using nonlinear-learning ensemble of deep learning time series prediction and extremal optimizationEnergy Conversion and Management, 2018