(34.229.64.28) 您好!臺灣時間:2021/05/06 06:06
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:::

我願授權國圖
: 
twitterline
研究生:林明河
研究生(外文):Ming-Ho Lin
論文名稱:短期饋線負載預測模型之研究
論文名稱(外文):A Study of Short-Term Feeder Load 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:2010
畢業學年度:98
語文別:中文
論文頁數:99
中文關鍵詞:饋線短期負載預測自迴歸整合移動平均最小平方法類神經網路
外文關鍵詞:Feeder short-term load forecastingAutoregressive Integrated Moving AverageLeast Squares MethodArtificial Neural Network
相關次數:
  • 被引用被引用:3
  • 點閱點閱:284
  • 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:88
  • 收藏至我的研究室書目清單書目收藏:0
負載預測對電力公司而言,是一項不可缺少的作業。有關電力網路的運轉與安全分析、維修排程、燃料採購,都需要負載預測結果作為分析的輸入參數。近年來,能源局正在推動「供電可靠度999方案」,促使國內供電品質的提升。能源局預期採用「同一用戶多次停電」(Customers Experiencing Multiple Interrupts, CEMI) 做為配電可靠度指標,影響CEMI的主要因素是用戶工作停電次數,換言之,如何依據饋線負載預測進行事先的負載轉供計畫,儘可能縮小工作停電戶數和範圍,是未來配電業務需謹慎面對的課題。
本文運用階層式叢集理論分析歷史負載曲線的季節特性,分割年負載曲線為六時段後,再將負載資料取對數以穩態化曲線,並建立各時段的自迴歸整合移動平均(Autoregressive Integrated Moving Average, ARIMA)、最小平方法 (Least Squares Method, LSM)、類神經網路(Artificial Neural Network, ANN)的預測模型,進行負載預測分析比較,再以最佳預測結果進行誤差修正取得最精準的負載預測。本文主要貢獻有:
1. 建立時間序列與類神經網路預測分析模型,
2. 預測方法建構方式可作為饋線負載預測之參考方向,
3. 比較各時段各預測模型可發現ANN模型的準確度較佳。

For the power company, load forecasting is an indispensable work which result is as input data for system operation, security analysis, outage maintenance scheduling, and fuel procurement, etc. In recent years, Bureau of Energy (BOE), Ministry of Economic Affairs, is promoting "power supply reliability 999" to improve the power quality. BOE expected to use the Customers Experiencing Multiple Interrupts (CEMI) as distribution reliability index, the main factor the CEMI affected is the work power cut number. In other words, how to make a good load transfer plans due to feeder load forecasting to minimize the number and scope of the work of a power outage, which is in the face of the future subject for the distribution business.
The clustering technology has been used firstly to carry on the historical load curve, six seasonal load characteristics have been found, and take the logarithm to smooth the load curves. The various types of ARIMA models and LSM models and ANN models have been developed, and compare each other to find the best model. The main contributions of this thesis have :
1. Build the time series and ANN load forecasting models,
2. Build one approach to decide the input nodes of ANN models,
3. The various types of models compare each other to find the ANN model is more available for feeder load forecasting.

摘要………………………………………………………………… I

Abstract………………………………………………………… II

目錄……………………………………………………………… III

圖目錄…………………………………………………………… V

表目錄…………………………………………………………… VII

第一章 緒論…………………………………………………… 1
1-1 研究動機與背景……………………………… 1
1-2 研究文獻探討………………………………… 2
1-3 研究方法與目的……………………………… 5
1-4 論文章節說明………………………………… 8
第二章 問題描述……………………………………………… 9
2-1 饋線負載預測問題描述……………………… 9
2-2 饋線負載預測所需考慮的因素……………… 10
2-3 負載預測方法的選用………………………… 12
第三章 理論描述……………………………………………… 13
3-1 負載分類理論………………………………… 13
3-2 時間序列分析法……………………………… 14
3-2-1 時間序列模型.……………………… 16
3-2-2 最小平方法.………………………… 17
3-2-3 單根檢定…………………………… 19
3-3 類神經網路…………………………………… 20
3-3-1 類神經網路簡介…………………… 20
3-3-2 倒傳遞網路演算法………………… 25
3-4 模型評價指標……………………………… 29
第四章 模擬結果與分析……………………………………… 32
4-1 五間饋線負載與宜蘭觀測站氣象資料分類… 32
4-2 時間序列模型建立………………………… 42
4-3 類神經網路模型建立………………………… 43
4-4 時間序列與類神經網路六時段模擬結果分析 49
第五章 結論…………………………………………………… 66
5-1 研究總結……………………………………… 66
5-2 未來研究方向探討…………………………… 68
參考文獻………………………………………………………… 71
【附錄】類神經網路各時段各模型之訓練結果…………………… 76


