Modeling Wind Energy Production Forecasting using Machine Learning: An In-depth Analysis of Wind Farms in Morocco
Received: 20 January 2025 | Revised: 20 March 2025 | Accepted: 2 April 2025 | Online: 28 April 2025
Corresponding author: Mohamed Bousla
Abstract
Accurate forecasting of wind energy production is essential for the stable integration of renewable energy sources into power grids, especially given the inherent variability of wind conditions. This study evaluates the effectiveness of Transformer-based models for improving wind energy forecasting accuracy, compared to traditional methods such as Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM), and Gated Recurrent Units (GRUs). Unlike the conventional sequential models, the Transformer models leverage an advanced attention mechanism, which processes all time steps simultaneously rather than sequentially, thereby efficiently capturing complex, long-term dependencies within the data. To conduct this analysis, we utilized a dataset collected from an operational wind farm located in Tetouan, northern Morocco, covering the period from 2019 to 2020. The experimental results show that the Transformer model consistently outperformed the traditional methods, achieving Mean Squared Error (MSE) of 0.275, 0.234, and 0.221, and Mean Absolute Error (MAE) of 0.305, 0.296, and 0.284 for daily, weekly, and monthly forecasting horizons, respectively. Specifically, the Transformer model achieved approximately a 10% reduction in Mean Absolute Percentage Error (MAPE) compared to the LSTM model. These findings demonstrate the substantial advantage of Transformer-based approaches in wind energy forecasting and underline their potential to significantly enhance the reliability of renewable energy integration into modern power grids.
Keywords:
ML, transformer-based models, RNN, LSTM, GRU, wind power forecast, wind energyDownloads
References
A. Allouhi, "A hybrid PV/wind/battery energy system to assist a run-of-river micro-hydropower for clean electrification and fuelling hydrogen mobility for young population in a rural Moroccan site," Journal of Cleaner Production, vol. 442, Feb. 2024, Art. no. 140852.
A. El-Maaroufi, M. Daoudi, and R. Ahl Laamara, "Optimal design and techno-economic analysis of a solar-wind hybrid power system for laayoune city electrification with hydrogen and batteries as a storage device," Physics and Chemistry of the Earth, Parts A/B/C, vol. 136, Dec. 2024, Art. no. 103719.
M. Bousla, A. Haddi, Y. El Mourabit, A. Sadki, A. Mouradi, and A. El Kharrim, "Detection and Prevention of Repetitive Major Faults of a WTG by Analysis of Alarms Through SCADA," in Digital Technologies and Applications, 2023, pp. 745–752.
M. Bousla, Y. El Mourabit, and A. Haddi, "Optimizing Wind Farm Maintenance in Northern Morocco through SCADA System Failure Data Analysis," in 2024 International Conference on Computing, Internet of Things and Microwave Systems (ICCIMS), Gatineau, QC, Canada, Jul. 2024.
X. Zhao, C. Wang, J. Su, and J. Wang, "Research and application based on the swarm intelligence algorithm and artificial intelligence for wind farm decision system," Renewable Energy, vol. 134, pp. 681–697, Apr. 2019.
S. Jafarian-Namin, A. Goli, M. Qolipour, A. Mostafaeipour, and A.-M. Golmohammadi, "Forecasting the wind power generation using Box–Jenkins and hybrid artificial intelligence: A case study," International Journal of Energy Sector Management, vol. 13, no. 4, pp. 1038–1062, Jun. 2019.
M. Bousla et al., "Analysis and Comparison of Wind Potential by Estimating the Weibull Distribution Function: Application to Wind Farm in the Northern of Morocco," Sustainability, vol. 15, no. 20, Jan. 2023, Art. no. 15087.
Y. Amellas, O. E. Bakkali, A. Djebli, and A. Echchelh, "Short-term wind speed prediction based on MLP and NARX network models," Indonesian Journal of Electrical Engineering and Computer Science, vol. 18, no. 1, pp. 150–157, Apr. 2020.
Y. Li et al., "An Explainable Deep Learning Model for Daily Sea Ice Concentration Forecast," IEEE Transactions on Geoscience and Remote Sensing, vol. 62, pp. 1–17, 2024.
G. De Moliner, P. Giani, G. Lonati, and P. Crippa, "Sensitivity of multiscale large Eddy simulations for wind power calculations in complex terrain," Applied Energy, vol. 364, Jun. 2024, Art. no. 123195.
