Integrasi Citra Satelit dan Inverter Berbasis Transfer Learning untuk Prediksi PLTS Tropis
DOI:
https://doi.org/10.14421/jiska.6297Keywords:
Multimodal Deep Learning, Solar Forecasting, Himawari-9, CNN-LSTM, Transfer LearningAbstract
Integrating photovoltaic (PV) power plants into smart grids requires reliable short-term forecasting, particularly under highly variable tropical atmospheric conditions. Conventional univariate temporal models, such as LSTM, struggle to anticipate abrupt cloud cover changes as they rely solely on historical electrical data. This study proposes a hybrid multimodal CNN-LSTM framework integrating 16-channel Himawari-9 spatio-temporal satellite imagery and real-time inverter electrical parameters via cross-climate transfer learning and Solar Polar Image Normalization (SPIN). Multimodal alignment was achieved using linear temporal and bilinear spatial interpolations across 9,622 synchronized 5-minute samples from Universitas Pamulang, while a dedicated multimodal adapter enabled partial weight transfer from the Stanford SKIPP’D dataset. Experimental results demonstrate superior performance, achieving an MAE of 3,73 kW, RMSE of 5,61 kW, a Forecast Skill of +5,98%, and mitigating extreme Q95 error to 12,37 kW compared to persistence and univariate LSTM baselines. With a CPU inference latency of 15,58 ms per sample, this architecture provides high accuracy and computational efficiency for real-time tropical grid operations.
References
Alcañiz, A., Grzebyk, D., Ziar, H., & Isabella, O. (2023). Trends and Gaps in Photovoltaic Power Forecasting with Machine Learning. Energy Reports, 9, 447–471. https://doi.org/10.1016/j.egyr.2022.11.208
Al-Dahidi, S., Alahmer, H., Rinchi, B., Bani-Abdullah, A., Alrbai, M., Ayadi, O., & Al-Ghussain, L. (2025). Multistep PV Power Forecasting Using Deep Learning Models and the Reptile Search Algorithm. Results in Engineering, 27, Article ID: 106265. https://doi.org/10.1016/j.rineng.2025.106265
Alsafrani, A., Sherazi, H. I., Alrumayh, O., Habib, S., Alburidy, A. A., & Islam, M. (2025). Photovoltaic Power Forecasting for Sustainable Grid Integration: A Hybrid Deep Learning Approach. IEEE Access, 13, 216013–216025. https://doi.org/10.1109/ACCESS.2025.3640216
Badan Meteorologi Klimatologi dan Geofisika. (2025). Analisis Cuaca Ekstrem Wilayah Banten 3 Maret 2025. https://bbmkg2.bmkg.go.id/wp-content/uploads/2025/03/Analisis-Cuaca-Ekstrem-Wilayah-Banten-3-Maret-2025.pdf
Benni, N. S., Anil, B. C., Jayasimha, S. R., Girish, K., Vishal, C., & Khaiyum, S. (2026). A Lightweight Deep Learning Framework for Real-Time Predictive Analytics in Edge Computing Environments. SN Computer Science, 7(4), Article ID: 361. https://doi.org/10.1007/s42979-026-04948-z
Bramasto, S., & Khairiani, D. (2022). Prediksi Daya Output Sistem Pembangkit Listrik Tenaga Surya (PLTS) Menggunakan Regresi Linear Berganda. Faktor Exacta, 15(3), 139–150. https://doi.org/10.30998/faktorexacta.v15i2.13254
Buzzi, L. H., Weihmann, L., & Jaskowiak, P. (2024). Deep Learning and Satellite Images for Photovoltaic Power Forecasting: A Case Study. Anais Do XVI Congresso Brasileiro de Inteligência Computacional, 1–8. https://doi.org/10.21528/CBIC2023-120
