Journal of Researches in Mechanics of Agricultural Machinery

Journal of Researches in Mechanics of Agricultural Machinery

Short-Term Wind Power Forecasting Using a Hybrid Deep Learning Model

Document Type : Special English issue

Authors
Mahsa Barzegarkhas
Tarahom Mesri Gundoshmian
University of Mohaghegh Ardabili, Ardabil, Iran
10.22034/jrmam.2026.15006.766
Abstract
Due to the variable and non-deterministic nature of wind, accurate prediction of wind turbine power output is crucial for integrating this renewable energy source into the power grid and optimizing operational management. This study proposes a hybrid deep learning framework for accurate short-term prediction. The proposed model, by sequentially integrating a Convolutional Neural Network (CNN) and a Long Short-Term Memory (LSTM) network, can simultaneously extract and model local patterns and short-term dependencies through the CNN layers and long-term temporal dependencies through the LSTM layers from time-series data. The data used are real operational supervisory data from wind turbines in the Manjil region of Iran over a one-year period (from April 2024 to March 2025). After outlier removal, noise reduction, and normalization, a set of key variables including wind speed, rotor speed, generator speed, and temperatures of critical turbine components were selected as input features. The performance of the proposed hybrid CNN-LSTM model was compared with three baseline machine learning models (Linear Regression, Random Forest, and Gradient Boosting) based on the common evaluation metrics of Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and the Coefficient of Determination (R²). The results clearly demonstrate the superiority of the hybrid model. The CNN-LSTM model, with the lowest MAE and the highest coefficient of determination (R² = 0.892), performed significantly better than the comparative models. Correlation analyses revealed that wind speed-related variables had the greatest influence on power output. Furthermore, time-series and scatter plots demonstrated a close match between the model's predictions and actual values, effectively showcasing its ability to track complex fluctuations, seasonal variations, and even transient events. This study demonstrated that hybrid deep learning methods, due to their inherent ability to model non-linear and multi-scale relationships, represent an effective solution to the challenge of wind power forecasting. Applying this model to the operational data of a wind farm site constitutes a fundamental step towards localizing and developing intelligent management solutions for renewable energy in the country.
Keywords
Renewable Energy
Short-Term Wind Power Forecasting
Long Short-Term Memory (LSTM)
SCADA Data
Convolutional Neural Network (CNN)
Hybrid Model
Deep Learning
Ghorbani, A., Mesri Gundoshmian, T., Khodkam, H., & Ghaebi, H. (2025). Comparison of vehicles with biofuel, electric, fuel cell, and solar energy for decarbonization of the transportation sector. Journal of Renewable and New Energy, 12(1), 200-208. (In Persian).  https://doi.org/10.22034/jrenew.2025.216127
 
Khodkam, H., Pourdarbani, R., & Najafi, B. (2026). Investigating the status of agricultural waste and providing new disposal solutions. Journal of Renewable and New Energy, 13(1), 142-152. (In Persian). https://doi.org/10.22034/jrenew.2026.219649‏
 
Veers, P., Bottasso, C. L., Manuel, L., Naughton, J., Pao, L., Paquette, J., ... & Rinker, J. (2023). Grand challenges in the design, manufacture, and operation of future wind turbine systems. Wind Energy Science, 8(7), 1071-1131.‏ https://doi.org/10.5194/wes-8-1071-2023
 
Zhou, F., Chen, Y., & Liu, J. (2023). Application of a new hybrid deep learning model that considers temporal and feature dependencies in rainfall–runoff simulation. Remote Sensing, 15(5), 1395.‏ https://doi.org/10.3390/rs15051395
 
Khodkam, H., Pourdarbani, R., & Hernandez-Hernandez, J. L. (2025). Selection of the Most Appropriate Vehicles with the Aim of Decarbonising the Transportation Sector Using AHP. Acta Technologica Agriculturae, 28(2), 63-70.‏ DOI: 10.2478/ata-2025-0009
 
Herges, T., Maniaci, D. C., Debnath, M. C., Fao, R. M., Hamilton, N., Krsithnamurthy, R., & Naughton, J. W. (2024). Wind Energy Instrumentation Development Roadmap (No. SAND-2024-14247). Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); National Renewable Energy Laboratory (NREL), Golden, CO (United States); Pacific Northwest National Laboratory (PNNL), Richland, WA (United States).‏
 
Kaur, J., Parmar, K. S., & Singh, S. (2023). Autoregressive models in environmental forecasting time series: a theoretical and application review. Environmental Science and Pollution Research, 30(8), 19617-19641.‏ https://doi.org/10.1007/s11356-023-25148-9
 
