LSTM-Based Daily Power Forecasting for a 1 MWp PV System in Tropical Indonesia: Toward Operational Optimization
DOI:
https://doi.org/10.55981/jet.777Keywords:
Photovoltaic Power Forecasting, LSTM Neural Network, Tropical Climate, Utility-Scale PV, Real-Time Prediction, Smart Grid Integration, Data-Driven ModelingAbstract
Variations in solar irradiance and module temperature significantly affect the performance and operational efficiency of large-scale photovoltaic (PV) power systems, especially in tropical regions. This study investigates the application of a Long Short-Term Memory (LSTM) network for accurate real-time power prediction in a 1 MWp PV power plant at Institut Teknologi Sumatera (ITERA), Indonesia. Unlike traditional approaches and conventional artificial neural networks (ANN), LSTM networks can effectively capture long-term temporal dependencies and highly nonlinear patterns in PV output data. A five-minute resolution dataset, including actual power output, solar irradiance, and module temperature, was collected throughout March 2025 for model training, with validation performed using independent data from April. The developed LSTM model achieved a mean absolute error (MAE) of 42.8 kW (approximately 4–6% of maximum plant capacity) and a coefficient of determination (R²) of 0.84 during active hours (05:00–19:00) on the validation dataset. These findings indicate that the model performs well not only on the training data, but also maintains strong generalization to unfamiliar data. The proposed approach enables reliable real-time power prediction, supporting applications such as energy forecasting, inverter control, dispatch planning, and anomaly detection in PV systems. This work provides a practical and scalable solution for improving the adaptability and integration of solar power plants in dynamic tropical environments, contributing to the advancement of AI-driven sustainable energy systems.
Downloads
References
[1] International Energy Agency, “Renewables 2024: Analysis and forecast to 2030,” Paris, 2024. Accessed: Jun. 05, 2025. [Online]. Available: https://www.iea.org/reports/renewables-2024
[2] PT PLN (Persero), “Rencana Usaha Penyediaan Tenaga Listrik (RUPTL) PT PLN (Persero) 2021–2030,” 2021. Accessed: Jun. 05, 2025. [Online]. Available: https://jdih.esdm.go.id/common/dokumen-external/RUPTL%20PLN%202021%20-%202030.pdf
[3] K. Hayawi, H. Maliakkal, N. Venugopal, T. M. Hussain, and G. B. Rajagopalan, “Machine learning - driven solar forecasting in dust-prone regions for sustainable energy systems,” Sol. Energy Adv., vol 5, pp. 1-13, May 2025, Art. no. 100108, doi: 10.1016/j.seja.2025.100108.
[4] S. Huang, J. Zhang, Z. Lyu, and X. Bai, “Research on data-driven combined network reconfiguration and local control with smart inverter for voltage regulation problem,” Energy Rep., vol. 13, pp. 2000–2012, Jun. 2025, doi: 10.1016/j.egyr.2025.01.051.
[5] Y. Zhou, “Artificial intelligence in renewable systems for transformation towards intelligent buildings,” Energy AI, vol. 10, Nov. 2022, Art. no. 100182, doi: 10.1016/j.egyai.2022.100182.
[6] O. A. Balogun, Y. Sun, and P. A. Gbadega, “Optimal PV active power curtailment in a PV-penetrated distribution network using optimal smart inverter Volt-Watt control settings,” Energy Rep., vol. 12, pp. 5396–5419, Dec. 2024, doi: 10.1016/j.egyr.2024.11.014.
[7] S. Kanata, S. Baqaruzi, A. Muhtar, P. Prasetyawan, and T. Wina-ta, “Optimal planning of hybrid renewable energy system using HOMER in Sebesi Island, Indonesia,” Int. J. Renewable Energy Res., vol. 11, no. 4, 2021, pp. 1507–1516. [Online]. Available: https://www.ijrer.org/index.php/ijrer/article/view/12296
[8] N. L. M. Jailani et al., “Investigating the power of LSTM-based models in solar energy forecasting,” Processes, vol. 11, no. 5, May 2023, Art. no. 1382, doi: 10.3390/pr11051382.
