Deep Learning-Based Solar Energy Forecasting Under Climate Variability
DOI:
https://doi.org/10.33050/italic.v5i1.1094Keywords:
Long Short-Term Memory, Solar Energy Forecasting, Deep Learning, Climate Variability, Machine LearningAbstract
Rapid growth in renewable energy adoption and increasing climate variability have created significant challenges for accurately forecasting solar energy generation, as fluctuations in environmental conditions directly influence photovoltaic system performance and energy stability. This study aims to develop a deep learning based forecasting framework capable of improving solar energy prediction accuracy under changing climatic conditions by effectively capturing complex nonlinear relationships among meteorological variables and energy production patterns. The proposed approach utilizes historical solar irradiance, temperature, humidity, wind speed, cloud cover, and atmospheric pressure data as predictive inputs and employs a Long Short-Term Memory (LSTM) deep learning architecture to model temporal dependencies and environmental variability affecting solar energy generation. Experimental evaluation was conducted using publicly available renewable energy datasets, with model performance assessed through Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and the coefficient of determination (R²). The results demonstrate that the proposed deep learning framework achieved an RMSE of 4.12, an MAE of 3.08, a MAPE of 5.43%, and an R² value of 0.952, indicating strong predictive capability and high agreement between predicted and actual solar energy outputs. These findings suggest that deep learning models can effectively support intelligent renewable energy management by improving forecasting reliability under climate uncertainty, thereby contributing to energy efficiency, grid stability, and sustainable green technology development.
References
[1] S.-C. Lim, J.-H. Huh, S.-H. Hong, C.-Y. Park, and J.-C. Kim, “Solar power forecasting using cnn-lstm hybrid model,” Energies, vol. 15, no. 21, p. 8233, 2022.
[2] J. Qin, H. Jiang, N. Lu, L. Yao, and C. Zhou, “Enhancing solar pv output forecast by integrating ground and satellite observations with deep learning,” Renewable and Sustainable Energy Reviews, vol. 167, p. 112680, 2022.
[3] L. Cheng, H. Zang, Z. Wei, F. Zhang, and G. Sun, “Evaluation of opaque deep-learning solar power forecast models towards power-grid applications,” Renewable Energy, vol. 198, pp. 960–972, 2022.
[4] Y. Durachman, A. S. Bein, E. P. Harahap, T. Ramadhan, and F. P. Oganda, “Technological and islamic environments: Selection from literature review resources,” International Journal of Cyber and IT Service Management (IJCITSM), vol. 1, no. 1, pp. 37–47, 2021.
[5] X. Guo, Y. Mo, and K. Yan, “Short-term photovoltaic power forecasting based on historical information and deep learning methods,” Sensors, vol. 22, no. 24, p. 9630, 2022.
[6] A. Gupta, K. Gupta, and S. Saroha, “Short term solar irradiation forecasting using ceemdan decomposition based bilstm model optimized by genetic algorithm approach,” International Journal of Renewable Energy Development, vol. 11, no. 3, p. 736, 2022.
[7] T. Limouni, R. Yaagoubi, K. Bouziane, K. Guissi, and E. H. Baali, “Univariate and multivariate lstm models for one step and multistep pv power forecasting,” International Journal of Renewable Energy Development, vol. 11, no. 3, p. 815, 2022.
[8] S. Soleymani and S. Mohammadzadeh, “Comparative analysis of machine learning algorithms for solar irradiance forecasting in smart grids,” arXiv preprint arXiv:2310.13791, 2023.
[9] F. M. Wuaten, “The role of sustainable finance and technology at bank bjb in supporting the” sustainable development goals”,” Aptisi Transactions on Technopreneurship (ATT), vol. 5, no. 1Sp, pp. 97–108, 2023.
[10] F. Li, “Chord-based music generation using long short-term memory neural networks in the context of artificial intelligence: F. li,” The Journal of Supercomputing, vol. 80, no. 5, pp. 6068–6092, 2024.
[11] A. R. Singh, R. S. Kumar, M. Bajaj, C. B. Khadse, and I. Zaitsev, “Machine learning-based energy management and power forecasting in grid-connected microgrids with multiple distributed energy sources,” Scientific Reports, vol. 14, no. 1, p. 19207, 2024.
