Comparison of Machine Learning and Deep Learning Models Performance in predicting wind energy
DOI:
https://doi.org/10.4108/ew.7114Keywords:
Wind Energy Prediction, Machine Learning, Time Series Forecasting, Evaluation Metrics, Cross-Validation , Renewable EnergyAbstract
The prediction of wind energy generation is important to enhance the performance and dependability of renewable energy systems due to the rising demand for wind-generated electricity and advancements in wind energy technology competitiveness. This study leverages advanced machine learning (ML) and some other statistical and deep learning based time series forecasting models to enhance the accuracy of wind energy predictions. This comprehensive analysis includes nine ML models—Linear Regression, Random Forests (RF), Gradient Boosting Machines (GBM), Support Vector Machines (SVM), K-Nearest Neighbors (KNN), AdaBoost, XGBoost, Support Vector Regression (SVR), and Neural Networks—as well as Four time-series forecasting models—ARIMA, Temporal Convolutional Networks (TCNs), Long Short-Term Memory (LSTM) networks and GRU. Each ML model underwent rigorous cross-validation to ensure optimal performance. The assessment criteria utilized here comprised the Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and the R² Score. It was found that among the nine ML models, Random Forests, GBM and KNN consistently provided superior accuracy and robustness, making them the top choices for wind energy prediction whereas the performance of linear regression, SVM and SVR were very poor for the considered dataset. From the experiment, Random Forest, GBM, and KNN showed the best performance with low MSE values of 0.77, 1.95, and 1.51 respectively, while other models had MSEs above 7.5, with AdaBoost reaching 30. Their RMSEs (0.88, 1.40, 1.23) and MAEs (0.093, 0.73, 0.10) also indicate strong predictive accuracy compared to the rest.In this paper, time series forecasting, TCNs, LSTM and GRU networks showed strong capabilities in capturing temporal dependencies and trends within the wind energy data. Visualization techniques were employed to compare model performances comprehensively, providing clear insights into their predictive power. Therefore, this present study offers a robust framework for researchers and practitioners aiming to leverage machine learning and time series forecasting in the realm of renewable energy prediction.
Downloads
References
[1] Sengupta AR, Biswas A, Gupta R. Studies of some high solidity symmetrical and unsymmetrical blade H-Darrieus rotors with respect to starting characteristics, dynamic performances and flow physics in low wind streams. Renewable Energy. 2016 Aug 1;93:536-47.
[2] Global Wind Energy Council. Global Wind Report 2024. Brussels: Available from: https://gwec.net/wpcontent/uploads/2024/04/GWR-2024_digital-version_final-1.pdf (accessed on 16/07/2024)
[3] Sengupta AR, Biswas A, Gupta R. Comparison of low wind speed aerodynamics of unsymmetrical blade H-Darrieus rotors-blade camber and curvature signatures for performance improvement. Renewable Energy. 2019 Aug 1;139:1412-27.
[4] Sengupta AR, Biswas A, Gupta R. The aerodynamics of high solidity unsymmetrical and symmetrical blade H-Darrieus rotors in low wind speed conditions. Journal of Renewable and Sustainable Energy. 2017 Jul 1;9(4).
[5] Sengupta AR, Biswas A, Gupta R. Aerodynamic analysis of cambered blade H-Darrieus rotor in low wind velocity using CFD. Wind & structures. 2021 Jan;33(6):471-80.
[6] Sengupta AR, Biswas A, Gupta R, Srinagar N. Vertical axis wind turbines in the built environment: A review. ISESCO journal of science and technology. 2016;12:11-6.
[7] Wang H, Ruan J, Wang G, Zhou B, Liu Y, Fu X, Peng J. Deep learning-based interval state estimation of AC smart grids against sparse cyber attacks. IEEE Transactions on Industrial Informatics. 2018 Feb 9;14(11):4766-78.