Hanifi, S., Liu, X., Lin, Z., & Lotfian, S. (2020). A critical review of wind power forecasting methods—past, present and future. Energies, 13(15), 3764.‏ https://doi.org/10.3390/en13153764
 
Trehan, M., Bhanotia, D., Shaikh, T. A., Sharma, S., & Sharma, S. (2023). Artificial intelligence-based automated model for prediction of extraction using neural network machine learning: A scope and performance analysis. J. Contemp. Orthod, 7, 281-286.‏ https://doi.org/10.18231/j.jco.2023.048
 
Tian, C., & Chan, W. K. (2021). Spatial‐temporal attention wavenet: A deep learning framework for traffic prediction considering spatial‐temporal dependencies. IET Intelligent Transport Systems, 15(4), 549-561.‏
 
Choudhury, P., Allen, R. T., & Endres, M. G. (2021). Machine learning for pattern discovery in management research. Strategic Management Journal, 42(1), 30-57.‏
 
Khodkam, H. (2025). Effect of different pretreatments and their parameters on biogas production performance: A review. Energy Storage and Conversion, 3(4).‏ DOI: https://doi.org/10.59400/esc3842
 
Hanif, S., Alam, M. J. E., Roshan, K., Bhatti, B. A., & Bedoya, J. C. (2022). Multi-service battery energy storage system optimization and control. Applied Energy, 311, 118614.‏ https://doi.org/10.1016/j.apenergy.2022.118614
 
Wu, B., Yu, S., Peng, L., & Wang, L. (2024). Interpretable wind speed forecasting with meteorological feature exploring and two-stage decomposition. Energy, 294, 130782.‏ https://doi.org/10.1016/j.energy.2024.130782
 
Hossain, M. A., Gray, E., Lu, J., Islam, M. R., Alam, M. S., Chakrabortty, R., & Pota, H. R. (2023). Optimized forecasting model to improve the accuracy of very short-term wind power prediction. IEEE Transactions on Industrial Informatics, 19(10), 10145-10159.‏ 10.1109/TII.2022.3230726
 
Figurski, M. J., Nykiel, G., Jaczewski, A., Bałdysz, Z., & Wdowikowski, M. (2022). The impact of initial and boundary conditions on severe weather event simulations using a high-resolution WRF model. Case study of the derecho event in Poland on 11 August 2017. Meteorology Hydrology and Water Management. Research and Operational Applications, 10.‏
 
Aggarwal, R., & Kumar, R. (2013). A comprehensive review of numerical weather prediction models. International Journal of Computer Applications, 74(18).‏
 
He, B., Ye, L., Pei, M., Lu, P., Dai, B., Li, Z., & Wang, K. (2022). A combined model for short-term wind power forecasting based on the analysis of numerical weather prediction data. Energy Reports, 8, 929-939.‏ https://doi.org/10.1016/j.egyr.2021.10.102
 
Kaur, J., Parmar, K. S., & Singh, S. (2023). Autoregressive models in environmental forecasting time series: a theoretical and application review. Environmental Science and Pollution Research, 30(8), 19617-19641.‏ https://doi.org/10.1007/s11356-023-25148-9
 
Acar, E., Bayrak, G., Jung, Y., Lee, I., Ramu, P., & Ravichandran, S. S. (2021). Modeling, analysis, and optimization under uncertainties: a review. Structural and Multidisciplinary Optimization, 64(5), 2909-2945.
https://doi.org/10.1007/s00158-021-03026-7 ‏
 
Dhaka, P., Sreejeth, M., & Tripathi, M. M. (2024). A survey of artificial intelligence applications in wind energy forecasting. Archives of Computational Methods in Engineering, 31(8), 4853-4878.‏ https://doi.org/10.1007/s11831-024-10182-8
 
Kumar, K., Prabhakar, P., Verma, A., Saroha, S., & Singh, K. (2025). Advancements in wind power forecasting: A comprehensive review of artificial intelligence-based approaches. Multimedia Tools and Applications, 84(10), 8331-8360.‏ https://doi.org/10.1007/s11042-024-18916-3
 
Zhang, Y., Li, R., & Zhang, J. (2021). Optimization scheme of wind energy prediction based on artificial intelligence. Environmental Science and Pollution Research, 28(29), 39966-39981.‏ https://doi.org/10.1007/s11356-021-13516-2
 
Qureshi, S., Shaikh, F., Kumar, L., Ali, F., Awais, M., & Gürel, A. E. (2023). Short-term forecasting of wind power generation using artificial intelligence. Environmental Challenges, 11, 100722.‏ https://doi.org/10.1016/j.envc.2023.100722
 
