近年來由於地球的暖化效應，使得再生能源發電系統占總裝置容量比例愈來愈高，將影響整體電力規劃。風力發電是再生能源重要的一員，因此預測風能對於風力發電系統發電量的電力調度相對地重要。電網之穩定度、電力配置及排程，牽動了國家的經濟，風力電發電系統間歇性發電的特性是影響整體電網穩定度的主要原因。本研究先後建立，以回歸型最簡定址架構之類化型小腦模型控制器(RSCMAC)為基礎之風力機模型與短期風速預測模型，建立風與風能之關係進而預測風能。風力發電預測系統對於整體的電力配置與排程提供一個可用的資訊，提高整體電網之穩定度。對於風能預測研究，目前大都著眼於每小時風力預測，本研究目的是應用RSCMAC預測極短時間的風能，其用途在風力電發電系統中用來預測發電量，做為電力調度之評估。因此本研究以回歸型最簡定址架構之類化型小腦模型控制器(RSCMAC)為基礎結合小波輸入狀態建立一可行且準確度高之極短期風力預測模型。

In recent years, due to the Earth''s warming effect, making renewable energy generation systems increasingly occupy a high proportion of the total installed capacity, and this will affect the overall power planning. Wind power is an important renewable energy, so predicting wind generating capacity for the electricity dispatch of wind power generation systems are relatively important. The stability, power allocation and schedule of the grid affect the economy of a country. The intermittent power generation characteristic of a wind power generation system is the major cause of affecting the overall power grid stability. This study has established a Recurrent Simple addressing structure for Cerebellar Model Articulation Controller with General Basis Function (RSCMAC) based wind turbine model and a short-term wind speed forecasting model, the relationship between the wind and the wind power is also built to predict wind power. Wind power forecasting system provides usable information to the overall power allocation and schedule, and improve the stability of the overall grid. For the wind power forecasting, current researches focus on hourly wind forecasting, the purpose of this study is to apply RSCMAC to predict extremely short-term wind power, so it can be used in evaluation of electricity dispatch. Therefore, this study established a RSCMAC based combined with wavelet input state extremely short-term wind power forecasting model and shows its feasibility and high accuracy.

中文摘要 i
英文摘要 ii
誌謝 iii
目錄 iv
表目錄 vii
圖目錄 viii
第一章 緒論 1
1.1 研究背景與動機 1
1.2 研究目的 2
1.3 研究方法 3
1.4 論文架構 4
第二章 回歸型最簡定址架構之類化型小腦模型控制器之介紹 5
2.1 傳統小腦模型控制器(CMAC) 5
2.1.1傳統小腦模型控制器之基礎架構 6
2.1.2傳統小腦模型控制器之學習法則 9
2.2類化型小腦模型控制器(CMAC_GBF) 10
2.2.1類化型小腦模型控制器之基礎架構 10
2.3回歸型最簡定址架構之類化型小腦模型控制器(RSCMAC) 12
2.3.1回歸型最簡定址架構之類化型小腦模型控制器基礎架構 13
2.3.2回歸型最簡定址架構之類化型小腦模型控制器學習法則 16
2.4結語 18
第三章　氣象監測系統、監測資料與風力機數學模型之介紹 19
3.1 氣象監測系統之介紹 19
3.1.1 氣象監測站之架設 20
3.2 監設點選擇與監測資料 21
3.2.1 氣象站之監測點選擇 22
3.2.2 氣象站之量測系統 27
3.2.3 氣象站之資料收集情況 29
3.3 風力機數學模型 31
3.3.1 自然風的特性 32
3.3.2 風力機數學模型介紹 34
3.4 結語 36
第四章　基於RSCMAC為基礎之風力機模型 38
4.1 風力機模型基地選取 38
4.2 以貝茲係數為基礎之風力機模型 40
4.3 以RSCMAC為基礎之風力機模型 43
4.3.1 風力機模型之建立流程 44
4.3.2 RSCMAC風力機模型之模擬結果 48
4.3 結語 50
第五章　極短期風速與風能發電預測系統 52
5.1 極短期風速預測模型 52
5.1.1 風速、風向與周遭環境之關係 53
5.1.2 以RSCMAC為基礎之極短期致力於發電預測模型 56
5.1.3 模擬方法與資料選取 57
5.1.4 模擬結果 59
5.2 RSCMAC極短期風能預測模型 61
5.2.1 預測模型 62
5.2.2 資料擷取 62
5.2.3 模擬方法 63
5.2.4 模擬結果 64
5.3 結語 66
第六章　基於RSCMAC結合小波輸入狀態之風能預測系統 67
6.1 風速與風能標準狀態波形之介紹 67
6.2小波分析法在輸入訊號之運用 69
6.2.1 小波分析法 69
6.2.2 輸入訊號之分析 74
6.3 以RSCMAC為基礎結合小波分析輸入訊號之風能預測模型 76
6.4 模擬結果 77
6.4 結語 89
第七章　結論 90
7.1研究成果 90
7.2 研究問題與解決方法 91
7.3 研究心得 92
7.4 未來展望 93
參考文獻 94
簡 歷 97

