臺灣博碩士論文加值系統

太陽能發電儼然已經成為了再生能源中最重要的角色，而台灣政策也不斷地朝向非核家園邁進，對於太陽能發電的遠景相當看好，然而再生能源本身的間歇性和不穩定性一直以來都是大家所關心的議題，因此預測太陽能發電量也成為了相當熱門的研究目標。而在多數的機器學習方法中，類神經網路的相關模型卻是近幾年才開始逐漸被大家所使用，但中具有記憶性的LSTM模型之相關研究也十分有限。本研究將針對以日特徵（24小時）為基礎之LSTM預測方法進行探討，取代以往以季節特徵（365天）為基礎之預測模型，進而對下一小時進行太陽能發電量預測。將情境設定在短時間內的發電量以及有限數據集(6個月)的情況下提升準確率。此外，本研究提出針對不同時間步數各自選取不同高影響性之特徵（features）之方法，藉以強化LSTM對輸入樣本（samples）之時間相依性之特徵學習，進而提高預測準確率。藉由案場所收集之實際樣本資料進行實驗，在使用相同數據集之情形下，結果顯示其決定係數（coefficient of determination）效能可從原92–95%之準確率提升至94–95.5%。

Solar photovoltaic (PV) generation has received great attention in recent years due to the promotion of green environment awareness. Accurate forecasting of solar power benefits the preparation for switching other renewable energies into the power grids when PV power becomes low. In particular, the harmful consequence from the large peak and off-peak gaps of the so-called “duck curve” for PV power can be mitigated. Motivated by the fact that the contingency reserve typically requires thirty to sixty minutes to start up, we mainly focus on the PV power prediction at the hourly level.
Among numerous studies in the literature dealing with solar power forecasting via various machine learning methods, the application of long short-term memory (LSTM) on hourly PV power prediction has been recently proposed to capture both hourly patterns in a day and seasonal patterns across days. For hourly prediction, however, we argue that the contribution of seasonal factors might be marginal since the correlation of meteorological information between days is much higher than between years. In this paper, we consider the LSTM-based hourly PV power prediction with the daily factor (24 hours) instead of the seasonal factor (day and month) and improve the pattern learning by selecting the highly-effective features toward the different number of time steps. This design is to enhance the information of time-dependency between each set of training input which is crucial for hourly prediction. By using the real-world data, the experimental results show that the accuracy of hourly PV power prediction can improve from 92–95% to 94–95.5% in terms of coefficient of determination (R2) whilst using the same dataset.

英文摘要Ⅰ
中文摘要Ⅱ
目錄Ⅲ
圖目錄Ⅴ
表目錄Ⅵ
第壹章 緒論1
1.1緒言 1
1.2研究動機與目標 1
1.3論文結構 2
第貳章 太陽能發電 3
2.1 前言 3
2.2太陽能發電基本原理 3
2.3太陽能發電近年發展狀況 4
2.4太陽能發電預測 8
第參章 類神經網路與LSTM模型 10
3.1 前言 10
3.2類神經網路 10
3.3倒傳遞神經網路(Back-propagation Neural Network) 15
3.4 具有記憶性的類神經網路模型RNN與LSTM 18
3.4.1 RNN(Recurrent Neural Network) 19
3.4.2 LSTM (Long Short-Term Memory) 20

第肆章 基於LSTM架構之改良式預測模型 25
4.1 前言 25
4.2 基於LSTM的每小時太陽能預測模型 25
4.3 資料處理以及標準化 27
4.4 特徵與發電量相關係數計算與選擇 27
第伍章 實驗設計與模擬結果 30
5.1 數據來源與程式語法 30
5.2 實驗設計與結果 30
5.3 本研究之預測值與實際值比較 32
第陸章 總結 35
6.1 模型結果之比較 35
6.2 結論 36
6.3 未來的研究工作 37
參考文獻 37

