Performance Analysis of Photovoltaic Power Forecasting Based on Input Feature Configuration and Selection

Sohyun Lee; Daejong Lee; Myunggeun Chun

doi:10.7836/kses.2026.46.4.001

All Issue

2026 Vol.46, Issue 4 Next Page

Performance Analysis of Photovoltaic Power Forecasting Based on Input Feature Configuration and Selection 입력 특징 구성 및 선택에 따른 태양광 발전량 예측 성능 분석

30 August 2026. pp. 1-13

PDF XML

Abstract

This study investigated the impact of different input feature configurations on photovoltaic (PV) power forecasting performance. Four feature groups were defined: a basic feature group comprising solar position and temporal information, a meteorological feature group, an autoregressive feature group, and a dynamic and lagged feature group. These feature groups were subsequently combined to construct eight input feature configurations. The resulting configurations were evaluated using a tree-based model (LightGBM) and a time-series deep learning model (LSTM) to compare their forecasting performance. The experimental results showed that incorporating temporal features reduced prediction errors in terms of MAE, NMAE, RMSE, and MSE. Overall, LightGBM consistently achieved lower prediction errors than LSTM across all feature configurations. These findings highlight the importance of incorporating temporal dependencies when designing input feature structures for PV power forecasting.

Keywords

Photovoltaic power forecasting

Input feature design

Feature selection

Feature grouping

Forecasting performance evaluation

키워드

태양광 발전량 예측

입력 변수 설계

특징 선택

특징군 구성

예측 성능 평가

References

Babu, A. R. V., Bharath Kumar, N., Narasipuram, R. P., Periyannan, S., Hosseinpour, A., and Flah, A., Solar Energy Forecasting Using Machine Learning Techniques for Enhanced Grid Stability, IEEE Access, Vol. 13, pp. 93735-93754, 2025, https://doi.org/10.1109/ACCESS.2025.3574093.

10.1109/ACCESS.2025.3574093

Lee, D. H., Jung, A. H., Kim, J. Y., Kim, C. K., Kim, H. G., and Lee, Y. S., Solar Power Generation Forecast Model Using Seasonal ARIMA, Journal of the Korean Solar Energy Society, Vol. 39, No. 3, pp. 59-66, 2019.

10.7836/kses.2019.39.3.059

Kim, H. J., Lee, S. H., and Park, K. S., Short-Term Photovoltaic Power Forecasting Using LSTM Networks, Journal of the Korean Solar Energy Society, Vol. 40, No. 2, pp. 45-54, 2020.

Choi, Y. M. and Lee, J. H., Photovoltaic Power Forecasting Using Artificial Neural Networks, Transactions of the Korean Institute of Electrical Engineers, Vol. 68, No. 5, pp. 812-819, 2019.

Park, J. S., Kim, D. H., and Yoo, S. H., Photovoltaic Power Forecasting Using Numerical Weather Prediction Data, Journal of the Korean Solar Energy Society, Vol. 43, No. 4, pp. 25-34, 2023.

10.7836/kses.2023.43.6.087

Voyant, C., Notton, G., Kalogirou, S. A., 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.

10.1016/j.renene.2016.12.095

Zhang, Y., Wang, J., and Wang, X., Short-Term Photovoltaic Power Forecasting Using Multi-Source Meteorological Features and LightGBM, Applied Energy, Vol. 338, 120926, 2023.

Li, G., Shi, J., and Qu, X., Autoregressive Modeling Approach for Photovoltaic Power Forecasting, Energy Conversion and Management, Vol. 125, pp. 319-331, 2016.

Garoudja, E., Harrou, F., Sun, Y., Kara, K., Chouder, A., and Silvestre, S., Monitoring and Fault Detection of Photovoltaic Systems Using Machine Learning Techniques, Renewable and Sustainable Energy Reviews, Vol. 77, pp. 310-327, 2017.

10.1016/j.solener.2017.04.043

Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T. Y., LightGBM: A Highly Efficient Gradient Boosting Decision Tree, Advances in Neural Information Processing Systems 30, Long Beach, CA, USA, pp. 3146-3154, December 2017.

Wang, H., Li, G., Wang, G., Peng, J., Jiang, H., and Liu, Y., Deep Learning Based Short-Term Photovoltaic Power Forecasting: A Review and Comparative Study, Energy Reports, Vol. 8, pp. 114-132, 2022.

Park, J. M., Lee, D. W., Joe, K., and Yoon, H. S., Transformer-Based Photovoltaic Power Prediction Model Utilizing Multiple Weather Forecasts, Journal of the Korean Solar Energy Society, Vol. 43, No. 6, pp. 87-95, 2023.

10.7836/kses.2023.43.6.087

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 :4
Pages :1-13
Received Date : 2026-04-14
Revised Date : 2026-06-30
Accepted Date : 2026-06-30
DOI :https://doi.org/10.7836/kses.2026.46.4.001

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

All Issue