基于大数据分析的配电网故障监测方法

A Method for Distribution Network Fault Monitoring Based on Big Data Analysis

针对当前配网监测手段有限、数据利用率低等问题,提出一种基于大数据分析的配电网故障监测方法。分析目前供电企业配网调度支持系统技术特点与数据流程,选取海量历史遥测数据作为研究对象,采用C均值模糊聚类算法辨识配电线路负荷模式并进行负荷预测。定义了考虑隶属度和欧式距离因素的失配度指标,作为线路故障评价判据。算例分析表明,能有效辨识配电线路负荷模式,较为可靠地判定线路故障,并在一定程度上避免因负荷正常波动造成的误动作。应用效果显示,提供了一种简便、实用的监测手段,能有效监测现有手段监视不到的配电网故障情况。

In order to solve the problems of the limited distribution network monitoring means and inefficient data utilization,a method for distribution network fault monitoring based on big data analysis is proposed.In this paper,the load pattern is identified and the load forecast is carried out by analyzing the current characteristics and the data flow of the distribution network dispatching support system of power supply enterprises,using the massive historical telemetry data as the research object and the C means fuzzy clustering algorithm.The mismatch index is re-defined by taking the membership degree and Euclidean distance into account and used as the evaluation criteria of the line faults.The example presented in this paper shows that the proposed method can effectively identify the load pattern of distribution lines,determine the line faults sufficient accurately and to a certain extent,avoid the mishandling caused by the normal fluctuation of the load.Application results show that the method provides a simple and practical mean of monitoring the fault of the distribution network effectively whose effectiveness is beyond the reach of the existing means.