S. Rüstemli, O. Güntas, G. Şahin, A. Koç, W. van Sark, and S. Ş. Doğan, "Wind power plant site selection problem solution using GIS and resource assessment and analysis of wind energy potential by estimating Weibull distribution function for sustainable energy production: The case of Bitlis/Turkey," Energy Strategy Reviews, vol. 56, Nov. 2024, Art. no. 101552.
W. Li, Y. Chong, X. Guo, and J. Liu, "A hybrid wind power prediction model based on seasonal feature decomposition and enhanced feature extraction," Energy and AI, vol. 18, Dec. 2024, Art. no. 100442.
S. M. Valdivia-Bautista, J. A. Domínguez-Navarro, M. Pérez-Cisneros, C. J. Vega-Gómez, and B. Castillo-Téllez, "Artificial Intelligence in Wind Speed Forecasting: A Review," Energies, vol. 16, no. 5, Jan. 2023, Art. no. 2457.
L.-L. Li, X. Zhao, M.-L. Tseng, and R. R. Tan, "Short-term wind power forecasting based on support vector machine with improved dragonfly algorithm," Journal of Cleaner Production, vol. 242, Jan. 2020, Art. no. 118447.
L.-L. Li, Y.-B. Chang, M.-L. Tseng, J.-Q. Liu, and M. K. Lim, "Wind power prediction using a novel model on wavelet decomposition-support vector machines-improved atomic search algorithm," Journal of Cleaner Production, vol. 270, Oct. 2020, Art. no. 121817.
B. Memon, M. H. Baloch, A. H. Memon, S. H. Qazi, R. Haider, and D. Ishak, "Assessment of Wind Power Potential Based on Raleigh Distribution Model: An Experimental Investigation for Coastal Zone," Engineering, Technology & Applied Science Research, vol. 9, no. 1, pp. 3721–3725, Feb. 2019.
M. Bousla, A. Haddi, Y. E. Mourabit, A. Sadki, A. Mouradi, and A. E. Kharrim, "Optimizing Wind Farm Performance in Northern Morocco with Weibull Distribution," in Digital Technologies and Applications, 2024, pp. 454–463.
S. Hu, Y. Xiang, D. Huo, S. Jawad, and J. Liu, "An improved deep belief network based hybrid forecasting method for wind power," Energy, vol. 224, Jun. 2021, Art. no. 120185.
Z. Jiang, J. Che, M. He, and F. Yuan, "A CGRU multi-step wind speed forecasting model based on multi-label specific XGBoost feature selection and secondary decomposition," Renewable Energy, vol. 203, pp. 802–827, Feb. 2023.
J.-P. Lai, Y.-M. Chang, C.-H. Chen, and P.-F. Pai, "A Survey of Machine Learning Models in Renewable Energy Predictions," Applied Sciences, vol. 10, no. 17, Jan. 2020, Art. no. 5975.
L. Donadio, J. Fang, and F. Porté-Agel, "Numerical Weather Prediction and Artificial Neural Network Coupling for Wind Energy Forecast," Energies, vol. 14, no. 2, Jan. 2021, Art. no. 338.
Z. Zhang, H. Dai, D. Jiang, Y. Yu, and R. Tian, "Multi-step ahead forecasting of wind vector for multiple wind turbines based on new deep learning model," Energy, vol. 304, Sep. 2024, Art. no. 131964.
M. Bousla, M. Belfkir, A. Haddi, Y. El Mourabit, and B. Bossoufi, "Comparison of artificial intelligence approaches for estimating wind energy production: A real-world case study," Results in Engineering, vol. 24, Dec. 2024, Art. no. 103626.
Adomako, Abigail Birago, et al. "Deep learning approaches for bias correction in WRF model outputs for enhanced solar and wind energy estimation: A case study in East and West Malaysia." Ecological Informatics (2024): 102898.
U. Singh and M. Rizwan, "SCADA system dataset exploration and machine learning based forecast for wind turbines," Results in Engineering, vol. 16, Dec. 2022, Art. no. 100640.
J. He and J. Xu, "Ultra-short-term wind speed forecasting based on support vector machine with combined kernel function and similar data," EURASIP Journal on Wireless Communications and Networking, vol. 2019, no. 1, Nov. 2019, Art. no. 248.
