IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v14y2021i3p753-d490780.html
   My bibliography  Save this article

Convolutional Neural Network for High-Resolution Cloud Motion Prediction from Hemispheric Sky Images

Author

Listed:
  • Cristian Crisosto

    (Institute for Meteorology and Climatology, Leibniz Universität Hannover, Herrenhäuser Straße 2, 30419 Hannover, Germany)

  • Eduardo W. Luiz

    (Institute for Meteorology and Climatology, Leibniz Universität Hannover, Herrenhäuser Straße 2, 30419 Hannover, Germany)

  • Gunther Seckmeyer

    (Institute for Meteorology and Climatology, Leibniz Universität Hannover, Herrenhäuser Straße 2, 30419 Hannover, Germany)

Abstract

A novel high-resolution method for forecasting cloud motion from all-sky images using deep learning is presented. A convolutional neural network (CNN) was created and trained with more than two years of all-sky images, recorded by a hemispheric sky imager (HSI) at the Institute of Meteorology and Climatology (IMUK) of the Leibniz Universität Hannover, Hannover, Germany. Using the haze indexpostprocessing algorithm, cloud characteristics were found, and the deformation vector of each cloud was performed and used as ground truth. The CNN training process was built to predict cloud motion up to 10 min ahead, in a sequence of HSI images, tracking clouds frame by frame. The first two simulated minutes show a strong similarity between simulated and measured cloud motion, which allows photovoltaic (PV) companies to make accurate horizon time predictions and better marketing decisions for primary and secondary control reserves. This cloud motion algorithm principally targets global irradiance predictions as an application for electrical engineering and in PV output predictions. Comparisons between the results of the predicted region of interest of a cloud by the proposed method and real cloud position show a mean Sørensen–Dice similarity coefficient ( SD ) of 94 ± 2.6% (mean ± standard deviation) for the first minute, outperforming the persistence model (89 ± 3.8%). As the forecast time window increased the index decreased to 44.4 ± 12.3% for the CNN and 37.8 ± 16.4% for the persistence model for 10 min ahead forecast. In addition, up to 10 min global horizontal irradiance was also derived using a feed-forward artificial neural network technique for each CNN forecasted image. Therefore, the new algorithm presented here increases the SD approximately 15% compared to the reference persistence model.

