本論文使用全天空影像進行分析，來發展雲層為特徵的日射量估計與預測系統。在全天空影像中，使用紅藍比例法擷取雲層特徵影像，使用自適應閾值在不同亮度的情況下更精確判定雲層資訊計算雲層整張圖的占比，以及太陽周圍雲特徵分析，透過RAFT (Recurrent All-Pairs Field Transforms)光流法推估雲層移動情形，製作未來數分鐘至小時之雲層情況，並提取雲層特徵，作為生成式對抗網路(GAN)模型之輸入，日射計測出之日射量為輸出。並使用三個評估指標來查看模型學習的狀況，有相對均方根誤差(rRMSE)、相對絕對平均誤差(rMAE)、預測技巧(FS)比較估計及預測成果。

This study analyzes all-sky images to develop a cloud feature irradiance estimation and prediction system. In the all-sky images, the red-blue ratio method is used to extract cloud feature images, while adaptive thresholding enables more accurate cloud information detection under varying brightness conditions. The system calculates the cloud coverage ratio for the entire image and analyzes cloud features around the sun. The RAFT (Recurrent All-Pairs Field Transforms) method of estimating cloud movement produces forecasts of cloud conditions for the next few minutes to hours. Cloud features are extracted and used as input for a Generative Adversarial Network (GAN) model with solar irradiance measured by a pyranometer as output. Three evaluation metrics—relative root mean square error (rRMSE), relative mean absolute error (rMAE), and forecasting skill (FS)—are used to assess the model's performance in estimation and prediction tasks.

[1] B. Pillot, M. Muselli, P. Poggi, and J. B. Dias, “On the impact of the global energy policy framework on the development and sustainability of renewable power systems in Sub-Saharan Africa: The case of solar PV,” Renewable Energy, vol. 114, pp. 58-72, Mar. 2017.
[2] A. M. Bunea, P. Manfredi, P. Della Posta, and M. Guidolin, “What do adoption patterns of solar panels observed so far tell about governments' incentive? Insight from diffusion models,” Renewable and Sustainable Energy Reviews, vol. 112, pp. 549-559, Jan. 2019.
[3] A. Al-lahham, O. Theeb, K. Elalem, T. A. Alshawi, and S. A. Alshebeili, “Sky imager-based forecast of solar irradiance using machine learning,” Renewable Energy, vol. 171, pp. 819-829, Oct. 2023.
[4] J. Zhang, R. Verschae, S. Nobuhara, and J. F. Lalonde, “Deep photovoltaic nowcasting,” IEEE Transactions on Sustainable Energy, vol. 9, no. 4, pp. 1647-1655, Nov. 2018.
[5] M. Zakroum, M. Ghogho, M. Faqir, and M. A. Ahajjam, “Deep learning for inferring the surface solar irradiance from sky imagery,” Renewable and Sustainable Energy Reviews, vol. 82, pp. 3470-3481, Jan. 2019.
[6] R. J. Adrian, “Particle-Imaging Techniques for Experimental Fluid Mechanics,” Annual Review of Fluid Mechanics, vol. 23, no. 1, pp.261-304, Jan. 1991.
[7] Z. Teed, J. Deng, "RAFT: Recurrent All-Pairs Field Transforms for Optical Flow," European Conference on Computer Vision (ECCV), vol. 12347, pp. 402–419, 2020.
[8] D. P. Kingma and M. Welling, “Auto-Encoding Variational Bayes,” International Conference on Learning Representations (ICLR), 2014.
[9] I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative Adversarial Nets,” Advances in Neural Information Processing Systems (NeurIPS), vol. 27, pp. 2672–2680, 2014.
[10] A. B. L. Larsen, S. K. Sønderby, H. Larochelle, and O. Winther, “Autoencoding beyond pixels using a learned similarity metric,” International Conference on Machine Learning (ICML), vol. 48, pp. 1558–1566, Jun. 2016.
[11] C. W. Chow, B. Urquhart, M. Lave, A. Dominguez, J. Kleissl, J. Shields and B. Washom, “Intra-hour forecasting with a total sky imager at the UC San Diego solar energy testbed,” Solar Energy, vol. 85, no. 11, pp. 2881-2893, Nov. 2011.
[12] J. Polo, L. F. Zarzalejo, L. Ramirez, and B. Espinar, “Iterative filtering of ground data for qualifying statistical models for solar irradiance estimation from satellite data,” Solar Energy, vol. 80, no. 3, pp. 240-247, Mar. 2006.
[13] P. Liu, X. Tong, J. Zhang, P. Meng, J. Li, and J. Zhang, “Estimation of half-hourly diffuse solar radiation over a mixed plantation in north China,” Renewable Energy, vol. 149, pp. 1360-1369, Oct. 2020.
[14] A. Alzahrani, P. Shamsi, M. Ferdowsi, and C. Dagli, "Solar irradiance forecasting using deep recurrent neural networks," in 2017 IEEE 6th international conference on renewable energy research and applications (ICRERA), pp. 988-994. 2017.