C.-S. Tu, C.-M. Hong, H.-S. Huang, and C.-H. Chen, "Short Term Wind Power Prediction Based on Data Regression and Enhanced Support Vector Machine," Energies, vol. 13, no. 23, Jan. 2020, Art. no. 6319.
Y.-D. Syu et al., "Ultra-Short-Term Wind Speed Forecasting for Wind Power Based on Gated Recurrent Unit," in 2020 8th International Electrical Engineering Congress (iEECON), Chiang Mai, Thailand, Mar. 2020.
R. Yu et al., "LSTM-EFG for wind power forecasting based on sequential correlation features," Future Generation Computer Systems, vol. 93, pp. 33–42, Apr. 2019.
Z. Niu, Z. Yu, W. Tang, Q. Wu, and M. Reformat, "Wind power forecasting using attention-based gated recurrent unit network," Energy, vol. 196, Apr. 2020, Art. no. 117081.
M. A. Saeed, Z. Ahmed, J. Yang, and W. Zhang, "An optimal approach of wind power assessment using Chebyshev metric for determining the Weibull distribution parameters," Sustainable Energy Technologies and Assessments, vol. 37, Feb. 2020, Art. no. 100612.
F. Pedregosa et al., "Scikit-learn: Machine Learning in Python," J. Mach. Learn. Res., vol. 12, no. null, pp. 2825–2830, Aug. 2011.
H. Zhou et al., "Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting," Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 12, pp. 11106–11115, May 2021.
S. Mo, H. Wang, B. Li, Z. Xue, S. Fan, and X. Liu, "Powerformer: A temporal-based transformer model for wind power forecasting," Energy Reports, vol. 11, pp. 736–744, Jun. 2024.
Y. Wang, R. Zou, F. Liu, L. Zhang, and Q. Liu, "A review of wind speed and wind power forecasting with deep neural networks," Applied Energy, vol. 304, Dec. 2021, Art. no. 117766.
M. R. Sarkar, S. G. Anavatti, T. Dam, M. Pratama, and B. A. Kindhi, "Enhancing Wind Power Forecast Precision via Multi-head Attention Transformer: An Investigation on Single-step and Multi-step Forecasting," in 2023 International Joint Conference on Neural Networks (IJCNN), Gold Coast, Australia, Jun. 2023.
A. Ghasemi and M. Hashemi, "Harnessing the Power of Transformer Learning with Long-Term Memory for Renewable Energy Forecasting," in 2023 IEEE Virtual Conference on Communications (VCC), NY, USA, Aug. 2023, pp. 171–176.
S. Huang, C. Yan, and Y. Qu, "Deep learning model-transformer based wind power forecasting approach," Frontiers in Energy Research, vol. 10, Jan. 2023.
M. Robith, R. S. Wibowo, and W. Wibowo, "Short-Term Wind Power Forecasting in East Java Using Gated Recurrent Unit: 3rd International Conference on Electronic and Electrical Engineering and Intelligent System, ICE3IS 2023," Proceedings - 2023 3rd International Conference on Electronic and Electrical Engineering and Intelligent System, pp. 58–63, 2023.
D. Sakubu and Q. Liu, "Microgrid Forecasting Using Multiple Deep learning Models," in 2021 IEEE 23rd Int Conf on High Performance Computing & Communications; 7th Int Conf on Data Science & Systems; 19th Int Conf on Smart City; 7th Int Conf on Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC/DSS/SmartCity/DependSys), Haikou, Hainan, China, Sep. 2021, pp. 1490–1497.
A. A. Ewees, M. A. A. Al-qaness, L. Abualigah, and M. A. Elaziz, "HBO-LSTM: Optimized long short term memory with heap-based optimizer for wind power forecasting," Energy Conversion and Management, vol. 268, Sep. 2022, Art. no. 116022.
A. Banik, C. Behera, Tirunagaru. V. Sarathkumar, and A. K. Goswami, "Uncertain wind power forecasting using LSTM-based prediction interval," IET Renewable Power Generation, vol. 14, no. 14, pp. 2657–2667, 2020.
Downloads
How to Cite
License
Copyright (c) 2025 Mohamed Bousla, Mohamed Belfkir, Omar Elharrouss, Ahmed Sadki, Ali Haddi, Youness El Mourabit, Badre Bossoufi, Abderrahman Mouradi, Abderrahman Elkharrim
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License 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) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
