Skip to main content

Advertisement

SpringerLink
Log in

Using a Multi-view Convolutional Neural Network to monitor solar irradiance

  • S.I. : Effective and Efficient Deep Learning
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

In the last years, there is an increasing interest for enhanced method for assessing and monitoring the level of the global horizontal irradiance (GHI) in photovoltaic (PV) systems, fostered by the massive deployment of this energy. Thermopile or photodiode pyranometers provide point measurements, which may not be adequate in cases when areal information is important (as for PV network or large PV plants monitoring). The use of All Sky Imagers paired convolutional neural networks, a powerful technique for estimation, has been proposed as a plausible alternative. In this work, a convolutional neural network architecture is presented to estimate solar irradiance from sets of ground-level Total Sky Images. This neural network is capable of combining images from three cameras. Results show that this approach is more accurate than using only images from a single camera. It has also been shown to improve the performance of two other approaches: a cloud fraction model and a feature extraction model.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

References

  1. Renewables I et al (2018) Analysis and forecast to 2023. International Energy Agency, Paris, France

    Google Scholar 

  2. Anagnostos D, Schmidt T, Cavadias S, Soudris D, Poortmans J, Catthoor F (2019) A method for detailed, short-term energy yield forecasting of photovoltaic installations. Renew Energy 130:122–129

    Article  Google Scholar 

  3. Merei G, Moshövel J, Magnor D, Sauer DU (2016) Optimization of self-consumption and techno-economic analysis of PV-battery systems in commercial applications. Appl Energy 168:171–178

    Article  Google Scholar 

  4. Agüera-Pérez A, Palomares-Salas JC, González de la Rosa JJ, Florencias-Oliveros O (2018) Weather forecasts for microgrid energy management: review, discussion and recommendations. Appl Energy 228:265–278

    Article  Google Scholar 

  5. Woyte A, Richter M, Moser D, Reich N, Green M, Mau S, Beyer H.G (2014) Analytical monitoring of grid-connected photovoltaic systems. IEA-PVPS T13-03, vol. 2014

  6. Sengupta M, Habte A, Kurtz S, Dobos A, Wilbert S, Lorenz E, Stoffel T, Renné D, Gueymard CA, Myers D, Wilcox S, Blanc P, Perez R (2015) Best practices handbook for the collection and use of solar resource data for solar energy applications. National Renewable Energy Laboratory, Colarado, p 236

    Book  Google Scholar 

  7. Rigollier C, Lefèvre M, Wald L (2004) The method Heliosat-2 for deriving shortwave solar radiation from satellite images. Sol Energy 77:159–169

    Article  Google Scholar 

  8. Blanc P, Remund J, Vallance L (2017) 6 - Short-term solar power forecasting based on satellite images. Renewable Energy Forecasting. Woodhead Publishing, Cambridge, pp 179–198. https://doi.org/10.1016/B978-0-08-100504-0.00006-8

    Chapter  Google Scholar 

  9. Elsinga B, van Sark WGJHM (2017) Short-term peer-to-peer solar forecasting in a network of photovoltaic systems. Appl Energy 206:1464–1483

    Article  Google Scholar 

  10. Scolari E, Sossan F, Paolone M (2017) Photovoltaic-model-based solar irradiance estimators: performance comparison and application to maximum power forecasting. IEEE Trans Sustain Energy 9:35–44

    Article  Google Scholar 

  11. Kazantzidis A, Tzoumanikas P, Blanc P, Massip P, Wilbert S, Ramirez-Santigosa L (2017) 5 - Short-term forecasting based on all-sky cameras. Renewable Energy Forecasting. Woodhead Publishing, Cambridge, pp 153–178

    Chapter  Google Scholar 

  12. Schmidt T, Kalisch J, Lorenz E, Heinemann D (2016) Evaluating the spatio-temporal performance of sky-imager-based solar irradiance analysis and forecasts. Atmos Chem Phys 16(5):3399–3412

    Article  Google Scholar 

  13. Alonso-Montesinos J, Batlles FJ (2015) The use of a sky camera for solar radiation estimation based on digital image processing. Energy 90:377–386

    Article  Google Scholar 

  14. Kurtz B, Kleissl J (2017) Measuring diffuse, direct, and global irradiance using a sky imager. Solar Energy 141:311–322

    Article  Google Scholar 

  15. Scolari E, Sossan F, Haure-Touzé M, Paolone M (2018) Local estimation of the global horizontal irradiance using an all-sky camera. Sol Energy 173:1225–1235

    Article  Google Scholar 

  16. Senkal O, Kuleli T (2009) Estimation of solar radiation over turkey using artificial neural network and satellite data. Appl Energy 86:1222–1228

