A Hybrid GRU-BiLSTM Deep Learning Framework for Solar Radiation Forecasting and Photovoltaic Energy Yield Assessment in Timor Island, Indonesia

Yobel Eliezer Mahardika; Agustina Rachmawardani; Marzuki Sinambela

Authors

Yobel Eliezer Mahardika Undergraduate Program in Applied Instrumentation Meteorology Climatology Geophysics, STMKG, Tangerang, Indonesia
Agustina Rachmawardani Undergraduate Program in Applied Instrumentation Meteorology Climatology Geophysics, STMKG, Tangerang, Indonesia
Marzuki Sinambela Undergraduate Program in Applied Instrumentation Meteorology Climatology Geophysics, STMKG, Tangerang, Indonesia

Keywords:

solar radiation forecasting, GRU-BiLSTM, photovoltaic potential assessment, climatological approach, Timor Island.

Abstract

Timor Island in East Nusa Tenggara possesses abundant solar energy resources, yet the technical feasibility of solar power plant (PLTS) development in the region has rarely been assessed using data-driven quantitative methods. This study aims to develop and validate a hybrid GRU-BiLSTM deep learning model for short-term solar radiation forecasting, to assess whether this model can be reliably extended into long-horizon autoregressive projection, to estimate the solar radiation potential and photovoltaic energy production across five locations in Timor Island, and to characterize the radiation variability relevant to PLTS design. A hybrid GRU-BiLSTM deep learning model was developed and evaluated for short-term hourly solar radiation forecasting using ERA5 reanalysis data (2015-2025), achieving R² of 0.9507-0.9584 across five locations. Because chained autoregressive projection using this model was found to be unreliable for annual-horizon estimation (R² = -0.53, +46% overestimation), a climatological approach based on 2015-2025 historical averages was applied instead for potential assessment. The results show that the five locations possess high and relatively uniform solar potential, with annual totals ranging from 2,023 to 2,109 kWh/m² (5.54-5.78 kWh/m²/day), corresponding to estimated photovoltaic energy production of 273.1-284.8 kWh/m² per year. Coefficient of variation values (69.6-71.0%) indicate substantial short-term fluctuation despite the locations' consistent seasonal pattern, with the lowest production occurring in June and the highest in October. These findings provide a quantitative basis for PLTS capacity planning and energy storage design in Timor Island, demonstrating that a validated short-term forecasting model can be meaningfully extended into practical renewable energy resource assessment.

Downloads

Download data is not yet available.

References

J. Giwangkara and B. van Campen, "Planning the Electrification of Rural Villages in East Nusa Tenggara Using Renewable Energy Generation," Indones. J. Energy, vol. 1, no. 1, pp. 5-21, 2018, doi: 10.33116/ije.v1i1.10.

M. A. Bou-Rabee, M. Y. Naz, I. E. D. Albalaa, and S. A. Sulaiman, "BiLSTM Network-Based Approach for Solar Irradiance Forecasting in Continental Climate Zones," Energies, vol. 15, no. 6, 2022, doi: 10.3390/en15062226.

J. B. Fernandes and K. Mannepalli, "Enhanced Deep Hierarchal GRU & BiLSTM Using Data Augmentation and Spatial Features for Tamil Emotional Speech Recognition," Int. J. Mod. Educ. Comput. Sci., 2022, doi: 10.5815/ijmecs.2022.03.03.

X. Lei, "A Photovoltaic Prediction Model With Integrated Attention Mechanism," Mathematics, vol. 12, no. 13, 2024, doi: 10.3390/math12132103.

A. Al Bataineh and D. Kaur, "Immunocomputing-Based Approach for Optimizing the Topologies of LSTM Networks," IEEE Access, vol. 9, pp. 78993-79004, 2021, doi: 10.1109/ACCESS.2021.3084131.

N. Sutarna, C. Tjahyadi, P. Oktivasari, M. Dwiyaniti, and Tohazen, "Hyperparameter Tuning Impact on Deep Learning Bi-LSTM for Photovoltaic Power Forecasting," J. Robot. Control, vol. 5, no. 3, pp. 677-693, 2024, doi: 10.18196/jrc.v5i3.21120.

