A Hybrid Computational Framework for Enhance Wind Power Forecasting Using Improved Akima-Empirical Mode Decomposition and Deep Neural Networks in Smart Grid Applications

Haihua  Lv

doi:10.6180/jase.202606_29(6).0001

A Hybrid Computational Framework for Enhance Wind Power Forecasting Using Improved Akima-Empirical Mode Decomposition and Deep Neural Networks in Smart Grid Applications

Computer Science and Information Engineering

Haihua LvThis email address is being protected from spambots. You need JavaScript enabled to view it.

College of Information, Shenyang Institute of Engineering, Shenyang 110136, Liaoning, China

Received: April 22, 2025
Accepted: August 10, 2025
Publication Date: October 19, 2025

Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: ||https://doi.org/10.6180/jase.202606_29(6).0001

Precise Wind Power Forecasting (WPF) is essential for ensuring grid stability and improving the integration of Renewable Energy Sources (RESs). This research introduces an innovative hybrid forecasting model that integrates an enhanced Akima-based Empirical Mode Decomposition (Akima-EMD) with Deep Learning (DL) frameworks, specifically Long Short Term Memory (LSTM) and Bidirectional Gated Recurrent Units (BiGRU). The enhanced Akima-EMD method reduces false oscillations and mode mixing in signal decomposition, while a soft-thresholding approach effectively denoises the input data. The model uses Non Parametric Kernel Density Estimation (NPKDE) to measure uncertainty, while feature selection is conducted using Discrete Wavelet Transform (DWT) with greatest relevance and least redundancy. Simulation results show that the proposed model enhances forecasting accuracy, reducing Root Mean Square Error (RMSE) by 18.7% and elevating the correlation coefficient to 0.92 . In the Smart Grid (SG) Energy Management (EM) scenario, Wind Turbines (WTs) supplied 24.96% of energy demand, while Battery Energy Storage Systems (BESSs) and Electric Vehicles (EVs) provided 7.46% and 3.39% respectively, therefore reducing the reliance on the primary grid and diesel generators. This comprehensive framework enhances forecasting accuracy and energy dispatch adaptability, providing a robust solution for advanced SG applications.

Keywords: Empirical Mode Decomposition, Energy Management, Improved Akima, Grid Stability, Long Short-Term Memory, Wind Power Forecast.