[9] V. Demir and H. Citakoglu, “Forecasting of solar radiation using different machine learning approaches,” Neural Comput. Appl., vol. 35, no. 1, pp. 887–906, Jan. 2023, doi: 10.1007/s00521-022-07841-x.
[10] A. Muhtar, I. W. Mustika, and Suharyanto, “The comparison of ANN-BP and ANN-PSO as learning algorithm to track MPP in PVSystem,” in Proc. 7th Int. Ann. Eng. Sem. (InAES 2017), 2017, pp. 1–6, doi: 10.1109/INAES.2017.8068573.
[11] Y. Wang, W. Liao, and Y. Chang, “Gated recurrent unit net-work-based short-term photovoltaic forecasting,” Energies (Ba-sel), vol. 11, no. 8, Aug. 2018, Art. no. 2163, doi: 10.3390/en11082163.
[12] A. A. Aziz, E. C. Diamal, and R. Ilyas, “Paraphrase detection using Manhattan’s recurrent neural networks and long short-term memory,” in Proc. 2019 6th Int. Conf. Elect. Eng. Comput. Sci. Inform. (EECSI), Sep. 2019, pp. 432–437. doi: 10.23919/EECSI48112.2019.8976951.
[13] S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Comput., vol. 9, no. 8, pp. 1735–1780, Nov. 1997, doi: 10.1162/neco.1997.9.8.1735.
[14] B. N. Nguyen, E. Ogliari, E. Pafumi, D. Alberti, S. Leva, and M. Q. Duong, “Forecasting generating power of sun tracking PV plant using long-short term memory neural network model: A case study in Ninh Thuan - Vietnam,” in Proc. 2024 10th Int. Conf. Commun. Electron. (ICCE), Jul. 2024, pp. 333–338. doi: 10.1109/ICCE62051.2024.10634629.
[15] M. Golam, R. Akter, J.-M. Lee, and D.-S. Kim, “A long short-term memory-based solar irradiance prediction scheme using meteorological data,” IEEE Geosci. Remote Sens. Lett., vol. 19, 2022, Art. no. 1003705, doi: 10.1109/LGRS.2021.3107139.
[16] M. Ehteram, M. Afshari Nia, F. Panahi, and A. Farrokhi, “Read-First LSTM model: A new variant of long short term memory neural network for predicting solar radiation data,” Energy Convers. Manag., vol. 305, Apr. 2024, Art. no. 118267 doi: 10.1016/j.enconman.2024.118267.
[17] M. S. Ibrahim, S. M. Gharghory, and H. A. Kamal, “A hybrid model of CNN and LSTM autoencoder-based short-term PV power generation forecasting,” Elect. Eng., vol. 106, no. 4, pp. 4239–4255, Aug. 2024, doi: 10.1007/s00202-023-02220-8.
[18] M. Sabri and M. El Hassouni, “Photovoltaic power forecasting with a long short-term memory autoencoder networks,” Soft Comput, vol. 27, no. 15, pp. 10533–10553, Aug. 2023, doi: 10.1007/s00500-023-08497-y.
[19] Y. Yu, G. Hu, C. Liu, J. Xiong, and Z. Wu, “Prediction of solar irradiance one hour ahead based on quantum long short-term memory network,” IEEE Trans. Quantum Eng., vol. 4, 2023, Art. no. 3100815, doi: 10.1109/TQE.2023.3271362.
[20] J. Ma et al., “A comparative study of photovoltaic power prediction model with different inputs by long short-term memory network,” in Proc 2023 Int. Conf. on Power Syst. Technol. (PowerCon), Sep. 2023, pp. 1–5. doi: 10.1109/PowerCon58120.2023.10331443.
[21] Z. Wang, Z. Li, Y. Liu, and H. Ma, “Wind and PV power ramp events prediction based on long short-term memory network,” in Proc. 2023 IEEE Sustainable Power Energy Con. (iSPEC), Nov. 2023, pp. 1–5. doi: 10.1109/iSPEC58282.2023.10402807.
