臺灣博碩士論文加值系統

全球不可再生能源短缺，風能作為一種環境友好型能源，成為替代化石能源的重要選擇。但風具有間歇性、波動性、隨機性等特點。風力發電給電力系統的穩定性帶來了一定的挑戰。而對風場的風功率進行預測是解決這一問題的重要途徑。風速預測是風功率預測的重要組成部分。
在此背景下，本文針對風場的短期功率預測，重點完成以下幾方面的工作：
根據歷史記錄資料，使用時間序列法建立模型，根據前3小時的資料預測下一小時的風速，並建立風速與功率曲線。
針對Back Propagation（缩写 BP）神經網路，通過對比相同輸入的不同結構之神經網路，確定誤差最小的神經網路架構；對風機的輸入資料進行預處理，利用神經網路確定對功率輸出相關度最大的特徵。
對於支援向量機，收斂速度快,學習能力強,泛化能力好,即使風速劇烈變化時,也能有效的預測序列的變化趨勢。
最後建立了組合預測模型，有效的提升了預測精度，減小了預測誤差，降低了不穩定性。

Because of the shortage of non-renewable energy, wind energy, which an environmentally friendly energy, has become an important alternative to fossil fuels. But the wind has the characteristics of intermittence, volatility and randomness. Wind power has brought some challenges to the stability of power system. The prediction of wind power is an important way to solve this problem. Wind speed forecasting is an important part of wind power prediction.
Under this background, this paper focuses on the following aspects of the short-term wind power prediction:
Use the time series method to build a model based on historical data, and predicts wind speed with three-hour-ahead wind speed, and establish a wind speed and power curve.
For the BP neural network, the neural network architecture with the smallest error is determined by comparing the neural networks of different structures with the same input; the input data of the wind turbine is preprocessed, and the neural network is used to determine the variable with the highest correlation with the power output.
For the support vector machine(SVM), the convergence speed is fast, the learning ability is strong, and the generalization ability is good. Even when the wind speed changes drastically, the trend of the sequence can be effectively predicted.
Finally, a combined prediction model is established, which effectively improves the prediction accuracy, and reduces the prediction error, and reduces the instability.

致謝
摘要 I
ABSTRACT II
目錄1 III
圖目錄 V
表目錄 VII

第一章 緒論 1
1-1 課題研究的背景 1
1-2 研究的目的與意義 3
1-3 風力預測模型簡介 4
1-3-1 按預測時間分類 4
1-3-2 按預測對象範圍分類 5
1-3-3 按預測模型分類 5
1-3-4 基於歷史資料的風力發電預測研究 6
1-4 章節摘要 8
第二章 基於時間序列模型的功率預測研究 11
2-1 引言 11
2-2 時間序列模型 11
2-2-1 時間序列模型概述 11
2-2-2 時間序列模型的建立過程 12
2-3 時間序列模型在風電預測中的應用 16
2-4 小結 22
第三章 基於神經網路的功率預測研究 23
3-1 引言 23
3-2 神經網路的特性及優點 23
3-3 反向傳播演算法與深度神經網路模型 24
3-4 基於BP神經網路的短期風速預測 28
3-5 小結 38
第四章 基於支援向量機的功率預測研究 39
4-1 引言 39
4-2 支援向量機基礎 39
4-3 基於支援向量機的短期風速預測 42
4-4 基於時間序列模型與支援向量機的組合模型 43
4-5 小結 44
第五章 風電場功率組合預測方法研究 46
5-1 引言 46
5-2 各種組合預測方法 46
5-3 線性組合預測方法在風電機組功率預測中的應用 49
5-4 非線性組合預測方法在風電機組功率預測中的應用 51
5-5 小結 52
第六章 結論與未來研究方向 53
5-1 結論 53
5-2 未來研究方向 53
參考文獻 55

