Volume 11 • Issue 2 • PP: 55–73 • 2026
Intelligent Solar Radiation Forecasting Using Recurrent Deep Learning Models for Photovoltaic Energy Planning
View PDF Abstract
Accurate solar radiation forecasting is essential for improving the reliability of photovoltaic energy generation and supporting effective solar battery management, particularly because solar radiation is highly variable and depends on nonlinear interactions among meteorological and temporal factors. Although conventional prediction methods can provide useful estimates, they often struggle to capture the sequential behavior of solar radiation caused by daily sunlight cycles, atmospheric variation, and changing weather conditions. Therefore, this study aims to develop and evaluate deep learning models for predicting Solar_radiation using meteorological data collected from the HI-SEAS weather station over four months, from September to December 2016, where the main input variables include temperature, humidity, pressure, wind direction, wind speed, and time-related features. Five recurrent deep learning models were implemented and compared, namely Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Bidirectional Long Short Term Memory (BiLSTM), and Attention-LSTM. Before model training, the dataset was preprocessed by handling missing values, checking temporal consistency, arranging the observations chronologically, and applying Min–Max normalization to ensure stable learning. Model performance was assessed using multiple regression metrics, including MSE, RMSE, MAE, MBE, correlation coefficient, R2, RRMSE, NSE, and WI. The experimental results showed that BiLSTM achieved the best overall forecasting performance, with an MSE of 0.0014, RMSE of 0.0379, MAE of 0.0182, MBE of 0.0039, correlation coefficient of 0.9750, R2 of 0.9494, RRMSE of 0.3645, NSE of 0.9494, and WI of 0.9865. GRU and RNN also produced competitive results, achieving RMSE values of 0.0381 and 0.0382 and R2 values of 0.9489 and 0.9486, respectively, while Attention-LSTM showed comparatively lower performance with an RMSE of 0.0492 and R2 of 0.9149. These findings indicate that recurrent deep learning models are effective for learning nonlinear and temporal patterns in solar radiation data, with BiLSTM providing the most accurate and reliable predictions. The proposed forecasting framework can support photovoltaic energy planning and solar battery decision-making by estimating future solar radiation levels and helping determine whether solar energy utilization will be feasible under expected weather conditions.
Keywords
References
[1] D. R. Vora and K. Rajamani, “A hybrid classification model for prediction of academic performance of students: A big data application,” Evolutionary Intelligence, vol. 15, no. 2, pp. 1083–1096, 2022.
[2] J. C. Gamez-Granados, A. Esteban, F. J. Rodriguez- Lozano, and A. Zafra, “An algorithm based on fuzzy ordinal classification to predict students’ academic performance,” Applied Intelligence, vol. 53, no. 22, pp. 27 537–27 559, 2023.
[3] H. Pallathadka, A. Wenda, E. Ramirez-Asis, M. Asis- Lopez, J. Flores-Albornoz, and K. Phasinam, “Classification and prediction of student performance data using various machine learning algorithms,” Materials Today: Proceedings, vol. 80, pp. 3782–3785, 2023.
[4] K. Yurtkan, A. Adalier, and T. E. K. G. Umut, “Student success prediction using feedforward neural networks,” Romanian Journal of Information Science and Technology, vol. 2023, no. 2, pp. 121–136, 2023.
[5] I. H. Sarker, “Machine learning: Algorithms, real-world applications and research directions,” SN Computer Science, vol. 2, no. 3, p. 160, 2021.
[6] E.-S. M. El-Kenawy, S. Mirjalili, A. A. Abdelhamid, A. Ibrahim, N. Khodadadi, and M. M. Eid, “Metaheuristic optimization and keystroke dynamics for authentication of smartphone users,” Mathematics, vol. 10, no. 16, 2022.
[7] E.-S. El-Kenawy, A. Abdelhamid, A. Ibrahim, S. Mirjalili, N. Khodadad, A. Alhussan, and D. Khafaga, “Albiruni earth radius (ber) metaheuristic search optimiza- tion algorithm,” Computer Systems Science and Engineering, vol. 45, no. 2, pp. 1917–1934, 2022.
[8] Q. Al-Tashi, H. Md Rais, S. J. Abdulkadir, S. Mirjalili, and H. Alhussian, “A review of grey wolf optimizerbased feature selection methods for classification,” in Evolutionary Machine Learning Techniques. Springer, 2020, pp. 273–286.
