基于多源数据融合策略的配电网停电故障分析

摘要

配电网停电原因比较复杂,为精准地对停电故障进行预警,需采用大数据分析方法从多视角来深入剖析停电事件,尝试全景分析停电诱因及其对配电网影响程度的变化.因此,提出了一种简单易行的基于多源数据融合策略的配电网停电故障分析方法.方法首先融合停电池数据、配电网运行数据及气象数据来构建停电场景,然后采用成熟的主成分分析和逻辑回归来区分停电场景和其对应的非停电场景间的差异,进而发现配电网停电故障发生前的明显征兆.%Causes of an outage in a distribution network are rather complicated.In order to accurately predict the outage,we need to analyze the outrage from multiple perspectives by using the big data analysis method,and try to have a panoramic analysis of the causes of the outage and its impacts on the distribution network.To this end,this paper proposes a simple and feasible analysis method based on the multi-source data fusion strategy for power distribution network outages.By this method,the outrage pool data,operation data of the distribution network and weather data are integrated to construct the outage scenario first,and then the principal component analysis and logistic regression are used to differentiate between the the outage scenario and normal operation state,and in this way the prominent signs of the outage can be detected.