Database Autonomy Service (DAS) provides the anomaly detection feature to detect exceptions 24/7 based on machine learning and fine-grained monitoring data. This detection mechanism allows DAS to detect database exceptions faster than traditional threshold-based alerting mechanisms. This topic provides the benefits of this feature and describes how to view the detection results.


  • The database instance that you want to manage is of one of the following types:
    • ApsaraDB RDS for MySQL
    • ApsaraDB MyBase for MySQL
    • ApsaraDB RDS for PostgreSQL
    • ApsaraDB for Redis instance
    • PolarDB for MySQL Cluster Edition
  • The database instance is connected to DAS and is in the Accessed state.
    Note For more information about how to connect a database instance to DAS, see Access instances.


ItemTraditional solutionDAS
MethodRule- or threshold-based AI-based
Monitored objectsMetrics A wide range of objects, such as metrics, SQL statements, logs, locks, and O&M events
LatencyFrom 5 minutes to one or more days Quasi-real-time
Detection methodFault-driven Exception-driven
Periodic detectionNot supported Automatic and periodic
AdaptabilityNot supported Adaptive to services that have different characteristics
PredictionNot supported Supported

View anomaly detection results

In the autonomy center, you can view events that are detected within a specific time range. For example, you can view exceptions, optimization suggestions, auto scaling events, and other events.

  1. Log on to the DAS console.
  2. In the left-side navigation pane, click Instance Monitoring.
  3. On the page that appears, find the database instance that you want to manage and click the instance ID. The instance details page appears.
  4. In the left-side navigation pane, click Autonomy Center.
  5. Select a time range to view the anomaly detection results within the specified time range. Anomaly Detection


Q: How is the change rate of the related metric in the Analysis of Abnormal Metrics section of the Anomaly Snapshots tab of the Anomaly Detection of Metrics (Time Series Anomaly Detection) event calculated? Abnormal Metric

A: Change rate of the metric = Actual metric value/Predicated metric value. DAS uses the data at a granularity of hours of a database instance in a specific past period of time to predict the metric value of the database instance in the current time range. The predicted metric value is used as a baseline and compared with the actual metric value. This way, the change rate of the metric is calculated.