[9] A. G. Gad, “Particle swarm optimization algorithm and its applications: A systematic review,” Archives of Computational Methods in Engineering, vol. 29, no. 5, pp. 2531–2561, 2022.
[10] E. A. Amreih, T. Hamtini, and I. Aljarah, “Student’s academic performance dataset (xapi-edu-data),” Kaggle, 2023.
[11] S. Guo, H. B. A. Halim, and M. R. B. M. Saad, “Leveraging ai-enabled mobile learning platforms to enhance the effectiveness of english teaching in universities,” Scientific Reports, vol. 15, no. 1, 2025.
[12] E. Hussein, M. A. Hussein, and M. Al-Hendawi, “Investigation into the applications of artificial intelligence in special education,” Social Sciences, vol. 14, no. 5, p. 288, 2025.
[13] J. T. K. Phua, H. F. Neo, and C.-C. Teo, “Evaluating the impact of artificial intelligence tools on enhancing student academic performance,” Big Data and Cognitive Computing, vol. 9, no. 5, p. 131, 2025.
[14] G. A. Anghel, C. M. Zanfir, F. L. Matei, C. D. Voicu, and R. A. Neacsa, “The integration of artificial intelligence in academic learning practices,” Education Sciences, vol. 15, no. 5, p. 616, 2025.
[15] H. Yaseen, A. S. Mohammad, N. Ashal, H. Abusaimeh, A. A. A. Ali, and A. A. Sharabati, “The impact of adaptive learning technologies and ai tools on student engagement,” Sustainability, vol. 17, no. 3, p. 1133, 2025.
[16] C. d. R. Navas-Bonilla, J. A. Guerra-Arango, D. A. Oviedo-Guado, and D. E. Murillo-Noriega, “Inclusive education through technology: A systematic review of types, tools and characteristics,” Frontiers in Education, vol. 10, 2025.
[17] W.Walters,W. Barber, and M. Jutras, “The consolidated framework for implementation research: Application to education,” Education Sciences, vol. 15, no. 5, p. 613, 2025.
[18] M. Yagci, “Educational data mining: Prediction of students’ academic performance using machine learning algorithms,” Smart Learning Environments, vol. 9, no. 1, p. 11, 2022.
[19] B. Cheng, Y. Liu, and Y. Jia, “Evaluation of students’ performance using xgboost classifier-enhanced aeo hybrid model,” Expert Systems with Applications, vol. 238, p. 122136, 2023.
[20] S. B. Keser and S. Aghalarova, “Hela: A novel hybrid ensemble learning algorithm for predicting academic performance,” Education and Information Technologies, vol. 27, no. 4, pp. 4521–4552, 2022.
[21] E. T. Lau, L. Sun, and Q. Yang, “Modelling, prediction and classification of student academic performance using neural networks,” SN Applied Sciences, vol. 1, no. 9, p. 982, 2019.
[22] B. K. Francis and S. S. Babu, “Predicting academic performance using a hybrid data mining approach,” Journal of Medical Systems, vol. 43, no. 6, p. 162, 2019.
[23] G. Deeva, J. De Smedt, C. Saint-Pierre, R. Weber, and J. De Weerdt, “Predicting student performance using sequence classification with time-based windows,” Expert Systems with Applications, vol. 209, p. 118182, 2022.
[24] P. Nayak, S. Vaheed, S. Gupta, and N. Mohan, “Predicting students’ academic performance using machine learning,” Education and Information Technologies, 2023.
[25] B. Yt and S. Rk, “Predictive modeling and analytics of students’ grades,” Education and Information Technologies, vol. 28, no. 3, 2023.
[26] A. Khan, S. K. Ghosh, D. Ghosh, and S. Chattopadhyay, “Random wheel: An algorithm for early classification of student performance,” Engineering Applications of Artificial Intelligence, vol. 102, p. 104270, 2021.
[27] M. Khosravi et al., “A comprehensive review of ai-based student performance prediction techniques,” Computers & Education: Artificial Intelligence, vol. 2, p. 100019, 2021.
[28] W. Dissanayake et al., “Bayesian hyperparameter optimization for predicting academic performance,” Applied Sciences, vol. 11, no. 7, p. 3194, 2021.
[29] A. A. Alhussan et al., “Classification of diabetes using hybrid ber and dto,” Diagnostics, vol. 13, no. 12, p. 2038, 2023.
[30] E.-S. M. El-Kenawy et al., “Optimizing potato disease classification using metaheuristics,” Potato Research, vol. 68, no. 1, pp. 551–585, 2025.
Cite This Article
Choose your preferred format