Anomaly detection

The Anomaly detection module could also be called Baseline in Canopsis.

It allows to identify and alert the user when an anomaly is detected in relation to a projection.

The first step is to identify or define reference periods for measurements, and then to warn when the cycle is not following its usual course. This is called an anomaly.

The first iteration of the Anomaly detection module focuses on data sources (connectors). A new anomaly detection service is introduced, based on the Isolation Forest algorithm and relying on TimescaleDB. It enables:

• Monitor the frequency of events emitted by each connector,
• Automatically detect flow anomalies (too many/enough events),
• Save results in a dedicated table (event_anomaly),
• Make this information available for display in a connector dashboard.

This first step paves the way for a wider extension of the Anomaly detection module to other areas (alarms, services, etc.).

For further information about KPI / Return on Investment, visit the Canopsis documentation (in French, please use your browser translator to read in other languages).