Hybrid Decomposition ICEEMDAN-EWT Deep Learning Framework for Wind Speed Forecasting
DOI:
https://doi.org/10.30871/jaic.v9i4.10241Keywords:
ICEEMDAN, IMF, EWT, BiLSTM, Wind Speed PredictionAbstract
Accurate wind speed forecasting plays a crucial role in supporting early warning systems for extreme wind events. However, the inherent non-linearity and non-stationarity of wind speed data pose significant challenges. This study addresses these issues by evaluating the effectiveness of targeted Empirical Wavelet Transform (EWT) denoising applied to specific Intrinsic Mode Functions (IMFs) derived from Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN). Daily wind speed data from 2000 to 2023 were decomposed using ICEEMDAN, and denoising was selectively applied to IMF1, IMF2, and IMF3. Each IMF was then modeled using a Bidirectional Long Short-Term Memory (BiLSTM) network under a time-series cross-validation framework. Among all model configurations, the ICEEMDAN+EWT(IMF1 & IMF2)+BiLSTM model achieved the highest predictive accuracy, with an R² of 0.8885, RMSE of 0.501, and MAPE of 7.64%. This result outperformed both the baseline BiLSTM model (R² = 0.0501) and the ICEEMDAN+BiLSTM model without EWT denoising (R² = 0.6433). Moreover, denoising on IMF1 alone also yielded a strong performance (R² = 0.8879), emphasizing the importance of early component selection. Conversely, applying EWT to IMF2 or IMF3 individually resulted in lower R² values of 0.6639 and 0.6327, respectively, indicating limited individual contribution. These findings confirm that selective denoising, especially on the high-frequency IMFs, substantially enhances forecasting accuracy. The proposed approach holds significant potential to improve the timeliness and reliability of wind-related early warning systems, thus contributing to more effective disaster risk reduction strategies.
Downloads
References
[1] X. Zhao, Q. Sun, W. Tang, S. Yu, and B. Wang, “A comprehensive wind speed forecast correction strategy with an artificial intelligence algorithm,” Front Environ Sci, vol. 10, Nov. 2022, doi: 10.3389/fenvs.2022.1034536.
[2] C. Barış, C. Yanarateş, and A. Altan, “A robust chaos-inspired artificial intelligence model for dealing with nonlinear dynamics in wind speed forecasting,” PeerJ Comput Sci, vol. 10, 2024, doi: 10.7717/PEERJ-CS.2393.
[3] H. Zhang, J. Wang, Y. Qian, and Q. Li, “Point and interval wind speed forecasting of multivariate time series based on dual-layer LSTM,” Energy, vol. 294, May 2024, doi: 10.1016/j.energy.2024.130875.
[4] M. U. Yousuf, I. Al-Bahadly, and E. Avci, “Wind speed prediction for small sample dataset using hybrid first-order accumulated generating operation-based double exponential smoothing model,” Energy Sci Eng, vol. 10, no. 3, pp. 726–739, Mar. 2022, doi: 10.1002/ese3.1047.
[5] R. Yang, H. Liu, N. Nikitas, Z. Duan, Y. Li, and Y. Li, “Short-term wind speed forecasting using deep reinforcement learning with improved multiple error correction approach,” Energy, vol. 239, Jan. 2022, doi: 10.1016/j.energy.2021.122128.
[6] J. Du, S. Chen, L. Pan, and Y. Liu, “A Wind Speed Prediction Method Based on Signal Decomposition Technology Deep Learning Model,” Energies (Basel), vol. 18, no. 5, Mar. 2025, doi: 10.3390/en18051136.
[7] Q. Yang and D. An, “EMD and wavelet transform based fault diagnosis for wind turbine gear box,” Advances in Mechanical Engineering, vol. 2013, 2013, doi: 10.1155/2013/212836.
[8] D. Dong, S. Wang, Q. Guo, W. Zou, X. Li, and Z. Wang, “Enhanced Short-Term Wind Speed Prediction by ICEEMDAN and Feature Engineering,” in Proceedings - 2023 China Automation Congress, CAC 2023, Institute of Electrical and Electronics Engineers Inc., 2023, pp. 1063–1068. doi: 10.1109/CAC59555.2023.10451255.