[8] Pillot B, Muselli M, Poggi P, Dias JB. Historical trends in global energy policy and renewable power system issues in Sub-Saharan Africa: The case of solar PV. Energy policy. 2019 Apr 1;127:113-24.
[9] Zhao Y, Ye L, Li Z, Song X, Lang Y, Su J. A novel bidirectional mechanism based on time series model for wind power forecasting. Applied energy. 2016 Sep 1;177:793-803.
[10] Sengupta AR, Biswas A, Gupta R. A statistical analysis of Wind energy potential of Agartala (Tripura, India) based on different models-a case study. International Journal of Advanced Information Science and Technology. 2015;4(12):94-101.
[11] Sengupta AR, Biswas A, Gupta R. An Analysis of Wind Energy Potential of Silchar (Assam, India) By using different models. IJEMS. 2016;7(2):100-7.
[12] Ayua TJ, Emetere ME. Technical analysis of wind energy potentials using a modified Weibull and Raleigh distribution model parameters approach in the Gambia. Heliyon. 2023 Sep 1;9(9).
[13] Ayua TJ, Emetere ME. Technical and economic simulation of a hybrid renewable energy power system design for industrial application. Scientific Reports. 2024 Nov 20;14(1):28739.
[14] Hodge BM, Martinez-Anido CB, Wang Q, Chartan E, Florita A, Kiviluoma J. The combined value of wind and solar power forecasting improvements and electricity storage. Applied Energy. 2018 Mar 15;214:1-5.
[15] Daut MA, Hassan MY, Abdullah H, Rahman HA, Abdullah MP, Hussin F. Building electrical energy consumption forecasting analysis using conventional and artificial intelligence methods: A review. Renewable and Sustainable Energy Reviews. 2017 Apr 1;70:1108-18.
[16] Wang H, Lei Z, Zhang X, Zhou B, Peng J. A review of deep learning for renewable energy forecasting. Energy Conversion and Management. 2019 Oct 15;198:111799.
[17] Li LL, Zhao X, Tseng ML, Tan RR. Short-term wind power forecasting based on support vector machine with improved dragonfly algorithm. Journal of Cleaner Production. 2020 Jan 1;242:118447.
[18] Manero J, Béjar J, Cortés U. Wind energy forecasting with neural networks: A literature review. Computación y Sistemas. 2018 Dec;22(4):1085-98.
[19] Sideratos G, Hatziargyriou ND. An advanced statistical method for wind power forecasting. IEEE Transactions on power systems. 2007 Jan 29;22(1):258-65.
[20] Zhang W, Wang J, Wang J, Zhao Z, Tian M. Short-term wind speed forecasting based on a hybrid model. Applied Soft Computing. 2013 Jul 1;13(7):3225-33.
[21] Deng X, Shao H, Hu C, Jiang D, Jiang Y. Wind power forecasting methods based on deep learning: A survey. Computer Modeling in Engineering & Sciences. 2020 Jan 15;122(1):273-302.
[22] Wang X, Guo P, Huang X. A review of wind power forecasting models. Energy procedia. 2011 Jan 1;12:770-8.
[23] Bali V, Kumar A, Gangwar S. Deep learning based wind speed forecasting-A review. In2019 9th international conference on cloud computing, data science & engineering (confluence) 2019 Jan 10 (pp. 426-431). IEEE.
[24] Wang Y, Zou R, Liu F, Zhang L, Liu Q. A review of wind speed and wind power forecasting with deep neural networks. Applied energy. 2021 Dec 15;304:117766.
[25] Lin B, Zhang C. A novel hybrid machine learning model for short-term wind speed prediction in inner Mongolia, China. Renewable Energy. 2021 Dec 1;179:1565-77.
[26] Colak I, Sagiroglu S, Yesilbudak M. Data mining and wind power prediction: A literature review. Renewable energy. 2012 Oct 1;46:241-7.
[27] Zafirakis D, Tzanes G, Kaldellis JK. Forecasting of wind power generation with the use of artificial neural networks and support vector regression models. Energy Procedia. 2019 Feb 1;159:509-14.
