臺灣博碩士論文加值系統

自步入工業化的以後，人們為了滿足生活上的需求而大量地使用能源，舊有的能源通常以化石燃料與核能為主要能源，而隨著人們的無節制的使用著這些能源，造成了全球暖化與溫室效應的惡果。如何能開發使用新的再生能源與妥善的利用電力能源已經成了大家所重視的方向。在眾多的環保能源中，太陽能為無汙染而且幾乎提供源源不絕的能源，為此太陽能的發展技術成為下一個替代能源的明日之星。
本論文將預測系統分成太陽能與電力負載這兩個方向，為了分析能源與各個相關的參數屬性，本論文選擇以數據挖掘技術來實作，並提出以歷史數據依照所定出之條件分群的方法來進行下一日太陽能發電量與電力負載能源預測。這些過程包含前處理、參數選擇、異常值的估計及處理與制定本研究的決策樹規則;在經過前處理的步驟先進行空缺值填補及彙整數據，接著就是使用資料探勘軟體選擇參數去除不必要之參數，而再異常值估計的部分則將產生結果的異常值去除並將所有數據做正規化以方便預測，最後使用回歸分析做預測。資料的選取往往會影響到輸出與最終預測的結果，參數選擇是很重要的。為了使預測結果更精確，依照不同的溫度與濕度等特徵以決策樹將資料做分群。最後本論文與原始資料互相做了比較，證明分群後的預測是比原始資料較好。

With the rapid industrialized development the energy for satisfying the needs of the people, and most of the electricity must be generated from Fossil fuels. However, the storage of the traditional fossil energy is decreasing by people did not treasure , and lead to the global warming phenomenon and greenhouse effects more and more serious. These environmental protection phenomena and question make the people to value the development of renewable energy, In many renewable energy ,the solar power are the most promising and rapidly developing renewable energy technologies that exist in our world today for the reason that solar power energy have the advantages of energy saving and not pollute the environment.
In this paper, the forecasting system is divided into two directions: solar energy forecasting and electricity load forecasting. In order to analyze the solar energy and weather’s parameter attribute this paper chooses to adopt data mining technology and put forward the method of grouping data according to the condition data day-ahead solar power and electricity load forecast. These processes include preprocessing, parameter selection, estimation of outliers, and the development of decision tree rules for the study;
Therefore, before the forecast, in order to reduce the accuracy of the data and increase the accuracy of the degree, the collected historical power output and weather data for pre-processing, make up the collection of information on the missing and abnormal values. The selection of the data often affects the output and the final prediction of the results, parameter selection is very important. In order to make the prediction results more accurate, according to different temperature and humidity characteristics of the decision tree to group the data. Finally, this paper compared with the original data to prove that the prediction after the group is better than the original data.

中文摘要 II
誌 謝 V
目錄 VI
圖目錄 VIII
表目錄 VIII
第一章、 緒論 1
第一節、 研究背景 1
第二節、 研究目的 3
第三節、 研究流程與方法 4
第四節、 論文架構 5
第二章、 文獻回顧與探討 7
第一節、 負載預測 7
第二節、 太陽能發電預測 9
第三章、 太陽能與負載預測系統 11
第一節、 系統架構概述 11
第二節、 資料前置處理 13
第三節、 參數特徵選擇 14
第四節、 異常值去除 17
第五節、 決策分類 18
(一) Decision tree選擇最佳參數組合 18
(二) 預測分析方法: 19
(三) 人工分群流程: 24
第四章、 測試結果與分析 25
第一節、 測試方法設定 25
(一) 異常值去除 25
(二) 參數選擇 26
(三) 使用的方法比較 26
第二節、 測試環境 27
第三節、 評估參數 27
第四節、 測試結果與分析 28
第五章、 結論與未來展望 33
第一節、 結論 33
第二節、 未來展望 34
參考文獻 35

[1]Ssekulima, E. B., Anwar, M. B., Al Hinai, A., & El Moursi, M. S. (2016). Wind speed and solar irradiance forecasting techniques for enhanced renewable energy integration with the grid: a review. IET Renewable Power Generation, 10(7), 885-989.
[2]M. Q. Raza, & A. Khosravi, A review on artificial intelligence based load demand forecasting techniques for smart grid and buildings. Renewable and Sustainable Energy Reviews, 50, (2015) 1352-1372.
[3]A. I. Saleh, A. H. Rabie, & K. M. Abo-Al-Ez, A data mining based load forecasting strategy for smart electrical grids. Advanced Engineering Informatics, 30(3), (2016) 422-448.
