建構關聯規則資料挖礦架構及其在台電配電事故定位之研究

Constructing a Data Mining Framework of Association Rule and an Empirical Study for Fault Location

彭金堂(Jin-Tang Peng) ； 張盛鴻(Sheng-Hung Chang) ； 簡禎富(Chen-Fu Chien) ； 楊景晴(Jing-Ching Yang)

《資訊管理學報》 12卷4期 (2005/10) Pp. 121-141

https://doi.org/10.6382/JIM.200510.0121

摘要

電力是現代社會不可或缺的能源，配電事故為影響電力系統安全性、可靠度以及供電品質的重要因素。當配電事故發生時，台電人員必須藉由檢視或利用發電試驗找出事故發生位置，並進一步將之隔離與維修。但經由這樣一連串的測試與試驗，不僅將對會線路造成一定程度的損害，亦無法在短時間內找到事故位置以儘快修復恢復供電。因此如何發展一套可以快速有效找到事故發生地點方法，來縮短恢復供電時間減少經濟損失，成為非常重要的議題。本研究目的即針對此一需求，利用關聯規則的資料挖礦方法來分析配電事故歷史資料，並結合領域專家的知識，找出事故發生原因的關聯性，本文以台電配電事故停電記錄表所記錄之資料為實證來檢驗研究效度。研究發現本研究可以提供維修人員在特定決策環境下推測配電事故原因的規則，來減少事故定位所需的時間增加事故診斷正確性，進而減少停電損失提升供電品質。

關鍵字

資料挖礦 ； 關聯規則 ； 配電事故定位 ； 能源 ； 決策分析

並列摘要

Electrical power is a crucial energy in modem world. Distribution feeder fault causes power outage: It is crucial to locate the fault quicker so to reduce the outage time and thus avoid huge economical loss. In practice, feeder patrols usually identify the fault locations by referencing to the regional distribution of the trouble calls, the abnormal observations of the feeders, complained or reported in the calls, and the conditions in the surrounding environments. Then, feeder patrols have to rush into the field along feeder to locate the fault mainly by visual inspection and by trial energization of the feeder, section by section. Such a trial feeder energization is harmful to the cable and frequently takes a long time for power restoration. This study aims to develop a data mining framework based on association rule to derive useful patterns and rules for distribution feeder fault location. In particular, the historical data of distribution feeder faults of Taiwan power Company is used for validation. This database has recorded each fault with a table including time, date, month, year, address, equipment of fault, causes or accidents and so on for many years. The results have demonstrated practical viability of data mining approach for fault location.

並列關鍵字

Data Mining ； Association Rule ； Fault Location ； Energy ； Decision Analysis

參考文獻

陳家仁、陳彥良、陳禹辰(2003)。在少樣商品或短交易長度情況下挖掘關聯規則。資訊管理學報。9(2)，55-72。

Berry, M.,G. Linoff(1997).Data Mining Techniques for Marketing, Sales and Customer Support.New York:John Wiley and Sons.

Berzal, F.,J. Cubero,N. Mann,J. Serrano(2001).TBAR: An efficient method for association rule mining in relational databases.Data & Knowledge Engineering.37,47-64.

Cardozo, E.,S. N. Talukdar(1988).A Distributed Expert System for Fault Diagnosis.IEEE Transactions on Power Systems.3(2),641-646.

Changchien, S. W.,T. C. Lu(2001).Mining Association Rules Procedure to Support On-Line Recommendation by Customers and Products Fragmentation.Expert Systems with Applications.20,325-335.