[22] Y. Liu, Q. Zhang, R. Li, H. Hui, L. Fan, and J. Wu, “PV power probability density prediction based on the long short-term memory network with quantile regression,” in Proc. 2023 IEEE 18th Conf. Ind. Electron. Appl. (ICIEA), IEEE, Aug. 2023, pp. 800–804. doi: 10.1109/ICIEA58696.2023.10241566.
[23] J. Xu, Z. Wang, X. Li, Z. Li, and Z. Li, “Prediction of daily climate using long short-term memory (LSTM) model,” Int. J. Innov. Sci. Res. Technol., vol. 9, no.7, pp. 83–90, Jul. 2024, doi: 10.38124/ijisrt/IJISRT24JUL073.
[24] Y. Fan, Z. Ma, W. Tang, J. Liang, and P. Xu, “Using crested porcupine optimizer algorithm and CNN-LSTM-attention model combined with deep learning methods to enhance short-term power forecasting in PV generation,” Energies (Basel), vol. 17, no. 14, Jul. 2024, Art. no. 3435, doi: 10.3390/en17143435.
[25] 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,” Int. J. Renewable Energy Develop., vol. 11, no. 3, pp. 815–828, Aug. 2022, doi: 10.14710/ijred.2022.43953.
[26] W. Wang, W. Shi, D. Nan, Y. Peng, Q. Wang, and Y. Zhu, “New energy output prediction and demand response optimization based on LSTM-BN,” Int. J. Renewable Energy Develop., vol. 14, no. 1, pp. 72–82, Jan. 2025, doi: 10.61435/ijred.2025.60632.
[27] H. T. C. Pedro and C. F. M. Coimbra, “Assessment of forecasting techniques for solar power production with no exogenous inputs,” Sol. Energy, vol. 86, no. 7, pp. 2017–2028, Jul. 2012, doi: 10.1016/j.solener.2012.04.004.
[28] C. Voyant et al., “Machine learning methods for solar radiation forecasting: A review,” Renew. Energy, vol. 105, pp. 569–582, May 2017, doi: 10.1016/j.renene.2016.12.095.
[29] J. Antonanzas, N. Osorio, R. Escobar, R. Urraca, F. J. Martinez-de-Pison, and F. Antonanzas-Torres, “Review of photovoltaic power forecasting,” Sol. Energy, vol. 136, pp. 78–111, Oct. 2016, doi: 10.1016/j.solener.2016.06.069.
[30] J. Shi, W.-J. Lee, Y. Liu, Y. Yang, and P. Wang, “Forecasting power output of photovoltaic system based on weather classification and support vector machine,” in Proc. 2011 IEEE Ind. Appl. Soc. Ann. Meeting, Oct. 2011, pp. 1–6. doi: 10.1109/IAS.2011.6074294.
[31] H.-T. Yang, C.-M. Huang, Y.-C. Huang, and Y.-S. Pai, “A weather-based hybrid method for 1-day ahead hourly forecasting of PV power output,” IEEE Trans. Sustain Energy, vol. 5, no. 3, pp. 917–926, Jul. 2014, doi: 10.1109/TSTE.2014.2313600.
[32] M. S. Bhutta et al., “Optimizing solar power efficiency in smart grids using hybrid machine learning models for accurate energy generation prediction,” Sci. Rep., vol. 14, no. 1, Dec. 2024, Art. no. 17101, doi: 10.1038/s41598-024-68030-5.
[33] X. Zi, F. Liu, M. Liu, and Y. Wang, “A deep learning method for photovoltaic power generation forecasting based on a time-series dense encoder,” Energies (Basel), vol. 18, no. 10, May 2025, Art. no. 2434, doi: 10.3390/en18102434.
[34] W. Khan, S. Walker, and W. Zeiler, “Improved solar photovol-taic energy generation forecast using deep learning-based en-semble stacking approach,” Energy, vol. 240, Feb. 2022, Art. no. 122812, doi: 10.1016/j.energy.2021.122812.