[12] K. Sarkar, “Load and renewable energy forecasting using deep learning for grid stability,” arXiv preprint arXiv:2501.13412, 2025.
[13] L. S. Sua, H. Wang, and J. Huang, “Deep learning in renewable energy forecasting: A cross-dataset evaluation of temporal and spatial models,” Energy & Environment, p. 0958305X251367102, 2025.
[14] Q. Aini, A. Faturahman, H. Agustian, F. J. Aritonang, and H. Zainarthur, “Analysis of inorganic waste classification orange box based on tensorflow lite using raspberry pi 5,” ADI Journal on Recent Innovation (AJRI), vol. 7, no. 2, pp. 185–196, 2026.
[15] G. Guthi, P. K. Didde, Z. Shaik, S. M. Y. Vangala, and M. Kurni, “Deep learning-based solar energy forecasting using environmental time-series data,” in 2025 2nd International Conference on Recent Trends in Electrical, Electronics and Computing Technologies (ICRTEECT). IEEE, 2025, pp. 1–5.
[16] U. Mamodiya, I. Kishor, P. Ganguly, I. Mukherjee, and N. Naik, “A machine learning approach to assess the climate change impacts on single and dual-axis tracking photovoltaic systems,” Scientific Reports, vol. 15, no. 1, p. 24910, 2025.
[17] C. Nichols, M. Hill, X. Liu, and L. Kiboma, “Climate change impacts on solar energy generation in the continental united states, forecasts from deep learning,” Environmental Modelling & Software, vol. 192, p. 106535, 2025.
[18] F. Rodr´ıguez, I. Azc´arate, J. Vadillo, and A. Galarza, “Forecasting intra-hour solar photovoltaic energy by assembling wavelet based time-frequency analysis with deep learning neural networks,” International Journal of Electrical Power & Energy Systems, vol. 137, p. 107777, 2022.
[19] U. Rahardja, N. P. L. Santoso, F. P. Oganda, M. Madani, and M. S. T. Saputra, “Digital innovation in smart waste sorting using renewable energy for sustainable startups,” Startupreneur Business Digital (SABDA Journal), vol. 5, no. 1, pp. 42–54, 2026.
[20] R. Yang, “Deep-learning-powered probabilistic net-load forecasting with enhanced behind-the-meter pv visibility,” National Renewable Energy Laboratory, Golden, CO, USA, Solar Energy Technologies Office Project, 2022, [Online]. Available: https://www.energy.gov/cmei/systems/2022-seto- peer-review-systems-integration-projects. [Online]. Available: https://www.energy.gov/cmei/systems/ 2022-seto-peer-review-systems-integration-projects
[21] C. Idogho, E. O. Abah, J. O. Onuhc, C. Harsito, K. Omenkaf, A. Samuel, A. Ejila, I. P. Idoko, and U. E. Ali, “Machine learning-based solar photovoltaic power forecasting for nigerian regions,” Energy Science & Engineering, vol. 13, no. 4, pp. 1922–1934, 2025.
[22] F. Zulqarnain and Z. Hasan, “Artificial intelligence applications for predicting renewable-energy demand under climate variability,” American Journal of Scholarly Research and Innovation, vol. 3, no. 01, pp. 84–116, 2024.
[23] B. N. S. Reddy, K. Gautam, and N. Pachauri, “Solar potential assessment using machine learning and climate change projections for long-term energy planning,” Scientific Reports, vol. 15, no. 1, p. 39935, 2025.
[24] Z. Zaharuddin, S. Wahyuningsih, A. Sutarman, and I. N. Hikam, “Understanding purposeful leadership in entrepreneurial contexts: A bibliometric analysis,” Aptisi Transactions on Technopreneurship (ATT), vol. 6, no. 2, pp. 213–230, 2024.
[25] N. E. Benti, M. D. Chaka, and A. G. Semie, “Forecasting renewable energy generation with machine learning and deep learning: Current advances and future prospects,” Sustainability, vol. 15, no. 9, p. 7087, 2023.
[26] M. Shafiullah, A. R. Katranji, M. Hassan, M. M. Rahman, and S. A. Shezan, “Advanced multivariate deep learning methodology for forecasting wind speed and solar irradiation,” Smart Cities, vol. 9, no. 4, p. 59, 2026.
