隨著環保意識提升，太陽能源的發展日漸興起，臺灣整體年均日照長，發展條件良好，並配合智慧電網的應用，能夠把間歇性的太陽能源轉換成穩定可隨時調度的電力，使電力系統變得更加彈性。
由於，太陽能光電系統的產電量主要受到太陽輻射量的影響，因此，針對太陽輻射量的預測進行深入的研究，不同於傳統統計學，本論文採用深度學習的方式，使用卷積神經網路與長短期記憶模型，根據歷史輻射量資訊，對未來逐小時平均太陽輻射強度做預測，利用卷積神經網路提取特徵的特性，以及長短期記憶模型適合預測時間序列資料的特性，提出此兩種架構的混和模型。
本論文致力於長時間的預測，包括預測1日、3日與7日後之太陽輻射量，此外，結合天氣資訊，使預測結果更加準確，然而，考慮到需預測未來的日輻射量，會有缺乏實際觀測天氣數據的狀況，而採用天氣預報的資訊作為判斷標準，預報天氣資訊亦能夠幫助模型預測，以上實驗驗證於臺灣北部與南部地區的案場，證實提出的方法能夠適用於臺灣不同地區的氣候，並且有良好的效果。

With the increasing awareness of environmental protection, the development of solar power has become more popular. In Taiwan, there has been a great potential to develop solar power due to high annual sunlight. With the application of smart grid, we can build a more flexible power system by converting the intermittent solar energy into a more stable and ready to use energy.
Because solar radiation is the main factor effecting the power generation of photovoltaic system, therefore the research on the prediction of solar radiation is necessity. Different from the traditional statistic methods, this paper is using a deep learning method in conducting the research. We propose a model using convolutional neural network and long short-term memory, based on the historical solar radiation data to predict the hourly average solar irradiance in the future. This hybrid method is a result of using the unique features of convolutional neural network and the suitable long short-term memory prediction on time series of solar data.
This paper is dedicated to the long-term prediction of solar radiation, including the prediction in one, three and seven days ahead. Besides, the prediction accuracy of our model is increased by combining the meteorological information. Considering that there will be a lack of actual weather information, we have shown that the use of weather forecast information is still helpful for prediction modelling. The above experiments were done at various locations in the north and south of Taiwan. Our model has yielded a good result and is suitable for different weather condition in Taiwan.

[1] 科技新報：十年來台灣太陽能發電量成長近九成，成為第二綠電主力。2019年12月16日，取自http://technews.tw/2019/12/16/taiwan-solar-power-generation/
[2] EnergyTrend：2025年台灣太陽能安裝目標高，能源新政改革面向廣。2016年02月17日，取自https://www.energytrend.com.tw/research/20160217-13335.html
[3] 泛科學：【還能怎樣】林法正：智慧電網與再生能源。2014年11月25日，取自https://pansci.asia/archives/71670
[4] Mohamed Abuella and Badrul Chowdhury. “Solar power probabilistic forecasting by using multiple linear regression analysis.” SoutheastCon 2015. IEEE, 1-5, 2015.
[5] Cheng, Hsu-Yung. “Hybrid solar irradiance now-casting by fusing Kalman filter and regressor.” Renewable Energy 91, 434-441, 2016.
[6] J Schmidhuber. “Deep learning in neural networks: An overview.” Neural networks, 61, 85-117, 2015.
[7] Yinghao Chu, Hugo T.C. Pedro, Mengying Li, and Carlos F.M. Coimbra. “Real-time forecasting of solar irradiance ramps with smart image processing.” Solar Energy, 114, 91-104, 2015.
[8] A. Mellit, S.A. Kalogirou, S. Shaari, H. Salhi , and A. Hadj Arab. “Methodology for predicting sequences of mean monthly clearness index and daily solar radiation data in remote areas: Application for sizing a stand-alone PV system.” Renewable Energy, 33(7), 1570-1590, 2008.
[9] T. C. McCandless, S. E. Haupt, and G. S Young. “A regime-dependent artificial neural network technique for short-range solar irradiance forecasting.” Renewable Energy, 89, 351-359, 2016.

