Deep Learning Prediction Model of Surface Solar Radiation and Photovoltaic Power Using Stepwise Overlapped Grouping of Extraterrestrial Radiation

Hwangkyu Choi

doi:10.7836/kses.2026.46.1.065

All Issue

2026 Vol.46, Issue 1 Preview Page Next Page

Research Article

Deep Learning Prediction Model of Surface Solar Radiation and Photovoltaic Power Using Stepwise Overlapped Grouping of Extraterrestrial Radiation 대기권 밖 일사량의 구간별 중복 그룹핑 기법을 적용한 딥러닝 기반 지표면 일사량 및 태양광 발전량 예측 모델

28 February 2026. pp. 65-76

PDF XML

Abstract

As the proportion of renewable energy sources has increased, the demand for accurate photovoltaic (PV) power forecasting to mitigate its inherent intermittency has intensified. Although solar radiation is the most critical factor influencing the PV output, the lack of direct irradiance forecasts in standard meteorological systems causes significant prediction uncertainties. This study proposes a two-stage deep learning forecasting model that incorporates extraterrestrial radiation (ESR), a theoretically calculable parameter, using stepwise overlapped grouping. The proposed method categorizes data into intervals based on the ESR intensity, while overlapping the data between adjacent groups. This approach ensures temporal continuity and enhances the adaptability of the model to abrupt weather changes at interval boundaries. Investigations using meteorological and PV power data from Jeju Island demonstrate that the proposed model improves the mean absolute error for solar radiation forecasting by approximately 12.4% when compared to conventional time-based grouping models. Furthermore, the model exhibits high precision in tracking the patterns of actual PV power generation.

Keywords

Deep Learning

Photovoltaic Power Prediction

Solar Radiation Prediction

Extraterrestrial Radiation

Overlapped Grouping

키워드

딥러닝

태양광 전력량 예측

일사량 예측

대기권 밖 일사량

중복 그룹핑

References

Jayasankar, K. C., Anandhakumar, G., and Kalaimurugan, A., Prediction of Solar Radiation using Deep LSTM- based Machine Learning Algorithm, Journal of Environmental Nanotechnology, Vol. 13, No. 3, pp. 1-8, 2024, https://doi.org/10.13074/jent.2024.09.242585.

10.13074/jent.2024.09.242585

Yu, Y., Cao, J., and Zhu, J., An LSTM Short-term Solar Irradiance Forecasting under Complicated Weather Conditions, IEEE Access, Vol. 7, pp. 145651-145666, 2019, https://doi.org/10.1109/ACCESS.2019.2946057.

10.1109/ACCESS.2019.2946057

Yoon, S. J., Kim, H. G., and Kwak, J. S., A Study on LSTM-based Solar Radiation Prediction Considering Hourly Meteorological Changes, KIPS Transactions on Software and Data Engineering, Vol. 10, No. 1, pp. 1-8, 2021, https://doi.org/10.3745/KTSDE.2021.10.1.1.

10.3745/KTSDE.2021.10.1.1

Liu, J., Huang, X., Li, Q., Chen, Z., Liu, G., and Tai, Y., Hourly Stepwise Forecasting for Solar Irradiance using Integrated Hybrid Models CNN-LSTM-MLP Combined with Error Correction and VMD, Energy Conversion and Management, Vol. 280, 116804, 2023, https://doi.org/10.1016/j.enconman.2023.116804.

10.1016/j.enconman.2023.116804

Acikgoz, H., A Novel Approach based on Integration of Convolutional Neural Networks and Deep Feature Selection for Short-term Solar Radiation Forecasting, Applied Energy, Vol. 305, 117911, 2022, https://doi.org/10.1016/j.apenergy.2021.117912.

10.1016/j.apenergy.2021.117912

Kim, S. H., Kim, K. J., and Choi, H. J., Deep Neural Network Model for Estimating Daily Solar Radiation Using Temperature and Precipitation, Journal of the Korean Meteorological Society, Vol. 21, No. 2, pp. 85-96, 2019, https://doi.org/10.5532/KJAFM.2019.21.4.264.

10.5532/KJAFM.2019.21.4.264

Cho, Y. R., Kim, J. H., and Lee, S. H., Solar Radiation Prediction Based on Multiple Deep Learning Models Using Meteorological Data and Meteorological Satellite Imagery, Journal of the Korea Society of Computer and Information, Vol. 26, No. 2, pp. 1-10, 2021.

Yang, D., Yeo, N., Kim, S., Lee, J., Kim, S., and Mah, P., A Piecewise Prediction Model of Solar Radiation using Weather Sensing Information for stand-alone Photovoltaic Systems, Proceedings of KIISE : KCC2017, pp. 15-17, June 2017, Jeju, Korea, https://doi.org/10.5626/KTCP.2017.23.11.632.

10.5626/KTCP.2017.23.11.632

Kim, K., Jang, B., and Choi, H., Piecewise Overlapped-Grouping Insolation Prediction Model for Solar Power Generation, Proceedings of The ITFE Summer Conference, August 2022, Sokcho, Republic of Korea.

Yang, D., Yoe, N., and Mah, P., A Dynamic Piecewise Prediction Model of Solar Insolation for Efficient Photovoltaic Systems, KIISE Transactions on Computing Practices, Vol. 23, No. 11, pp. 632-640, 2017, https://doi.org/10.5626/KTCP.2017.23.11.632.

10.5626/KTCP.2017.23.11.632

Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., and Zheng, X., TensorFlow: Large-scale Machine Learning on Heterogeneous Systems, 2015. Software available from tensorflow.org.

Korea East-West Power Co., Ltd., Training Dataset for Photovoltaic Power Generation Prediction in Jeju Region, 2025. https://data.go.kr. last accessed on the 9th November 2025.

Information

Publisher :Korean Solar Energy Society
Publisher(Ko) :한국태양에너지학회
Journal Title :Journal of the Korean Solar Energy Society
Journal Title(Ko) :한국태양에너지학회 논문집
Volume : 46
No :1
Pages :65-76
Received Date : 2026-01-29
Revised Date : 2026-02-17
Accepted Date : 2026-02-19
DOI :https://doi.org/10.7836/kses.2026.46.1.065

Journal of the Korean Solar Energy Society ISSN:1598-6411(Print) 2508-3562(Online) 한국태양에너지학회 논문집

All Issue