由於日照強度會因為雲層厚度、空氣霾害等問題而受到影響，進而造成太陽光電發電量的不穩定，所以能夠準確的預測日射量是件重要的事情。在本論文中使用具長短期記憶(LSTM)的遞迴類神經網路(RNN)進行日射量的預測。首先建置一日射量紀錄系統，及天空影像採集系統，這兩種系統將記錄每天的日射量及天空影像變化，並儲存於MySQL資料庫。在天空影像方面，利用影像處理方法萃取出天空影像的特徵值，之後將影像特徵值與日射量做為LSTM遞迴類神經網路(LSTM-RNN) 輸入 ，以進行預測。最後，本文以領前五分鐘至六十分鐘進行日射量預測，並進行許多方法比較，以驗證本文所提方法的預測效能。

Since solar irradiance is affected by factors, such as the thickness of the clouds and the air pollution. These factors can cause instability in solar power generation. Therefore, it is important to be able to accurately predict the amount of solar irradiance. In this paper, recurrent neural networks (RNNs) with long short-term memory (LSTM) are used to develop a solar irradiance forecasting. First, a solar irradiance recording system and a sky image capture system were built. The two systems record daily solar irradiance and sky images, and then store them in the MySQL database. For sky images, some processing methods are used to obtain the feature values. The feature values and the solar irradiance amount are inputs of the LSTM recurrent neural networks (LSTM-RNN). Finally, the solar irradiance forecasting with lead times of 5 to 60 minutes is presented, and then some comparison results are conducted in order to verify the performance of the proposed method in this paper.

參考文獻
[1] Ahsen Ulutaş, Recep Çakmak, and İsmail Hakkı Altaş, “Hourly Solar Irradiation Prediction by Artificial Neural Network Based on Similarity Analysis of Time Series,” 2018 Innovations in Intelligent Systems and Applications Conference (ASYU), pp. 1-6, 2018.
[2] Stephen M. Ruffing, Ganesh K, and Venayagamoorthy, “Short to Medium Range Time Series Prediction of Solar Irradiance Using an Echo State Network,” 2009 15th International Conference on Intelligent System Applications to Power Systems, pp. 1-6, 2009.
[3] H. Nazaripouya, B. Wang, Y. Wang, P. Chu, H. R. Pota, and R. Gadh, “Univariate time series prediction of solar power using a hybrid wavelet-ARMA-NARX prediction method,” 2016 IEEE/PES Transmission and Distribution Conference and Exposition (T&D), pp. 1-5, 2016.
[4] Rui Huang, Tiana Huang, Rajit Gadh, and Na Li, “Solar generation prediction using the ARMA model in a laboratory-level micro-grid,” 2012 IEEE Third International Conference on Smart Grid Communications (SmartGridComm), pp. 528-533, 2012.
[5] Ilhami Colak, Mehmet Yesilbudak, Naci Genc, and Ramazan Bayindir, “Multi-period Prediction of Solar Radiation Using ARMA and ARIMA Models,” 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA), pp. 1045-1049, 2015.
[6] Ji Wu and C.K. Chan, “The Prediction of Monthly Average Solar Radiation with TDNN and ARIMA,” 2012 11th International Conference on Machine Learning and Applications, vol. 2, pp. 469.474, 2012.
[7] Md. Ziaul Hassan, Md. Erfan Khandakar Ali, A B M Shawkat Ali, and Jashnil Kumar, “Forecasting Day-Ahead Solar Radiation Using Machine Learning Approach,” 2017 4th Asia-Pacific World Congress on Computer Science and Engineering (APWC on CSE), pp. 252-258, 2017.
[8] Xiaoyan Shao, Siyuan Lu, and Hendrik F. Hamann, “Solar radiation forecast with machine learning,” 2016 23rd International Workshop on Active-Matrix Flatpanel Displays and Devices (AM-FPD), pp. 19-22, 2016.
[9] Xiyun Yang, Feifei Jiang, and Huan Liu, “Short-term solar radiation prediction based on SVM with similar data,” 2nd IET Renewable Power Generation Conference (RPG 2013), pp. 1-4, 2013.
[10] Han Seung Jang, Kuk Yeol Bae, Hong-Shik Park, and Dan Keun Sung, “Solar Power Prediction Based on Satellite Images and Support Vector Machine,” IEEE Transactions on Sustainable Energy, vol. 7, pp.1255-1263, 2016.
[11] F. Bellocchio, S. Ferrari, M. Lazzaroni, L. Cristaldi, M. Rossi, T. Poli, and R. Paolini, “Illuminance prediction through SVM regression,” 2011 IEEE Workshop on Environmental Energy and Structural Monitoring Systems, pp. 1-5, 2011.