[10] F. O. Hocaoğlu, Ömer N. Gerek, and Mehmet Kurban. “Hourly solar radiation forecasting using optimal coefficient 2-D linear filters and feed-forward neural networks.” Solar energy, 82(8), 714-726, 2008.
[11] Shuanghua Cao, and Jiacong Cao. “Forecast of solar irradiance using recurrent neural networks combined with wavelet analysis.” Applied Thermal Engineering, 25(2-3), 161-172, 2005.
[12] Jiacong Cao, and Xingchun Lin. “Application of the diagonal recurrent wavelet neural network to solar irradiation forecast assisted with fuzzy technique.” Engineering Applications of Artificial Intelligence, 21(8), 1255-1263, 2008.
[13] A. Mellit, M. Benghanem, and S. A. Kalogirou. “An adaptive wavelet-network model for forecasting daily total solar-radiation.” Applied Energy, 83(7), 705-722, 2006.
[14]David E.Rumelhart, Geoffrey E. Hinton, and Ronald J. Williams. “Learning representations by back-propagating errors.” nature, 323(6088), 533-536, 1986.
[15] Ah Chung Tsoi. “Recurrent neural network architectures: an overview.” In International School on Neural Networks, Initiated by IIASS and EMFCSC (pp. 1-26). Springer, Berlin, Heidelberg, 1997.
[16] Kyunghyun Cho, Bart van Merrienboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. “Learning phrase representations using RNN encoder-decoder for statistical machine translation.” arXiv preprint arXiv:1406.1078, 2014.
[17] Junyoung Chung, Caglar Gulcehre, KyungHyun Cho, and Yoshua Bengio. “Empirical evaluation of gated recurrent neural networks on sequence modeling.” arXiv preprint arXiv:1412.3555, 2014.
[18] S. Hochreiter, and J Schmidhuber. “Long short-term memory.” Neural computation, 9(8), 1735-1780, 1997.

[19] J Cheng, L Dong, and M Lapata. “Long short-term memory-networks for machine reading.” arXiv preprint arXiv:1601.06733, 2016.
[20] Bixuan Gao, Xiaoqiao Huang, Junsheng Shi, Yonghang Tai, and Rui Xiao. “Predicting day-ahead solar irradiance through gated recurrent unit using weather forecasting data.” Journal of Renewable and Sustainable Energy, 11(4), 043705, 2019.
[21] Xiangyun Qing, and Yugang Niu. “Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM.” Energy, 148, 461-468, 2018.
[22] Ping-Huan Kuo, Chiou-Jye Huang. “A green energy application in energy management systems by an artificial intelligence-based solar radiation forecasting model.” Energies, 11(4), 819, 2018.
[23] Corinna Cortes and Vladimir Vapnik. “Support-vector networks.” Machine learning, 20(3), 273-297, 1995.
[24] Tin Kam Ho. “Random decision forests.” In Proceedings of 3rd international conference on document analysis and recognition (Vol. 1) IEEE, pp. 278-282, 1995.
[25] S. R. Safavian, and D Landgrebe. “A survey of decision tree classifier methodology.” IEEE transactions on systems, man, and cybernetics, 21(3), 660-674, 1991.
[26] Sujan Ghimire, Ravinesh C. Deo, Nawin Raj, Jianchun Mi. “Deep solar radiation forecasting with convolutional neural network and long short-term memory network algorithms.” Applied energy, 253, 113541, 2019.
[27] K Fukushima. “Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position.” Biological cybernetics, 36(4), 193-202, 1980.
[28] Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, and L. D Jackel. “Backpropagation applied to handwritten zip code recognition.” Neural computation, 1(4), 541-551, 1989.

[29] CWB Observation Data Inquire System 觀測資料查詢，取自https://e-service.cwb.gov.tw/HistoryDataQuery/index.jsp
[30] Weather.com，取自https://weather.com/
[31] 詹麒璋、曾美惠、徐國昌、盧明德、鄭旭詠、黃宇睿，“使用類神經網路並結合氣象資料應用在日射量預測”，2020 National Symposium on System Science and Engineering，Taichung，Taiwan，22~23 May，2020