(3.235.245.219) 您好!臺灣時間:2021/05/10 01:55
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

: 
twitterline
研究生:李瑋倫
研究生(外文):Wei-Lun Lee
論文名稱:川流式水力發電預測模型之研究
論文名稱(外文):A Study of Run-of-River Hydropower Generation Forecasting Model
指導教授:陸臺根陸臺根引用關係
指導教授(外文):Tai-Ken Lu
學位類別:碩士
校院名稱:國立臺灣海洋大學
系所名稱:電機工程學系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2012
畢業學年度:100
語文別:中文
論文頁數:88
中文關鍵詞:川流式水力發電發電預測再生能源類神經網路
外文關鍵詞:Run-of-River Hydropower GenerationPower Generation ForecastRenewable EnergyArtificial Neural Network
相關次數:
  • 被引用被引用:2
  • 點閱點閱:1656
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:52
  • 收藏至我的研究室書目清單書目收藏:0
隨著時代演進,人類對於電力日益依賴,傳統石化燃料的發電方式會造成汙染且有耗盡的一天。因此節能減碳以及發展再生能源為當代之顯學,我國也為此制定了能源國家型科技計畫,其中一項重點研發領域即為智慧電網,而分散型電源之發電預測為建構智慧電網的關鍵性因素之一。以台灣現況而言,川流式水力發電為分散式電源中發展的最完善的。本文將以木瓜溪流域為例,分析該流域內之地形地貌、各電廠間的關係與雨量觀測站資料,以找出建立預測模型的關鍵性因素,並利用類神經網路來建構川流式水力電廠之預測模型,以提供未來發展各種再生能源長期預測與微電網之分散型電源預測之參考。本文建立了五個類神經網路預測模型,訓練之平均誤差率約為1.20%至3.31%,隨機抽取的10天資料驗證之平均誤差率約為0.76%至5.64%,足以證明本文所建模型的適用性。
In the wake of developments in science and technology, people has relied more on the electricity. Conventional fossil fuel power generation will cause pollution and be exhausted in future. Therefore carbon reduction and developing renewable energy are important more and more. Our country also develop National Science Technology Program-Energy (NSTPE), one of the key research is the smart grid. The power generation forecast of distributed power is one of the key factors of developing smart grid. The most complete of distributed power is the Run-of-River hydropower generation in Taiwan. This paper focus on the Mugua River, analyze the relationship between the power plants, the topography of the Mugua River, and the relationship between power generation and rainfall data, is to find the key factors of the forecasting model. And use the artificial neural network to construct the Run-of-River hydropower generation forecasting model, as the reference for developing the long-term power generation forecast of distributed power in future. This paper established five neural network forecasting model, the training Mean Absolute Percentage Error(MAPE) is about 1.20% to 3.31%, the MAPE is about 0.76% to 5.64% for the random testing sample of ten days data, could prove the applicability of these models.
摘要 IV
Abstract V
目錄 VI
圖目錄 VII
表目錄 X
第一章 緒論 1
1.1 研究動機與背景 1
1.2 研究文獻探討 4
1.3 研究流程與目的 7
1.4 論文章節說明 9
第二章 問題描述 11
2.1 木瓜溪流域介紹 11
2.2 木瓜溪流域川流式發電預測模型之問題描述 14
2.3 木瓜溪流域川流式發電預測模型建立所遭遇的問題 16
第三章 木瓜溪流域川流式水力發電廠發電預測理論模型 19
3.1 類神經網路 19
3.2 常見的類神經網路 25
3.3 模型評價指標 30
3.4 本文之建模流程 31
第四章 模擬結果分析 36
4.1 清水發電廠之發電預測類神經網路模型 37
4.2 清流發電廠之發電預測類神經網路模型 47
4.3 水濂發電廠之發電預測類神經網路模型 55
4.4 銅門發電廠之發電預測類神經網路模型 64
4.5 榕樹發電廠與初英發電廠之發電預測類神經網路模型 74
第五章 結論與未來研究方向 83
5.1 結論 83
5.2 未來研究方向 84
參考文獻 86

