本論文以負載特性調查研究為基礎，收集住宅、商業及工業類型用戶用電量資料，推導各類型用戶標準化日負載模式，配合台電用戶資訊系統(CIS)之售電資料，推估區處各類型用戶日負載組成。根據中央氣象局收集之溫度資料，配合各類型用戶用電量資料，應用類神經網路訓練學習各類型用戶用電量與溫度之關係，求解各類型用戶用電量之溫度敏感度，並分析溫升1℃時，不同匯流排的負載變化量。
為測試負載溫升效應對系統可靠度之影響，本論文以”IEEE Reliability Test System”作為模擬系統。應用本文推導之各類型用戶每小時用電量溫度敏感度，分析溫度上升後之系統負載量之變化及發電機組容量裕度。由於系統的用電增加量與系統之負載組成有很大的關係，當系統之負載組成以商業類型用戶為主時，其溫升效應引起之用電增加量最大，對系統的供電可靠度影響亦最大；反之當系統上之負載組成以工業類型用戶為主時，溫升效應對用電增加量相對較小，其對供電可靠度之影響較不明顯。
就台電系統而言，透過用戶用電量之溫度敏感度分析，可了解負載變動範圍，有效掌握溫度上升時，相對之系統負載增加量與容量裕度，評估溫升效應之系統供電可靠度，將溫度變化納入未來變電所及未來系統容量規劃之參考。

This paper is to investigate the impact of temperature sensitivity to the load profiles of power system by artificial neural networks (ANN). The load survey study is performed to derive the typical load patterns of the residential, commercial, and industrial customers respectively. By executing the training process of customer power consumption and temperature, the ANN model is created to derive the temperature sensitivity of power consumption for each customer class, which is then used to solve the impact of temperature rise to system power profiles. According to the system load composition and temperature sensitivity of power consumption by each customer class, the hourly increase of system power loading due to 1℃ temperature rise is solved.
To study the temperature effect to the system reliability, the “IEEE Reliability Test System” is selected as test system for power system reliability analysis. Based on the temperature sensitivity of power consumption for each customer class and load composition of each load bus. The power demand is updated with the temperature rise. The temperature sensitivity of commercial customers is very significant because of the high air conditioner loading. When the system load composition is most composed of commercial customers, the power demand are due to temperature rise will have very critical impact to system reliability. On the other hand, the tempearture rise will have less impact of reliability analysis for the system which serves high percentage of industrial customers.
It is concluded that the research of temperature sensitivity on power consumption can provide important information for system reliability analysis. Better substation planning and system capacity expansion can be obtained to meet system reliability criterion by taking into account the temperature effect to system loading.

中文摘要 Ⅰ
Abstract Ⅱ
目錄 Ⅳ
圖目錄 Ⅵ
表目錄 Ⅶ

第一章 緒論 1
1-1 研究背景及目的 1
1-2 研究步驟 2
1-3 各章節概要 4
第二章 負載特性調查與類神經網路 5
2-1 前言 5
2-2 負載調查與負載組成 5
2-3 類神經網路前言 11
2-3-1 類神經網路之應用 11
2-4 類神經網路數學模型 11
2-4-1 類神經網路神經元 11
2-4-2 類神經元運作之數學模型 13
2-5 類神經網路架構 14
2-5-1 類神經網路之主要架構 14
2-5-2 類神經網路之學習方式 14
2-6 類神經網路學習法則 15
2-6-1 倒傳遞式演算法（BP） 16
2-6-2 Levenberg-Marquardt倒傳遞式演算法（L-M BP） 21
2-6-3 訓練類神經網路之流程 23
2-7 刪除演算法（Pruning Algorithm） 23
2-8 Early Stopping 24
第三章 系統負載之溫度敏感度分析 25
3-1 前言 25
3-2 應用類神經網路於負載之溫度敏感度分析 27
3-2-1 前言 27
3-2-2 輸入變數的選擇 27
3-2-3 類神經網路架構設計 29
3-2-4 訓練和驗證 30
3-3 各類型用戶用電量之溫度敏感度分析 31
3-3-1 溫度敏感度定義 31
3-3-2 溫升效應之用電增加量求法 32
3-4 區處與系統負載之溫度敏感度分析 33
3-4-1 北市區處負載之溫度敏感度分析 35
3-4-2 鳳山區處負載之溫度敏感度分析 37
3-4-3 北市及鳳山區處溫升效應之比較與資料驗證 39
3-4-4 台電系統溫度敏感度分析 40
3-5 其他類型之類神經網路演算法收斂特性 42
3-6 類神經網路與迴歸分析方法比較 43
3-7 本章結論 44
第四章 電力系統可靠度分析 46
4-1 系統可靠度簡介 46
4-2 IEEE測試系統 52
4-3 系統可靠度分析 57
4-3-1 互聯支援系統 59
4-3-2 求解等效支援機組(系統)步驟 64
4-4 考慮溫度效應之系統可靠度 64
4-5 本章結論 74
第五章 結論與未來研究方向 76
5-1 結論 76
5-2 未來研究方向 78

