臺灣博碩士論文加值系統

太陽能發電等再生能源隨著非再生能源的消耗日益重要，但如何決定優先建造的太陽能裝置的地點呢？透過一些高精密的儀器的測量結果，可以用來衡量一個地點是否適合太陽能發展，但其高精密儀器耗費太高，因此可以透過預測的方式，作為判斷一個地點是否適合發展太陽能的根據。

本研究利用太陽能發電量數據與氣象局網站資料，資料時間範圍從2015年1月1日到2015年12月29日，經過合併資料、篩選變數、建立多個預測模型，利用類神經網路與支援向量機等演算法，多次反覆訓練模型，並調整隱藏層神經元個數與核函數，藉此找出預測台灣太陽能發電量的最佳模型。

研究結果發現使用類神經網路預測台灣地區太陽能發電量較為準確，並且從原先十六個變數中，去除影響程度較低、資料取得困難的變數，最後十個變數的模型7(MAPE: 12.25%)有最佳預測結果。同時期盼台灣能有更多的太陽能發電量數據與其他外在因素、氣象資料，以便能有更加精準的模型與預測結果。

Renewable energy such as solar power is becoming increasingly important as the consumption of non-renewable energy, but how to decide on the location of the solar energy plant? Though we can make the decision from the measurement of some high-precision instruments, it costs a lot. Apart from that, we thus can use prediction model for judging whether a location is suitable for the development of solar energy.

In this study, we use the solar energy data and the data of the Central Weather Bureau, and the data interval is from January 1, 2015 to December 29, 2015, then through the merger of data, screening variables, and the establishment of multiple prediction models. Then we use neural networks, support vector machines and other algorithms. Repeat training model, and adjust the hidden layer of nerve Meta-number and kernel function, to find out the best model for predicting the amount of solar power in Taiwan.

The results show that the use of neural networks to predict the amount of solar power in Taiwan is more accurate. Besides, from original sixteen variables, we remove the variables which has low impact for prediction or is obtained difficult variables, the last ten variables can contribute to the best prediction in model 7 whose MAPE is 12.25%. Furthermore, we are looking forward to Taiwan to have more solar power data, other external factors and meteorological data, and thus we have a more accurate model and predict the results.

誌謝辭 i
摘要 ii
Abstract iii
目次 iv
圖目次 vi
表目次 vii
1. 緒論 1
1.1. 研究動機與目的 1
1.2. 論文架構 2
2. 文獻探討 3
2.1. 預測太陽能相關文獻 3
2.2. 機器學習演算法相關文獻 5
2.2.1. 類神經網路簡介（Artificial Neural Network, ANN） 5
2.2.2. 支援向量機簡介（Support Vector Machine, SVM） 6
3. 研究方法 9
3.1. 實驗資料 9
3.1.1. 太陽能資料 9
3.1.2. 氣象資料 9
3.2. 建立預測模型 10
3.2.1. 模型1－所有變數 10
3.2.2. 模型2－考量四季，加入月份 10
3.2.3. 模型3－考量梅雨颱風，加入前天最高低溫 11
3.2.4. 模型4－刪減不適用變數 11
3.2.5. 模型5－考量四季，加入月份 11
3.2.6. 模型6－考量梅雨颱風，加入前天最高低溫 11
3.2.7. 模型7－加入月份與前天最高低溫 11
3.3. 預測驗證標準 11
3.4. 研究使用之工具－MATLAB 12
3.4.1. 類神經網路之相關參數 12
3.4.2. 支援向量機之程式碼 13
3.5. 研究流程 14
4. 實驗結果 15
4.1. 類神經網路 15
4.1.1. 模型1－所有變數 15
4.1.2. 模型2－考量四季，加入月份 17
4.1.3. 模型3－考量梅雨颱風，加入前天最高低溫 18
4.1.4. 模型4－刪減不適用變數 20
4.1.5. 模型5－考量四季，加入月份 21
4.1.6. 模型6－考量梅雨颱風，加入前天最高低溫 23
4.1.7. 模型7－加入月份與前天最高低溫 24
4.1.8. 小結 26
4.2. 類神經網路－隱藏層神經元個數 26
4.3. 支援向量機 28
4.4. 太陽能發電預測模型之資訊管理意涵 30
5. 結論與未來研究方向 31
參考文獻 32
附錄一 嘉義2015年太陽能發電量預測結果 34
附錄二 高雄2015年太陽能發電量預測結果 46
附錄三 金門2015年太陽能發電量預測結果 58