[9] H. Yao, Y. Tan, J. Hou, Y. Liu, X. Zhao, and X. Wang, “Short-Term Wind Speed Forecasting Based on the EEMD-GS-GRU Model,” Atmosphere (Basel), vol. 14, no. 4, Apr. 2023, doi: 10.3390/atmos14040697.
[10] H. Wei, T. Qi, G. Feng, and H. Jiang, “Comparative Research on Noise Reduction of Transient Electromagnetic Signals Based on Empirical Mode Decomposition and Variational Mode Decomposition,” Radio Sci, vol. 56, no. 10, Oct. 2021, doi: 10.1029/2020RS007135.
[11] X. Xia and X. Wang, “A Novel Hybrid Model for Short-Term Wind Speed Forecasting Based on Twice Decomposition, PSR, and IMVO-ELM,” Complexity, vol. 2022, 2022, doi: 10.1155/2022/4014048.
[12] Z. Tian and J. Wang, “A Novel Wind Speed Interval Prediction System Based on Neural Network and Multi-objective Grasshopper Optimization,” International Transactions on Electrical Energy Systems, vol. 2022, 2022, doi: 10.1155/2022/5823656.
[13] Q. Zhuang, L. Gao, W. Li, and X. Shu, “Ultra-Short-Term Wind Power Prediction Based on ICEEMDAN-Nons-Transformer,” in 2024 International Conference on Energy and Electrical Engineering (EEE), IEEE, Jul. 2024, pp. 1–6. doi: 10.1109/EEE59956.2024.10709682.
[14] I. Karijadi, S. Y. Chou, and A. Dewabharata, “Wind power forecasting based on hybrid CEEMDAN-EWT deep learning method,” Renew Energy, vol. 218, Dec. 2023, doi: 10.1016/j.renene.2023.119357.
[15] J. Gilles, “Empirical wavelet transform,” IEEE Transactions on Signal Processing, vol. 61, no. 16, pp. 3999–4010, 2013, doi: 10.1109/TSP.2013.2265222.
[16] B. S. Bommidi, V. Kosana, K. Teeparthi, and S. Madasthu, “Hybrid attention-based temporal convolutional bidirectional LSTM approach for wind speed interval prediction,” Environmental Science and Pollution Research, vol. 30, no. 14, pp. 40018–40030, Mar. 2023, doi: 10.1007/s11356-022-24641-x.
[17] Y. Liu, J. He, Y. Wang, Z. Liu, L. He, and Y. Wang, “Short-Term Wind Power Prediction Based on CEEMDAN-SE and Bidirectional LSTM Neural Network with Markov Chain,” Energies (Basel), vol. 16, no. 14, Jul. 2023, doi: 10.3390/en16145476.
[18] M. A. Colominas, G. Schlotthauer, and M. E. Torres, “Improved complete ensemble EMD: A suitable tool for biomedical signal processing,” Biomed Signal Process Control, vol. 14, no. 1, pp. 19–29, 2014, doi: 10.1016/j.bspc.2014.06.009.
[19] J. Liu, Y. Wu, X. Cheng, B. Li, and P. Yang, “Short-term wind power prediction based on ICEEMDAN-Correlation reconstruction and BWO-BiLSTM,” Electrical Engineering, 2024, doi: 10.1007/s00202-024-02574-7.
[20] L. Jian, X. Wang, H. Hao, H. Wang, and L. Yang, “Fusion of PSO-SVM and ICEEMDAN for high stability GNSS-MR sea level height estimation,” All Earth, vol. 36, no. 1, pp. 1–15, 2024, doi: 10.1080/27669645.2024.2331328.
[21] Z. Zhan and S. K. Kim, “Versatile time-window sliding machine learning techniques for stock market forecasting,” Artif Intell Rev, vol. 57, no. 8, Aug. 2024, doi: 10.1007/s10462-024-10851-x.
[22] A. A. Saputra, K. Ma’Ruf, R. J. Setiawan, Darmono, and N. Azizah, “Enhancing Predictive Accuracy of LSTM Neural Networks for Diabetes Risk through K-Fold Cross-Validation: Comparison with K-Nearest Neighbors and Expert Systems,” in 2024 International Conference on Decision Aid Sciences and Applications, DASA 2024, Institute of Electrical and Electronics Engineers Inc., 2024. doi: 10.1109/DASA63652.2024.10836564.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Dedi Arman Alif Hidayat; Muhamad Hilmil Muchtar Aditya Pradana , Ahmad Saikhu
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
