WIND SPEED PREDICTION IN MICROGRID ENERGY MANAGEMENT USING THE RANDOM FOREST AND ARTIFICIAL NEURAL NETWORKS METHODS

Year 2025, Volume: 11 Issue: 2, 276 - 289, 30.12.2025

Ahmet Nur , Bayram Güre , Sabir Rüstemli , Özlem Bezek Güre

https://doi.org/10.51477/mejs.1738993

https://izlik.org/JA28KB32GU

Abstract

Although wind energy, which is frequently utilized in microgrid systems, has relatively high initial investment costs compared to conventional energy generation systems, the low operation and maintenance costs of wind turbines make it an economically attractive alternative. However, the highly variable nature of wind speed depending on time and geography complicates the predictability of energy output, introducing uncertainties in investment decisions. Therefore, accurate short-term wind speed forecasting is critically important for reliable estimation of potential production, system design, and performance-cost analysis. In this study, the Random Forest (RF) and Artificial Neural Networks (ANN) machine learning algorithms were employed for short-term wind speed prediction. The study examines the parameters that affect the efficiency of wind systems. The dataset used in the analysis was obtained from a SCADA system associated with a wind measurement station located in Türkiye, with measurements recorded at 10-minute intervals and made available via the Kaggle platform. The dataset was partitioned into 70% for training and 30% for testing. To enhance the generalizability of the model, 10-fold cross-validation was applied. Performance evaluation of the model was conducted using metrics including MSE, RMSE, MAE, MAPE and the R². The results show that the Random Forest method provides higher prediction accuracy in wind speed estimation compared to Artificial Neural Network methods. The obtained values also confirm the suitability of this Random Forest method for short-term forecasting applications.

Keywords

Microgrid , Wind Speed , Short-Term Forecasting , Random Forest

Ethical Statement

The authors declare that this document does not require ethics committee approval or any special permission. Our study does not cause any harm to the environment and does not involve the use of animal or human subjects.

