Abstract
To ensure the normal operation of the system, the enterprise’s operations engineer will monitor the system through the KPI (key performance indicator). For example, web page visits, server memory utilization, etc. KPI anomaly detection is a core technology, which is of great significance for rapid fault detection and repair. This paper proposes a novel dual-stage attention-based LSTM-VAE (DA-LSTM-VAE) model for KPI anomaly detection. Firstly, in order to capture time correlation in KPI data, long–short-term memory (LSTM) units are used to replace traditional neurons in the variational autoencoder (VAE). Then, in order to improve the effect of KPI anomaly detection, an attention mechanism is introduced into the input stage of the encoder and decoder, respectively. During the input stage of the encoder, a time attention mechanism is adopted to assign different weights to different time points, which can adaptively select important input sequences to avoid the influence of noise in the data. During the input stage of the decoder, a feature attention mechanism is adopted to adaptively select important latent variable representations, which can capture the long-term dependence of time series better. In addition, this paper proposes an adaptive threshold method based on anomaly scores measured by reconstruction probability, which can minimize false positives and false negatives and avoid adjustment of the threshold manually. Experimental results in a public dataset show that the proposed method in this paper outperforms other baseline methods.
Funder
National Natural Science Foundation of China
Subject
General Physics and Astronomy
Reference40 articles.
1. Intelligent operation and maintenance based on machine learning;Commun. CCF,2017
2. He, S., Yang, B., and Qiao, Q. (2021, January 23–25). Overview of Key Performance Indicator Anomaly Detection. Proceedings of the IEEE Region 10 Symposium (TENSYMP), Jeju, Republic of Korea.
3. Optimization of statistical methodologies for anomaly detection in gas turbine dynamic time series;J. Eng. Gas Turbines Power,2018
4. Reis, B.Y., and Mandl, K.D. (2003). Time series modeling for syndromic surveillance. BMC Med. Inform. Decis. Mak., 3.
5. Malhotra, P., Vig, L., Shroff, G., and Agarwal, P. (2015, January 22–24). Long Short Term Memory Networks for Anomaly Detection in Time Series. Proceedings of the 23rd European Symposium on Artificial Neural Networks (ESANN), Bruges, Belgium.
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献