[4]Ghasemi, A., Shayeghi, H., Moradzadeh, M., & Nooshyar, M. (2016). A novel hybrid algorithm for electricity price and load forecasting in smart grids with demand-side management. Applied Energy, 177, 40-59.
[5]Coelho, V. N., Coelho, I. M., Coelho, B. N., Reis, A. J., Enayatifar, R., Souza, M. J., & Guimarães, F. G. (2016). A self-adaptive evolutionary fuzzy model for load forecasting problems on smart grid environment. Applied Energy, 169, 567-584.
[6]Li, S., Wang, P., & Goel, L. (2016). A novel wavelet-based ensemble method for short-term load forecasting with hybrid neural networks and feature selection. IEEE Transactions on Power Systems, 31(3), 1788-1798.
[7]Li, S., Wang, P., & Goel, L. (2015). Short-term load forecasting by wavelet transform and evolutionary extreme learning machine. Electric Power Systems Research, 122, 96-103.
[8]Sáez, D., Ávila, F., Olivares, D., Cañizares, C., & Marín, L. (2015). Fuzzy prediction interval models for forecasting renewable resources and loads in microgrids. IEEE Transactions on Smart Grid, 6(2), 548-556.
[9]Cecati, C., Kolbusz, J., Różycki, P., Siano, P., & Wilamowski, B. M. (2015). A novel RBF training algorithm for short-term electric load forecasting and comparative studies. IEEE Transactions on industrial Electronics, 62(10), 6519-6529.
[10]Høverstad, B. A., Tidemann, A., Langseth, H., & Öztürk, P. (2015). Short-term load forecasting with seasonal decomposition using evolution for parameter tuning. IEEE Transactions on Smart Grid, 6(4), 1904-1913.
[11]Chen, Y., Yang, Y., Liu, C., Li, C., & Li, L. (2015). A hybrid application algorithm based on the support vector machine and artificial intelligence: an example of electric load forecasting. Applied Mathematical Modelling, 39(9), 2617-2632.
[12]Jiang, P., & Ma, X. (2016). A hybrid forecasting approach applied in the electrical power system based on data preprocessing, optimization and artificial intelligence algorithms. Applied Mathematical Modelling, 40(23), 10631-10649.
[13]Gupta, S., Singh, V., Mittal, A. P., & Rani, A. (2016, February). Weekly load prediction using wavelet neural network approach. In Computational Intelligence & Communication Technology (CICT), 2016 Second International Conference on (pp. 174-179). IEEE.
[14]Rana, M., & Koprinska, I. (2016). Forecasting electricity load with advanced wavelet neural networks. Neurocomputing, 182, 118-132.
[15]Sudheer, G., & Suseelatha, A. (2015). Short term load forecasting using wavelet transform combined with Holt–Winters and weighted nearest neighbor models. International Journal of Electrical Power & Energy Systems, 64, 340-346.
[16]Bahrami, S., Hooshmand, R. A., & Parastegari, M. (2014). Short term electric load forecasting by wavelet transform and grey model improved by PSO (particle swarm optimization) algorithm. Energy, 72, 434-442.
[17]Ali, U., Buccella, C., & Cecati, C. (2016, October). Households electricity consumption analysis with data mining techniques. In Industrial Electronics Society, IECON 2016-42nd Annual Conference of the IEEE (pp. 3966-3971). IEEE.
[18]Bessa, R. J., Trindade, A., & Miranda, V. (2015). Spatial-temporal solar power forecasting for smart grids. IEEE Transactions on Industrial Informatics, 11(1), 232-241.
[19]Golestaneh, F., Pinson, P., & Gooi, H. B. (2016). Very short-term nonparametric probabilistic forecasting of renewable energy generation—With application to solar energy. IEEE Transactions on Power Systems, 31(5), 3850-3863.
[20]Shah, A. S. B. M., Yokoyama, H., & Kakimoto, N. (2015). High-precision forecasting model of solar irradiance based on grid point value data analysis for an efficient photovoltaic system. IEEE Transactions on Sustainable Energy, 6(2), 474-481.
[21]Fidan, M., Hocaoğlu, F. O., & Gerek, Ö. N. (2014). Harmonic analysis based hourly solar radiation forecasting model. IET Renewable Power Generation, 9(3), 218-227.
[22]Sperati, S., Alessandrini, S., & Delle Monache, L. (2016). An application of the ECMWF Ensemble Prediction System for short-term solar power forecasting. Solar Energy, 133, 437-450.