References

• E. Alegria, T. Brown, E. Minear, and R. H. Lasseter, “CERTS Microgrid Demonstration with Large-Scale Energy Storage and Renewable Generation”, IEEE Transactions on Smart Grid, 5(2), 937–943, 2013.
• A. Hirsch, Y. Parag, and J. Guerrero, “Microgrids: A Review of Technologies, Key Drivers, and Outstanding Issues”, Renewable and Sustainable Energy Reviews, 90, 402–411, 2018.
• M. Ramesh and A. K. Yadav, "Wind Contributed Load Frequency Control Scheme for Standalone Microgrid Using Grey Wolf Optimization", IEEE Delhi Section Conference, New Delhi, India, 2022.
• S. Mallikarjunaswamy, N. Sharmila, D. Maheshkumar, M. Komala, and H. N. Mahendra, “Implementation of an Effective Hybrid Model for Islanded Microgrid Energy Management”, Indian J. Sci. Technol., 13(27), 2733–2746, 2020.
• M. A. Mohandes, T. O. Halawani, S. Rehman, and A. A. Hussain, “Support Vector Machines for Wind Speed Prediction”, Renew. Energy, 29(6), 939–947, 2004.
• S. Rüstemli, O. Güntas, G. Sahin, A. Koç, W. van Sark, and S. 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 Rev., 56, 101552, 2024.
• H. Lund, “The Kyoto Mechanisms and Technological Innovation”, Energy, 31(13), 2325–2332, 2006.
• Y. Wang, X. Zhao, Z. Li, W. Zhu, and R. Gui, “A Novel Hybrid Model for Multi-Step-Ahead Forecasting of Wind Speed Based on Univariate Data Feature Enhancement”, Energy, 312, 1–19, 2024.
• M. N. Almalı, S. Rüstemli, and K. Gürçam, “Ortalama Rüzgâr Hızı ve Güç Yoğunluğunun Tahmin Edilmesinde Kullanılan Farklı Yöntemler”, J. Inst. Sci. Technol., 3(1), 73–78, 2014.
• T. Çelebioğlu, M. Tayanç, and H. Oruç, “Determination of Temperature Variabilities and Trends in Turkey”, UUJFE, 26(3), 1003–1020, 2021.
• Z. Ilkılıç, “Wind Energy and Development of Wind Energy Systems in Turkey”, Batman Univ. J. Life Sci., 6(2/2), 1–13, 2016.
• C. F. Chien and L. F. Chen, “Data Mining to Improve Personnel Selection and Enhance Human Capital: A Case Study in High-Technology Industry”, Expert Syst. Appl., 34, 280–290, 2018.
• S. Akhtar et al., “Short-Term Load Forecasting Models: A Review of Challenges, Progress, and the Road Ahead”, Energies, 16, 4060, 2023.
• L. Breiman, “Random Forests”, Mach. Learn., 45, 5–32, 2001.
• Ö. B. Güre, H. Şevgin, and M. Kayri, “Reviewing the Factors Affecting PISA Reading Skills by Using Random Forest and MARS Methods”, Int. J. Contemp. Educ. Res., 10(1), 181–196, 2023.
• L. Jinhua, Z. Desen, and L. Chunxiang, “Comparative Analysis of BPNN, SVR, LSTM, Random Forest, and LSTM-SVR for Conditional Simulation of Non-Gaussian Measured Fluctuating Wind Pressures”, Mech. Syst. Signal Process., 178, 109285, 2022.
• M. J. Somers and J. C. Casal, “Using Artificial Neural Networks to Model Nonlinearity: The Case of the Job Satisfaction—Job Performance Relationship”, Organizational Research Methods, 12(3), 403–417, 2009.
• P. P. G. Hernandez and M. Rosales, "Short-Term Forecasting Solar Power Generation with Artificial Neural Network and CNN-LSTM," 2025 6th International Conference on Big Data Analytics and Practices (IBDAP), Chiang Mai, Thailand, 2025.
• Ö. Künteş and Ö. B. Güre, “Yapay Sinir Ağı Kullanılarak Petrol Sektöründe Yaşanan İş Kazalarının İncelenmesi”, Journal of the Institute of Science and Technology, 14(3), 1000–1012, 2024.
• M. Kayri, “An Intelligent Approach to Educational Data: Performance Comparison of the Multilayer Perceptron and the Radial Basis Function Artificial Neural Networks”, Educational Sciences: Theory & Practice, 15(5), 1247–1255, 2015.
• K. A. Jyotsna and G. Vishal, "Design of Analog Microelectronic Artificial Neural Network in 90nm CMOS Technology," 2025 7th International Conference on Intelligent Sustainable Systems (ICISS), India, 2025, pp. 226–230.
• R. Nisbet, J. Elder, and G. Miner, Handbook of Statistical Analysis and Data Mining Applications, Elsevier Inc., 2009.
• Ö. B. Güre, “Classification of Students' Dropout Status Using the Random Forest Method”, Int. J. Eurasia Soc. Sci., 15(57), 1401–1411, 2024.
• G. H. Riahy and M. Abedi, “Short-Term Wind Speed Forecasting for Wind Turbine Applications Using Linear Prediction Method”, Renew. Energy, 33(1), 35–41, 2008.
• H. L. Chang and C. S. Chiu, “Hour-Ahead Wind Power and Speed Forecasting Using Simultaneous Perturbation Stochastic Approximation (SPSA) Algorithm and Neural Network with Fuzzy Inputs”, Energy, 35(9), 3870–3876, 2010.
• A. Kusiak and Z. Zhang, “Short-Horizon Prediction of Wind Power: A Data-Driven Approach”, IEEE Trans. Energy Convers., 25(4), 1112–1122, 2010.
• H. Liu, J. Shi, and E. Erdem, “Prediction of Wind Speed Time Series Using Modified Taylor Kriging Method”, Energy, 35(12), 4870–4879, 2010.
• H. Bouzgou and N. Benoudjit, “Multiple Architecture System for Wind Speed Prediction”, Appl. Energy, 88(7), 2463–2471, 2011.
• M. A. Yassen, E. S. M. El-kenawy, M. G. Abdel-Fattah, I. Ismael, and H. E. D. Salah Mostafa, “Machine Learning Models with Statistical Analysis Techniques for Forecasting Wind Turbines SCADA Systems Measurement”, Fusion: Practice & Applications, 19(2), 2024.
• F. M. A. Mazen, Y. Shaker, and R. A. Abul Seoud, “A Two‐Stage Model for Outlier Detection and Power Prediction of Wind Turbine Using SCADA Dataset”, International Journal of Energy Research, 2025(1), 2527561, 2025.
• T. A. Rajaperumal and C. Christopher Columbus, “Enhanced Wind Power Forecasting Using Machine Learning, Deep Learning Models and Ensemble Integration”, Scientific Reports, 15(1), 20572, 2025.
• C. Emexidis and P. Gkonis, “The Integration of Internet of Things and Machine Learning for Energy Prediction of Wind Turbines”, Applied Sciences, 14(22), 10276, 2024.
• R. K. Reja et al., “A New ANN Technique for Short-Term Wind Speed Prediction Based on SCADA System Data in Turkey”, Atmosphere, 14(10), 1516, 2023.
• S. M. Malakouti, “Prediction of Wind Speed and Power with LightGBM and Grid Search: Case Study Based on SCADA System in Turkey”, Int. J. Energy Prod. Manage., 8(1), 35–40, 2023.
• H. K. Gharehbagh, A. Safari, K. Zare, and A. A. Ghavifekr, “A Hybrid CNN-LSTM Approach Utilizing SCADA Data Enhancing Wind Power Predictions: A Dataset Case Study of Turkey”, Proc. 9th Int. Conf. Technol. Energy Management, 1–5, 2024.
• D. Gupta, N. Natarajan, and M. Berlin, “Short-Term Wind Speed Prediction Using Hybrid Machine Learning Techniques”, Environ. Sci. Pollut. Res., 29(34), 909–927, 2022.
• E. Cadenas and W. Rivera, “Wind Speed Forecasting in Three Different Regions of Mexico, Using a Hybrid ARIMA–ANN Model”, Renew. Energy, 35(12), 2732–2738, 2010.
• D. Liu, D. Niu, H. Wang, and L. Fan, “Short-Term Wind Speed Forecasting Using Wavelet Transform and Support Vector Machines Optimized by Genetic Algorithm”, Renew. Energy, 62, 592–597, 2014.
• S. Hur, “Short-Term Wind Speed Prediction Using Extended Kalman Filter and Machine Learning”, Energy Rep., 7, 1046–1054, 2021.
• S. Samadianfard et al., “Wind Speed Prediction Using a Hybrid Model of the Multi-Layer Perceptron and Whale Optimisation Algorithm”, Energy Rep., 6, 1147–1159, 2020.
• P. S. Kumar, “Improved Prediction of Wind Speed Using Machine Learning”, EAI Endorsed Trans. Energy Web, 6(23), 2019.