[35] A. M. Almarzooqi, M. Maalouf, T. H. M. El-Fouly, V. E. Katzourakis, M. S. El Moursi, and C. V Chrysikopoulos, “A hybrid machine-learning model for solar irradiance forecasting,” Clean Energy, vol. 8, no. 1, pp. 100–110, Feb. 2024, doi: 10.1093/ce/zkad075.
[36] W. Castillo-Rojas, F. M. Quispe, and C. Hernández, “Photovoltaic energy forecast using weather data through a hybrid model of recurrent and shallow neural networks,” Energies (Basel), vol. 16, no. 13, Jul. 2023, Art. no. 5093, doi: 10.3390/en16135093.
[37] C. Lyu and S. Eftekharnejad, “Probabilistic solar generation forecasting for rapidly changing weather conditions,” IEEE Ac-cess, vol. 12, pp. 79091–79103, 2024, doi: 10.1109/ACCESS.2024.3407778.
[38] R. A. Rajagukguk, R. A. A. Ramadhan, and H.-J. Lee, “A review on deep learning models for forecasting time series data of solar irradiance and photovoltaic power,” Energies (Basel), vol. 13, no. 24, Dec. 2020, Art. no. 6623, doi: 10.3390/en13246623.
[39] J. Arefin, A. Aziz, and S. Akhter, “AI-based energy forecasting for smart grids with renewable integration,” J. Comp. Sci. Technol. Stud., vol. 7, no. 4, pp. 461–480, May 2025, doi: 10.32996/jcsts.2025.7.4.55.
[40] Y. Jouane, M. C. Sow, O. Oussous, N. Vontobel, and M. Zghal, “Forecasting photovoltaic energy for a winter house using a hybrid deep learning model,” in Proc. 2023 12th Int. Conf. Renewable Energy Res. Appl. (ICRERA), Aug. 2023, pp. 1–5. doi: 10.1109/ICRERA59003.2023.10269444.
[41] G. Moreno, P. Martin, C. Santos, F. J. Rodriguez, and E. Santi-so, “A day-ahead irradiance forecasting strategy for the integra-tion of photovoltaic systems in virtual power plants,” IEEE Ac-cess, vol. 8, pp. 204226–204240, 2020, doi: 10.1109/ACCESS.2020.3036140.
[42] M. Houchati, A. H. Beitelmal, and M. Khraisheh, “Predictive modeling for rooftop solar energy throughput: a machine learn-ing-based optimization for building energy demand schedul-ing,” J. Energy Resource Technol., vol. 144, no. 1, Jan. 2022, Art. no. 011302, doi: 10.1115/1.4050844.
[43] G. Moreno, C. Santos, P. Martín, F. J. Rodríguez, R. Peña, and B. Vuksanovic, “Intra-day solar power forecasting strategy for managing virtual power plants,” Sensors, vol. 21, no. 16, Aug. 2021, Art. no. 5648, doi: 10.3390/s21165648.
[44] M. Thangavelu, V. J. Parthiban, D. Kesavaraman, and T. Murugesan, “Forecasting of solar radiation for a cleaner environment using robust machine learning techniques,” Environ. Sci. Pollut. Res., vol. 30, no. 11, pp. 30919–30932, Nov. 2022, doi: 10.1007/s11356-022-24321-w.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 National Research and Innovation Agency
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
The copyright to this article is transferred to BRIN if and when the article is accepted for publication. The undersigned hereby transfers any and all rights in and to the paper including without limitation all copyrights to BRIN. The undersigned hereby represents and warrants that the paper is original and that he/she is the author of the paper, except for material that is clearly identified as to its original source, with permission notices from the copyright owners where required. The undersigned represents that he/she has the power and authority to make and execute this assignment. The copyright transfer form can be downloaded here.
The corresponding author signs for and accepts responsibility for releasing this material on behalf of any and all co-authors. This agreement is to be signed by at least one of the authors who have obtained the assent of the co-author(s) where applicable. After submission of this agreement signed by the corresponding author, changes of authorship or in the order of the authors listed will not be accepted.
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