[1] “BP statistical review of world energy full report 2011,”
[2] “能源局99年報, ” 經濟部能源局, 2010.
[3] “Kyoto Protocol to the United Nations Framework Convention on Climate Change, ” UNITED NATIONS, 1998.
[4] “再生能源發電系統調度操作準則, ” 台灣電力公司, 2007.
[5] “台灣電力股份有限公司再生能源發電系統倂聯技術要點, ” 台灣電力公司, 2009.
[6] “能源國家型科技計畫, ” 行政院能源政策及科技發展指導小組,pp. 56-58, Nov-Dec, 2007.
[7] “Hydrologic Forecasting & Modeling System,”
https://www.baronservices.com/sites/default/files/brochures
/201012_Hydro_email.pdf
[8] G. Bastin, L. Moens, and P. Dierickx, “On-line river flow forecasting with Hydromax : successes and challenges after twelve years of experience,” Preprints of the 15th IFAC Symposium on System Identification Saint-Malo, France., July 6-8, 2009.
[9] V. Balvet, J. Bourret, and Jean-Emmanuel Maubois, “Massive Data Acquisition for the Short Term Wind Power Forecasting in a Large Grid: The Hydro-Québec SAGIPE System Experience,” Proceedings of the Power Systems Conference and Exposition., pp. 1-7, 15-18 March. 2009.
[10] K. Ichiyauagi, H. Kobayashi, T. Matsumura, and Y. IGto
“Application of Artificial Neural Network to Forecasting Methods of Time Variation of thc Flow rate into a Dam for a Hydro-Power Plant” Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems, pp. 349-354, 1993.
[11] T. gtokelj, and R Golob, “Application of neural networks for hydro power plant water inflow forecasting,” Proceedings of the 5th Seminar on Neural Network Applications in Electrical Engineering, pp189-193, 2000.
[12] T. Stokelj, D. Paravan, and R. Golob, “Short and mid term hydro power plant reservoir inflow forecasting,” Proceedings International Conference on Power System Technology, pp. 1107 - 1112 vol.2, 2000.
[13] T. Baumann, and Main J. Germond, “Application of the Kohonen Network to Short-Term Load Forecasting,” Neural Networks to Power Systems, 1993. ANNPS '93., Proceedings of the Second International Forum on Applications of ,pp.407-412, 1993.
[14] I. Coroama, and M. Gavrilas, “A Study on Wind Energy Generation Forecasting Using Connectionist Models,” International Conference on Optimization of Electrical and Electronic Equipment (OPTIM)., pp. 1257-1262, 20-22 May. 2010.
[15] Ronaldo R. B. de Aquino, Milde M. S. Lira, Josinaldo B. de Oliveira, Manoel A. Carvalho Jr., Otoni N. Neto, and Givanildo J. de Almeida, “Application of Wavelet and Neural Network Models for Wind Speed and Power Generation Forecasting in a Brazilian Experimental Wind Park,” International Joint Conference on Neural Networks, pp. 172-178, 14-19 June. 2009.
[16] Che Guan, Peter B. Luh, and Wen Cao, “Short-term Wind Generation Forecasting and Confidence Interval Estimation Based on Neural Networks Trained by Extended Kalman Particle Filter,” Proceedings of the 8th orld Congress on Intelligent Control and Automation,Taipei Taiwan, pp. 1173-1179, 21-25 June.2011.
[17] Dong-xiao Niu, Bing-en Kou, and Yun-yun Zhang, “Mid-long Term Load Forecasting Using Hidden Markov Model, ” 2009 Third International Symposium on Intelligent Information Technology Application, IEEE,pp.481-483, 2009.
[18] Liu Nan, “Based on Dynamic Regression Model Medium and
Long-term Demand Forecast and Analysis of China’s Electric Power, ” Information Science and Engineering (ICISE), 2010 2nd International Conference on, pp. 1053 -1056, Dec 2010.
[19] H. M. Al-Hamadi, “Long-Term Electric Power Load Forecasting Using Fuzzy Linear Regression Technique, ” Power Engineering and Automation Conference (PEAM), 2011 IEEE, pp.96-99, Sep 2011.
[20] J.Szczupak, D. Sica, D. Silva, L. Pinto, L. Macêdo, and F. Savi “AI Identification of New Hydro-Climate Models, ” Circuits and Systems, 2009. MWSCAS '09. 52nd IEEE International Midwest Symposium on, pp.901-904, Aug 2009.
[21] Yan-fang Sang, and Dong Wang, “A Stochastic Model for Mid-to-Long-Term Runoff Forecast, ” Natural Computation, 2008. ICNC '08. Fourth International Conference on, pp.44-48, Oct 2008.
[22] Hossein Daneshi, Mohammad Shahidehpour, and Azim Lotfjou Choobbari “Long-Term Load Forecasting in Electricity Market, ” Electro/Information Technology, 2008. EIT 2008. IEEE International Conference on, pp.395-400, May 2008.
[23] QianZhang, and Tongna Liu, “A Fuzzy Rules and Wavelet Neural Network Method for Mid-long-term Electric Load Forecasting, ” Computer and Network Technology (ICCNT), 2010 Second International Conference on, pp.442-446, April 2010.
[24] K. Mohammadi1, H. R. Eslami, and Sh. Dayyani Dardashti, “Comparison of Regression, ARIMA and ANN Models for Reservoir Inflow Forecasting using Snowmelt Equivalent (a Case study of Karaj),” http://www.sid.ir/en/VEWSSID/J_pdf/84820050203.pdf, Vol. 7: 17-30, 2005.
[25] 維基百科:
http://zh.wikipedia.org/wiki/%E6%9C%A8%E7%93%9C%E6%BA%AA , June 2012.
[26] Tadashi Kondo, “Feedback GMDH-type neural network using prediction error criterion and its application to 3-dimensional medical image recognition, ” SICE Annual Conference 2008, Aug 2008.
[27] S. Lennon, and E. Ambikairajah, “A Two-Layer Kohonen Neural Network Using a Cochlear Model as a front-end Processor for a Speech Recognition System, ” Neural Networks for Signal Processing [1992] II., Proceedings of the 1992 IEEE-SP Workshop, pp.139-148,Sep 1992.
[28] HOU Xuan, and HE Mingyi, “Study of Detection Technique Simulation of High Resolution Radar Based on BP Neural Network, ” Natural Computation, 2007. ICNC 2007. Third International Conference on, pp.426-430,Aug 2007.
[29] 張斐章, 張麗秋, “類神經網路導論原理與應用, ” 滄海書局,2010。
[30] 蘇木春, 張孝德, “機器學習類神經網路、模糊系統以及基因演算法則, ” 全華書局,2010。
[31] 林明河, “短期饋線負載預測模型之研究, ” 碩士學位論文,2010。

連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