[15] S. Mishra and P. Palanisamy, "Multi-time-horizon solar forecasting using recurrent neural network," in 2018 IEEE Energy Conversion Congress and Exposition (ECCE), pp. 18-24. 2018.
[16] S. Srivastava and S. Lessmann, "A comparative study of LSTM neural networks in forecasting day-ahead global horizontal irradiance with satellite data," Solar Energy, vol. 162, pp. 232-247, 2018.
[17] X. Qing and Y. Niu, "Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM," Energy, vol. 148, pp. 461-468, 2018.
[18] Z. D. Jones, “Machine learning for solar irradiance forecasting,” Master's thesis, University of Georgia, May 2019.
[19] D. Yang, Z.Ye, "Very short term irradiance forecasting using the lasso, "Sol Energy vol.114, pp. 314-316, 2015.
[20] N. Engerer , "Minute resolution estimates of the diffuse fraction of global irradiance for southeastern Australia, " Sol Energy vol.116, pp. 215-237, 2015.
[21] H. Jiang, Y. Dong, L. Xiao, "A multi_stage intelligent approach based on an ensemble of two-way interaction model for forecasting the global horizontal radiation of India, " Energy Convers Manage, vol. 137, pp. 142-154, 2017.
[22] L. Olatomiwa, "A support vector machine-firefly algorithm-based model for global solar radiation prediction" Sol Energy vol.115, pp. 632-644, 2015.
[23] P. Kumari ,D. Toshiwal, "Deep learning models for solar irradiance forecasting : A comprehensive review," Journal of Cleaner Production, vol.318 ,128566 ,2021.
[24] S. Sun et al., "Short term cloud coverage prediction using ground based all sky imager," in 2014 IEEE international conference on smart grid communications (SmartGridComm), pp. 121-126. 2014.
[25] A. Taravat, F. Del Frate, C. Cornaro, and S. Vergari, "Neural networks and support vector machine algorithms for automatic cloud classification of whole-sky ground-based images," IEEE Geoscience and remote sensing letters, vol. 12, no. 3, pp. 666-670, 2014.
[26] F. Xie, M. Shi, Z. Shi, J. Yin, and D. Zhao, "Multilevel cloud detection in remote sensing images based on deep learning," IEEE Journal of Selected Topics I Applied Earth Observations and Remote Sensing, vol. 10, no. 8, pp. 3631-3640, 2017.
[27] D. Aicardi, P. Musé and R. Alonso-Suárez, “A comparison of satellite cloud motion vectors techniques to forecast intra-day hourly solar global horizontal irradiation,” Solar Energy, vol. 233, pp 46-60, Feb. 2022.
[28] L. M. Aguiar, B. Pereira. P. Lauret, F. Diaz, M. David, "Combining solar irradiance measurements, satellite-derived data and a numerical weather prediction model to improve intra-day solar forecasting, " Renew. Energy 97, 599–610,2016.
[29] P. Kumari, R. Wadhvani, "Wind power prediction using KLMS algorithm, " in 2018 International Conference on Inventive Research in Computing Applications (ICIRCA). IEEE, pp. 154–161,2018.
[30] G. Corea, " Forecasting short-term solar irradiance based on artificial neural networks and data from neighboring meteorological stations, " Sol. Energy 134, 119–131,2016.
[31] M. Ozgoren, M. Bilgili, B. Sahin, " Estimation of global solar radiation using ANN over Turkey, " Expert Syst. Appl. 39 (5), 5043–5051,2012.
[32] 高碩，“區塊匹配應用於雲層移動估計之全天空影像與衛星雲圖日射量估計與預測系統”，國立臺灣師範大學電機工程學系碩士論文，2024年8月。
[33] S. Sun, E. Ritzhaupt-Kleissl and T. Chen, “Short term cloud coverage prediction using ground based all sky imager,” in IEEE International Conference on Smart Grid Communications, Venice, Italy, pp. 121-126. Jan. 2014.
[34] I. Reda and A. Andreas, “Solar position algorithm for solar radiation applications,” Solar Energy, vol. 76, no. 5, pp. 577-589, Jan. 2004.
[35] H. Dilantha, D. Daswin, S. Seppo, A. Damminda, N. Rashmika, J. Andrew and V. Valeriy, “Solar Irradiance Nowcasting for Virtual Power Plants Using Multimodal Long Short-Term Memory Networks,” Frontiers in Energy Research, vol. 9, Aug. 2021.
[36] T. P. Chu, J. H. Gou, Y. G. Leu and L. F. Chou, “Estimation of solar irradiance and solar power based on all-sky images,” Solar Energy, vol. 249, pp.495-506, Jan. 2023.
[37] 謝濟元，“基於Transformer之全天空影像進行估計與預測日射量之系統”，國立臺灣師範大學電機工程學系碩士論文，2023年8月。