Suggested Citation

  • Cristian Crisosto & Eduardo W. Luiz & Gunther Seckmeyer, 2021. "Convolutional Neural Network for High-Resolution Cloud Motion Prediction from Hemispheric Sky Images," Energies, MDPI, vol. 14(3), pages 1-11, February.
    • Handle: RePEc:gam:jeners:v:14:y:2021:i:3:p:753-:d:490780
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/14/3/753/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/1996-1073/14/3/753/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Ariana Moncada & Walter Richardson & Rolando Vega-Avila, 2018. "Deep Learning to Forecast Solar Irradiance Using a Six-Month UTSA SkyImager Dataset," Energies, MDPI, vol. 11(8), pages 1-16, July.
    2. Cristian Crisosto & Martin Hofmann & Riyad Mubarak & Gunther Seckmeyer, 2018. "One-Hour Prediction of the Global Solar Irradiance from All-Sky Images Using Artificial Neural Networks," Energies, MDPI, vol. 11(11), pages 1-16, October.
    3. Escrig, H. & Batlles, F.J. & Alonso, J. & Baena, F.M. & Bosch, J.L. & Salbidegoitia, I.B. & Burgaleta, J.I., 2013. "Cloud detection, classification and motion estimation using geostationary satellite imagery for cloud cover forecast," Energy, Elsevier, vol. 55(C), pages 853-859.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Alen Jakoplić & Dubravko Franković & Juraj Havelka & Hrvoje Bulat, 2023. "Short-Term Photovoltaic Power Plant Output Forecasting Using Sky Images and Deep Learning," Energies, MDPI, vol. 16(14), pages 1-18, July.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Ahmed, R. & Sreeram, V. & Mishra, Y. & Arif, M.D., 2020. "A review and evaluation of the state-of-the-art in PV solar power forecasting: Techniques and optimization," Renewable and Sustainable Energy Reviews, Elsevier, vol. 124(C).
    2. Yongju Son & Yeunggurl Yoon & Jintae Cho & Sungyun Choi, 2022. "Cloud Cover Forecast Based on Correlation Analysis on Satellite Images for Short-Term Photovoltaic Power Forecasting," Sustainability, MDPI, vol. 14(8), pages 1-24, April.
    3. Mahmoud Dhimish & Pavlos I. Lazaridis, 2022. "Approximating Shading Ratio Using the Total-Sky Imaging System: An Application for Photovoltaic Systems," Energies, MDPI, vol. 15(21), pages 1-16, November.
    4. Arumugham, Dinesh Rajan & Rajendran, Parvathy, 2021. "Modelling global solar irradiance for any location on earth through regression analysis using high-resolution data," Renewable Energy, Elsevier, vol. 180(C), pages 1114-1123.
    5. Ajith, Meenu & Martínez-Ramón, Manel, 2023. "Deep learning algorithms for very short term solar irradiance forecasting: A survey," Renewable and Sustainable Energy Reviews, Elsevier, vol. 182(C).
    6. Musaed Alhussein & Syed Irtaza Haider & Khursheed Aurangzeb, 2019. "Microgrid-Level Energy Management Approach Based on Short-Term Forecasting of Wind Speed and Solar Irradiance," Energies, MDPI, vol. 12(8), pages 1-27, April.
    7. Alonso-Montesinos, J. & Martínez-Durbán, M. & del Sagrado, J. & del Águila, I.M. & Batlles, F.J., 2016. "The application of Bayesian network classifiers to cloud classification in satellite images," Renewable Energy, Elsevier, vol. 97(C), pages 155-161.
    8. Alonso, J. & Batlles, F.J., 2014. "Short and medium-term cloudiness forecasting using remote sensing techniques and sky camera imagery," Energy, Elsevier, vol. 73(C), pages 890-897.
    9. Zang, Haixiang & Liu, Ling & Sun, Li & Cheng, Lilin & Wei, Zhinong & Sun, Guoqiang, 2020. "Short-term global horizontal irradiance forecasting based on a hybrid CNN-LSTM model with spatiotemporal correlations," Renewable Energy, Elsevier, vol. 160(C), pages 26-41.
    10. Tang, Yugui & Yang, Kuo & Zhang, Shujing & Zhang, Zhen, 2022. "Photovoltaic power forecasting: A hybrid deep learning model incorporating transfer learning strategy," Renewable and Sustainable Energy Reviews, Elsevier, vol. 162(C).
    11. Alonso-Montesinos, J. & Monterreal, R. & Fernández-Reche, J. & Ballestrín, J. & Carra, E. & Polo, J. & Barbero, J. & Batlles, F.J. & López, G. & Enrique, R. & Martínez-Durbán, M. & Marzo, A., 2019. "Intra-hour energy potential forecasting in a central solar power plant receiver combining Meteosat images and atmospheric extinction," Energy, Elsevier, vol. 188(C).
    12. Llinet Benavides Cesar & Miguel Ángel Manso Callejo & Calimanut-Ionut Cira & Ramon Alcarria, 2023. "CyL-GHI: Global Horizontal Irradiance Dataset Containing 18 Years of Refined Data at 30-Min Granularity from 37 Stations Located in Castile and León (Spain)," Data, MDPI, vol. 8(4), pages 1-21, March.
    13. Lin, Fan & Zhang, Yao & Wang, Jianxue, 2023. "Recent advances in intra-hour solar forecasting: A review of ground-based sky image methods," International Journal of Forecasting, Elsevier, vol. 39(1), pages 244-265.
    14. Dong, Zibo & Yang, Dazhi & Reindl, Thomas & Walsh, Wilfred M., 2013. "Short-term solar irradiance forecasting using exponential smoothing state space model," Energy, Elsevier, vol. 55(C), pages 1104-1113.
    15. Alonso-Montesinos, J. & Batlles, F.J., 2015. "The use of a sky camera for solar radiation estimation based on digital image processing," Energy, Elsevier, vol. 90(P1), pages 377-386.
    16. Dong, Zibo & Yang, Dazhi & Reindl, Thomas & Walsh, Wilfred M., 2015. "A novel hybrid approach based on self-organizing maps, support vector regression and particle swarm optimization to forecast solar irradiance," Energy, Elsevier, vol. 82(C), pages 570-577.
    17. Javier Huertas Tato & Miguel Centeno Brito, 2018. "Using Smart Persistence and Random Forests to Predict Photovoltaic Energy Production," Energies, MDPI, vol. 12(1), pages 1-12, December.
    18. Qu, Jiaqi & Qian, Zheng & Pei, Yan, 2021. "Day-ahead hourly photovoltaic power forecasting using attention-based CNN-LSTM neural network embedded with multiple relevant and target variables prediction pattern," Energy, Elsevier, vol. 232(C).
    19. Terrén-Serrano, Guillermo & Martínez-Ramón, Manel, 2021. "Multi-layer wind velocity field visualization in infrared images of clouds for solar irradiance forecasting," Applied Energy, Elsevier, vol. 288(C).
    20. Vateanui Sansine & Pascal Ortega & Daniel Hissel & Marania Hopuare, 2022. "Solar Irradiance Probabilistic Forecasting Using Machine Learning, Metaheuristic Models and Numerical Weather Predictions," Sustainability, MDPI, vol. 14(22), pages 1-16, November.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jeners:v:14:y:2021:i:3:p:753-:d:490780. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.