由於間歇性的風能，導致風力發電不穩定輸出。為降低風力發電所帶來的影響，
維持系統供電可靠度，需準備額外增加的備轉容量。本論文應用次日風力發電預測，
再搭配歷史變動量分析結果，獲得次日需準備的備轉容量。本論文透過類神經網路
(Artificial Neural Network, ANN)技術，建立風力發電短期預測模型。利用時間序列
決定輸入訓練資料期數，再加入數值天氣預測風速資訊，完成風力發電量之次日預
測。本論文先對風場歷史資料進行風能最大變動量分析，針對各區域、季節、時間
進行歸類。利用統計分析結果建立備轉容量需求資料庫，以供查詢。結合歷史資料
以及即時預測，算出系統加入風場後的額外增加之調頻備轉容量，將有益電力系統
的排程與穩定性。本研究最後利用PSSE 軟體分析風力發電預測準確性對電力系統
的影響。

Due to the intermittent nature of wind power, wind power generation is unstable. In
order to reduce the impact of wind farm, additional operate reserve is requried. In this
thesis, next day wind power forecast and historical wind power ramping analysis are
applied to determine the required additional regulation reserve. Wind power forecasting
model is established by using Artificial Neural Network (ANN). Wind power time series
data and numerical weather prediction wind speed data are applied to day-ahead wind
power prediction. In this study, through historical output data of wind farms, output
ramping analysis is conducted. Depending on location, season and time, output variation
are different. The analysis results are used to determine additional regulation reserve
required. Finally, the impact of wind power generation on power system is analyzed by
using PSSE package.

論文審定書 ......................................................................................................... i
致謝.................................................................................................................... ii
中文摘要 ........................................................................................................... iii
Abstract ............................................................................................................. iv
目錄.................................................................................................................... v
圖目錄 .............................................................................................................. vii
表目錄 ............................................................................................................... xi
第一章 緒論 ...................................................................................................... 1
1.1 研究背景與動機 ............................................................................... 1
1.2 再生能源發展現況 ........................................................................... 2
1.2.1 國際再生能源發展 ------------------------------------------------------------ 2
1.2.2 台灣再生能源發展 ------------------------------------------------------------ 7
1.3 風力發電預測模型簡介 .................................................................. 12
1.3.1 預測尺度 ---------------------------------------------------------------------- 12
1.3.2 預測模型種類 ---------------------------------------------------------------- 12
1.4 再生能源發電對系統備轉容量的影響 .......................................... 16
1.5 風力發電預測對系統衝擊影響 ...................................................... 16
1.6 文獻回顧 ......................................................................................... 17
1.7 論文貢獻與架構 ............................................................................. 19
第二章 風力發電預測模型與輸出變動分析 ...................................................20
2.1 以類神經網路為基礎之短期風力發電預測模型 ........................... 20
2.1.1 類神經網路介紹 ------------------------------------------------------------- 20
2.1.2 類神經網路模型建立 ------------------------------------------------------- 25
2.2 風力發電廠輸出變動量分析 .......................................................... 30
2.3 利用發電變動統計資料決定備轉容量需求之步驟 ....................... 32
2.4 討論 ................................................................................................. 36
第三章 風力發電預測結果比較與應用 ..........................................................37
3.1 預測結果 ......................................................................................... 37
3.1.1 彰濱地區風力發電預測 ---------------------------------------------------- 37
3.1.2 北部、中部風力發電廠預測----------------------------------------------- 42
3.1.3 預測模型結果比較 ---------------------------------------------------------- 44
3.2 北部、中部風力發電廠輸出變動量分析 ....................................... 56
3.2.1 地區性變動差異比較 ------------------------------------------------------- 57
3.2.2 季節性變動差異比較 ------------------------------------------------------- 63
3.2.3 時間性變動差異比較 ------------------------------------------------------- 67
3.3 結合風力發電預測及發電變動量統計資料之備轉容量分析結果
........................................................................................................ 77
3.4 風力發電預測對系統衝擊影響分析 .............................................. 89
3.4.1 分析案例說明 ---------------------------------------------------------------- 89
3.4.2 電力潮流分析 ---------------------------------------------------------------- 91
3.4.3 偶發事故分析 ---------------------------------------------------------------- 94
3.4.4 次日需額外增加備轉容量是否充足 ------------------------------------- 103
3.4.5 討論 --------------------------------------------------------------------------- 105
第四章 結論與未來研究方向 ........................................................................ 106
4.1 結論 ............................................................................................... 106
4.2 未來研究方向 ............................................................................... 108
參考文獻 ......................................................................................................... 109

[1] R. Adib, H. E. Murdock, F. Appavou, A. Brown, B. Epp, A. Leidreiter, and T. C.
