计算机应用研究2023，Vol.40Issue(12)：3717-3722,3727,7.DOI:10.19734/j.issn.1001-3695.2023.07.0337
基于深度孪生自回归网络的无监督异常用电检测
Unsupervised abnormal power consumption detection via deep siamese autoregressive network
摘要
Abstract
Abnormal electricity consumption detection aims to identify electricity consumption behaviors that do not conform to normal electricity consumption patterns or violate electricity consumption contracts.To address the issues of existing recon-struction-based detection methods relying on labeled normal samples and failing to capture complex time dependencies,this paper proposed an unsupervised abnormal electricity consumption detection model based on deep siamese autoregressive net-works(DSAD),which used two siamese autoregressive subnetworks to independently reconstruct the unlabeled input data,and then combined the reconstruction errors of the two subnetworks to predict the normal samples in the data,and utilized multi-head self-attention mechanism to effectively capture complex features such as time dependency,periodicity and random-ness.The results obtained from experiments on large-scale time series datasets and real electricity consumption datasets from state grid show that the proposed method achieves better detection performance in terms of AUC and AP.关键词
智能电网/异常用电检测/深度孪生自回归网络/多头注意力机制/无监督学习Key words
smart grid/abnormal electricity consumption detection/deep siamese autoregressive network/multi-head atten-tion/unsupervised learning分类
信息技术与安全科学引用本文复制引用
李琪林,严平,宿欣宇,袁钟,彭德中,刘益志..基于深度孪生自回归网络的无监督异常用电检测[J].计算机应用研究,2023,40(12):3717-3722,3727,7.基金项目
国网四川省电力公司科技项目(521997230015) （521997230015）
