AI(Artificial Intelligence) to support Event Management in London Release

[Manikandan Subr]

Hi,

Good day to you. I wanted to understand how Artificial Intelligence in London release can support Event Management.

For Example, today i have set up my event management to trigger an Incident when the Memory usage goes more than 90%, but this is a static approach. Can we set up any Artificial Intelligence to identify the pattern of the Server memory usage and if it is a regular pattern then trigger a warning or if any irregular pattern then trigger an Incident. 

I heard that there is some new features available in London release on Artificial Intelligence, so i want to explore on the same.

Any support will be appreciated

Thanks,

Manikandan

[Tony Branton]

Machine Learning features are available in Event Management and also in Operational Intelligence.

Event Management features machine learning to automatically:

• Aggregate alerts to create alert groups.
• Correlate alerts based on CI relationships to create CMDB alert groups.
• Analyze existing alerts in an automated alert group, to predict future alerts for that group.
• Identify Root Cause CIs in automated alert groups or application service maps.

Read more about these features in the Alert aggregation and RCA in the Product Documentation.

A solution that is more likely to address your requirement is Operational Intelligence.  Although Operational Intelligence is licensed separately from Event Management, it requires Event Management.

Operational Intelligence learns from historical metric data, and builds standard statistical models to project expected metric values along with upper and lower bounds. Operational Intelligence then uses these projections to detect statistical outliers and to calculate anomaly scores. High anomaly scores for CI attributes can indicate that a CI is at risk of causing a service outage. Anomaly alerts can be promoted to regular alerts and appear on the Alert Console and service health dashboard in Event Management for preventive actions.

Metric data is collected by various data sources such as SCOM, SolarWinds, Nagios XI, AWS CloudWatch and Azure. These monitoring systems collects metric data from the source environment regularly. Operational Intelligence captures the raw data from these monitoring systems, and uses event rules and the CMDB identification engine to map this data to existing CIs. Operational Intelligence then analyzes the data to detect anomalies and to provide other statistical scores. By default, Operational Intelligence is already partially configured for using some data sources.

More information can be found in Understanding Operational Intelligence in the Product Documentation.