[1] L. Lv, Z. Fang, Z. Yang, L. Wu, and Y. Yang, (2024) “Stability Study of Grid-Connected Power System for Wind Farms Considering Power Control" Scalable Computing: Practice and Experience 25: 700–708. DOI: https: //doi.org/10.12694/scpe.v25i2.2543.
[2] B. Sobhani and S. Afzal, (2022) “Combinatorial price offer for a wind turbine with flexible load considering the uncertainty to increase the benefit of wind turbine" Advances in Engineering and Intelligence Systems 1: 13–21. DOI: https: //doi.org/10.22034/aeis.2022.147971.
[3] A. Niknami, M. T. Askari, M. A. Ahmadi, M. B. Nik, and M. S. Moghaddam, (2024) “Resilient day-ahead microgrid energy management with uncertain demand, EVs, storage, and renewables" Cleaner Engineering and Technology 20: 100763. DOI: https: //doi.org/10.1016/j.clet.2024.100763.
[4] W.-C. Tsai, C. -M. Hong, C.-S. Tu, W. -M. Lin, and C. -H. Chen,(2023) “Areviewofmodernwindpowergeneration forecasting technologies" Sustainability 15: 10757. DOI: https: //doi.org/10.3390/su151410757.
[5] W. Liu, Y. Liu, S. Li, and Y. Chen, (2023) “A review of variational mode decomposition in seismic data analysis" Surveys in Geophysics 44: 323–355. DOI: https: //doi.org/10.1007/s10712-022-09742-z.
[6] Z.MaandG.Mei,(2022)“Ahybridattention-baseddeep learning approach for wind power prediction" Applied Energy 323: 119608. DOI: https: //doi.org/10.1016/j.apenergy.2022.119608.
[7] K. Ullah, A. Basit, Z. Ullah, F. R. Albogamy, and G. Hafeez, (2022) “Automatic generation control in modern power systems with wind power and electric vehicles" Energies 15: 1771. DOI: https: //doi.org/10.3390/en15051771.
[8] M. M. Islam, T. Yu, G. Giannoccaro, Y. Mi, M. L. Scala, M. N.Rajabi, and J. Wang, (2024) “Improving reliability and stability of the power systems: A comprehensive review on the role of energy storage systems to enhance flexibility" IEEE Access: DOI: http: //dx.doi.org/10.1109/ACCESS.2024.3476959.
[9] P. Lu, N. Zhang, L. Ye, E. Du, and C. Kang, (2024) “Advances in model predictive control for large-scale wind power integration in power systems" Advances in Ap plied Energy 14: 100177. DOI: https: //doi.org/10.1016/j.adapen.2024.100177.
[10] W.-c. Wang, B. Wang, K.-w. Chau, and D.-m. Xu, (2023) “Monthly runoff time series interval prediction based on WOA-VMD-LSTM using non-parametric kernel density estimation" Earth Science Informatics 16: 2373–2389. DOI: https: //doi.org/10.1007/s12145-023-01038-z.
[11] L. Ali, M. M. Al-Sakhnini, D. Kalra, F. Afzaal, M. Pervaiz, and M. F. Khan. “Distributed search engine query optimization using artificial neural network”. In: 2022 International Conference on Cyber Resilience (ICCR). IEEE, 2022, 1–5. DOI: https: //doi.org/10.1109/iccr56254.2022.9995958.
[12] Z. Sun, M. Zhao, and G. Zhao, (2022) “Hybrid model based on VMD decomposition, clustering analysis, long short memory network, ensemble learning and error complementation for short-term wind speed forecasting assisted by Flink platform" Energy 261: 125248. DOI: https: //doi.org/10.1016/j.energy.2022.125248.
[13] V. K. Saini, R. Kumar, A. S. Al-Sumaiti, and E. Heydarian-Forushani, (2023) “Learning based short term wind speed forecasting models for smart grid applications: An extensive review and case study" Electric Power Systems Research 222: 109502. DOI: https: //doi.org/10.1016/j.epsr.2023.109502.
[14] Y. Du, K. Zhang, Q. Shao, and Z. Chen, (2023) “A short-term prediction model of wind power with outliers: An integration of long short-term memory, ensemble empirical mode decomposition, and sample entropy" Sustainability 15: 6285. DOI: https: //doi.org/10.3390/su15076285.
[15] L. Zhao, Z. Li, J. Zhang, and B. Teng, (2023) “An integrated complete ensemble empirical mode decomposition with adaptive noise to optimize LSTM for significant wave height forecasting" Journal of Marine Science and Engineering 11: 435. DOI: https: //doi.org/10.3390/jmse11020435.
[16] Z. Liu, S. Zhang, X. Shao, and Z. Wu, (2023) “Ac curate and efficient urban wind prediction at city-scale with memory-scalable graph neural network" Sustain able Cities and Society 99: 104935. DOI: https: //doi.org/10.1016/j.scs.2023.104935.
