How NetBackup detects backup anomalies
Example scenario
An organization usually backs up about 1 GB of data each day for a specific client and using a backup policy. If the backup size increases to 10 GB on a given day, NetBackup identifies and reports it as an image size anomaly because the current image size is much larger than the typical 1 GB size.
How the anomaly score is calculated
The anomaly score is calculated by comparing the current data with a cluster of similar historical observations. In this example, the cluster consists of backups that are about 1 GB. Higher anomaly scores indicate greater severity.
Significant deviation in the metadata is termed as an anomaly based on its anomaly score.
An anomaly score is calculated based on how far the current data is from the cluster of similar observations of the data in the past. In this example, a cluster is of 1 GB of data backups. You can determine the severity of anomalies based on their scores.
For example:
Anomaly score of Anomaly A = 7
Anomaly score of Anomaly B = 2
Anomaly A has a higher anomaly score than Anomaly B. Showing a more significant deviation from prior backups.
NetBackup considers the configured anomaly detection settings, including default and advanced settings when available, during anomaly detection.