A. Barnett and X. Wang, "The Evolving Value of Photovoltaic Module Efficiency," Appl. Sci., vol. 9, no. 6, 2019, doi: 10.3390/app9061227..

N. Sugiartha, "Energy Yield of a 1.3 kWp Grid-Connected Photovoltaic System Design: Case for a Small House in Bali," Matrix J. Manaj. Teknol. Inform., vol. 10, no. 1, pp. 19-25, 2020, doi: 10.31940/matrix.v10i1.1838.

A. J. Veldhuis and A. H. M. E. Reinders, "Reviewing the Potential and Cost-Effectiveness of Grid-Connected Solar PV in Indonesia on a Provincial Level," Renew. Sustain. Energy Rev., vol. 27, pp. 315-324, 2013, doi: 10.1016/j.rser.2013.06.010.

C. A. Alvares, P. C. Sentelhas, and H. B. Dias, "Southeastern Brazil Inland Tropicalization: Köppen System Applied for Detecting Climate Change Throughout 100 Years of Meteorological Observed Data," Theor. Appl. Climatol., vol. 149, no. 3-4, pp. 1431-1450, 2022, doi: 10.1007/s00704-022-04122-4.

Z. M. Abbood and O. T. Al-Taai, "Study of Absorbance and Emissivity Solar Radiation by Clouds, Aerosols and Some Atmospheric Gases," J. Appl. Adv. Res., vol. 3, no. 5, pp. 128-134, 2018, doi: 10.21839/jaar.2018.v3i5.222.

D. I. Prasetyo, A. Rachmawardani, B. Satrio, and D. B. Adinara, “Comparative Analysis of Machine Learning and Deep Learning Models for PM2 . 5 and PM10 Time Series Forecasting Using the SISANAPAS Web Platform,” vol. 14, no. November, pp. 377–386, 2025.

L. Benali, G. Notton, A. Fouilloy, C. Voyant, and R. Dizene, "Solar Radiation Forecasting Using Artificial Neural Network and Random Forest Methods: Application to Normal Beam, Horizontal Diffuse and Global Components," Renew. Energy, vol. 132, pp. 871-884, 2019, doi: 10.1016/j.renene.2018.08.044.

C. Bergmeir, R. J. Hyndman, and B. Koo, "A Note on the Validity of Cross-Validation for Evaluating Autoregressive Time Series Prediction," Comput. Stat. Data Anal., vol. 120, pp. 70-83, 2018, doi: 10.1016/j.csda.2017.11.003.

K. Bhatt and M. Kambli, "Comparative Analysis of Ocean Color Forecasting Models: A Case Study on Indian Southern Peninsula Using SARIMA and Deep Learning Approaches," Int. Res. J. Modernization Eng. Technol. Sci., no. 11, 2023, doi: 10.56726/irjmets46878.

H. Hersbach et al., "The ERA5 Global Reanalysis," Q. J. R. Meteorol. Soc., vol. 146, no. 730, pp. 1999-2049, 2020, doi: 10.1002/qj.3803.

Y. Li, L. Guo, J. Wang, Y. Wang, D. Xu, and J. Wen, “An Improved Sap Flow Prediction Model Based on CNN-GRU-BiLSTM and Factor Analysis of Historical Environmental Variables,” Forests, vol. 14, no. 7, pp. 1–21, 2023.

O. J. Ilemobayo et al., "Hyperparameter Tuning in Machine Learning: A Comprehensive Review," J. Eng. Res. Rep., vol. 26, no. 6, pp. 388-395, 2024, doi: 10.9734/jerr/2024/v26i61188.

M. Bessafi et al., "Spatial and Temporal Non-Linear Dynamics Analysis and Predictability of Solar Radiation Time Series for La Reunion Island (France)," Entropy, vol. 20, no. 12, 2018, doi: 10.3390/e20120946.