[1] Haydari Z., Kavehnia F., Askari M. and Ganbariyan M., “Time-series load modelling and load forecasting using neuro-fuzzy techniques,” Electrical Power Quality and Utilisation, 2007. EPQU 2007. 9th International Conference on, pp.1-6, Oct 9-11, 2007.
[2] Rahman S., and Hazim O., “A generalized knowledge-based short-termload-forecasting technique,” IEEE Trans. Power Syst., vol. 8, no. 2, pp.508–514, May 1993.
[3] Chicco G., Napoli R., and Piglione F., “Load pattern clustering for short-term load forecasting of anomalous days,” Power Tech Proceedings 2001 IEEE Porto, vol. 2, 10-13, pp. 6, Sept.2001.
[4] Gonzalez-Romera E., Jaramillo-Moran M.A., Carmona-Fernandez D., “Monthly Electric Energy Demand Forecasting Based on Trend Extraction,” Power Systems, IEEE Transactions on, vol. 21 Issue 4, 10-13, pp. 1946-1953, Nov. 2006.
[5] Mori H., and Urano S., “Short-term load forecasting with chaos time series analysis,” Intelligent Systems Applications to Power Systems, 1996. Proceedings, ISAP '96., International Conference on, 28 Jan.-2 , pp. 133-137, Feb. 1996.
[6] Hassnain S., Asar A. and Mahmood F., “Performance of STLF model from the PSO, time series and regression perspectives,” Neural Networks, 2009. IJCNN 2009. International Joint Conference on, pp. 1157-1162 , June 14-19, 2009.
[7] Abbas S. R., and Arif M., “Competitive Neural Network Based Algorithm for Long Range Time Series Forecasting Case Study: Electric Load Forecasting,” 9th International Multitopic Conference, IEEE INMIC, pp. 1-6, Dec 24-25, 2005.
[8] Limin Huo., Xinqiao Fan., Yunfang Xie and Jinliang Yin., “Short-Term Load Forecasting Based on the Method of Genetic Programming,” Mechatronics and Automation, 2007. ICMA 2007. International Conference on, pp. 839-843, Aug 5-8, 2007.
[9] Moghram I., and Rahman S., “Analysis and evaluation of five short-term load forecasting techniques,” Power Systems, IEEE Transactions on, vol. 4, Issue 4, pp.1484–1491, Nov. 1989.
[10] Chao-Ming Huang., Chi-Jen Huang and Ming-Li Wang., “A particle swarm optimization to identifying the ARMAX model for short-term load forecasting,” Power Systems, IEEE Transactions on , vol. 20, Issue 2, pp.1126–1133, May 2005.
[11] Razak I.A.B.W.A., Bin Majid S., Rahman H.A., and Hassan M.Y., “Short term load forecasting using data mining technique,” Power and Energy Conference, 2008. PECon 2008. IEEE 2nd International, pp.139–142 Dec1-3, 2008.
[12] Komprej I., and Zunko P., “Short term load forecasting,” Electrotechnical Conference, 1991. Proceedings., 6th Mediterranean, vol.2, pp.1470–1473, May 22-24, 1991.
[13] Amjady N., “Short-term hourly load forecasting using time-series modeling with peak load estimation capability,” Power Systems, IEEE Transactions on, vol.16 Issue 3, pp.498-505, Aug. 2001.
[14] Hagan Martin T., and Behr Suzanne M., “The Time Series Approach to Short Term Load Forecasting,” Power Systems, IEEE Transactions on , vol.2 Issue 3, pp.785–791,Aug. 1987.
[15] Juberias G., Yunta R., Garcia Moreno J., and Mendivil C., “A new ARIMA model for hourly load forecasting,” Transmission and Distribution Conference, 1999 IEEE ,vol.1, pp.314–319 ,April 11-16, 1999.
[16] Hor C. L., Watson S.J. and Majithia S., “Daily Load Forecasting and Maximum Demand Estimation using ARIMA and GARCH,” Probabilistic Methods Applied to Power Systems, 2006. PMAPS 2006. International Conference on, pp.1–6, June 11-15, 2006.