    Article  Google Scholar 

  17. Chu Y, Pedro HT, Coimbra CF (2013) Hybrid intra-hour DNI forecasts with sky image processing enhanced by stochastic learning. Solar Energy 98:592–603

    Article  Google Scholar 

  18. Scolari E, Sossan F, Haure-Touzé M, Paolone M (2018) Local estimation of the global horizontal irradiance using an all-sky camera. Solar Energy 173:1225–1235

    Article  Google Scholar 

  19. LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436

    Article  Google Scholar 

  20. Siddiqui T. A, Bharadwaj S, Kalyanaraman S (2019) A deep learning approach to solar-irradiance forecasting in sky-videos. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), IEEE. pp. 2166–2174

  21. Zhao X, Wei H, Wang H, Zhu T, Zhang K (2019) 3d-cnn-based feature extraction of ground-based cloud images for direct normal irradiance prediction. Solar Energy 181:510–518

    Article  Google Scholar 

  22. Alonso J, Batlles F, Villarroel C, Ayala R, Burgaleta J (2014) Determination of the sun area in sky camera images using radiometric data. Energy Convers Manag 78:24–31

    Article  Google Scholar 

  23. Alonso-Montesinos J, Batlles FJ (2015) The use of a sky camera for solar radiation estimation based on digital image processing. Energy 90(P1):377–386

    Article  Google Scholar 

  24. SuH, Maji S, Kalogerakis E, Learned-Miller E (2015) Multi-view convolutional neural networks for 3d shape recognition. In: 2015 IEEE International Conference on Computer Vision (ICCV), IEEE. pp. 945–953

  25. Chen L, Yan G, Wang T, Ren H, Calbó J, Zhao J, McKenzie R (2012) Estimation of surface shortwave radiation components under all sky conditions: modeling and sensitivity analysis. Remote Sens Environ 123:457–469

    Article  Google Scholar 

  26. Breiman L (2001) Random forests. Mach Learn 45:5–32

    Article  Google Scholar 

  27. Heinle A, Macke A, Srivastav A (2010) Automatic cloud classification of whole sky images. Atmos Meas Tech 3(3):557–567

    Article  Google Scholar 

  28. Reda I, Andreas A (2004) Solar position algorithm for solar radiation application. Sol Energy 76:577–589

    Article  Google Scholar 

  29. Yu F, Koltun V (2015) Multi-scale context aggregation by dilated convolutions. arXiv

  30. Li Q, Lu W, Yang J (2011) A hybrid thresholding algorithm for cloud detection on ground-based color images. J Atmos Ocean Technol 28:1286–1296

    Article  Google Scholar 

  31. Kingma D. P, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980

  32. R Core Team (2018) R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria

    Google Scholar 

  33. Chen T, Li M, Li Y, Lin M, Wang N, Wang M, Xiao T, XuB, Zhang C, Zhang Z (2015) Mxnet: a flexible and efficient machine learning library for heterogeneous distributed systems. arXiv preprint arXiv:1512.01274

Download references

Acknowledgements

This work has been made possible by the Ministerio de Economia y Empresa of Spain, under the project PROSOL (ENE2014-56126-C2).

The authors thank Abengoa Co. (plant operators) and Atlantica Sustainable Infrastructure Co. (plant owners) for providing the dataset used in this work.

Authors from the University of Jaen are supported by the Junta de Andalucía (Research group TEP-220) and by FEDER funds.

This work has been made possible by projects funded by Agencia Estatal de Investigación (PID2019-107455RB-C21 and PID2019-107455RB-C22 / AEI / 10.13039/501100011033).

Author information

Authors and Affiliations

  1. Universidad Europea de Madrid, Madrid, Spain

    Javier Huertas-Tato

  2. Universidad Carlos III de Madrid, Madrid, Spain

    Inés M. Galván & Ricardo Aler

  3. Universidad de Jaen, Jaen, Spain

    Francisco Javier Rodríguez-Benítez & David Pozo-Vázquez

Authors
  1. Javier Huertas-Tato
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Inés M. Galván
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ricardo Aler
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Francisco Javier Rodríguez-Benítez
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. David Pozo-Vázquez
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Javier Huertas-Tato.

Ethics declarations

Conflict of interest

There is no conflict of interest to declare.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Huertas-Tato, J., Galván, I.M., Aler, R. et al. Using a Multi-view Convolutional Neural Network to monitor solar irradiance. Neural Comput & Applic 34, 10295–10307 (2022). https://doi.org/10.1007/s00521-021-05959-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-021-05959-y

Keywords

Search

Navigation