本論文探討使用類電磁演算法優化類神經網路並應用於日射量預測問題。首先，建置一日射量資料平台以收集日射量預測所需相關數據，該日射量資料平台設備包括日射計、單板電腦(single-board computer)、攝影機與雲端伺服器等。藉由整合該日射量資料平台設備以即時擷取日射量與當前天空之影像圖，並儲存於雲端伺服器MySQL資料庫。利用該資料庫日射量與天空之影像圖資料，建立一即時日射量類神經網路預測系統，該日射量類神經網路預測系統可領前1至6小時預測日射量。為了使預測結果更加準確，透過類電磁演算法的改造與改良，使該演算法可以用於優化該類神經網路預測系統。最後，將本文所提之類電磁神經網路和傳統類神經網路進行預測誤差比較，以驗證本文所提之類電磁神經網路之效能。

In the thesis, a solar irradiance forecasting system is developed by using an electromagnetism-like neural network. The hardware of the solar irradiance forecasting system includes a pyranometer, single-board computer, webcam and cloud server. The hardware devices are used to collect and store the solar data, including solar irradiance data and sky images. The electromagnetism-like mechanism algorithm is improved and involved in the neural network in order to increase the forecasting efficiency. The input features of the neural network includes real-time sky and solar irradiance data and past solar irradiance data. Based on the trained neural network, the solar irradiance forecasting system can calculate the hourly 1-6 hours ahead solar irradiance values. Finally, some comparison results are given to verify the efficiency of solar irradiance forecasting system.

[1] G. Reikard,“Predicting solar radiation at high resolutions: A comparison of time series forecasts,” Solar Energy, vol. 83, pp.342-349, 2009.
[2] P. Bacher, H. Madsen, and HA. Nielsen, “Online short-term solar power forecasting,” Solar Energy, vol. 83, pp.1772-1783, 2009. .
[3] J. Boland, Modeling Solar Radiation at the Earth’s Surface: Time Series Modelling of Solar Radiation, pp.283-312, 2008.
[4] I. Colak, M. Yesilbudak, N. Genc and R. Bayindir, "Multi-period prediction of solar radiation using ARMA and ARIMA models," 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA), 2015, pp. 1045-1049.
[5] Y. Kemmoku, S. Orita, S. Nakagawa, and T. Sakakibara, “Daily Insolation Forecasting Using a Multi-Stage Neural Network” Solar Energy, vol. 66, no. 3, pp.193-199, 1999.
[6] A. Sfetsos and A. Cooknick,“Univariate and multivariate forecasting of hourly solar radiation with artificial intelligence techniques,” Solar Energy, vol. 68, no. 2, pp.169-178, 2000.
[7] G. Mihalakakou, M. Santamouris, and D. N. Asimakopoulos, “The total solar radiation time series simulation in Athens, using neural networks, ”Theoretical and Applied Climatology, vol. 66, pp.185-197, Aug, 2000.
[8] F.O. Hocaoglu, O.N. Gerek, and M. Kurban, “Hourly solar radiation forecasting using optimal coefficient 2-D linear filters and feed-forward neural networks,” Solar Energy, vol. 82, pp.714-726, 2008.
[9] 盧苹源，“應用類神經網路技術在金門風場之長時間風力發電預測”，國立台灣師範大學工業教育學系，碩士論文，2013
[10] 穆格銘，“倒傳遞類神經網路技術應用於太陽能發電預測”，國立台灣師範大學工業教育學系，碩士論文，2016
[11] F. Almonacid, P. J. P. -Higueras, E. F. Fernández, and L. Hontoria, "A methodology based on dynamic artificial neural network for short-term forecasting of the power output of a PV generator," Energ. Convers. Manage., vol. 85, pp. 389-398, Sept. 2014.
[12] A. Mellit, M. Benghanem, and S.A. Kalogirou, “An adaptive wavelet-network model for forecasting daily total solar-radiation”Applied Energy, vol. 83, pp.705-722, 2006.
[13] J. Cao and X. Lin,“Application of the diagonal recurrent wavelet neural network to solar irradiation forecast assisted with fuzzy technique” Engineering Applications of Artificial Intelligence, vol. 21, pp.1255-1263, 2008.
[14] Ş. İ. Birbil and S.-C. Fang, "An Electromagnetism-like Mechanism for Global Optimization," Journal of Global Optimization, vol. 25, pp. 263-282, 2003.
[15] J. Cao and X. Lin,“Application of the diagonal recurrent wavelet neural network to solar irradiation forecast assisted with fuzzy technique” Engineering Applications of Artificial Intelligence, vol. 21, pp.1255-1263, 2008.
[15] F. K. Chang and C. H. Lee, "Design of Fractional PID Control via Hybrid of Electromagnetism-Like and Genetic Algorithms," 2008 Eighth International Conference on Intelligent Systems Design and Applications, Kaohsiung, 2008, pp. 525-530.
[16] W. Yaonan, Y. Yimin, Y. Xiaofang, Y. Feng and W. Shuning, "A Model Predictive Control Strategy for Path-Tracking of Autonomous Mobile Robot Using Electromagnetism-Like Mechanism,"Electrical and Control Engineering (ICECE), 2010 International Conference on, Wuhan, 2010, pp. 96-100.
[17] P. Wu, K. J. Yang and B. Y. Huang, "A Revised EM-like Mechanism for Solving the Vehicle Routing Problems," Innovative Computing, Information and Control, 2007. ICICIC '07. Second International Conference on, Kumamoto, 2007, pp. 181-181.
[18] J. C. Chen, "Partial transmit sequences for PAPR reduction of OFDM signals with stochastic optimization techniques," in IEEE Transactions on Consumer Electronics, vol. 56, no. 3, pp. 1229-1234, Aug. 2010.
[19] S. Yun, "Research of Big Data Analysis on Rough Set and Electromagnetism-Like Mechanism Algorithm," Computer and Information Technology (CIT), 2014 IEEE International Conference on, Xi'an, 2014, pp. 923-926.
[20] 張富凱，“結合類電磁與倒傳遞演算法設計遞迴式模糊類神經系統”，私立元智大學電機工程學系，碩士論文，2008
[21] Qing Wu, Chun-Jiang Zhang, L. Gao and X. Li, "Training neural networks by electromagnetism-like mechanism algorithm for tourism arrivals forecasting," Bio-Inspired Computing: Theories and Applications (BIC-TA), 2010 IEEE Fifth International Conference on, Changsha, 2010, pp. 679-688..
[22] Raspberry Pi台灣樹莓派 https://www.raspberrypi.com.tw/
[23]樹梅派 wiki https://zh.wikipedia.org/wiki/%E6%A0%91%E8%8E%93%E6%B4%BE
[24] Embedded Linux Wiki http://elinux.org/RPi_USB_Webcams
[25]Logitech官方網站 http://support.logitech.com/zh_tw/product/webcam-c170
[26]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。