Farrell, “Renewables 2016 Global Status Report,“ Global Status Report renewable
energy policy network for the 21 st century (REN21),2016.
[2] A. Pullen, and S. Sawyer, “Global Wind Report. Annual market update 2010, ”2011.
[3] 中國風力發展Available online: http://www.knowledgeatwharton.com.cn/zhhant/
article/2796/.
[4] A. Tuohy, “Wind and Solar Power and their Impact on Operating Reserves in the
Taiwan Power System,” Electric power research institute, 2015.
[5] 中華民國經濟部， 臺灣再生能源發展受限 Available online:
http://www.ylfire.gov.tw/upload/news201101010000061/20140106144013098.pdf
[6] 台灣電力公司官方網，資訊揭露國家，再生能源未來展望Available online:
http://www.taipower.com.tw/content/new_info/new_info-b34.aspx?LinkID=8
[7] 千架海陸風機， Available online: http://www.twtpo.org.tw/intro.aspx?id=462
[8] S. D. Lu, W. C. Ho, W. H. Lu,“ a research on potential energy of offshore wind
powerand preferable block in Taiwan” Electrical Power Engineering 34th
2015/12/12
[9] 台灣電力公司官方網站， 國家再生能源未來展望Available online:
http://www.taipower.com.tw/content/new_info/new_info-b34.aspx?LinkID=8
[10] X. Wang, P. Guo, and X. Huang,“ A review of wind power forecasting
models,” Energy procedia, no. 12, pp. 770-778, 2011.
[11]陳美蘭，風力發電短期預測與應用現況，台電工程月刊第705 期96. 05.
[12] C. Monteiro, “Wind power forecasting: state-of-the-art 2009,” Argonne National
Laboratory (ANL), 2009.
[13] J. Shi, Z. Ding., W. J. Lee, Y. Yang, Y Liu.and M. Zhang.,” Hybrid forecasting model
for very-short term wind power forecasting based on grey relational analysis and
wind speed distribution features,” IEEE Transactions on Smart Grid, vol. 5, no. 1,
pp. 521-526, 2014.
[14] T. Acker, J. Buechler, S. Broome, C. Potter, H Gil., B. Zavadil, and R. La Peter,”
Arizona Public Service Wind Integration Cost Impact Study,” Prepared for Arizona
Public Service, 2007.
[15] B. Ernst, B. Oakleaf, M. L. Ahlstrom, M. Lange, C. Moehrlen, B. Lange, ..., and K.
Rohrig,’’ Predicting the wind,’’ IEEE power and energy magazine, vol. 5, no. 6, pp.
78-89, 2007
[16] J. P. D. S. Catalão, H. M. I. Pousinho, and V. M. F. Mendes,” An artificial neural
network approach for short-term wind power forecasting in Portugal,” 2009.
ISAP'09. 15th International Conference on IEEE, In Intelligent System Applications
to Power Systems, pp. 1-5, November, 2009.
[17] S. S. Sanz, A. Perez-Bellido, E. Ortiz-Garcia, A. Portilla-Figueras, L. Prieto, D
Paredes., and F. Correoso,” Short-term wind speed prediction by hybridizing global
and mesoscale forecasting models with artificial neural networks,” In Hybrid
Intelligent Systems, 2008. HIS'08. Eighth International Conference on, pp. 608-612,
IEEE, September, 2008.
[18] C. D. Park, M. A. El-Sharkawi, R. J Marks, L. E. Atlas, and M. J. Damborg,” Electric
load forecasting using an artificial neural network,” IEEE Transactions on Power
Systems, vol. 6, no. 2, pp. 442-449, 1991.