[28] Wang H, Li Y, Xiong M, Chen H. A combined wind speed prediction model based on data processing, multi-objective optimization and machine learning. Energy Reports. 2023 Sep 1;9:413-21.
[29] Ye XW, Ding Y, Wan HP. Machine learning approaches for wind speed forecasting using long-term monitoring data: a comparative study. Smart Structures and Systems. 2019 Jan;24(6):733-44.
[30] Daniel LO, Sigauke C, Chibaya C, Mbuvha R. Short-term wind speed forecasting using statistical and machine learning methods. Algorithms. 2020 May 26;13(6):132.
[31] Zhu R, Liao W, Wang Y. Short-term prediction for wind power based on temporal convolutional network. Energy Reports. 2020 Dec 1;6:424-9.
[32] Lin WH, Wang P, Chao KM, Lin HC, Yang ZY, Lai YH. Wind power forecasting with deep learning networks: Time-series forecasting. Applied Sciences. 2021 Nov 3;11(21):10335.
[33] Gong M, Yan C, Xu W, Zhao Z, Li W, Liu Y, Li S. Short-term wind power forecasting model based on temporal convolutional network and Informer. Energy. 2023 Nov 15;283:129171.
[34] Longxiang X. Wind Power Prediction based on LSTM neural network. Xiangtan University. 2023.
[35] Gupta D, Kumar V, Ayus I, Vasudevan M, Natarajan N. Short-Term Prediction of Wind Power Density Using [1] Sengupta AR, Biswas A, Gupta R. Studies of some high solidity symmetrical and unsymmetrical blade H-Darrieus rotors with respect to starting characteristics, dynamic performances and flow physics in low wind streams. Renewable Energy. 2016 Aug 1;93:536-47.
[36] Shahid F, Zameer A, Muneeb M. A novel genetic LSTM model for wind power forecast. Energy. 2021 May 15;223:120069.
[37] Ma Z, Guo S, Xu G, Aziz S. Meta learning-based hybrid ensemble approach for short-term wind speed forecasting. IEEE Access. 2020 Sep 22;8:172859-68.
[38] Peña-Gallardo R, Medina-Rios A. A comparison of deep learning methods for wind speed forecasting. In2020 IEEE International Autumn Meeting on Power, Electronics and Computing (ROPEC) 2020 Nov 4 (Vol. 4, pp. 1-6). IEEE.
[39] Pearre NS, Swan LG. Statistical approach for improved wind speed forecasting for wind power production. Sustainable Energy Technologies and Assessments. 2018 Jun 1;27:180-91.
[40] Jursa R, Rohrig K. Short-term wind power forecasting using evolutionary algorithms for the automated specification of artificial intelligence models. International Journal of Forecasting. 2008 Oct 1;24(4):694-709.
[41] Yatiyana E, Rajakaruna S, Ghosh A. Wind speed and direction forecasting for wind power generation using ARIMA model. In2017 Australasian universities power engineering conference (AUPEC) 2017 Nov 19 (pp. 1-6). IEEE.
[42] https://www.kaggle.com/datasets/fedesoriano/wind-speed-prediction-dataset?resource=download (accessed on 5/7/2024)
[43] https://mesonet.agron.iastate.edu/ (accessed on 05/05/2025)
[44] Ayua TJ, Uto OT, Fatty LK. An investigation of solar energy potential towards improving agriculture using angstrom and newly developed analytical models: in case of the Gambia. Scientific African. 2023 Sep 1;21:e01886.
[45] Tyovenda AA, Ayua TJ, Sombo T. Modeling of gaseous pollutants (CO and NO2) emission from an industrial stack in Kano city, northwestern Nigeria. Atmospheric Environment. 2021 May 15;253:118356.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Saswati Rakshit, Anal Ranjan Sengupta

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open-access article distributed under the terms of the Creative Commons Attribution CC BY 4.0 license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.