[17] Taylor J. W., “Short-term electricity demand forecasting using double seasonal exponential smoothing,” J. Oper. Res. Soc., vol. 54, pp.799–805, 2003.
[18] LEI Shao-lan, SUN Cai-xin, ZHOU Quan and ZHANG Xiao-xing, “The research of Local Linear Model of Short term Electrical Load on Multivariate Time Series,” Power Tech, 2005 IEEE Russia, Page(s):1 – 5, June 27-30, 2005.
[19] Hai-shan Wu., and Shen Zhang, “Power Load Forecasting with Least Squares Support Vector Machines and Chaos Theory,” Neural Networks and Brain, 2005. ICNN&B '05. International Conference on , vol.2, pp.1020-1024, Oct 13-15, 2005.
[20] El-Attar E.E., Goulermas J.Y., and Wu, Q.H., “Forecasting electric daily peak load based on local prediction,” Power & Energy Society General Meeting, 2009. PES '09. IEEE , pp.1-6, July 26-30, 2009.
[21] Feng Kong and Xiaojuan Wu., “Time Series Forecasting Model with Error Correction by Structure Adaptive Support Vector Machine,” Computer Science and Software Engineering, 2008 International Conference on, vol.2, pp.1067-1070, Dec12-14, 2009.
[22] Contreras J., Espinola R., Nogales F.J., and Conejo A.J., “ARIMA models to predict next-day electricity prices,” Power Systems, IEEE Transactions on, vol.18 Issue 3, pp.1014-1020, Aug. 2003.
[23] Espinoza M., Joye C., Belmans R. and De Moor B., “Short-Term Load Forecasting, Profile Identification, and Customer Segmentation: A Methodology Based on Periodic Time Series,” Power Systems, IEEE Transactions on, vol.20 Issue 3, pp.1622-1630, Aug. 2005.
[24] Taylor J.W., and McSharry P.E., “Short-Term Load Forecasting Methods: An Evaluation Based on European Data,” Power Systems, IEEE Transactions on, vol.22 Issue 4, pp.2213-2219, Nov. 2007.
[25]Gašperič S., Gerbec D., and Gubina F., "Determination of the Consumer's Load Porfiles," http://www.telmark.org/2002Sep/2-5_Gasperic.pdf.
[26]Ke Y. L., "Distribution Feeder Reconfiguration for Load Balancing and Service Restoration by Using G-Nets Inference Mechanism," IEEE Transactions on Power Delivery, vol. 19, pp. 1426-1433, 2004.
[27]C. H. Lin., C.S. Chen., H. J., Chuang., and C. Y. Ho., "Heuristic Rule-Based Phase Balancing of Distribution Systems by Considering Customer Load Patterns," IEEE Transactions on Power Systems, vol. 20, pp. 709-716, 2005.
[28]Lamedica R., Santolamazza L., Fracassi G., Martinelli G., and Prudenzi A., "A Novel Methodology Based on Clustering Techniques for Automatic Processing of MV Feeder Daily Load Patterns," IEEE Power Engineering Society Summer Meeting, pp. 96-101, 2000.
[29]"ELECTRICITY TARIFF RESTRUCTURING," National Energy Policy Office, 2001.
[30]Han J., and Kamber M., Data Mining Concepts and Techniques: Morgan Kanufmann.
[31]Lauritzen S. L., "The EM Algorithm for Graphical Association Models With Missing Data," Computational Statistics and Data Analysis, vol. 19, pp. 191-201, 1995.
[32]Ester M., Kriegel H. P., Sander J., and Xu X., "A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise," Published in Proceedings of 2nd International Conference on Knowledge Discovery and Data Mining (KDD-96).
[33]陳家文,“電力負載型態分類之研究”,國立臺灣海洋大學電機工程學系,2006,民95。
[34]楊亦農,“時間序列分析經濟與財務上之應用”,台北市:雙葉書廊,2008,民97。
[35]鄧民敦,“以類神經網路建立變壓器鐵損推估模式預測模型”,國立臺灣海洋大學電機工程學系,2005,民94。
[36]羅華強,“類神經網路-MATLAB 的應用”,台北縣:高立圖書,民94。
[37]張曉峒,“EViews使用指南與案例”,北京:機械工業,2007。

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