[19] A. R. Finamore, V. Galdi, V. Calderaro, A. Piccolo, G. Conio, and S. Grasso,”
Artificial neural network application in wind forecasting: An one-hour-ahead wind
speed prediction,” 5th IET International Conference on Renewable Power
Generation (RPG) 2016, pp.24-30, 2016.
[20] C. Perez-Llera, M. C. Fernandez-Baizan, J. L. Feito, and V. Gonzalez del Valle,”
Local short-term prediction of wind speed: a neural network analysis”, 1st
international vongress on environmental modelling and software-lugano, 2002.
[21] G. Reikard,” Predicting solar radiation at high resolutions: A comparison of time
series forecasts,” Solar Energy, vol. 83, no. 3, pp. 342-349, 2009.
[22] G. C. Contaxis, and J. Kabouris,” Short term scheduling in a wind/diesel autonomous
energy system,“ IEEE Transactions on Power Systems,vol. 6,no. 3, pp.1161-1167,
1991.
[23] R. Huang, T. Huang, R. Gadh, and N. Li,” Solar generation prediction using the
ARMA model in a laboratory-level micro-grid,” 2012 IEEE Third International
Conference on. IEEE, pp. 528-533, November, 2012.
[24] C. W. Potter, and M. Negnevitsky,” Very short-term wind forecasting for Tasmanian
power generation,” IEEE Transactions on Power Systems, vol. 21, no. 2, pp. 965-
972, 2006.
[25] F. Castellanos, and N. James,” Average hourly wind speed forecasting with ANFIS,”
In 11th American Conference on Wind Engineering, San Juan, Puerto Rico, June,
2009.
[26] B. Lotfi, B. M. Najiba, and M El Euch,” Impact of wind power integration on
operating reserves,” In Electrotechnical Conference (MELECON), 2012 16th IEEE
Mediterranean , pp. 67-71, March, 2012.
[27] H. Holttinen, M. Milligan, E. Ela, N. Menemenlis, J. Dobschinski, B. Rawn, and N.
K. Detlefsen,” Methodologies to determine operating reserves due to increased wind
power,” IEEE Transactions on Sustainable Energy, vol. 3, no. 4, pp. 713-723, 2012.
[28] 王彩霞，魯宗相，喬穎，閔勇，周雙喜，’’基於非參數回歸模型的短期風電功
率預測’’， 電力系統自動化，2010
[29] H. Holttinen, P. Meibom, A. Orths, B. Lange, M. O'Malley, J. O. Tande, and J. C.
Smith,” Impacts of large amounts of wind power on design and operation of power
systems,” Wind Energy, vol. 14, no 2, pp. 179-192, 2011.
[30]陳斌魁，李建松，楊宗穎，”澎湖風機容量信用度分析(II)”，104 年度科技部電
力學門專題研究計畫成果發表會報告。
[31] M. Milligan, and K. Porter,“ Wind capacity credit in the United States,” In Power
and Energy Society General Meeting-Conversion and Delivery of Electrical Energy
in the 21st Century, July, 2008.
[32] K. Porter, “Determining the Capacity Value of Wind: A Survey of Methods and
Implementation,” National Renewable Energy Laboratory, 2005.
[33] V. Gevorgian, and S. Booth,” Review of PREPA technical requirements for
interconnecting wind and solar generation,” National Renewable Energy Laboratory,
2013.
[34] E. Grigonyte, and E. Butkeviciute,“ Short-term wind speed forecasting using
ARIMA model,” Energetika, 2016.
[35] C. Wan, J. Zhao, Y. Song, Z. Xu, J. Lin, and Z. Hu,“ Photovoltaic and solar power
forecasting for smart grid energy management”, CSEE Journal of Power and Energy
Systems, vol. 1, no. 4, pp. 38-46, 2015.
[36] 盧恆究，"改良式人工智慧方法於電力系統之預測應用"，國立中正大學電機工
程研究所博士論文，2017 年1 月。
[37] J. Zhao, Y. Guo, X. Xiao, J. Wang, D. Chi, and Z. Guo,’’ Multi-step wind speed and
power forecasts based on a WRF simulation and an optimized association
method,’’ Applied Energy, no. 197, pp. 183-202, 2017.
[38] 台灣電力股份有限公司輸電系統規劃準則Available online:
http://www.taipower.com.tw/UpFile/UHVFile/台電