Short-term prediction of solar radiation using satellite images and a long-term recurrent convolutional neural network
UDC: 621.311
DOI: 10.33285/2782-604X-2022-10(591)-37-44
Authors:
VELICHKO ARSENY I.
1,
ZUBAKIN VASILY A.1,
TERNIKOV OLEG V.1,
TREGUBENKO MAXIM D.2
1 National University of Oil and Gas "Gubkin University", Moscow, Russia
2 Southern Federal University, Rostov-on-Don, Russia
Keywords: renewable energy sources, satellite imagery, deep learning, computer vision, solar power plant, cloud motion vector, convolutional neural network, wholesale electricity and power market
Annotation:
The article describes the main methods of short-term prediction of insolation on the Earth's surface; the prediction was carried out using a model based on the processing of satellite images and the CNN-LSTM neural network.
Bibliography:
1. Yap W.K., Karri V. Comparative study in predicting the global solar radiation for Darwin, Australia // J. of Solar Energy Engineering. – 2012. – Vol. 134, No. 3. – DOI: 10.1115/1.4006574
2. Akarslan E., Hacaoglu F.O. A novel adaptive approach for hourly solar radiation forecasting // Renewable Energy. – 2016. – Vol. 87, Part 1. – P. 628–633. – DOI: 10.1016/J.RENENE.2015.10.063
3. A Weather-Based Hybrid Method for 1-Day Ahead Hourly Forecasting of PV Power Output / Hong-Tzer Yang, Chao-Ming Huang, Yann-Chang Huang, Yi-Shiang Pai // IEEE Transactions on Sustainable Energy. – 2014. – Vol. 5, Issue 3. – P. 917–926. – DOI: 10.1109/TSTE.2014.2313600
4. Prasad A.A., Kay M. Prediction of Solar Power Using Near-Real Time Satellite Data // Energies. – 2021. – Vol. 14, Issue 18. – DOI: 10.3390/en14185865
5. Preliminary assessment of two spatio-temporal forecasting techniques for hourly satellite-derived irradiance in a complex meteorological context / M. André, R. Perez, T. Soubdhan [et al.] // Solar Energy. – 2019. – Vol. 177. – P. 703–712. – DOI: 10.1016/j.solener.2018.11.010
6. Spatiotemporal Optimization for Short-Term Solar Forecasting Based on Satellite Imagery / Oh Myeongchan, Chang Ki Kim, Boyoung Kim [et al.] // Energies. – 2021. – Vol. 14, Issue 8. – DOI: 10.3390/en14082216
7. Soldatov S.A., Strel'nikov K.N., Vatolin D.S. Bystroe i nadezhnoe opredelenie global'nogo dvizheniya v videoposledovatel'nostyakh // Materialy 16-y Mezhdunar. konf. po komp'yuternoy grafike i ee prilozheniyam. – Novosibirsk: In-t vychislitel'noy matematiki i matematicheskoy geofiziki SO RAN, 2006. – S. 430–437.
8. Solar Radiation Prediction: Nabor otkrytykh dannykh spublichnoy veb-platformy Kaggle. – URL: https://www.kaggle.com/datasets/dronio/SolarEnergy (data obrashcheniya 07.06.2022).
9. Rigollier C., Bauer O., Wald L. On the clear sky model of the ESRA – European Solar Radiation Atlas – With respect to the Heliosat method // Solar Energy. – 2000. – Vol. 68, Issue 1. – P. 33–48. – DOI: 10.1016/S0038-092X(99)00055-9
Back to issue