附錄A i

[1] C.S. Chen, J.C. Hwang and C.W. Huang, “Determination of customer load characteristics by load survey system at Taipower”, IEEE Trans. on Power Delivery, Vol. 11, No. 3, Jul. 1996, pp. 1430-1435.
[2] C.S. Chen, M.S. Kang, J.C. Hwang, C.W. Huang, “Synthesis of power system load profiles by class load study”, Electrical Power & Energy Systems, Vol. 22, No. 5, Jun. 2000, pp. 325-330.
[3] C.S. Chen, M.S. Kang, J.C. Hwang, C.W. Huang, “Implementation of the load survey system in Taipower”, Proceeding of 1999 IEEE/PES T & D Conference, Apr. 11-17, 1999.
[4] 張健邦， ”應用多變量分析”， 文富出版社， 1993年2月。
[5] 陳順宇， ”多變量分析”， 華泰書局， 1998年7月。
[6] 康渼松， “台電負載特性之研究及其對電力系統運轉之影響”，國立中山大學電機工程研究所博士論文， 2001年。
[7] “台電系統負載特性調查分析研究”， 第三期計劃期末報告， 台灣電力公司， 2002年。
[8] Martin T. Hagan, Howard B. Demuth Mark Beale, “Neural Network Design”, PWS Publishing Company.
[9] L.M. Saini, M.K. Soni, “Artificial Neural Network Based Peak Load Forecasting Using Levenberg-Marquardt and Quasi-Newton methods”, IEEE Proceedings on Generation, Transmission and Distribution, Vol. 149 5, Sep. 2002.
[10] E.D. Karnin, “A Simple Procedure for Pruning Back-Propagation Trained Neural Networks”, IEEE Trans. on Neural Networks, Vol. 1, No. 2, Jun. 1990.
[11] C.S. Chen, M.S. Kang, J.C Wang, J.C. Hwang, C.W. Huang, “Temperature sensitivity analysis of system power profiles”, IEEE Power Engineering Society Summer Meeting, Vol. 2, pp854-859, 2001.
[12] C.S. Chen, M.S. Kang, J.C. Hwang, C.W. Huang, “Temperature effect to distribution system load profiles and feeder losses”, IEEE Trans. On Power System, Vol. 16, No. 4, Nov. 2001.
[13] 陳智宏，“應用類神經網路於電力系統之溫度敏感度分析”，國立中山大學電機工程學系碩士論文，2002年。
[14] D.R. Anderson, D.J. Sweeney, T.A. Williams, “Statistics for Business and Economics”, South-Western College Publishing.
[15] Wiktor Charytoniuk, E. Don Box, Wei-Jen Lee, Mo-Shing Chen, Paul Kotas, and Peter Van Olinda, “Neural-Network-Based Demand Forecasting in a Deregulated Environment”, IEEE Trans. on Industry Application, Vol. 36, No. 3, May./Jun. 2000, pp. 893-898.
[16] Henrique Steinherz Hippert, Carlos Eduardo Pedreira, and Reinaldo Castro Souza, “Neural networks for short-term load forecasting: a review and evaluation”, IEEE Trans. On Power System, Vol. 16, No. 1 Feb. 2001.
[17] Roy Billinton, Ronald N. Allan, “Reliability Evaluation of Power Systems”, Plenum Press New York and London.
[18] Peng Wang, Roy Billinton, “Time sequential distribution reliability worth analysis considering time varying load and models”, IEEE Trans. On Power Delivery, Vol. 14, No. 3, Jul. 1999.
[19] Peng Wang and Roy Billinton, “Reliability cost/worth assessment of distribution systems incorporating time-varying weather conditions and restoration resources”, IEEE Trans. On Power Delivery, Vol. 17, No. 1, Jan. 2002.
[20] D. Atanackovic, D.T. McGillis, F.D. Galiana, “Reliability Comparison of Substation Designs”, IEEE Trans. on Power Delivery, Vol. 14, No. 3, Jul. 1999.
[21] “IEEE Reliability Test System”, a report prepared by the Reliability Test System Task Force of the Application of Probability Methods Subcommittee, IEEE Trans. on Power Apparatus and Systems, Vol. PAS-98, No.6 Nov./Dec. 1979.
[22] 張智星， ”MTLAB程式設計與應用”， 清蔚科技出版事業部，2000年11月。