台電公司近年來積極推動各項方案，以提高用戶的供電可靠度，並以用戶全年平均恢復供電時間及用戶全年平均恢復供電次數（SAIFI）列為公司的重要營運目標。台電自91年度起，設定公司的SAIDI和SAIFI全年目標值，再將此目標分配至公司內的各個區處。此目標之設定（包括如何將公司的營運目標分配至各個區處），僅憑藉著公司管理階層的經驗，而無邏輯方法，導致區處之間目標值的分配不盡公平。若目標設定過於嚴苛，由於目前缺少高、低壓用戶停電之自動監測設施，台電公司的區處承辦單位可能會對於用戶停電記錄造假，此造假行為對於公司的基層士氣影響甚鉅。
有鑑於此，本論文旨在設計一套方法，將公司的營運目標合理分配至公司內的個別部門，作為各部門的營運目標。而以台電公司的用戶停電時間為例，探討應考量那些主要因素以及如何將這些主要因素納入至分配流程或計算公式內。
本論文係針對台電公司的「輸電事故停電時間」進行研究，採用解析式階層程序法將用戶停電時間的多項影響因素，以階層式架構呈現，經由篩選評估準則（或用戶停電時間的影響因素），建構階層式架構，據以說明眾多影響因素之間的相互關係，並對所探討的問題予以模組化。再對於位在最底層的評估準則，選擇量化指標，以衡量評估準則於不同區處之背景差異；並以問卷方式取得專家意見，計算評估準則的相對權重；由最底層向上層反覆推演，直至計算出評估目標值，並用於分配公司降低用戶停電時間的總目標至各個區處。最後，以此分配比重值，與92年度台電6個區營運處（區處）的用戶事故停電時間之實績值相比較，探討二者之間的異同。在演算過程中，另對於不同背景之專家，經由問卷填答所得出的權重差異進行比較分析，深入探討本法在未來應用上之特性。

In recent years, Taiwan Power (Taipower) company has endeavored to implement various programs, in order to reduce customers’ power interruption duration and frequency, as part of the corporate operational goals. Since 2002, Taipower has set the corporate operational target for the yearly SAIDI (System Average Interruption Duration Index) and SAIFI (System Average Interruption Frequency Index), and then has distributed the corporate target to the regional transmission offices to serve as the regional management target.
The Methods for setting the targets, including how to distribute the corporate target to the regional offices, relied purely on the engineering and managerial experiences. No logical or any rational method has been adopted, which thus has led to the distribution of corporate target sometimes on an unfair basis. Due to the lack of automatic monitoring on power interruption, an over-expected, or sometimes unviable, target may adversely force the regional offices forge the field data, which can cause a significant depression on field engineers’ morale.
To resolve this difficulty, this thesis presents a method which can logically distribute the corporate target to the regional offices, serving as the regional managerial target. In the thesis, the SAIDI target has been adopted as an example to illustrate the methods, which include selecting a variety of influential factors on SAIDI and accounting these factors according to their relative impact on SAIDI in the design of corporate target distribution process or distribution formula.
The thesis focuses on the target setting for Taipower’s SAIDI due to the transmission system faults. The analytic hierarchy process (AHP) has been adopted, by which all the relation among influential factors on SAIDI can be presented into the hierarchical structure. The process begins with the model formulation by selection of influential factors on SAIDI and the formulation of factors into the modulized hierarchical model. At the second stage, the process then finds out 2 groups of parameters. One group refer to the evaluation indices which measure the regional status influential factors designed at the lowest layer of the hierarchical model, so to identify the disparity among Taipower’s 6 regional transmission offices.
The second group of parameters refer to the relative weights among the influential factors, which are derived from the linguistic comparison results obtained by the questionnaire survey conducted on Taipower’s maintenance and operation engineers of the 6 regional transmission offices. At the third stage of AHP, by combining these 2 groups of parameters, the process evaluates the evaluation index values to each influential factor from the lowest layer upwards until the objective value at the top of hierarchical structures is calculated.
