Multi-site Wind Energy Prediction System Based on Power Decomposition and Deep Model Integration

Abstract

To address the limitations of existing wind power forecasting methods in mixed-frequency signal modeling, multi-site spatial correlation capture, and single-model generalization, this paper proposes a multi-site wind power forecasting system based on power decomposition and deep model ensemble. The system applies Variational Mode Decomposition (VMD) to separate raw power sequences into high-frequency and low-frequency components, each directed into a structurally symmetric dual-branch framework. Within each branch, three heterogeneous sub-models – ConvGAT-LSTM, Spectral Transformer, and TCN – operate in parallel; branch outputs are aggregated by simple averaging and linearly combined into a base prediction, which is subsequently refined by an XGBoost residual correction layer. Experiments on six Chinese wind farm datasets demonstrate that the proposed system achieves an average RMSE of 0.1065±0.0021 and R2 of 0.8335±0.0167 at the 24-step forecast horizon, improving over the state-of-the-art baseline TCOAT by 1.4% and 0.5%, respectively. The VMD module alone contributes an 11.6% RMSE reduction, and the system reduces local RMSE during ramp events at Site 6 by 34.9% relative to the baseline. Ablation experiments and statistical significance tests (p<0.05, Cohen’s d>0.82) confirm that each module contributes meaningfully to overall performance.