Search

In power systems, an asset class is a group of power equipment that has the same function and shares similar electrical and/or mechanical characteristics. Predicting failures for different asset classes is critical for electric utilities toward developing cost-effective asset management strategies. Previously, physical age based Weibull distribution has been widely used for failure prediction. However, this mathematical model cannot incorporate asset condition data. As a result, the prediction cannot be very specific and accurate for individual assets. To solve this important problem, this paper proposes a novel and comprehensive data-driven approach based on asset condition data: K-means clustering as an unsupervised learning method is used to analyze the inner structure of historical asset condition data and produce the asset conditional ages; logistic regression as a supervised learning method takes in both asset physical ages and conditional ages to classify and predict asset operation statuses. Furthermore, an index called average aging rate is defined to quantify, track, and estimate the relationship between asset physical age and conditional age. This approach was applied to a medium-voltage cable class in an urban distribution system in West Canada. Case studies and comparison with standard Weibull distribution are provided. The proposed approach demonstrates higher accuracy measured by F1-Score than Weibull distribution method for asset class failure prediction. [ABSTRACT FROM AUTHOR]

In this paper, an integrated simulation—optimization approach is proposed for annual planning of power restoration workforce related to an electricity distribution company in a province of Canada. Internal and external workforces are employed to perform maintenance actions and restore power after interruptions throughout the province. According to the electricity distribution network, the province is divided into a number of work locations (WL), each having local crews to perform maintenance actions and fix power interruptions. However, determining the size of the crew in each WL over the year is challenging because of high fluctuation in interruption frequency and consequently in projected demand during the year. The frequency of interruptions is affected by various factors such as geographical location, time calendar, and particularly weather conditions. The objective is to determine the optimal combination of internal and external workforce over the year to cover the interruptions across the province with minimum cost and minimum customer interruption duration. [ABSTRACT FROM PUBLISHER]