VMware, Inc.
SYSTEM AND METHOD FOR DETECTING ANOMALIES BASED ON FEATURE SIGNATURE OF TASK WORKFLOWS

Abstract:

A system and method for detecting anomalies in task workflows uses a directed acyclic graph constructed using metrics for a workflow of a task collected from software entities that perform operations to execute the task. A feature signature of the task workflow is generated using key values extracted from the directed acyclic graph, which is then used to compute a similarity value by comparing the feature signature with a reference feature signature for a baseline task workflow. The similarity value is then used to diagnose any performance issues in the workflow of the task executed by the software entities.