Browse > Article
http://dx.doi.org/10.12673/jant.2021.25.6.569

Radiation Prediction Based on Multi Deep Learning Model Using Weather Data and Weather Satellites Image  

Jae-Jung Kim (Department of Energy IT, Gachon University)
Yong-Hun You (Department of Energy IT, Gachon University)
Chang-Bok Kim (Department of Electrical Engineering, Gachon University)
Abstract
Deep learning shows differences in prediction performance depending on data quality and model. This study uses various input data and multiple deep learning models to build an optimal deep learning model for predicting solar radiation, which has the most influence on power generation prediction. did. As the input data, the weather data of the Korea Meteorological Administration and the clairvoyant meteorological image were used by segmenting the image of the Korea Meteorological Agency. , comparative evaluation, and predicting solar radiation by constructing multiple deep learning models connecting the models with the best error rate in each model. As an experimental result, the RMSE of model A, which is a multiple deep learning model, was 0.0637, the RMSE of model B was 0.07062, and the RMSE of model C was 0.06052, so the error rate of model A and model C was better than that of a single model. In this study, the model that connected two or more models through experiments showed improved prediction rates and stable learning results.
Keywords
Satellites Image; Weather Data; Multi Deep Learning Model; Radiation Prediction; Artificial Intelligence;
Citations & Related Records
연도 인용수 순위
  • Reference
1 M. A. Islam, M. Hasanuzzaman, N. A. Rahim, A. Nahar, and M. Hosenuzzaman, "Global renewable energy-based electricity generation and smart grid system for energy security," The Scientific World Journal, Vol. 2014, pp. 1-13, Aug. 2014.
2 Y. R. Lee, H. J. Kim, D. H. Lee, C. J. Lee and D. H. Lee, "Validation of Forecasting Performance of Two-Stage Probabilistic Solar Irradiation and Solar Power Forecasting Algorithm using XGBoost," The transactions of The Korean Institute of Electrical Engineers, Vol. 68, No. 12, pp. 1704-1710, DEC, 2019.   DOI
3 J. H. Choi, D. W. An, and J. H. Gang, "A Survey on Prognostics and Comparison Study on the Model-Based Prognostics," Journal of institute of control, robotics and systems, Vol. 17, No. 11, pp. 1095 - 1100, 2011.   DOI
4 S. H. Hwan, T. G. Kim, and S. H. Lee and J. Y. Choi, "Trend Analysis of Projected Climate Data based on CMIP5 GCMs for Climate Change Impact Assessment on Agricultural Water Resources," Journal of The Korean Society of Agricultural Engineers, Vol. 57, No. 5, pp. 69- 80, 2015.   DOI
5 J. H. Park, D. H. Shin, and C. B. Kim, "Deep Learning Model for Electric Power Demand Prediction Using Special Day Separation and Prediction Elements Extention," Journal of Advanced Navigation Technology, Vol. 21, No. 4, pp. 365-370, 2017.
6 Y. S. Kim, and H. J. Park, "Modeling and Predicting South Korea's Daily Electric Demand Using DNN and LSTM," Journal of Climate Change Research, Vol. 12, No. 3, pp. 241-253, 2021.   DOI
7 Y. H. Lee and Y. S. Kim , "Comparison of CNN and YOLO for Object Detection," Journal of the Semiconductor & Display Technology, Vol. 19, No. 1, pp. 86-92, 2020.
8 Y. S. Kim, S. H. Lee and H. W. Kim , "Prediction Method of Photovoltaic Power Generation Based on LSTM Using Weather Information", Vol. 44, No. 12, pp. 2231-2238, 2019.
9 J. S. Sim and D. S. Song , "Effect of Atmospheric Particulate Matter Concentration on Solar Insolation," The Society Of Air-Conditioning And Refrigerating Engineers Of Korea, Pyeongchang : Yongpyeong Resort , pp. 167-170, 2019.