[1] 台灣能源局，『風力發電4年推動計畫（核定本）』，2017.
[2]Global Wind Energy Council, “Global Wind Report”, pp. 20, April 2018
[3]BP p.l.c, “BP Statistical Review of World Enegy”, pp. 47, June 2018
[4]穀興凱,范高峰,王曉蓉,風電功率預測技術綜述[J],現代電力,31(2),pp.335-338. December 2007.
[5]孫永川, 『風電場風電功率短期預報技術研究』，博士論文，蘭州大，2007.
[6]X. Wang, P. Guo, and X. Huang, “A review of wind power forecasting models,” Energy procedia, no. 12, pp. 770-778, 2011.
[7]J. L. Torres, A. Garcia, M. De Blas, et al. “Forecast of Hourly Average Wind Speed with ARMA Models in Navarre (Spain).” Solar Energy, 2005, 79: 65-77
[8] ABossanyi E A. “Short-term wind prediction using kalman filters.” Wind Engineering, 1985, 9(1): 1—8
[9] Z.Huang, Z.S.Chalabi. “Use of time-series analysis to model and forecast wind speed.” Journal of Wind Engineering and Industrial Aerodynamics, 1995, 56,311-322
[10] A.Sfetsos. “A comparison of various forecasting techniques applied to mean hourly wind speed time series.” Renewable Energy, 2000, 21:23-35
[11] A.Sfetsos. “A novel approach for the forecasting of mean hourly wind speed time series.” Renewable Energy, 2002, 27, 163-174
[12]Sfetsos A. “Time series forecasting of wind speed and solar radiation for renewable energy sources,” Ph.D. Thesis 1999. Imperial College, London, UK
[13]A.Sfetsos. “A comparison of various forecasting techniques applied to mean hourly wind speed time series.” Renewable Energy, 2000, 21:23-35
[14] Bates J M, Granger C. “The combination of forecast. Operation Research Quarterly,” 1969, 20: 451—468
[15]牛東曉,曹樹華,趙磊,張文文. 『電力負荷預測技術及其應用』. 北京:中國電力出版社,1998
[16]Sanchez I, Usaola J, Ravelo O, Velasco C, Domínguez J, Lobo M, et al. “Sipreólico-a wind prediction system based on flexible combination of dynamical models. Application to the Spanish power system.” In: Proceedings of the first joint action symposium on wind forecasting techniques. Norrköping: International Energy Agency(IEA), 2002
[17]楊叔子,吳雅,軒建平等『時間序列分析的工程應用上冊〔M〕』.武漢；華中科技大學出版，2007
[18]鐘珞,饒文碧,鄒承明.『人工神經網路及其融合應用技術』. 北京:科學出版社,2007
[19] Zhou Weihong,Xiong Shunqing.”Optimization of BP Neural Network Classifier Using Genetic Alogorithm.” Energy Procedia,2011,11:
[20] Liu, Qiu-Xia. “Gas Detection System Based on Multi-Sensor Fusion with BP Neural Network[J]”. Sensors & Transducers,2013,15710.
[21] 史峰,王小川,郁磊,李洋. 『Matlab神經網路30個案例〔M〕』.北京:北京航太航空出版社，2010
[22] Mitchell T M. “Machine learning.” 北京:機械工業出版社，2003
[23] 莫維仁,張伯明,孫宏斌,鬍子衡.『短期負荷綜合預測模型的探討』. 電力系統自動化, 2004, 28(1):30-34
[24] 鐘平安,陳筱雲,陳凱.『工業需水量綜合預測方法』.河海大學學報, 2001,29(4):68-71
[25] 高峰，康重慶，夏清，黃永皓，尚金成，孟遠景，何南強.『負荷預測中多模型的自動篩選方法』. 電力系統自動化, 2004,28(6),11-13
[26] 陳華友,劉春林.『基於IOWA運算元的組合預測演算法』.預測, 2003, 22(6):61-65
[27] 何永貴,韓月娥,楊實俊,張振剛.『人力資源需求預測模型的優選』. 華北電力大學學報, 2005, 32(6): 80-83
[28] Alexandre Costa, Antonio Crespo, Jorge Navarro, Gil Lizcano, Henrik Madsen, Everaldo Feitosa. “A review on the young history of the wind power short-term prediction, Renewable and Sustainable Energy Reviews.” article in press
[29] Jeremy Parkes, Lunis Munoz, Jack Wasey, et al.” Wind energy trading benefits through short term forecasting.” [Online]：
http://www.garradhassan.com
[30] Julio Usaola, Oswaldo Ravelo, Gerardo González Feranando Soto, M Carmen Dávlia, Belén Díaz-Guerra. “Benefits for wind energy in electricity markets from using short term wind power prediction tools: a simulation study.” Wind Engineering, 2004, 28(1):119-128
[31] DNN結構示意圖[Online]:
https://www.cnblogs.com/pinard/p/6418668.html