Alshingiti, Z., Alaqel, R., Al-Muhtadi, J., Haq, Q. E. U., Saleem, K., & Faheem, M. H. (2023). A deep learning-based phishing detection system using CNN, LSTM, and LSTM-CNN. Electronics, 12(1), 232.‏  https://doi.org/10.3390/electronics12010232
 
Nabipour, N., Mosavi, A., Hajnal, E., Nadai, L., Shamshirband, S., & Chau, K. W. (2020). Modeling climate change impact on wind power resources using adaptive neuro-fuzzy inference system. Engineering Applications of Computational Fluid Mechanics, 14(1), 491-506. https://doi.org/10.1080/19942060.2020.1722241
 
Hou, Y., Wang, Q., Bao, Y., & Tan, T. (2025). Decoding wind power uncertainty: A Bayesian-optimized machine learning approach for multi-timescale dynamic transitions. Energy Strategy Reviews, 62, 101937.‏ https://doi.org/10.1016/j.esr.2025.101937
 
Jalali, S. M. J., Ahmadian, S., Khosravi, A., Shafie-khah, M., Nahavandi, S., & Catalão, J. P. (2021). A novel evolutionary-based deep convolutional neural network model for intelligent load forecasting. IEEE Transactions on Industrial Informatics, 17(12), 8243-8253.‏ DOI: 10.1109/TII.2021.3065718
 
Sherstinsky, A. (2020). Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Physica D: Nonlinear Phenomena, 404, 132306.‏ https://doi.org/10.1016/j.physd.2019.132306
 
Gunther, S., Ruthotto, L., Schroder, J. B., Cyr, E. C., & Gauger, N. R. (2020). Layer-parallel training of deep residual neural networks. SIAM Journal on Mathematics of Data Science, 2(1), 1-23.‏
 
Veluru, S. R., Erukude, S. T., & Marella, V. C. (2025, October). From ARIMA to Attention: Power Load Forecasting Using Temporal Deep Learning. In 2025 IEEE 2nd International Conference on Green Industrial Electronics and Sustainable Technologies (GIEST) (pp. 1-5). IEEE.‏ arXiv:2603.06622v1
 
Hakim, G. J., & Masanam, S. (2024). Dynamical tests of a deep learning weather prediction model. Artificial Intelligence for the Earth Systems, 3(3).‏ https://doi.org/10.1175/AIES-D-23-0090.1
 
Nahid, F. A., Jahangir, M. N., Chowdhury, H. M., & Akter, K. (2025). Evaluation and Performance Metrics for Forecasting Renewable Power Generation, Demand, and Electricity Price. Forecasting Methods for Renewable Power Generation, 173-218.‏https://doi.org/10.1002/9781394249466.ch7
 
Koltai, P., & Kunde, P. (2024). A Koopman–Takens theorem: Linear least squares prediction of nonlinear time series. Communications in Mathematical Physics, 405(5), 120.‏ https://doi.org/10.48550/arXiv.2405.15945
 
Binetti, M. S., Campanale, C., Massarelli, C., & Uricchio, V. F. (2022). The use of weather radar data: Possibilities, challenges and advanced applications. Earth, 3(1), 157-171.‏  https://doi.org/10.3390/earth3010012
 
Dinmohammadi, A., & Shafiee, M. (2017). Determination of the most suitable technology transfer strategy for wind turbines using an integrated AHP-TOPSIS decision model. Energies, 10(5), 642.‏ https://doi.org/10.3390/en10050642
 
Burton, T., Jenkins, N., Sharpe, D., & Bossanyi, E. (2011). Wind energy handbook. John Wiley & Sons.‏
 
Manwell, J. F., McGowan, J. G., & Rogers, A. L. (2010). Wind energy explained: theory, design and application. John Wiley & Sons.‏
 
Zhou, B., Ma, X., & Luo, Y. (2023). Spatiotemporal feature extraction for short-term wind power prediction using a hybrid CNN-LSTM model with attention mechanism. Renewable Energy, 195, 470-483.
 
Lahouar, A., & Slama, J. B. H. (2017). Hour-ahead wind power forecast based on random forests. Renewable energy, 109, 529-541.‏ https://doi.org/10.1016/j.renene.2017.03.064
 
Wang, J., Li, Y., & Li, Z. (2022). A novel hybrid deep learning model for short-term wind power forecasting based on adaptive signal decomposition and feature selection. Energy, 239, 122287.