At the final stage, Taipower’s corporate SAIDI target is distributed to be the 6 regional targets based on the relative comparison among the above 6 objective values.
To give a further insight into the numerical evaluation results, the AHP results on Taipower’s corporate target distribution have been compared with Taipower’s SAIDI record at 2003. In addition, the disparity on the questionnaire results among Taipower’s 6 regional offices as well as between the feeder and the substation departments of regional offices are analyzed to investigate the potential characteristics of designed model in future application.

[1]T. L. Saaty, The Analytic Hierarchy Process : Planning, Priority Setting, Resource Allocation (Vol. I), RWS Publications, U.S.A., 1990.
[2]T. L. Saaty, Fundamentals of Decision Making and Priority Theory with The Analytic Hierarchy Process (Vol. VI), RWS Publications, U.S.A., 1994.
[3]T. L. Saaty, “Axiomatic Foundation of the Analytic Hierarchy Process”, Management Science, Vol. 32, No. 7, July 1986, pp.841~855.
[4]T. L. Saaty, and M. Takizawa, “Dependence and Independence: from Linear Hierarchies to Nonlinear Networks”, European Journal of Operations Research, Vol. 26, 1986, pp.229~237.
[5]T. L. Saaty, L. G. Vargas, “Inconsistency and Rank Preservation”, Journal of Mathematical Psychology, Vol. 28, No. 2, June 1984, pp.205~214.
[6]T. L. Saaty, “Absolute and Relative Measurement with the AHP: The Most Livable Cities in the United States”, Socio-Economic Planning Sciences, Vol. 20, No. 6, 1986, pp.327~331.
[7]T. L. Saaty, “Exploring Optimization Through Hierarchies and Ratio Scales”, Socio-Economic Planning Sciences, Vol. 20, No. 6, 1986, pp.355~360.
[8]T. L. Saaty, “A Note on AHP and Expected Value Theory”, Socio-Economic Planning Sciences, Vol. 20, No. 6, 1986, pp.397~398.
[9]D. M. DeTurck, “The Approach to Consistency in the Analytic Hierarchy Process”, Mathematical Modeling, Vol. 9, No. 3-5, 1987, pp.345~352.
[10]P. T. Harker, “Alternative Modes of Questioning in the Analytic Hierarchy Process”, Mathematical Modeling, Vol. 9, 1987, pp.353~360.
[11]B. L. Golden, and E. A. Wasil (eds.), “The Analytic Hierarchy Process – Applications and Studies”, Springer-Verlag, NY, 1989.
[12]L. G. Vargas, “Reciprocal Matrices with Random Coefficients”, Mathematical Modeling, Vol. 3, 1982, pp.69~81.
[13]R. Kumar，研究方法步驟化學習指南，胡龍藤、黃瑋瑩、潘中道合譯，學富文化事業有限公司，2000年8月。
[14]朱家勳，台灣有線電視系統台經營績效之研究 — 綜合用DEA與AHP模式，長庚大學企業管理研究所在職專班碩士論文。
[15]刀根 薰，競賽式決策制訂法 — AHP入門，陳名揚譯，建宏出版社，1993年11月。
[16]王玉民，社會科學研究方法原理，紅葉文化，1994年12月。
[17]台電系統降低用戶停電時間之具體作法完成報告，EPRI Worldwide S.A.委託清大研究計畫期末報告（中文版），計畫主持人：陳士麟，協同主持人：盧豐彰，2004年3月。
[18]供電單位達成系統可靠度指標執行辦法，台電供電處內部文件，2002年。
[19]輸變電設備事故統計表，台電供電處內部文件，2002年。
[20]R. Billinton, and J. E. Billinton, “Distribution System Reliability Indices”, IEEE Trans. On Power Delivery, Vol. 4, No. 1, January 1989, pp.561~568.