Multi-site Wind Energy Prediction System Based on Power Decomposition and Deep Model Integration
DOI:
https://doi.org/10.13052/dgaej2156-3306.4147Keywords:
Wind power forecasting, variational mode decomposition, deep model ensemble, graph attention network, temporal convolutional network, residual correctionAbstract
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.
Downloads
References
Chen Y, Xu J. Solar and wind power data from the Chinese state grid renewable energy generation forecasting competition[J]. Scientific Data, 2022, 9(1): 577.
Hu Y, Liu H, Wu S, et al. Temporal collaborative attention for wind power forecasting[J]. Applied Energy, 2024, 357: 122502.
Hu Y, Wu S, Chen Y, et al. CTRL: Collaborative temporal representation learning for wind power forecasting[C]//Proceedings of the 2024 8th International Conference on Electronic Information Technology and Computer Engineering. New York: ACM, 2024: 1219–1227.
Jiang J, Han C, Wang J. Buaa_bigscity: Spatial-temporal graph neural network for wind power forecasting in Baidu KDD CUP 2022[J/OL]. arXiv preprint, 2023: arXiv:2302.11159. https://arxiv.org/abs/2302. 11159.
Li J, Geng D, Zhang P, et al. Ultra-short term wind power forecasting based on LSTM neural network[C]//2019 IEEE 3rd International Electrical and Energy Conference (CIEEC). Piscataway: IEEE, 2019: 1815–1818.
Sarkar M R, Anavatti S G, Ferdaus M M, et al. ASPEN-WIND: Adaptive spectral and self-supervised interactive CNN-LSTM for enhanced wind power forecasting[J]. Expert Systems With Applications, 2026, 296: 129171.
Solas M, Cepeda N, Viegas J L. Convolutional neural network for short-term wind power forecasting[C]//2019 IEEE PES Innovative Smart Grid Technologies Europe (ISGT-Europe). Piscataway: IEEE, 2019: 1–5.
Wan A, Chang Q, Khalil A B, et al. Short-term power load forecasting for combined heat and power using CNN-LSTM enhanced by attention mechanism[J]. Energy, 2023, 282: 128274.
Wang H, Li B, Xue Z, et al. Powerformer: A temporal-based transformer model for wind power forecasting[J]. Energy Reports, 2024, 11: 736–744.
Wu Q, Guan F, Lv C, et al. Ultra-short-term multi-step wind power forecasting based on CNN-LSTM[J]. IET Renewable Power Generation, 2021, 15(5): 1019–1029.
Xiong B, Lou L, Meng X, et al. Short-term wind power forecasting based on attention mechanism and deep learning[J]. Electric Power Systems Research, 2022, 206: 107776.
Yang M, Wang D, Xu C, et al. Power transfer characteristics in fluctuation partition algorithm for wind speed and its application to wind power forecasting[J]. Renewable Energy, 2023, 211: 582–594.
Zhang Y, Kong X, Wang J, et al. Wind power forecasting system with data enhancement and algorithm improvement[J]. Renewable and Sustainable Energy Reviews, 2024, 196: 114349.
Zhao S, Zhou X, Jin M, et al. Rethinking self-supervised learning for time series forecasting: A temporal perspective[J]. Knowledge-Based Systems, 2024, 305: 112652.
Zheng X, Li X. Wind electricity power prediction based on CNN-LSTM network model[C]//2023 IEEE International Conference on Sensors, Electronics and Computer Engineering (ICSECE). Piscataway: IEEE, 2023: 231–236.
Wang K, Tang X Y, Zhao S. Robust multi-step wind speed forecasting based on a graph-based data reconstruction deep learning method[J]. Expert Systems with Applications, 2024, 238: 121886.
Dragomiretskiy K, Zosso D. Variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2014, 62(3): 531–544.
Huang N E, Shen Z, Long S R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings of the Royal Society of London Series A, 1998, 454(1971): 903–995.
Veličković, Cucurull G, Casanova A, et al. Graph attention networks[C]//International Conference on Learning Representations (ICLR). 2018.
Chen T, Guestrin C. XGBoost: A scalable tree boosting system[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2016: 785–794.
Bea S, Oord A, Simonyan K, et al. WaveNet: A generative model for raw audio[J/OL]. arXiv preprint, 2016: arXiv:1609.03499. https://arxiv.org/abs/1609.03499.
Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]// Advances in Neural Information Processing Systems (NeurIPS). 2017, 30: 5998–6008.
Loshchilov I, Hutter F. Decoupled weight decay regularization[C]// International Conference on Learning Representations (ICLR). 2019.
Ragab M, Eldele E, Chen Z, et al. Self-supervised autoregressive domain adaptation for time series data[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022, 35(1): 1341–1351.
Li Jinzhong, Xie Yuguang, Ma Wei, et al. Research on Intelligent Control Technology for Cooperative Game Implementation in Source-Grid-Load-Storage Systems Based on Reinforcement Learning[J]. Distributed Generation & Alternative Energy Journal, 2026, 41(2). DOI:10.13052/dgaej2156-3306.
Wang D, Wu S. Accurate Modeling of Carbon Emissions Under Urban Energy Consumption[J]. Distributed Generation & Alternative Energy Journal, 2025, 40(05–06): 1259–1280. DOI:10.13052/dgaej2156-3306.405614.
