Renewable Energy Forecasting using Machine Learning Techniques and Comparative Analysis
Nayeemuddin MOHAMMED, Hiren MEWADA, Tasneem SULTANA, Tabassum Nahid SULTANA
Abstract. Efficient grid management, scheduling, and increased clean energy system reliability depend on accurate electricity generation forecasting. Several machine learning methods, including Decision Tree, Random Forest, Gradient Boosting, AdaBoost, Bagging, CatBoost, ExtraBoost, and XGBoost, were employed in this study to forecast energy production. The results were compared methodically. Standard error metrics, such as mean absolute error (MAE), mean squared error (MSE), and root mean squared error (RMSE), were used to evaluate the model on both the training and test datasets. Although all chosen models use a decision tree as the base, their performance varies with the decision tree model. The CatBoost and Bagging demonstrated greater generalization than the other models. CatBoost achieved the highest R2 of 0.8690 and the lowest RMSE of 0.0167 on the test dataset. The performance of Bagging, Random Forest, and Gradient Boosting is nearly similar. In contrast, the XGBoost and Decision Tree performed well on the training dataset. However, for unseen data, their predictions are far from the actual values, with a high MSE and a lower R2 score on the test dataset. Overall, an ensemble approach of decision trees provided better performance at the cost of computation compared to XGBoost.
Keywords
Forecasting, Renewable Energy, Machine Learning, Photovoltaic, Sustainability
Published online 4/25/2026, 7 pages
Copyright © 2026 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA
Citation: Nayeemuddin MOHAMMED, Hiren MEWADA, Tasneem SULTANA, Tabassum Nahid SULTANA, Renewable Energy Forecasting using Machine Learning Techniques and Comparative Analysis, Materials Research Proceedings, Vol. 64, pp 2-8, 2026
DOI: https://doi.org/10.21741/9781644904091-1
The article was published as article 1 of the book Energy Futures
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
References
[1] K. K. Jaiswal et al., “Renewable and sustainable clean energy development and impact on social, economic, and environmental health,” Energy Nexus, vol. 7, p. 100118, Sep. 2022. https://doi.org/10.1016/j.nexus.2022.100118
[2] Q. Hassan, S. Algburi, A. Z. Sameen, H. M. Salman, and M. Jaszczur, “A review of hybrid renewable energy systems: Solar and wind-powered solutions: Challenges, opportunities, and policy implications,” Results in Engineering, vol. 20, p. 101621, Dec. 2023. https://doi.org/10.1016/j.rineng.2023.101621
[3] S. Muhammad Salman Bukhari et al., “Federated transfer learning with orchard-optimized Conv-SGRU: A novel approach to secure and accurate photovoltaic power forecasting,” Renewable Energy Focus, vol. 48, p. 100520, Mar. 2024. https://doi.org/10.1016/j.ref.2023.100520
[4] M. Khalid, “Smart grids and renewable energy systems: Perspectives and grid integration challenges,” Energy Strategy Reviews, vol. 51, p. 101299, Jan. 2024. https://doi.org/10.1016/j.esr.2024.101299
[5] M. A. Khasawneh et al., “Renewable energy in pavement engineering and its integration with sustainable materials: A review paper,” in Materials Research Proceedings, Aug. 2024, pp. 377–384. https://doi.org/10.21741/9781644903216-49
[6] Z. Zhang, F.-Q. Xuan, X.-X. Ruan, and L.-Z. Li, “Hybrid model with temporal convolutional network and transformer encoder for privacy-preserving wind power forecasting,” Adv. Manuf., Apr. 2025. https://doi.org/10.1007/s40436-025-00552-1
[7] V. I. Kontopoulou, A. D. Panagopoulos, I. Kakkos, and G. K. Matsopoulos, “A Review of ARIMA vs. Machine Learning Approaches for Time Series Forecasting in Data Driven Networks,” Future Internet, vol. 15, no. 8, p. 255, Jul. 2023. https://doi.org/10.3390/fi15080255
[8] A. Talukdar, B. Panda, S. Hota, M. Maharana, N. Mohammed, and S. Panda, Intelligent Solar Power Forecast with Machine Learning. 2024. https://doi.org/10.1109/ISAECT64333.2024.10799562
[9] A. Rizwan et al., “Enhancing energy consumption prediction in smart homes: a convergence-aware federated transfer learning approach,” Sci. Tech. Energ. Transition, vol. 79, p. 85, 2024. https://doi.org/10.2516/stet/2024060
[10] E. Sarmas, N. Dimitropoulos, V. Marinakis, Z. Mylona, and H. Doukas, “Transfer learning strategies for solar power forecasting under data scarcity,” Sci Rep, vol. 12, no. 1, p. 14643, Aug. 2022. https://doi.org/10.1038/s41598-022-18516-x
[11] G. Tong, X. Qian, and Y. Liu, “Prognostics and Predictive Maintenance Optimization Based on Combination BP-RBF-GRNN Neural Network Model and Proportional Hazard Model,” Journal of Sensors, vol. 2022, no. 1, p. 8655669, 2022. https://doi.org/10.1155/2022/8655669
[12] I. Price et al., “Probabilistic weather forecasting with machine learning,” Nature, vol. 637, no. 8044, pp. 84–90, Jan. 2025. https://doi.org/10.1038/s41586-024-08252-9
[13] H. Kim, S. Dorjgochoo, H. Park, and S. Lee, “Personalized Federated Transfer Learning for Building Energy Forecasting via Model Ensemble with Multi-Level Masking in Heterogeneous Sensing Environment,” Electronics, vol. 14, no. 9, p. 1790, Jan. 2025. https://doi.org/10.3390/electronics14091790
[14] M. Mansoor, G. Tao, A. F. Mirza, B. Yousaf, M. Irfan, and W. Chen, “FTLNet: federated deep learning model for multi-horizon wind power forecasting,” Discov Internet Things, vol. 5, no. 1, p. 21, Mar. 2025. https://doi.org/10.1007/s43926-025-00112-w
[15] L. Zhang, S. Zhu, S. Su, X. Chen, Y. Yang, and B. Zhou, “Wind power prediction method based on cloud computing and data privacy protection,” J Cloud Comp, vol. 13, no. 1, p. 137, Sep. 2024. https://doi.org/10.1186/s13677-024-00679-9
[16] “https://www.kaggle.com/datasets/itsrohithere/renewable-energy-forecasting.” accessed on Dec 2025.
[17] F. Alzahrani, “Application of artificial intelligence (AI) in wind energy system with a case study,” presented at the Renewable Energy: Generation and Application, Aug. 2024, pp. 96–103. https://doi.org/10.21741/9781644903216-13