[1]http://www.taipower.com.tw/content/new_info/new_info-b31.aspx?LinkID=8
[2]http://web3.moeaboe.gov.tw/ECW/populace/home/Home.aspx
[3]http://www.davisnet.com/weather/index.asp
[4]https://zh.wikipedia.org/wiki/%E9%9B%A2%E6%95%A3%E5%B0%8F%E6%B3%A2%E8%AE%8A%E6%8F%9B
[5]牛山泉著，風車工學入門，林輝政審定，澎湖科技大學，澎湖，民國九十八年。
[6]許佳偉，「區域化學習之最簡定址架構類化型小腦模型控制器設計」，私立清雲科技大學，碩士論文，民國九十六年。
[7]鍾招名，「最簡定址架構之類化型小腦模型控制器硬體實現」，私立清雲科技大學，碩士論文，民國九十四年。
[8]謝佳諺，「最簡定址架構類化型小腦模型控制器之學習收斂」，私立清雲科技大學，碩士論文，民國九十八年。
[9]盧智偉，「基於回歸型小腦模型控制器及區域氣象資訊預估全天空太陽能輻射量」，私立清雲科技大學，碩士論文，民國九十九年。
[10]李効儒，「基於RSCMAC及區域氣象資訊之太陽照射度預測系統」，私立清雲科技大學，碩士論文，民國一百零一年。
[11]謝少緯，「以RSCMAC為基礎結合氣象資訊之太陽能功率預測」，私立清雲科技大學，碩士論文，民國一百零一年。
[12]A.Betz, Das Maximum der theoretisch moeglichen Ausnuetzung des Windes durch Windmotoren, Zeitschrift fuer das gesamte Turbinenwesen, Heft 20, Sept., 1920
[13]A.Betz, Wind-Energie und ihre ausnutzung durch Windmuhlen., Gottingen, Vandenhoeck,1926.
[14]Bhaskar K, Singh S.N, “AWNN-Assisted Wind Power Forecasting Using Feed-Forward Neural Network”, IEEE Transactions on Sustainable Energy, Volume: 3, Page(s). 306 – 315, 2012.
[15]Ching-Tsan Chiang, Tung-Sheng Chiang, Chien Kuo Li, ”A simple and converged structure of addressing technique for CMAC”, IEEE International Conference on Man and Cybernetics, Volume 7, Page(s). 6097-6101, 10-13 Oct. 2004.
[16]C. T. Chiang and C. S. Lin, “CMAC with General Basis Functions.” Journal of Neural Network, Vol. 9, No. 7, pp. 119-1211, 1996.
[17]C. T. Chiang and T. S. Chiang, “A Converged Recurrent Structure for CMAC_GBF and S_CMAC_GBF,” IEEE International Symposium on Industrial Electronics, pp. 1876-1881, 2007.
[18]Ching-Tsan Chiang, Yung-Sheng Lee Xiao Ru Li, Chiung-Chou Liao, “A RSCMAC based forecasting for Solar Irradiance from local weather information”, Neural Networks (IJCNN), International Joint Conference, Page(s). 1 – 7, 2012.
[19]Chen Sheng, Ye Lin, Zhang Gengwu, Zeng Cheng, Dong Shijun, Dai Chao, “Short-term wind power prediction based on combined grey-Markov model”, Advanced Power System Automation and Protection (APAP), International Conference, Page(s). 1705 – 1711, 2011.
[20]Coroama, I.; Gavrilas, M.,“A study on wind energy generation forecasting using connectionist models”,International Conference, Page(s).1257-1262, 2010.
[21]D. Marr, “A Theory of Cerebellar Cortex,” J. Physiol, Vol. 202, pp. 437-470, 1969.
[22]F.W. Lanchester, “Contribution to the Theory of Propulsion and the Screw Propeller”, Transactions of the Institution of Naval Arehitects, Vol. LVII, pp.98-116,1957
[23]J. S. Albus, “A New Approach to Manipulator Control: The Cerebellar Model Articulation Controller (CMAC),” Journal of Dynamic System, and Control, Transaction of ASME, pp. 220-227, 1975.
[24]J. S. Albus, “Data Strorage in the Cerebellar Model Articulation Controller (CMAC),” Journal of Dynamic Systems, Measurement and Control, Transaction of ASME, pp. 228-233, 1975.
[25]P. Goupillaud, A. Grossman, and J. Morlet. “Cycle-Octave and Related Transforms in Seismic Signal Analysis,”Geoexploration, Pages. 85-102, 1984.
[26]Van der Hoven, “power Spectrum of Horizontal Windspeed in the Frequency Range form 0.0007 to 900 Cycles per Hour ”, J. of Meteor.,Vol. 14,pp. 160-164, 1957.
[27]Wu Yuan-Kang; Lee Ching-Ying, Tsai Shao-Hong; Sun-Nien Yu, “Actual experience on the short-term wind power forecasting at Penghu — From an island perspective”, Power System Technology (POWERCON), International Conference, Page(s). 1705 – 1711, 2011.
[28]Zhang Xinyu, Dong Lei, “A smooth scheme of wind power generation based on wind power prediction”, International Conference, Page(s): 958 – 961, 2011.