Overview of AI Model Monitor

AI Model Monitor User Manual

Portfolio
Industrial AI
Product
AI Model Monitor
Software version
2.0.0
Language
en-US

The main goal of the AI Model Monitor Agent is to collect the metrics that are related to the execution of pipelines in AI Inference Server and their environment. It is assumed that AI Inference Server executes valid pipelines.

Metrics contain:

  • Device level information from AI Edge Runtime

  • Pipeline level information from AI Inference Server

  • Metrics added with AI SDK Monitoring Extension

  • Custom metrics defined in AI SDK

The collected metrics are stored in a Prometheus database inside the AI Model Monitor Agent application, which provides Prometheus functionalities such as monitoring or alerting.

The AI Model Monitor application can be configured as a central metrics collector of multiple AI Model Monitor Agents installed on different IEDs. The application provides a Prometheus user interface where the received metric data can be queried. In addition, AI Model Monitor is prepared to be connected as data source to an externally hosted visualization application, for instance Grafana.

AI Model Monitor Agent****functionalities:

  • Obtain and store metrics

  • Analyze metrics directly on the IED via Prometheus

  • Configure alerting rules

  • Send alerts to configured receivers

  • Forward metrics to central AI Model Monitor application

AI Model Monitor****functionalities:

  • Receive and store metrics centrally