Journal
NEUROCOMPUTING
Volume 448, Issue -, Pages 130-139Publisher
ELSEVIER
DOI: 10.1016/j.neucom.2021.03.062
Keywords
Time series; Unsupervised anomaly detection; Robust prediction
Categories
Funding
- Bonree Inc., Beijing, China
- National Natural Science Foundation of China [61572408, 61972326]
- Xiamen University [20720180074]
Ask authors/readers for more resources
In this paper, a joint model Predictor & Anomaly Detector (PAD) is proposed to address status prediction and anomaly detection tasks by combining variational auto-encoder (VAE) and long short-term memory (LSTM). The model utilizes the reconstructed time series by VAE for robust prediction and LSTM for maintaining long-term sequential patterns, leading to better performance in anomaly detection. Integration of spectral residual analysis further boosts the performance of VAE and LSTM in the whole processing pipeline.
Status prediction and anomaly detection are two fundamental tasks in automatic IT systems monitoring. In this paper, a joint model Predictor & Anomaly Detector (PAD) is proposed to address these two issues under one framework. In our design, the variational auto-encoder (VAE) and long short-term memory (LSTM) are joined together. The prediction block (LSTM) takes clean input from the reconstructed time series by VAE, which makes it robust to the anomalies and noise for prediction task. In the meantime, the LSTM block maintains the long-term sequential patterns, which are out of the sight of a VAE encoding window. This leads to the better performance of VAE in anomaly detection than it is trained alone. In the whole processing pipeline, the spectral residual analysis is integrated with VAE and LSTM to boost the performance of both. The superior performance on two tasks is confirmed with the experiments on two challenging evaluation benchmarks. (c) 2021 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available