[1]經濟部能源局, “新及再生能源推動配套方案,” 17-Jan-2018.
[2]吳進忠, “再生能源併聯運轉對電力調度的挑戰與機會,” 08-Aug-2018.
[3]U. K. Das et al., “Forecasting of photovoltaic power generation and model optimization: A review,” Renew. Sustain. Energy Rev., vol. 81, pp. 912–928, Jan. 2018.
[4]M. N. Akhter, S. Mekhilef, H. Mokhlis, and N. Mohamed Shah, “Review on forecasting of photovoltaic power generation based on machine learning and metaheuristic techniques,” IET Renew. Power Gener., vol. 13, no. 7, pp. 1009–1023, May 2019.
[5]F. O. Hocaoğlu, Ö. N. Gerek, and M. Kurban, “Hourly solar radiation forecasting using optimal coefficient 2-D linear filters and feed-forward neural networks,” Sol. Energy, vol. 82, no. 8, pp. 714–726, Aug. 2008.
[6]A. Mellit, H. Eleuch, M. Benghanem, C. Elaoun, and A. M. Pavan, “An adaptive model for predicting of global, direct and diffuse hourly solar irradiance,” Energy Convers. Manag., vol. 51, no. 4, pp. 771–782, Apr. 2010.
[7]W. Ji and K. C. Chee, “Prediction of hourly solar radiation using a novel hybrid model of ARMA and TDNN,” Sol. Energy, vol. 85, no. 5, pp. 808–817, May 2011.
[8]P. Mandal, S. T. S. Madhira, A. U. haque, J. Meng, and R. L. Pineda, “Forecasting Power Output of Solar Photovoltaic System Using Wavelet Transform and Artificial Intelligence Techniques,” Procedia Comput. Sci., vol. 12, pp. 332–337, 2012.
[9]R. Marquez, V. G. Gueorguiev, and C. F. M. Coimbra, “Forecasting of Global Horizontal Irradiance Using Sky Cover Indices,” J. Sol. Energy Eng., vol. 135, no. 1, p. 011017, Feb. 2013.
[10]C. Voyant, P. Randimbivololona, M. L. Nivet, C. Paoli, and M. Muselli, “Twenty four hours ahead global irradiation forecasting using multi-layer perceptron: Twenty four hours ahead global irradiation forecasting,” Meteorol. Appl., vol. 21, no. 3, pp. 644–655, Jul. 2014.
[11]V. Sharma, D. Yang, W. Walsh, and T. Reindl, “Short term solar irradiance forecasting using a mixed wavelet neural network,” Renew. Energy, vol. 90, pp. 481–492, May 2016.
[12]V. Cherkassky and Y. Ma, “Practical selection of SVM parameters and noise estimation for SVM regression,” Neural Netw., vol. 17, no. 1, pp. 113–126, Jan. 2004.
[13]G. Rubio, H. Pomares, I. Rojas, and L. J. Herrera, “A heuristic method for parameter selection in LS-SVM: Application to time series prediction,” Int. J. Forecast., vol. 27, no. 3, pp. 725–739, Jul. 2011.
[14]M. Bouzerdoum, A. Mellit, and A. Massi Pavan, “A hybrid model (SARIMA–SVM) for short-term power forecasting of a small-scale grid-connected photovoltaic plant,” Sol. Energy, vol. 98, pp. 226–235, Dec. 2013.
[15]W. Lee, K. Kim, J. Park, J. Kim, and Y. Kim, “Forecasting Solar Power Using Long-Short Term Memory and Convolutional Neural Networks,” IEEE Access, vol. 6, pp. 73068–73080, 2018.
[16]D. Lee and K. Kim, “Recurrent Neural Network-Based Hourly Prediction of Photovoltaic Power Output Using Meteorological Information,” Energies, vol. 12, no. 2, p. 215, Jan. 2019.
[17]“觀測資料查詢系統.” [Online]. Available: https://e-service.cwb.gov.tw/HistoryDataQuery/index.jsp. [Accessed: 02-Jul-2019].
[18]“sklearn.linear_model.LinearRegression — scikit-learn 0.21.2 documentation.” [Online]. Available: https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LinearRegression.html. [Accessed: 02-Jul-2019].
[19]“3.2.4.3.2. sklearn.ensemble.RandomForestRegressor — scikit-learn 0.21.2 documentation.” [Online]. Available: https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.RandomForestRegressor.html. [Accessed: 02-Jul-2019].
[20]“3.2.4.3.6. sklearn.ensemble.GradientBoostingRegressor — scikit-learn 0.21.2 documentation.” [Online]. Available: https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.GradientBoostingRegressor.html. [Accessed: 02-Jul-2019].
[21]“Simple deep MLP with Keras.” [Online]. Available: https://kaggle.com/fchollet/simple-deep-mlp-with-keras. [Accessed: 02-Jul-2019].