智能电表数据异常在线检测的无监督学习

Unsupervised learning for on-line detection of abnormal data in smart meters

针对智能电表在应用过程中出现的数据异常问题,通过定义为超出各负荷正常使用模式的任何异常用电实例或趋势,设计了基于负载、上下文和环境等不同类型的特征来构建数据驱动模型,评估了基于回归、基于神经网络、基于聚类和基于投影的4种不同的无监督学习方法在实际智能电表数据异常检测中的性能。结果表明,不同的异常检测方法对不同类型的异常具有不同的检测能力,其性能取决于用于训练该方法的特征集。因此,对于每种异常检测方法,都要仔细检查不同类型的特征。

Aiming at the problem of abnormal data in the application of smart meters,by defining any abnormal power consumption instance or trend beyond the normal use mode of each load,a data-driven model based on different types of characteristics such as load,context and environment is designed,and four different unsupervised models based on regression,neural network,clustering and projection are evaluated the performance of the learning method in the actual smart meter data anomaly detection is analyzed.The results show that different anomaly detection methods have different detection ability for different types of anomalies,and their performance depends on the feature set used to train the method.Therefore,for each anomaly detection method,different types of features should be carefully examined.