Dinata, S., Ayob, A. F. M., Albani, A., Abdurahman, Huda, N., Kurniawan, R., & Rozak, O. A. (2024). Real-time Analysis of Inverter Performance via SCADA Haiwell Online Monitoring. Journal of Advanced Research in Applied Sciences and Engineering Technology, 37(1), 99–114. https://doi.org/10.37934/araset.37.1.99114
Elsaraiti, M., & Merabet, A. (2022). Solar Power Forecasting Using Deep Learning Techniques. IEEE Access, 10, 31692–31698. https://doi.org/10.1109/ACCESS.2022.3160484
Ferlito, S., Ippolito, S., Santagata, C., Schiattarella, P., & Di Francia, G. (2024). A Study on an IoT-Based SCADA System for Photovoltaic Utility Plants. Electronics, 13(11), Article ID: 2065. https://doi.org/10.3390/electronics13112065
He, K., Zhang, X., Ren, S., & Sun, J. (2015). Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. http://arxiv.org/abs/1502.01852
Husein, M., Gago, E. J., Hasan, B., & Pegalajar, M. C. (2024). Towards Energy Efficiency: A Comprehensive Review of Deep Learning-Based Photovoltaic Power Forecasting Strategies. Heliyon, 10(13), Article ID: e33419. https://doi.org/10.1016/j.heliyon.2024.e33419
Huva, R., Song, G., Zhong, X., & Zhao, Y. (2021). Comprehensive Physics Testing and Adaptive Weather Research and Forecasting Physics for Day‐Ahead Solar Forecasting. Meteorological Applications, 28(4), Article ID: e2017. https://doi.org/10.1002/met.2017
Kumar, A., Kashyap, Y., & Kosmopoulos, P. (2022). Enhancing Solar Energy Forecast Using Multi-Column Convolutional Neural Network and Multipoint Time Series Approach. Remote Sensing, 15(1), Article ID: 107. https://doi.org/10.3390/rs15010107
Liwijaya, A., Risma, P., Oktarina, Y., & Dewi, T. (2025). Implementasi Deep Learning dalam Prediksi Real-Time Iradian Surya. Journal of Applied Smart Electrical Network and Systems, 6(2), 90–96. https://doi.org/10.52158/pvdpsr36
Luo, X., & Zhang, D. (2023). A Cascaded Deep Learning Framework for Photovoltaic Power Forecasting with Multi-Fidelity Inputs. Energy, 268, Article ID: 126636. https://doi.org/10.1016/j.energy.2023.126636
Nadeem, A., Hanif, M. F., Naveed, M. S., Hassan, M. T., Gul, M., Husnain, N., & Mi, J. (2024). AI-Driven Precision in Solar Forecasting: Breakthroughs in Machine Learning and Deep Learning. AIMS Geosciences, 10(4), 684–734. https://doi.org/10.3934/geosci.2024035
Nie, Y., Li, X., Scott, A., Sun, Y., Venugopal, V., & Brandt, A. (2022). SKIPP’D: A SKy Images and Photovoltaic Power Generation Dataset for Short-term Solar Forecasting. http://arxiv.org/abs/2207.00913
Oktavia, P., Sutikno, T., & Murinto. (2026). Pemodelan Prediksi Global Horizontal Irradiance Berbasis Data Spasio-Temporal Citra Satelit Himawari Menggunakan Convolutional Neural Network dengan Transfer Learning. Journal of Information System and Computer, 6(1), 76–85. https://doi.org/10.34001/jister.v6i1.2067
Paletta, Q., Arbod, G., & Lasenby, J. (2023). Omnivision Forecasting: Combining Satellite and Sky Images for Improved Deterministic and Probabilistic Intra-Hour Solar Energy Predictions. Applied Energy, 336, Article ID: 120818. https://doi.org/10.1016/j.apenergy.2023.120818
Rezza, M., Ismail Yusuf, M., & Yacoub, R. R. (2024). Prediksi Radiasi Surya Menggunakan Metode Long Short-Term Memory. ILKOMNIKA: Journal of Computer Science and Applied Informatics, 6(1), 33–44. https://doi.org/10.28926/ilkomnika.v6i1.571
Schubnel, B., Simeunovic, J., Tissier, C., Alet, P.-J., & Carrillo, R. E. (2026). SolarCrossFormer: Improving Day-Ahead Solar Irradiance Forecasting by Integrating Satellite Imagery and Ground Sensors. IEEE Transactions on Sustainable Energy, 17(2), 1575–1587. https://doi.org/10.1109/TSTE.2025.3624044
Sekretariat Jenderal Dewan Energi Nasional. (2020). Grand Strategi Energi Nasional. https://den.go.id
Sharda, S., Singh, M., & Sharma, K. (2021). RSAM: Robust Self-Attention Based Multi-Horizon Model for Solar Irradiance Forecasting. IEEE Transactions on Sustainable Energy, 12(2), 1394–1405. https://doi.org/10.1109/TSTE.2020.3046098
Shukla, G., Shukla, A. K., Shukla, K. N., & Dixit, S. (2026). IoT-Enabled Solar PV Systems: Real-Time Monitoring and Efficiency Optimization. Results in Optics, 22, Article ID: 100949. https://doi.org/10.1016/j.rio.2025.100949
Sobri, S., Koohi-Kamali, S., & Rahim, N. Abd. (2018). Solar Photovoltaic Generation Forecasting Methods: A Review. Energy Conversion and Management, 156, 459–497. https://doi.org/10.1016/j.enconman.2017.11.019
Straub, N., Karalus, S., Herzberg, W., & Lorenz, E. (2024). Satellite‐Based Solar Irradiance Forecasting: Replacing Cloud Motion Vectors by Deep Learning. Solar RRL, 8(24), Article ID: 2400475. https://doi.org/10.1002/solr.202400475
Surathunmanun, S., Ongsakul, W., Singh, J. G., & Mehran, K. (2026). Short-Term Solar PV Forecasting in Microgrids Using Cloud Top Temperature and Vision Transformer Based Models. Frontiers in Energy Research, 13, Article ID: 1691881. https://doi.org/10.3389/fenrg.2025.1691881
Tahir, Z. ul R., Asim, M., Azhar, M., Moeenuddin, G., & Farooq, M. (2021). Correcting Solar Radiation from Reanalysis and Analysis Datasets with Systematic and Seasonal Variations. Case Studies in Thermal Engineering, 25, Article ID: 100933. https://doi.org/10.1016/j.csite.2021.100933
Wang, K., Shan, S., Dou, W., Wei, H., & Zhang, K. (2025). A Cross-Modal Deep Learning Method for Enhancing Photovoltaic Power Forecasting with Satellite Imagery and Time Series Data. Energy Conversion and Management, 323, Article ID: 119218. https://doi.org/10.1016/j.enconman.2024.119218
Wang, Y., Liao, W., & Chang, Y. (2018). Gated Recurrent Unit Network-Based Short-Term Photovoltaic Forecasting. Energies, 11(8), Article ID: 2163. https://doi.org/10.3390/en11082163
Xiao, Z., Gao, B., Huang, X., Chen, Z., Li, C., & Tai, Y. (2024). An Interpretable Horizontal Federated Deep Learning Approach to Improve Short-Term Solar Irradiance Forecasting. Journal of Cleaner Production, 436, Article ID: 140585. https://doi.org/10.1016/j.jclepro.2024.140585
Yin, W., Han, Y., Zhou, H., Ma, M., Li, L., & Zhu, H. (2020). A Novel Non-Iterative Correction Method for Short-Term Photovoltaic Power Forecasting. Renewable Energy, 159, 23–32. https://doi.org/10.1016/j.renene.2020.05.134
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Petricia Oktavia, Tole Sutikno, Murinto Murinto
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Authors who publish with this journal agree to the following terms as stated in http://creativecommons.org/licenses/by-nc/4.0
a. 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.
b. 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.
c. 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.
