基于图注意力机制和Transformer的异常检测
Abnormal Detection Based on Graph Attention Mechanisms and Transformer

严莉 ¹ ^* 张凯 ¹ 徐浩 ¹ 韩圣亚 ¹ 刘珅岐 ¹ 史玉良 ²

文摘	异常检测对电力行业的发展有着重要的影响,如何根据大规模电力数据进行异常检测是重要的研究热点.目前,大多数研究通过聚类或神经网络进行异常检测.但是这些方法忽略了时序数据之间潜在的关联关系及某些特点的重要信息,没有充分挖掘出数据的潜在价值.因此,提出了一种基于图注意力和Transformer的异常检测模型.该模型首先根据数据中台中获取的电力数据(主要包括用户ID、电能表ID、用户类型、电流、电压、功率等数据)构建一个异构信息网络;然后,为了减少模型参数和避免出现过拟合的现象,在图卷积网络(Graph Convolutional Network, GCN)模型的基础上,引入非负矩阵分解(Non-Negative Matrix Factorization,NNMF)的方法来进行相似性学习;最后采用图注意力网络(Graph Attention Network,GAT)和Transformer共同捕获数据间的相互关联关系,从而提高检测精度.以中国某地区的电力数据为基础进行验证,实验结果表明所提出的方法可以有效进行异常检测.
其他语种文摘	Anomaly detection has an important impact on the development of the electric power industry, and how to detect anomalies based on large-scale power data is a research hotspot. At present, most researches use clustering or neural network to detect anomalies. But these methods ignore the potential relationship between the data and miss some specific important information, and do not fully exploit the potential value of the data. Therefore, an abnormal detection model based on graph attention and transformer is proposed. The model first constructs a heterogeneous information network based on the power data(mainly including user ID, meter ID, user type, electrical current, voltage, power, etc.)collected in the data center; then, in order to reduce the model parameters and avoid the phenomenon of overfitting, on the basis of the graph convolutional network(GCN)model, a non-negative matrix factorization(NNMF)method is introduced to perform similarity learning; finally, a graph attention network(GAT)and Transformer are jointly used to capture the correlation relationships between data, thus improving the detection accuracy. The validation analysis is carried out based on the power data of a region in China. The experimental results show that the proposed method can effectively perform anomaly detection.
来源	电子学报 ,2022,50(4):900-908 【核心库】
DOI	10.12263/DZXB.20210722
关键词	异常检测 ; 异构信息网络 ; 相似性学习 ; 图注意力网络 ; Transformer
地址	1. 国网山东省电力公司信息通信公司, 山东, 济南, 250013 2. 山东大学软件学院, 山东, 济南, 250101
语种	中文
文献类型	研究性论文
ISSN	0372-2112
学科	自动化技术、计算机技术
基金	国网山东省电力公司科技项目
文献收藏号	CSCD:7190616