Abstract
Currently, multivariate time series anomaly detection has made great progress in many fields and occupied an important position. The common limitation of many related studies is that there is only temporal pattern without capturing the relationship between variables and the loss of information leads to false warnings. Our article proposes an unsupervised multivariate time series anomaly detection. In the prediction part, multiscale convolution and graph attention network are mainly used to capture information in temporal pattern with feature pattern. The threshold selection part uses the root mean square error between the predicted value and the actual value to perform extreme value analysis to obtain the threshold. Finally, the model in this paper outperforms other latest models on actual datasets.
Funding Information
  • National Natural Science Foundation of China (62072024, 61473111, UDC2019033324, UDC2017033322, KYJJ2017017, 2018A0303130026, F2018201096)
  • Beijing University of Civil Engineering and Architecture (62072024, 61473111, UDC2019033324, UDC2017033322, KYJJ2017017, 2018A0303130026, F2018201096)
  • Scientific Research Foundation of Beijing University of Civil Engineering and Architecture (62072024, 61473111, UDC2019033324, UDC2017033322, KYJJ2017017, 2018A0303130026, F2018201096)
  • Natural Science Foundation of Guangdong Province (62072024, 61473111, UDC2019033324, UDC2017033322, KYJJ2017017, 2018A0303130026, F2018201096)
  • Natural Science Foundation of Hebei Province (62072024, 61473111, UDC2019033324, UDC2017033322, KYJJ2017017, 2018A0303130026, F2018201096)

This publication has 13 references indexed in Scilit: