Evaluasi Model Bi-Lstm Dan Bi-Gru dalam Memprediksi Direct Normal Irradiance Sebagai Verifikasi Pyrheliometer CHP1

Roy Handoko; Sudarno Wiharjo; Yan Mitha Djaksana

doi:10.30998/jrami.v7i04.1742

Authors

Roy Handoko Universitas Pamulang Author
Sudarno Wiharjo Universitas Pamulang Author
Yan Mitha Djaksana Universitas Pamulang Author

DOI:

https://doi.org/10.30998/jrami.v7i04.1742

Keywords:

pyrheliometer, kalibrasi, Bi-LSTM, Bi-GRU, verifikasi

Abstract

Direct Normal Irradiance (DNI) plays an important role in global climate observation and the optimization of solar photovoltaic systems. Pyrheliometer calibration commonly refers to ISO 9059 by comparing an operational instrument with a reference standard. This study develops a Deep Learning-based virtual verification instrument to reconstruct the output of a CHP1 pyrheliometer while capturing nonlinear relationships between thermopile sensor response and meteorological dynamics. Two bidirectional architectures, Bidirectional Long Short-Term Memory (Bi-LSTM) and Bidirectional Gated Recurrent Unit (Bi-GRU), were trained using multivariate irradiance and meteorological data obtained from a calibration campaign in Kupang City during September 2025. Model performance was evaluated using the coefficient of determination, RMSE, and MAPE. The results show that bidirectional architectures achieved stronger performance than their unidirectional counterparts. Bi-GRU delivered the best performance, with a coefficient of determination of 0.986, an RMSE of 1.153 W/m², and a MAPE of 0.096%, while Bi-LSTM achieved a coefficient of determination of 0.885 and a MAPE of 0.309%. These findings demonstrate the potential of Bi-GRU as an adaptive virtual verification model for pyrheliometer response reconstruction. Further development may focus on validation across different periods, locations, weather conditions, and instruments.

Downloads

Download data is not yet available.

References

Adrian, B. (2024). Rancang Bangun Sistem Monitoring Intensitas Radiasi Matahari Menggunakan Sensor Pyranometer di Gedung DTNTF UGM.

Afif, F., & Martin, A. (2022). Tinjauan Potensi dan Kebijakan Energi Surya di Indonesia. 6(1), 43–52.

Arifin, R., & Hyunjin, L. (2023). Enhancing the Performance of Solar Radiation Decomposition Models Using Deep Learning. Journal of the Korean Solar Energy Society, 43(3), 73–86. https://doi.org/10.7836/kses.2023.43.3.073

Asad, D. M., Shahriar, M., & Chowdhury, A. H. (2025). Load Forecasting for Dhaka City Using RNN, LSTM, and GRU Architectures with Meteorological and Temporal Data. 2025 International Conference on Electrical, Computer and Communication Engineering (ECCE), 1–6. https://doi.org/10.1109/ECCE64574.2025.11013779

Azouzoute, A., Merrouni, A. A., Bennouna, E. G., & Gennioui, A. (2019). Accuracy measurement of pyranometer vs reference cell for PV resource assessment. Energy Procedia, 157, 1202–1209. https://doi.org/10.1016/j.egypro.2018.11.286

Balenzategui, J. L., Molero, M., Silva, J. P., Fabero, F., Cuenca, J., Mejuto, E., & De Lucas, J. (2022). Uncertainty in the Calibration Transfer of Solar Irradiance Scale: From Absolute Cavity Radiometers to Standard Pyrheliometers. Solar, 2(2), 158–185. https://doi.org/10.3390/solar2020010

Cobos, F., Valenzuela, R. X., Ramírez, L., Zarzalejo, L. F., Nouri, B., Wilbert, S., & García, G. (2018). Assessment of the impact of meteorological conditions on pyrheliometer calibration. Solar Energy, 168, 44–59. https://doi.org/10.1016/j.solener.2018.03.046

Jaihuni, M., Basak, J. K., Khan, F., Okyere, F. G., Sihalath, T., Bhujel, A., Park, J., Lee, D. H., & Kim, H. T. (2022). A novel recurrent neural network approach in forecasting short term solar irradiance. ISA Transactions, 121, 63–74. https://doi.org/10.1016/j.isatra.2021.03.043

Kim, T., Ko, W., & Kim, J. (2019). Analysis and Impact Evaluation of Missing Data Imputation in Day-ahead PV Generation Forecasting. Applied Sciences, 9(1), 204. https://doi.org/10.3390/app9010204

Koo, J., & Yoon, S. (2022). In-situ sensor virtualization and calibration in building systems. Applied Energy, 325, 119864. https://doi.org/10.1016/J.APENERGY.2022.119864

Kumar, R., Krishna Goswami, B., Motiram Mhatre, S., & Agrawal, S. (2024). Naive Bayes in Focus: A Thorough Examination of its Algorithmic Foundations and Use Cases. International Journal of Innovative Science and Research Technology (IJISRT), 2078–2081. https://doi.org/10.38124/ijisrt/IJISRT24MAY1438

Mubiyn, S. N., & Ilminnafik, N. (2024). Pengukuran Intensitas Radiasi Matahari di Wilayah Kabupaten Nganjuk Tahun 2016. Jurnal Energi Baru dan Terbarukan, 5(1), 20–26. https://doi.org/10.14710/jebt.2024.21580

Mudike, R., Barbate, I., Tripathi, A. K., Nikhil, P. G., & Banerjee, C. (2021). Calibration of solar radiometers with traceability to the world radiometric reference using an absolute cavity radiometer. Measurement: Journal of the International Measurement Confederation, 179. https://doi.org/10.1016/j.measurement.2021.109475

Nouri, B., Wilbert, S., García, G., Ramírez, L., Zarzalejo, L., Valenzuela, R., Ferrera, F., & Prahl, C. (2015). Report on established joint calibration facility for pyrheliometers at PSA to be operated as ACCESS facility. Dalam Sfera2 Project. FP7-INFRA-312643. http://sfera2.sollab.eu/uploads/images/jra/Files/SFERA2PyrhelCal_D11_2_151221.pdf

Parasyris, A., Alexandrakis, G., Kozyrakis, G. V, Spanoudaki, K., & Kampanis, N. A. (2022). Predicting Meteorological Variables on Local Level with SARIMA, LSTM and Hybrid Techniques. Atmosphere, 13(878). https://doi.org/10.3390/atmos13060878

Shahsavari, A., & Akbari, M. (2018). Potential of solar energy in developing countries for reducing energy-related emissions. Renewable and Sustainable Energy Reviews, 90, 275–291. https://doi.org/10.1016/J.RSER.2018.03.065

Vanlalchhuanawmi, C., Deb, S., Islam, M. M., & Ustun, T. S. (2025). Solar radiation prediction: A multi-model machine learning and deep learning approach. AIP Advances, 15(5). https://doi.org/10.1063/5.0237246

Viswanath, A., Kumar M, D., Srihari, B., & Prabhu, E. (2020). Calibration of a Pyranometer using Regression Analysis. Fifth International Conference on Communication and Electronics Systems (ICCES 2020).