[12] B.M. Alluhaidah, S.H. Shehadeh, and M.E. El-Hawary, “Most Influential Variables for Solar Radiation Forecasting Using Artificial Neural Networks,” 2014 IEEE Electrical Power and Energy Conference, pp. 71-75, 2014.
[13] Ke-Hung Lee, Ming-Wei Hsu, and Yih-Guang Leu, “Solar Irradiance Forecasting Based on Electromagnetism-like Neural Networks,” 2018 1st IEEE International Conference on Knowledge Innovation and Invention (ICKII), pp. 365-368, 2018.
[14] Aslam Muhammad, Jae Myoung Lee, Sug Won Hong, Seung Jae Lee, and Eui Hyang Lee, “Deep Learning Application in Power System with a Case Study on Solar Irradiation Forecasting,” 2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC), pp. 275-279, 2019.
[15] Rui Zhang, Minwei Feng, Wei Zhang, Siyuan Lu, and Fei Wang, “Forecast of Solar Energy Production - A Deep Learning Approach,” 2018 IEEE International Conference on Big Knowledge (ICBK), pp. 72-82, 2018.
[16] Murat Cihan Sorkun, Christophe Paoli, and Özlem Durmaz Incel, “Time series forecasting on solar irradiation using deep learning,” 2017 10th International Conference on Electrical and Electronics Engineering (ELECO), pp. 151-155, 2017.
[17] Kunjin Chen, Ziyu He, Kunlong Chen, Jun Hu, and Jinliang He, “Solar energy forecasting with numerical weather predictions on a grid and convolutionalnetworks,” 2017 IEEE Conference on Energy Internet and Energy System Integration (EI2), pp. 1-5, 2017.
[18] Ahmad Alzahrani, Pourya Shamsi, Mehdi Ferdowsi, and Cihan Dagli, “Solar irradiance forecasting using deep recurrent neural networks,” 2017 IEEE 6th International Conference on Renewable Energy Research and Applications (ICRERA), pp. 988-994, 2017.
[19] Sakshi Mishra and Praveen Palanisamy, “Multi-time-horizon Solar Forecasting Using Recurrent Neural Network,” 2018 IEEE Energy Conversion Congress and Exposition (ECCE), pp. 18-24, 2018.
[20] I.Reda and A.Andreas, Solar position algorithm for solar radiation applications, NREL, 2008.
[21] 公式參考：:http://www.pveducation.org/
[22] Avijit Kundu, “Modified block matching algorithm for fast block motion estimation,” 2010 International Conference on Signal and Image Processing, pp. 260-264, 2010
[23] Madhuri Bamankar, P. Muralidhar, and C. B. Ramarao, “Modified full search block matching algorithm,” 2013 Fourth International Conference on Computing, Communications and Networking Technologies (ICCCNT), pp. 1-4, 2013
[24] H. M. Jong, L. Gee, and T. D. Chiueh, "Parallel Architectures for 3-Step Hierarchical Search Block-Matching Algorithm," IEEE Transactions on Circuits and Systems for Video Technology, vol. 4, pp. 407 - 416, Aug. 1994.
[25] C. J. Duanmu, “Fast Scheme for the Four-Step Search Algorithm in Video Coding,” 2006 IEEE International Conference on Systems, Man and Cybernetics, vol. 4, pp. 3181-3185, 2006.
[26] N. A. Hamid, A. M, Darsono, N.A. Manap, R. A. Manap, and H. A. Sulaiman, “A new Orthogonal - Diamond Search algorithm for Motion Estimation,” 2014 International Conference on Computer, Communications, and Control Technology (I4CT), pp. 467-471, 2014
[27] 林大貴，TensorFlow+Keras深度學習人工智慧實務應用，博碩文化股份有限公司，2017。
[28] Jeffrey L. Elman, "Finding Structure in Time," Cognitive Science, vol. 14, no. 2, pp. 179-211, 1990.
[29] Sepp Hochreiter and Jürgen Schmidhuber, "Long Short-Term Memory," Neural Computation, vol. 9, no. 8, pp. 1735-1780, 1997.
[30] 徐銘偉，“以類電磁為基礎之類神經網路技術應用於太陽能預測”，國立台灣師範大學電機工程學系，碩士論文，2017
[31] Embedded Linux Wiki https://elinux.org/RPi_USB_Webcams
[32] 林震岩，多變量分析SPSS的操作與應用，智勝文化事業有限公司，2007。