基于历史告警数据的计量异常事件关联度分析

Correlation Analysis of Abnormal Metering Events Based on Historical Alarm Data

用电信息采集系统发出的异常事件告警信息数量庞大、种类繁多,目前缺乏计算异常事件关联度的模型和分析方法,因此提出一种计量异常事件关联度的分析方法。该方法以异常发生日期间隔天数为基础,通过构造关联系数函数实现关联度分析;设定关联度阈值,对存在关联的并发异常事件进行甄别。实例计算结果表明,该方法能够有效计算计量异常事件之间的关联度,提高异常告警数据利用率和异常诊断准确率。

There is a large number and a variety of abnormal event information issued by the power consumption information collection system.At present,there is no model and analysis method established to calculate the correlation of abnormal events.A correlation analysis method of metering abnormal is proposed.This method is based on the intervals of the date of occurrence and realizes correlation analysis by constructing correlation coefficient function.Then thresholds have been set to identify concurrent abnormal events.The results indicate that this method can calculate the correlation of abnormal events effectively and improve the utilization of abnormal data and the accuracy of abnormity diagnosis.