[17] E. Ghanbari and A. Avar, (2025) “Short-term wind power forecasting using the hybrid model of multivariate variational mode decomposition (MVMD) and long short-term memory (LSTM) neural networks" Electrical Engineering 107: 2903–2933. DOI: https: //doi.org/10.1007/s00202-024-02685-1.
[18] H. Hu, S. Deng, W. Yan, Y. He, and Y. Wu, (2024) “Prediction of operational noise uncertainty in automotive micro-motors based on multi-branch channel–spatial adaptive weighting strategy" Electronics 13: 2553. DOI: https: //doi.org/10.3390/electronics13132553.
[19] Z. Jiang, Q. Tan, N. Li, J. Che, and X. Tan, (2024) “A novel BiGRU multi-step wind power forecasting approach based on multi-label integration random forest feature selection and neural network clustering" Energy Con version and Management 319: 118904. DOI: https: //doi.org/10.1016/j.enconman.2024.118904.
[20] U. Yuzgec, E. Dokur, and M. Balci, (2024) “A novel hybrid model based on empirical mode decomposition and echo state network for wind power forecasting" Energy 300: 131546. DOI: https: //doi.org/10.1016/j.energy.2024.131546.
[21] J.K.ParkerandL.O.Hall,(2013)“Accelerating fuzzy-c means using an estimated subsample size" IEEE Trans actions on Fuzzy Systems 22: 1229–1244. DOI: https: //doi.org/10.1109/TFUZZ.2013.2286993.
[22] M. M. Romadanova. “Wind velocity data interpolation using a weighted cubic spline”. In: E3S Web of Conferences. 402. EDP Sciences, 2023, 05011. DOI: https: //doi.org/10.1051/e3sconf/202340205011.
[23] O. Abedinia, M. Lotfi, M. Bagheri, B. Sobhani, M. Shafie-Khah, and J. P. S. Catalão, (2020) “Improved EMD-based complex prediction model for wind power forecasting" IEEE Transactions on Sustainable Energy 11: 2790–2802. DOI: https: //doi.org/10.1109/TSTE.2020.2976038.
[24] K. Dragomiretskiy and D. Zosso, (2013) “Variational mode decomposition" IEEE transactions on signal pro cessing 62: 531–544. DOI: https: //doi.org/10.1109/TSP.2013.2288675.
[25] C. Gao, T. Tang, W. Wu, F. Zhang, Y. Luo, W. Wu, B. Yao, and J. Li, (2023) “Hyperspectral prediction model of nitrogen content in citrus leaves based on the CEEM DAN–SRalgorithm" Remote Sensing 15: 5013. DOI: https: //doi.org/10.3390/rs15205013.
[26] J. P. Muszkats, S. A. Seminara, and M. I. Tro parevsky. Applications of wavelet multiresolution anal ysis. Springer, 2021. DOI: https: //doi.org/10.1007/978-3-030-61713-4.
[27] D. Sundararajan. Discrete wavelet transform: a signal processing approach. John Wiley Sons, 2016.
[28] D. Sundararajan. Signals and Systems.
[29] J. Xu, J. Du, and C. Yuan, (2024) “An alternative 2D ICEEMDAN-based denoising method and its application in processing magnetic anomaly data" Geodesy and Geodynamics 15: 465–476. DOI: https: //doi.org/10.1016/j.geog.2024.04.002.
[30] P.Flandrin,P.Gonçalvès,andG.Rilling,(2005)“EMD EQUIVALENTFILTERBANKS,FROMINTERPRETA TION TO APPLICATIONS" Hilbert-Huang Trans form and Its Applications: 57–74. DOI: https: //doi.org/10.1142/8804.
[31] J. Xu, J. Du, and C. Yuan, (2024) “An alternative 2D ICEEMDAN-based denoising method and its application in processing magnetic anomaly data" Geodesy and Geodynamics 15: 465–476. DOI: https: //doi.org/10.1016/j.geog.2024.04.002.
[32] T. Zhang, Y. Huang, B. Gu, H. Liao, and C. Song, “Short-Term Forecasting and Uncertainty Analysis for Wind Power Generation Based on Hybrid Deep Learning and Cloud Model" Available at SSRN 3900344: DOI: https: //dx.doi.org/10.2139/ssrn.3900344.
[33] T. Zhang, Y. Huang, H. Liao, X. Gong, and B. Peng, (2024) “Short-term power forecasting and uncertainty analysis of wind farm at multiple time scales" Ieee Access 12: 25129–25145. DOI: https: //doi.org/10.1109/ACCESS.2024.3365493.
[34] T. Zhang, Y. Huang, H. Liao, X. Gong, and B. Peng, (2024) “Short-term power forecasting and uncertainty analysis of wind farm at multiple time scales" Ieee Access 12: 25129–25145. DOI: https: //doi.org/10.1109/ACCESS.2024.3365493.
[35] M. Ali, D. M. Khan, I. Saeed, and H. M. Alshanbari, (2023) “A new approach to empirical mode decomposition based on akimaspline interpolation technique" IEEE Ac cess 11: 67370–67384. DOI: http: //dx.doi.org/10.1109/ACCESS.2023.3253279.

Latest Articles