Search

Power distribution systems have been significantly affected by many fault causing events. Effective outage cause identification can help expedite the restoration procedure and improve the system reliability. However, the data imbalance issue in many real-world data often degrades the outage cause identification performance. In this paper, artificial immune recognition system (AIRS), an immune-inspired algorithm for supervised classification task is applied to the Duke Energy outage data for outage cause identification using three major causes (tree, animal, and lightning) as prototypes. The performance of AIRS on these real-world imbalanced data is compared with an artificial neural network (ANN). The results show that AIRS can greatly improve the performance by as much as 163% when the data are imbalanced and achieve comparable performance with ANN for relatively balanced data. Index Terms--Artificial immune system, classification, data imbalance, outage cause identification, neural network, power distribution systems.

Power distribution systems have been significantly affected by many outage-causing events. Good fault cause identification can help expedite the restoration procedure and improve the system reliability. However, the data imbalance issue in many real-world data sets often degrades the fault cause identification performance. In this paper, the E-algorithm, which is extended from the fuzzy classification algorithm by Ishibuchi et al. to alleviate the effect of imbalanced data constitution, is applied to Duke Energy outage data for distribution fault cause identification. Three major outage causes (tree, animal, and lightning) are used as prototypes. The performance of E-algorithm on real-world imbalanced data is compared with artificial neural network. The results show that the E-algorithm can greatly improve the performance when the data are imbalanced. Index Terms--Data imbalance, data mining, fault cause identification, fuzzy classification, g-mean, neural network, power distribution systems.

This paper presents an approach that uses statistical techniques to analyze and interpret Time of Outage Restoration (TOR) data in distribution systems with respect to several selected factors. The factors are classified into three main categories : (1) Time, (2) Consequence, and (3) Environment. Each category is further broken down into groups and classes for more detailed analysis. Both statistical, quantitative results and field engineering insights will be correlated and discussed. The approach taken in this paper can be easily modified for other utilities' TOR analysis. These analyses can provide a better understanding as to how the restoration time is affected by different influential factors. The methodology and general discussion in the paper will be useful for future research and development of the Time of Outage Restoration issues in distribution systems, such as model development for customer service improvement, distribution operations, and planning. Key Words : distribution systems, outages, restoration time, statistical analyses.

The reliability, security and quality of power systems are significantly affected by distribution faults. One of the current trends concerning distribution faults is the implementation of more preventive measures instead of reactive measures. In other words, we would like to prevent faults from happening rather than to restore the system after faults occur. Among the different categories of power distribution faults, animal-caused faults are probably the ones that can be prevented most easily and effectively if appropriate control actions are taken. This paper will discuss and analyze animal-caused faults in power distribution systems. The results of an animal fault prevention technique that can effectively reduce these faults will also be presented. Keywords: Power distribution systems, distribution system faults, animal faults, preventive maintenance, control action fault prevention.

This paper proposes to use four different measures: actual values, normalized values, relative values, and likelihood values for power systems' distribution faults analysis. This paper also discusses the general and local properties of distribution faults. The likelihood measure, based on the local region properties, provides important information for distribution fault cause identification when the fault cause is not known. Tree faults on the Duke Power System are used in this paper for illustration purposes. The proposed measures, analysis and discussion in this paper can be easily generalized for different types of distribution faults in other utility companies.

Faults are likely to occur in most power distribution systems. If the causes of the faults are known, specific action can be taken to eliminate the fault sources as soon as possible to avoid unnecessary costs, such as power system down-time cost, that are caused by failing to identify the fault sources. However, experts that can accurately recognize the causes of distribution faults are scarce and the knowledge about the nature of these faults is not easily transferable from person to person. Therefore, artificial neural networks are used in this paper to recognize the causes of faults in power distribution systems, based on fault currents information collected for each outage. Actual field data collected by Duke Power Company are used in this paper. The methodology and implementation of artificial neural networks and fuzzy logic for the identification of animal-caused distribution faults will be presented. Satisfactory results have been obtained, and the developed methodology can be easily generalized and used to identify other causes of faults in power distribution systems.