The Examination of Appropriate Learning Periods to Improve the Prediction Accuracy of Solar Power Generation with a LSTM Model

Yong-Jun Lee; Dong-Su Kim; Eun-Joo Oh; Eui-Hwan Ryu

doi:10.7836/kses.2026.46.1.039

All Issue

2026 Vol.46, Issue 1 Preview Page Next Page

Research Article

The Examination of Appropriate Learning Periods to Improve the Prediction Accuracy of Solar Power Generation with a LSTM Model LSTM 모델을 활용한 태양광 발전량 예측 모델의 예측 정확성 확보를 위한 적정 학습 기간에 관한 연구

28 February 2026. pp. 39-51

PDF XML

Abstract

The purpose of this study is to develop a PV power generation machine learning model using the LSTM model, verify its accuracy, and derive an appropriate learning period to ensure the appropriateness of the solar power generation prediction model. A comparison of short-term power generation data predicted by the machine learning model with data measured at the corresponding forecast time showed R² = 0.9499, indicating sufficient accuracy. Finally, the minimum learning period to secure a certain level of prediction through a review of the prediction result was reviewed using the power generation data already secured and the weather information at the same point during the period; 30 days were calculated as an appropriate learning period to ensure the accuracy of the solar power generation prediction model.

Keywords

Solar power generation prediction

Machine learning

Data-driven model

Time series data set

Appropriate learning period

Long Short-Term Memory

키워드

태양광 발전량 예측

기계학습

데이터 기반 모델

시계열 데이터 셋

적정 학습 기간

LSTM

References

Campbell-Lendrum, D. and Prüss-Ustün, A., Climate Change, Air Pollution and Noncommunicable Diseases, Bull, World Health Organ, Vol. 97, pp.160-161, 2019, https://doi.org/10.2471/BLT.18.224295.

10.2471/BLT.18.22429530728622PMC6357572

Thirugnanasambandam, M., Iniyan, S., and Goic, R., A Review of Solar Thermal Technologies, Renewable and Sustainable Energy Reviews, Vol. 14, pp.312-322, 2010, https://doi.org/10.1016/j.rser.2009.07.014.

10.1016/j.rser.2009.07.014

Goetzberger, A. and Hoffmann, V. U., Photovoltaic Solar Energy Generation; Freiburg Springer, Berlin/Heidelberg, Germany, 2005.

Ayvazoğluyüksel, Ö. and Filik, Ü.B., Estimation Methods of Global Solar Radiation, Cell Temperature and Solar Power Forecasting: A Review and Case Study in Eskisehir, Renewable and Sustainable Energy Reviews, Vol. 91, pp.639-653, 2018, https://doi.org/10.1016/j.rser.2018.03.084.

10.1016/j.rser.2018.03.084

EPIA, Connecting the Sun, Solar Photovoltaics on the Road to Large-Scale Grid Integration; Full Report; European Photovoltaic Industry Association, Brussels, Belgium, 2012.

Porter, K. and Rogers, J., Survey of Variable Generation Forecasting in the West: August 2011-June 2012, National Renewable Energy Lab. (NREL), Golden, CO, USA, 2012.

Tapakis, R. and Charalambides, A., Equipment and Methodologies for Cloud Detection and Classification: A Review, Solar Energy, Vol 95, pp.392-430, 2013, https://doi.org/10.1016/j.solener.2012.11.015.

10.1016/j.solener.2012.11.015

Das, U. K., Tey, K. S., Seyedmahmoudian, M., Mekhilef, S., Idris, M. Y. I., Van Deventer, W., Horan, B., and Stojcevski, A., Forecasting of Photovoltaic Power Generation and Model Optimization: A Review, Renewable and Sustainable Energy Reviews, Vol. 81, pp.912-928, 2018, https://doi.org/10.1016/j.rser.2017.08.017.

10.1016/j.rser.2017.08.017

Antonanzas, J., Osorio, N., Escobar, R., Urraca, R., Martinez-De-Pison, F. J., and Antonanzas-Torres, F., Review of Photovoltaic Power Forecasting, Solar Energy, Vol. 136, pp. 78-111, 2016, https://doi.org/10.1016/j.solener.2016.06.069.

10.1016/j.solener.2016.06.069

Bontempi, G., Ben Taieb, S., and Le Borgne, Y. A., Machine Learning Strategies for Time Series Forecasting, Business Intelligence: Second European Summer School, eBISS 2012, Brussels, Belgium, July 15-21, 2012, Tutorial Lectures 2, Springer, Berlin, Heidelberg, Germany, pp. 62-77, 2013.

10.1007/978-3-642-36318-4_3

Voyant, C., Notton, G., Kalogirou, S., Nivet, M. L., Paoli, C., Motte, F., and Fouilloy, A., Machine Learning Methods for Solar Radiation Forecasting: A Review, Renewable Energy, Vol. 105, pp.569-582, 2017, https://doi.org/10.1016/j.renene.2016.12.095.

10.1016/j.renene.2016.12.095

Hochreiter, S. and Schmidhuber, J., Long Short-Term Memory, Neural Computation, Vol. 9, No. 8, pp. 1735-1780, 1997, https://doi.org/10.1162/neco.1997.9.8.1735.

10.1162/neco.1997.9.8.1735

Atef, S. and Eltawil, A. B., Assessment of Stacked Unidirectional and Bidirectional Long Short-Term Memory Networks for Electricity Load Forecasting, Electric Power Systems Research, Vol. 187, 106489, 2020, https://doi.org/10.1016/j.epsr.2020.106489.

10.1016/j.epsr.2020.106489

Sagheer, A. and Kotb, M., Time Series Forecasting of Petroleum Production Using Deep LSTM Recurrent Networks, Neurocomputing, Vol. 323, pp.203-213, 2019, https://doi.org/10.1016/j.neucom.2018.09.082.

10.1016/j.neucom.2018.09.082

Kim, D. and Zhang, J., Implementation of a Long Short-Term Memory Transfer Learning-based Data-Driven Model for Building Energy Demand Forecasting, Sustainability, Vol. 15, 2340, 2023, https://doi.org/10.3390/su15032340.

10.3390/su15032340

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 :39-51
Received Date : 2026-01-04
Revised Date : 2026-01-22
Accepted Date : 2026-01-22
DOI :https://doi.org/10.7836/kses.2026.46.1.039

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

All Issue