[1]楊錦欽，2002，類神經網路運用於型材矯直之研究，國立中興大學機械工程學系碩士學位論文
[2]張孝澤，以類神經網路預估迴龍地區太陽能發電系統之發電量，碩士論文，龍華科技大學，2011
[3]觀測資料查詢系統CODiS
（http://e-service.cwb.gov.tw/HistoryDataQuery/index.jsp）
[4]Lewis CD. (1982). International and business forecasting methods. London: Butterworths.
[5]Yadav, A. K., Malik, H., & Chandel, S. S. (2014). Selection of most relevant input parameters using WEKA for artificial neural network based solar radiation prediction models. Renewable and Sustainable Energy Reviews, 31, 509-519.
[6]Belaid, S., & Mellit, A. (2016). Prediction of daily and mean monthly global solar radiation using support vector machine in an arid climate. Energy Conversion and Management, 118, 105-118.
[7]Quej, V. H., Almorox, J., Arnaldo, J. A., & Saito, L. (2017). ANFIS, SVM and ANN soft-computing techniques to estimate daily global solar radiation in a warm sub-humid environment. Journal of Atmospheric and Solar-Terrestrial Physics, 155, 62-70.
[8]dos Santos, C. M., Escobedo, J. F., Teramoto, É. T., & da Silva, S. H. M. G. (2016). Assessment of ANN and SVM models for estimating normal direct irradiation (H b). Energy Conversion and Management, 126, 826-836.
[9]Citakoglu, H. (2015). Comparison of artificial intelligence techniques via empirical equations for prediction of solar radiation. Computers and Electronics in Agriculture, 118, 28-37.
[10]Ozgoren, M., Bilgili, M., & Sahin, B. (2012). Estimation of global solar radiation using ANN over Turkey. Expert Systems with Applications, 39(5), 5043-5051.
[11]Bae, K. Y., Jang, H. S., & Sung, D. K. (2017). Hourly Solar Irradiance Prediction Based on Support Vector Machine and Its Error Analysis. IEEE Transactions on Power Systems, 32(2), 935-945.
[12]Gorjian, S., Ghobadian, B., & Tavakkoli Hashjin, T. (2015). Modeling of Solar Radiation Potential in Iran Using Artificial Neural Networks. Journal of Agricultural Science and Technology, 17, 1707-1723.
[13]Jang, H. S., Bae, K. Y., Park, H. S., & Sung, D. K. (2016). Solar power prediction based on satellite images and support vector machine. IEEE Transactions on Sustainable Energy, 7(3), 1255-1263.
[14]Khatib, T., Mohamed, A., & Sopian, K. (2012). A review of solar energy modeling techniques. Renewable and Sustainable Energy Reviews, 16(5), 2864-2869.
[15]McCulloch, W. S., & Pitts, W. (1943). A logical calculus of the ideas immanent in nervous activity. The bulletin of mathematical biophysics, 5(4), 115-133.
[16]Cortes C, Vapnik V. Support-vector networks. Mach Learn 1995;20:273–97.
[17]Smola A, Vapnik V. Support vector regression machines. Adv Neural Inform Process Syst 1997;9:155–61.
[18]Gunn, S, 1998. Support vector machines for classification and regression. ISIS technical report, 14.
[19]Tofallis, 2015, A Better Measure of Relative Prediction Accuracy for Model Selection and Model Estimation, Journal of the Operational Research Society, 66(8), 1352-1362
[20]https://www.mathworks.com/