Refining the Optimization Target for Automatic Univariate Time Series Anomaly Detection in Monitoring Services
This work addresses the need for automation in industrial monitoring services to reduce manual effort, though it appears incremental as it builds on existing model backbones.
The paper tackled the problem of automating parameter optimization for univariate time series anomaly detection in monitoring services, proposing a framework with three optimization targets that was applied online to over 50,000 time series per minute for six months.
Time series anomaly detection is crucial for industrial monitoring services that handle a large volume of data, aiming to ensure reliability and optimize system performance. Existing methods often require extensive labeled resources and manual parameter selection, highlighting the need for automation. This paper proposes a comprehensive framework for automatic parameter optimization in time series anomaly detection models. The framework introduces three optimization targets: prediction score, shape score, and sensitivity score, which can be easily adapted to different model backbones without prior knowledge or manual labeling efforts. The proposed framework has been successfully applied online for over six months, serving more than 50,000 time series every minute. It simplifies the user's experience by requiring only an expected sensitive value, offering a user-friendly interface, and achieving desired detection results. Extensive evaluations conducted on public datasets and comparison with other methods further confirm the effectiveness of the proposed framework.