RobustTAD: Robust Time Series Anomaly Detection via Decomposition and Convolutional Neural Networks

Abstract

The monitoring and management of numerous and diverse time series data at Alibaba Group calls for an effective and scalable time series anomaly detection service. In this paper, we propose RobustTAD, a Robust Time series Anomaly Detection framework by integrating robust seasonal-trend decomposition and convolutional neural network for time series data. The seasonal-trend decomposition can effectively handle complicated patterns in time series, and meanwhile significantly simplifies the architecture of the neural network, which is an encoder-decoder architecture with skip connections. This architecture can effectively capture the multi-scale information from time series, which is very useful in anomaly detection. Due to the limited labeled data in time series anomaly detection, we systematically investigate data augmentation methods in both time and frequency domains. We also introduce label-based weight and value-based weight in the loss function by utilizing the unbalanced nature of the time series anomaly detection problem. Compared with the widely used forecasting-based anomaly detection algorithms, decomposition-based algorithms, traditional statistical algorithms, as well as recent neural network based algorithms, RobustTAD performs significantly better on public benchmark datasets. It is deployed as a public online service and widely adopted in different business scenarios at Alibaba Group.

Extended version of the paper at ACM SIGKDD Workshop on Mining and Learning from Time Series (KDD-MiLeTS 2020); 9 pages, 5 figures, and 2 tables

References in corpus (7)

• Time-Series Anomaly Detection Service at Microsoft
• Time Series Anomaly Detection Using Convolutional Neural Networks and Transfer Learning
• A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data
• RobustPeriod: Time-Frequency Mining for Robust Multiple Periodicity Detection
• Data augmentation using synthetic data for time series classification with deep residual networks
• On the Runtime-Efficacy Trade-off of Anomaly Detection Techniques for Real-Time Streaming Data
• An Adaptive Approach for Anomaly Detector Selection and Fine-Tuning in Time Series

Cited by in corpus (7)

• An Empirical Survey of Data Augmentation for Time Series Classification with Neural Networks
• Artificial Intelligence based Anomaly Detection of Energy Consumption in Buildings: A Review, Current Trends and New Perspectives
• TFAD: A Decomposition Time Series Anomaly Detection Architecture with Time-Frequency Analysis
• RobustPeriod: Time-Frequency Mining for Robust Multiple Periodicity Detection
• Role of Data Augmentation Strategies in Knowledge Distillation for Wearable Sensor Data
• Sintel: A Machine Learning Framework to Extract Insights from Signals
• NVAE-GAN Based Approach for Unsupervised Time Series Anomaly Detection