Communications for Statistical Applications and Methods

The Korean Statistical Society (한국통계학회)
권호 표지
DOI QR코드

DOI QR Code

Solar radiation forecasting using boosting decision tree and recurrent neural networks

  • Hyojeoung, Kim (Department of Applied Statistics, University of Chung-Ang) ;
  • Sujin, Park (Department of Applied Statistics, University of Chung-Ang) ;
  • Sahm, Kim (Department of Applied Statistics, University of Chung-Ang)
  • Received : 2022.07.28
  • Accepted : 2022.09.05
  • Published : 2022.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, as the importance of environmental protection has emerged, interest in new and renewable energy is also increasing worldwide. In particular, the solar energy sector accounts for the highest production rate among new and renewable energy in Korea due to its infinite resources, easy installation and maintenance, and eco-friendly characteristics such as low noise emission levels and less pollutants during power generation. However, although climate prediction is essential since solar power is affected by weather and climate change, solar radiation, which is closely related to solar power, is not currently forecasted by the Korea Meteorological Administration. Solar radiation prediction can be the basis for establishing a reasonable new and renewable energy operation plan, and it is very important because it can be used not only in solar power but also in other fields such as power consumption prediction. Therefore, this study was conducted for the purpose of improving the accuracy of solar radiation. Solar radiation was predicted by a total of three weather variables, temperature, humidity, and cloudiness, and solar radiation outside the atmosphere, and the results were compared using various models. The CatBoost model was best obtained by fitting and comparing the Boosting series (XGB, CatBoost) and RNN series (Simple RNN, LSTM, GRU) models. In addition, the results were further improved through Time series cross-validation.

Keywords

Acknowledgement

This research was funded by Korea Institute of Energy Technology Evaluation and Planning (20199710100060), and the National Research Foundation of Korea (2016R1D1A1B01014954). This research was supported by the Chung-Ang University Research Grants in 2021.

References

  1. Lee K, Son HG, and Kim S (2018). A study on solar energy forecasting based on time series models, The Korean Journal of Applied Statistics, 31, 139-153. https://doi.org/10.5351/KJAS.2018.31.1.139
  2. Suh YM, Son H, and Kim S (2018). Solar radiation forecasting by time series models, The Korean Journal of Applied Statistics, 31, 785-799.
  3. Elizondo D, Hoogenboom G, and McClendon RW (1994). Development of a neural network model to predict daily solar radiation, Agricultural and Forest Meteorology, 71, 115-132. https://doi.org/10.1016/0168-1923(94)90103-1
  4. Rehman S and Mohandes M (2008). Artificial neural network estimation of global solar radiation using air temperature and relative humidity, Energy Policy, 36, 571-576. https://doi.org/10.1016/j.enpol.2007.09.033
  5. Alam S, Kaushik SC, and Garg SN (2009). Assessment of diffuse solar energy under general sky condition using artificial neural network, Applied Energy, 86, 554-564. https://doi.org/10.1016/j.apenergy.2008.09.004
  6. Sahm Kim (2017). A study on solar irradiance forecasting with weather variables, The Korean Journal of Applied Statistics, 30, 1005-1013.
  7. Fan J, Wang X, Wu L, Zhou H, Zhang F, Yu X, Lu X, and Xiang Y (2018). Comparison of support vector machine and extreme gradient boosting for predicting daily global solar radiation using temperature and precipitation in humid subtropical climates: A case study in China, Energy Conversion and Management, 164, 102-111.
  8. Fan J, Wang X, Zhang F, Ma X, and Wu L (2020). Predicting daily diffuse horizontal solar radiation in various climatic regions of China using support vector machine and tree-based soft computing models with local and extrinsic climatic data, Journal of Cleaner Production, 248, 119264.
  9. Pang Z, Niu F, and O'Neill Z (2020). Solar radiation prediction using recurrent neural network and artificial neural network: A case study with comparisons, Renewable Energy, 156, 279-289. https://doi.org/10.1016/j.renene.2020.04.042
  10. Obiora CN, Ali A, and Hasan AN (2021). Implementing extreme gradient boosting (XGBoost) algorithm in predicting solar irradiance, In Proceeding of the 2021 IEEE PES/IAS PowerAfrica, Nairobi, 1-5.
  11. Huang L, Kang J, Wan M, Fang L, Zhang C, and Zeng Z (2021). Solar radiation prediction using different machine learning algorithms and implications for extreme climate events, Frontiers in Earth Science, 9, 596860.
  12. Rocha PA and Santos VO (2022). Global horizontal and direct normal solar irradiance modeling by the machine learning methods XGBoost and deep neural networks with CNN-LSTM layers: A case study using the GOES-16 satellite imagery, International Journal of Energy and Environmental Engineering, 13, 1271-1286.
  13. Kim H and Kim S (2022). A study on frost prediction model using machine learning, The Korean Journal of Applied Statistics, 35, 543-552. https://doi.org/10.5351/KJAS.2022.35.4.543
  14. Sorkun MC, Paoli C, and Incel, OD (2017). Time series forecasting on solar irradiation using deep learning, In Proceeding of the 2017 10th international conference on electrical and electronics engineering (ELECO), IEEE, Bursa, 151-155.
  15. Hochreiter S and Schmidhuber J (1997). Long short-term memory, Neural Compute, 9, 1735-1780, Available from: 10.1162/neco.1997.9.8.1735. PMID: 9377276
  16. Kumari P and Toshniwal D (2019). Hourly solar irradiance prediction from satellite data using lstm.
  17. Sorkun MC, Incel OD, and Paoli C (2020). Time series forecasting on multivariate solar radiation data using deep learning (LSTM), Turkish Journal of Electrical Engineering and Computer Sciences, 28, 211-223. https://doi.org/10.3906/elk-1907-218
  18. Cho K, Van Merrienboer B, Bahdanau D, and Bengio Y (2014). On the properties of neural machine translation: Encoder-decoder approaches, Available from: arXiv preprint arXiv:1409.1259
  19. Boubaker S, Benghanem M, Mellit A, Lefza A, Kahouli O, and Kolsi L (2021). Deep neural networks for predicting solar radiation at Hail Region, Saudi Arabia, IEEE Access, 9, 36719-36729. https://doi.org/10.1109/ACCESS.2021.3062205