Article Details

Title · Authors · Abstract · Keywords · DOI · References

Research on Hybrid Wind Power Forecasting Based on Variational Mode Decomposition

DAI Xianyong1, LIU Luanqi2

(1.School of Intelligent Manufacturing and Control Engineering, Qilu Institute of Technology, Ji'nan 250200, China; 2.Shandong Provincial Key Laboratory of Industrial Big Data and Intelligent Manufacturing, Qilu Institute of Technology, Ji'nan 250200, China)

Section：Information Application · Vol. 2026, Issue 3 · Pages：169-177 · 2096-4706（2026）03-0169-09 · CLC number：TP19；TP183 · Document code：A · DOI：10.19850/j.cnki.2096-4706.2026.03.032

Abstract

High-precision prediction of wind power generation is of great significance for the optimal scheduling and stable operation of smart grids. However, wind power time-series data exhibit characteristics of nonlinearity, non-stationarity and long-term dependence, making it difficult for traditional methods to establish effective models. For this reason, a hybrid prediction model named VMD-BiLSTM is proposed based on Variational Mode Decomposition (VMD) and Bidirectional Long Short-Term Memory (BiLSTM) network. The model uses VMD to decompose the original wind power data into multiple stable modal components to alleviate the complex characteristics of the data, and adopts BiLSTM to extract the temporal dependency information in each component to achieve accurate prediction of wind power trends. Experimental results on two public wind power datasets show that VMD-BiLSTM outperforms many other advanced models in terms of data fitting and prediction accuracy, and effectively reduces the impact of intermittent instability in wind power generation on prediction results. This research provides new ideas for the modeling and prediction of complex wind power data and offers strong data support for decision-making in smart grids.