[23]Larson, D. P., Nonnenmacher, L., & Coimbra, C. F. (2016). Day-ahead forecasting of solar power output from photovoltaic plants in the American Southwest. Renewable Energy, 91, 11-20.
[24]Lin, K. P., & Pai, P. F. (2016). Solar power output forecasting using evolutionary seasonal decomposition least-square support vector regression. Journal of Cleaner Production, 134, 456-462.
[25]Masa-Bote, D., Castillo-Cagigal, M., Matallanas, E., Caamaño-Martín, E., Gutiérrez, A., Monasterio-Huelín, F., & Jiménez-Leube, J. (2014). Improving photovoltaics grid integration through short time forecasting and self-consumption. Applied Energy, 125, 103-113.
[26]Li, Y., Su, Y., & Shu, L. (2014). An ARMAX model for forecasting the power output of a grid connected photovoltaic system. Renewable Energy, 66, 78-89.
[27]Junior, J. G. D. S. F., Oozeki, T., Ohtake, H., Shimose, K. I., Takashima, T., & Ogimoto, K. (2014). Regional forecasts and smoothing effect of photovoltaic power generation in Japan: an approach with principal component analysis. Renewable Energy, 68, 403-413.
[28]Leva, S., Dolara, A., Grimaccia, F., Mussetta, M., & Ogliari, E. (2017). Analysis and validation of 24 hours ahead neural network forecasting of photovoltaic output power. Mathematics and Computers in Simulation, 131, 88-100.
[29]Almeida, M. P., Perpiñán, O., & Narvarte, L. (2015). PV power forecast using a nonparametric PV model. Solar Energy, 115, 354-368.
[30]AlHakeem, D., Mandal, P., Haque, A. U., Yona, A., Senjyu, T., & Tseng, T. L. (2015, July). A new strategy to quantify uncertainties of wavelet-GRNN-PSO based solar PV power forecasts using bootstrap confidence intervals. In Power & Energy Society General Meeting, 2015 IEEE (pp. 1-5). IEEE.
[31]Rana, M., Koprinska, I., & Agelidis, V. G. (2016, July). Solar power forecasting using weather type clustering and ensembles of neural networks. In Neural Networks (IJCNN), 2016 International Joint Conference on (pp. 4962-4969). IEEE.
[32]Mori, H., & Takahashi, A. (2012, May). A data mining method for selecting input variables for forecasting model of global solar radiation. In Transmission and Distribution Conference and Exposition (T&D), 2012 IEEE PES (pp. 1-6). IEEE.
[33]Wang, Z., Koprinska, I., & Rana, M. (2016, July). Clustering based methods for solar power forecasting. In Neural Networks (IJCNN), 2016 International Joint Conference on (pp. 1487-1494). IEEE.
[34]Ian H. Witten, Eibe Frank, Mark A. Hall. Data mining: practical machine learning tools and techniques (third edition). Morgan Kaufmann, San Francisco, CA, USA, 2011.
[35]C.C. Chang, C.J Li “LIBSVM: A Library for Support Vector Machines” Journal ACM Transactions on Intelligent Systems and Technology (TIST) Volume 2 Issue 3. April 2011.
[36]Hong, T., Pinson, P., & Fan, S. (2014). Global energy forecasting competition 2012.
[37]Paisitkriangkrai, P.(2012).Linear regression and support vector regression. University Lecture.
[38]Peirong, J., Juan, C., & Wenchen, Z. (2008, September). Theory of grey systems and its application in electric load forecasting. In Cybernetics and Intelligent Systems, 2008 IEEE Conference on (pp. 1374-1378). IEEE.
[39]Xin-hui, D., Feng, T., & Shao-qiong, T. (2010, September). Study of power system short-term load forecast based on artificial neural network and genetic algorithm. In Computational Aspects of Social Networks (CASoN), 2010 International Conference on (pp. 725-728). IEEE.
[40]Bi, Y., Zhao, J., & Zhang, D. (2004, November). Power load forecasting algorithm based on wavelet packet analysis. In Power System Technology, 2004. PowerCon 2004. 2004 International Conference on (Vol. 1, pp. 987-990). IEEE.
[41]Ming-guang, Z., & Lin-rong, L. (2011, September). Short-term load combined forecasting method based on BPNN and LS-SVM. In Power Engineering and Automation Conference (PEAM), 2011 IEEE (Vol. 1, pp. 319-322). IEEE.
[42]Feng, L., & Liu, Z. (2006). Effects of multi-objective genetic rule selection on short-term load forecasting for anomalous days. In Power Engineering Society General Meeting, 2006. IEEE (pp. 7-pp). IEEE.