Monitoring service predictions

Every twenty minutes, the algorithm considers the past 8 hours of data to forecast data for the next 24 hours. The data that has been forecasted for the next 24 hours is checked against the alarm policy. At any point in time, if the forecasted data meets the policy condition, a prediction event is generated. If the forecasted data does not violate the policy condition, the open prediction event is closed. 

Conditions for generating prediction events

 Prediction events are generated based on one of the following conditions:

• Alarm policy violation: ​​Prediction events are generated when the service health indicators violate the thresholds defined in the alarm policies that are configured for these health indicators in BMC Helix Operations Management. 
  ​​Alarm policies can be configured to consider the user-defined thresholds, baseline threshold, or both. For more information, see Alarm policies.

• Baseline data violation: Prediction events are generated when service health indicators violate the baseline threshhold. Low and high baseline values for a metric are calculated based on historical data in BMC Helix Operations Management. Baseline calculation begins after six hours of aggregated data is available for a metric. For more information, see Autoanomalies.
  Predictions based on baseline data are generated only if the Generate auto anomaly events option is enabled.
   

  Important

  Prediction events are generated based only on the baseline data when no alarm policy is configured for a health indicator. If a policy exists, prediction events are generated based on the conditions defined in the policy.  

   

Use the information in the following section to view, analyze, and understand the service failure prediction events.

Before you begin

To enable BMC Helix AIOps to generate predictions, perform the following tasks: 

1. Enable the service-centric predictions feature for BMC Helix AIOps.
   For more information, see Enabling-the-AIOps-features.
2. Make sure the service model is created by using BMC Helix AIOps and configured with health indicators. 
   For more information, see Creating service models.
3. Make sure that one of the following prerequisites is met: 
   • Alarm policies are configured for the health indiators.
     When adding health indicators, the service designers are automatically redirected to the BMC Helix Operations Management console to configure the alarm policies for the health indicators. If one of the policy conditions considers the baseline data, make sure the baseline data is enabled for that health indicator. 
     For more information about creating or editing an alarm policy, see Configuring alarm policies.
   • The baseline data is available for the service health indicators and the Generate auto anomaly events option is enabled in the Auto Anomalies configuration in BMC Helix Operations Management. For more information, see Configuring autoanomaly event generation.​​​
     
     Tip: To query whether the baseline data is enabled for a health indicator, and to enable the baseline data, use the BMC Helix Operations Manager GET and PUT endpoints. For information about the endpoints, see Alarm policy baseline metric management endpoints in the REST API.

To monitor service prediction events

1. Click Predictions to see the service prediction events. 
2. For each prediction event, view the list of potentially impacted services and their corresponding health indicators, forecast of impact, and severity of prediction.
   By default, the prediction is shown for the next 12 hours.
   • Service: Name of service to be impacted.
   • Metric: Health indicator for which the threshold limit is predicted to breach.
   • First Impact: First time the service impact occurs. 
   • Predicted Severity: Forecasted severity when the first impact occurs.

3. Click the expander button adjacent to the service name to view the prediction graph.

   The prediction graph

   The prediction graph contains two sections divided by a vertical line. The left of the vertical line is the historical data graph, and the right of the vertical line is the prediction analysis graph based on that historical data. The dotted orange line indicates the threshold line. The circular red dot on the right of the vertical line is the point where the threshold breach is predicted to occur. At any point in time, the algorithm considers the past 8 hours of data to forecast for the next 24 hours. For services with multiple metrics, each metric can have a predictive event. 
   

4. (Optional) For performing automation actions or working with the other optional UI elements, see the following information:
   ​​
   • Run an automation action or create/request an automated correction for the anticipated service failure: From the Automations column, run an existing automation, if it exists or from the Actions column, click the action menu and select an option to create or request for an automation. For more information, see Remediating-services-and-situations.
   • ​​Change the prediction period to shorten or extend it: Select a time range to view future or past predictions.
     • In the relative time range, select a duration to view future predictions (Next 3 hours, Next 6 hours, Next 12 hours, or Next 24 hours) or prediction events that occurred in the past (Last 24 hours, Last 7 days, or Last 30 days). By default, the list shows the services to be impacted after the next 12 hours. ​Generally, open predictions are displayed when you select a future time range, and closed predictions are displayed when you select a past time range.
     • In the absolute time range, select the start and end dates for which you want to see the predictions. In this view, both open and closed predictions are displayed.  
   • Filter the list of potentially impacted services: Click Advanced Filters and specify a suitable criteria to filter the list by one or all the criteria:
     • Service name
     • Prediction severity (Critical, Major, Minor, Warning, Information)
     • Status (Open, Closed). By default, the status is set to Open. 
   • Hide or view columns according to your choice: Click the column selector menu and select or clear the column names that you want to view or hide.

The prediction event is classified as an Info type event in BMC Helix Operations Management. From the Others tab, on the Event Details page, you can check the Predicted Severity for the event. For more information about event details, see Viewing event details.

Viewing historical service predictions in BMC Helix Dashboards

BMC Helix AIOps provides the past predictions analysis view of all the services in BMC Helix Dashboards. As an operator or SRE, use the Prediction Analysis dashboard in BMC Helix Dashboards to do the following:

• View the prediction analysis. By default, the analysis is displayed for the last 15 days. The analysis can be viewed up to 90 days
• Troubleshoot an issue
• Analyze a prediction event in the recent past that is connected to a current issue
• Get insights into past predictions that help in identifying issues that impact a service the most 
• Set up a high alert for the most impactful events in advance
• Optimize and minimize service degradation through proactive remediation

To view historical service predictions

1. Log in to BMC Helix Portal as an operator or SRE.
2. Click the BMC Helix Dashboards tile.
3. From the navigation menu, click Dashboards. 
4. From the Operations Management folder, locate the Prediction Analysis dashboard. ​​​By default, the prediction analysis is shown for the last 15 days.
   

5. Change the number of days to view and analyze the past prediction data of your choice.
   For more information, see Prediction Analysis dashboard.

FAQ