[27] K. Ukoba, O. R. Onisuru, and T.-C. Jen, “Harnessing machine learning for sustainable futures: advancements in renewable energy and climate change mitigation,” Bulletin of the National Research Centre, vol. 48, no. 1, p. 99, 2024.
[28] S. S. Punyam Rajendran and A. Gebremedhin, “Deep learning-based solar power forecasting model to analyze a multi-energy microgrid energy system,” Frontiers in Energy Research, vol. 12, p. 1363895, 2024.
[29] U. Rahardja, Q. Aini, D. Manongga, I. Sembiring, and Y. Sanjaya, “Enhancing machine learning with lowcost p m2. 5 air quality sensor calibration using image processing,” APTISI Transactions on Management, vol. 7, no. 3, pp. 201–209, 2023.
[30] A. R. V. Babu, N. B. Kumar, R. P. Narasipuram, S. Periyannan, A. Hosseinpour, and A. Flah, “Solar energy forecasting using machine learning techniques for enhanced grid stability,” IEEE Access, vol. 13, pp. 93 735–93 754, 2025.
[31] S. Khan, T. Mazhar, M. A. Khan, T. Shahzad, W. Ahmad, A. Bibi, M. M. Saeed, and H. Hamam, “Comparative analysis of deep neural network architectures for renewable energy forecasting: enhancing accuracy with meteorological and time-based features,” Discover Sustainability, vol. 5, no. 1, p. 533, 2024.
[32] P. Kumari and D. Toshniwal, “Extreme gradient boosting and deep neural network based ensemble learning approach to forecast hourly solar irradiance,” Journal of Cleaner Production, vol. 279, p. 123285, 2021.
[33] A. Awachat, A. Dube, and S. Chaudhri, “Ml for sustainable solutions: Applications in renewable energy optimization and climate change prediction,” in 2025 4th International Conference on Sentiment Analysis and Deep Learning (ICSADL). IEEE, 2025, pp. 1689–1694.
[34] A. Faturahman, N. S. Lubis, N. P. L. Santoso, A. Adiwijaya, M. Madisson et al., “Impact of blockchain enhanced digital marketing on brand awareness of solar panels,” Blockchain Frontier Technology, vol. 5, no. 1, pp. 1–12, 2025.
[35] H. A. Alif, “Temperature-based solar energy forecasting: a big data analysis for sustainable energy planning in ishwardi and rajshahi region of bangladesh,” Theoretical and Applied Climatology, vol. 156, no. 10, p. 526, 2025.
[36] M. A. Raza, A. Karim, M. Altayeb, M. I. Masud, M. Faheem, T. A. Jumani, and M. Aman, “Global solar energy potential forecasting through machine learning and deep learning models,” Scientific Reports, vol. 16, no. 1, p. 10466, 2026.
[37] I. Rojek, D. Mikołajewski, M. Andryszczyk, T. Bednarek, and K. Tyburek, “Leveraging machine learning in next-generation climate change adaptation efforts by increasing renewable energy integration and efficiency,” Energies, vol. 18, no. 13, p. 3315, 2025.
[38] P. Ramu and S. Gangatharan, “An ensemble machine learning-based solar power prediction of meteorological variability conditions to improve accuracy in forecasting,” Journal of the Chinese Institute of Engineers, vol. 46, no. 7, pp. 737–753, 2023.
[39] T. Rajasundrapandiyanleebanon, K. Kumaresan, S. Murugan, M. Subathra, and M. Sivakumar, “Solar energy forecasting using machine learning and deep learning techniques,” Archives of Computational Methods in Engineering, vol. 30, no. 5, pp. 3059–3079, 2023.
[40] F. Gerges, M. C. Boufadel, E. Bou-Zeid, H. Nassif, and J. T. Wang, “Long-term prediction of daily solar irradiance using bayesian deep learning and climate simulation data,” Knowledge and Information Systems, vol. 66, no. 1, pp. 613–633, 2024.
[41] A. A. M. Davidescu, M. A. Petcu, S. C. Curea, E. M. Manta, and D. Popa, “The economic impact of the innovative forecast of solar energy production based on machine learning and neural network models,” Energy Strategy Reviews, vol. 66, p. 102282, 2026.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Untung Rahardja, Nolan Liam, Sri Watini
This work is licensed under a Creative Commons Attribution 4.0 International License.
