Electrical Power Prediction of Polycrystalline Solar Panels based on LSTM Model with environmental influence
Abstract
Solar energy is one of the most promising renewable energy sources that can support the sustainable energy transition. However, the electrical power produced by photovoltaic (PV) panels is greatly influenced by environmental conditions such as irradiation, temperature, humidity, and wind speed, making them volatile and difficult to predict. This study aims to develop a prediction model based on Long Short-Term Memory (LSTM) to estimate the power output of polycrystalline panels. Environmental data is collected in real-time, processed through the normalization stage, and then used as input in several model variants, namely pure LSTM, CNN-LSTM, LSTM-Autoencoder, and GWO-LSTM with metaheuristic optimization. Evaluation was conducted using R², RMSE, and MAPE metrics. The results showed that the pure LSTM model provided good accuracy (R² = 0.95; MAPE = 6.2%), while CNN-LSTM and LSTM-AE improved performance with R² reaching 0.97 and 0.96, respectively. The best model is GWO-LSTM, with R² = 0.98, RMSE = 0.31 kW, and MAPE = 4.3%. These findings prove that metaheuristic optimization in LSTM can increase the reliability of PV power prediction and support a more efficient energy management system.
References
[1] G. H. Park and J. C. Kim, “Multivariate Variable-Based LSTM-AE Model for Solar Power Prediction,” Int. J. Adv. Sci. Eng. Inf. Technol., vol. 15, no. 1, pp. 293–299, 2025, doi: 10.18517/ijaseit.15.1.20944.
[2] H. S. F. Ali and N. K. Çerçevik, “Optimizing Renewable Energy Utilization: A Study on Solar Radiation Forecasting with LSTM-Conv1D Models in Libya,” in 2024 8th International Symposium on Innovative Approaches in Smart Technologies (ISAS), IEEE, Dec. 2024, pp. 1–8. doi: 10.1109/ISAS64331.2024.10845245.
[3] R. Al-Hajj, A. Assi, M. Fouad, and E. Mabrouk, “A hybrid lstm-based genetic programming approach for short-term prediction of global solar radiation using weather data,” Processes, vol. 9, no. 7, 2021, doi: 10.3390/pr9071187.
[4] Y. Jin, H. Guo, J. Wang, and A. Song, “A hybrid system based on LSTM for short-term power load forecasting,” Energies, vol. 13, no. 23, 2020, doi: 10.3390/en13236241.
[5] D. K. Dhaked, S. Dadhich, and D. Birla, “Power output forecasting of solar photovoltaic plant using LSTM,” Green Energy Intell. Transp., vol. 2, no. 5, p. 100113, 2023, doi: 10.1016/j.geits.2023.100113.
[6] Y. Li, W. Huang, K. Lou, X. Zhang, and Q. Wan, “Short-term PV power prediction based on meteorological similarity days and SSA-BiLSTM,” Syst. Soft Comput., vol. 6, no. December 2023, p. 200084, 2024, doi: 10.1016/j.sasc.2024.200084.
[7] N. L. M. Jailani et al., “Investigating the Power of LSTM-Based Models in Solar Energy Forecasting,” Processes, vol. 11, no. 5, 2023, doi: 10.3390/pr11051382.
[8] K. C. Jayasankar, G. Anandhakumar, and A. Kalaimurugan, “Prediction of Solar Radiation using Deep LSTM-based Machine Learning Algorithm,” J. Environ. Nanotechnol., vol. 13, no. 3, pp. 01–08, 2024, doi: 10.13074/jent.2024.09.242585.
[9] J. Wang, Z. Zhang, W. Xu, Y. Li, and G. Niu, “Short-Term Photovoltaic Power Forecasting Using a Bi-LSTM Neural Network Optimized by Hybrid Algorithms,” Sustain., vol. 17, no. 12, pp. 1–22, 2025, doi: 10.3390/su17125277.
[10] S. Gong, W. Chen, X. Jing, and C. Wang, “Research on Photovoltaic Power Prediction Method based on LSTM-KAN,” in 2024 6th International Conference on Electronic Engineering and Informatics (EEI), IEEE, Jun. 2024, pp. 479–482. doi: 10.1109/EEI63073.2024.10696287.
[11] Y. Tang, K. Yang, S. Zhang, and Z. Zhang, “Photovoltaic power forecasting: A hybrid deep learning model incorporating transfer learning strategy,” Renew. Sustain. Energy Rev., vol. 162, no. January, p. 112473, 2022, doi: 10.1016/j.rser.2022.112473.