Keywords

time series prediction; wind power; Big Data; Deep Learning; mode decomposition

References

  1. [1] Zhang Shengcai Research on Short term Wind Speed Hybrid Prediction of Wind Farm Based on Deep Learning [D]. Lanzhou: Lanzhou University of Technology, 2024
  2. [2] Zhang Min Analysis of the current situation and development trend of wind turbines [J]. China Machinery, 2024 (3): 58-61
  3. [3] Ye Jiaju Research on Wind Power Generation Prediction Method Based on Width Learning [D]. Harbin: Heilongjiang University, 2024
  4. [4] Zhou Yugao, Ye Hairui, Xu Dongshu Application Analysis of Intelligent Technology in Wind Power Generation Automation Control System [J]. East China Science and Technology, 2023 (6): 61-63
  5. [5] Wei Le, Dai Ze, Chen Yuanye, etc Short term wind power combination prediction model considering multiple to one spatiotemporal features [J]. Journal of Power Engineering, 2024, 44 (12): 1869-1877
  6. [6] Wang Fanrong, Mei Tao, Zhang Xudong, etc Short term wind power prediction based on SSA-VMD-INGO-RF [J]. Modern Electronic Technology, 2024, 47 (24): 88-96
  7. [7] HAN Y，MI L H，SHEN L，et al. A Short-term Wind Speed Prediction Method Utilizing Novel Hybrid Deep Learning Algorithms to Correct Numerical Weather Forecasting [J/OL].Applied Energy，2022，312：118777（2022-02-24）.https://doi.org/10.1016/j.apenergy.2022.118777.
  8. [8] YAZDI A. Nonlinear Model Predictive Control of a Vortex-induced Vibrations Bladeless Wind Turbine [J/OL].Smart Materials and Structures，2018，27（7）：075005：（2018-05-29）.https://iopscience.iop.org/article/10.1088/1361-665X/aac0b6.
  9. [9] WANG Y R，WANG D C，TANG Y. Clustered Hybrid Wind Power Prediction Model Based on ARMA，PSO-SVM，and Clustering Methods [J].IEEE Access，2020，8：17071-17079.
  10. [10] Zheng Yingying, Li Xin, Chen Yanxu, etc Short term wind power prediction method for extreme weather based on Stacking multi model fusion [J]. High Voltage Technology, 2024, 50 (9): 3871-3882
  11. [11] Wang Rui, Wang Yuning, Lu Jing Short term wind power prediction based on double decomposition and deep learning [J]. Journal of Wuhan University: Engineering Edition, 2025, 58 (8): 1346-1355
  12. [12] LIU H Y，HAN H，SUN Y，et al. Short-term Wind Power Interval Prediction Method Using VMD-RFG and Att-GRU [J/OL].Energy，2022，251：123807(2022-04-08).https://doi.org/10.1016/j.energy.2022.123807.
  13. [13] Jin Mengxue Research on Wind Power Prediction Based on Improved VMD and Deep Learning [D]. Xi'an: Xi'an University of Technology, 2023
  14. [14] ZHANG G，LIU H C，ZHANG J B，et al. Wind Power Prediction Based on Variational Mode Decomposition Multi-frequency Combinations [J].Journal of Modern Power Systems and Clean Energy，2018，7（2）：281-288.
  15. [15] Li Hao Application of GRNN and Markov Joint Model Based on SVR Outlier Detection and VMD Decomposition in Wind Speed Prediction [D]. Lanzhou: Lanzhou University, 2017
  16. [16] Hou Zaihong Research on Short term Wind Power Prediction Model Based on Deep Neural Network [D]. Lanzhou: Northwest Normal University, 2024
  17. [17] WANG R O E，LI C S，FU W L，et al. Deep Learning Method Based on Gated Recurrent Unit and Variational Mode Decomposition for Short-term Wind Power Interval Prediction [J].IEEE transactions on neural networks and learning systems，2019（99）：1-14.
  18. [18] Ma Yirong Short term wind power prediction based on improved variational mode decomposition and gated cyclic unit network [D]. Xi'an: Xi'an University of Technology, 2022
  19. [19] XIONG J L，PENG T，TAO Z H，et al. A Dual-scale Deep Learning Model Based on ELM-BiLSTM and Improved Reptile Search Algorithm for Wind Power Prediction [J/OL].Energy，2023，266：126419(2022-12-17).https://doi.org/10.1016/j.energy.2022.126419.
  20. [20] Yao Yue Short term wind power prediction based on attention mechanism and neural network [D]. Beijing: North China Electric Power University (Beijing), 2022
  21. [21] KISVARI A，LIN Z，LIU X. Wind Power Forecasting–A Data-driven Method Along with Gated Recurrent Neural Network [J].Renewable Energy，2021，163：1895-1909.
  22. [22] MUKHOTY B P，MAURYA V，SHUKLA S K. Sequence to Sequence Deep Learning Models for Solar Irradiation Forecasting [C]//2019 IEEE Milan PowerTech.Milan：IEEE，2019：1-6.
  23. [23] GRAVES M. Moral Attention Is All You Need [J].Theology and Science，2025，23（2）：241-248.
  24. [24] LAI G，CHANG W C，YANG Y，et al. Modeling Long-and Short-Term Temporal Patterns with Deep Neural Networks [C]//The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval.Ann Arbor：ACM，2018：95-104.
  25. [25] PENG C，LI Y，YU Y，et al. Multi-step-ahead Host Load Prediction with GRU Based Encoder-decoder in Cloud Computing [C]//2018 10th International Conference on Knowledge and Smart Technology(KST).Chiang Mai：IEEE，2018：186-191.
  26. [26] YU X N，WANG H F，WANG J R，et al. A Common Feature-driven Prediction Model for Multivariate Time Series Data [J/OL].Information Sciences，2024，677：120967（2024-08-01）.https://doi.org/10.1016/j.ins.2024.120967.

About the authors

Dai Xianyong (2004-), male, Han ethnicity, from Jinan, Shandong Province, undergraduate studies, research direction: pattern recognition and control systems; Correspondence author: Liu Wenqi (1997-), female, Han nationality, from Jinan, Shandong Province, associate professor, master's candidate, research direction: intelligent computing and edge computing.