[12] M. Elsaraiti and A. Merabet, “Solar Power Forecasting Using Deep Learning Techniques,” IEEE Access, vol. 10, pp. 31692–31698, 2022, doi: 10.1109/ACCESS.2022.3160484.
[13] T. Sana Amreen, R. Panigrahi, and N. R. Patne, “Solar Power Forecasting Using Hybrid Model,” 5th Int. Conf. Energy, Power, Environ. Towar. Flex. Green Energy Technol. ICEPE 2023, 2023, doi: 10.1109/ICEPE57949.2023.10201483.
[14] Mr. Muthu Selvam S, Mr. Dhevin Ananda Raj A S, and Mr. Manivannan R, “Optimized LSTM Model for Day-Ahead Solar Power Prediction,” Int. Res. J. Adv. Eng. Hub, vol. 3, no. 03, pp. 662–669, 2025, doi: 10.47392/irjaeh.2025.0092.
[15] K. Ijaz, Z. Hussain, J. Ahmad, S. F. Ali, M. Adnan, and I. Khosa, “A Novel Temporal Feature Selection Based LSTM Model for Electrical Short-Term Load Forecasting,” IEEE Access, vol. 10, no. June, pp. 82596–82613, 2022, doi: 10.1109/ACCESS.2022.3196476.
[16] A. Ahsan, A. Zafar, M. A. Afzal, M. Javed, D. Zafar, and M. Ali, “Improved Solar Power Prediction Using CNN-LSTM Models for Optimized Smart Grid Performance,” J. Eng. Sci. Technol. Trends, vol. 1, no. 2, 2024, doi: 10.48112/jestt.v1i2c.5.
[17] R. Wang, X. Liu, Y. Chang, D. Liu, and H. Yao, “Short-Term Photovoltaic System Output Power Prediction Based on Integrated Deep Learning Algorithms in the Clean Energy Sector,” Int. J. e-Collaboration, vol. 20, no. 1, pp. 1–15, 2024, doi: 10.4018/IJeC.346979.
[18] R. M. Rizk-Allah, L. M. Abouelmagd, A. Darwish, V. Snasel, and A. E. Hassanien, Explainable AI and optimized solar power generation forecasting model based on environmental conditions, vol. 19, no. 10. 2024. doi: 10.1371/journal.pone.0308002.
[19] H. Alharkan, S. Habib, and M. Islam, “Solar Power Prediction Using Dual Stream CNN-LSTM Architecture,” Sensors, vol. 23, no. 2, pp. 1–12, 2023, doi: 10.3390/s23020945.
[20] M. Mokarram, J. Aghaei, M. J. Mokarram, G. P. Mendes, and B. Mohammadi-Ivatloo, “Geographic information system-based prediction of solar power plant production using deep neural networks,” IET Renew. Power Gener., vol. 17, no. 10, pp. 2663–2678, 2023, doi: 10.1049/rpg2.12781.
[21] S. YALÇIN and M. S. HERDEM, “Prediction and Analysis of Weather Parameters with Global Horizontal Solar Irradiance Using LSTM-CNN Based Deep Learning Technique,” Bilecik Şeyh Edebali Üniversitesi Fen Bilim. Derg., vol. 9, no. 1, pp. 340–356, 2022, doi: 10.35193/bseufbd.1037563.
[22] H. Alkahtani, T. H. H. Aldhyani, and S. N. Alsubari, “Application of Artificial Intelligence Model Solar Radiation Prediction for Renewable Energy Systems,” Sustain., vol. 15, no. 8, 2023, doi: 10.3390/su15086973.
[23] N. Zhou, B. Shang, M. Xu, L. Peng, and G. Feng, “Enhancing photovoltaic power prediction using a CNN-LSTM-attention hybrid model with Bayesian hyperparameter optimization,” Glob. Energy Interconnect., vol. 7, no. 5, pp. 667–681, 2024, doi: 10.1016/j.gloei.2024.10.005.
[24] Z. Xu, K. Xiang, B. Wang, and X. Li, “Study on PV Power Prediction Based on VMD-IGWO-LSTM,” Distrib. Gener. Altern. Energy J., vol. 39, no. 3, pp. 507–530, 2024, doi: 10.13052/dgaej2156-3306.3936.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Alfin Sahrin, Erna Utami, Nur Shoffiana, Imam Abadi
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
