Cisco Cloud Observability Anomaly Detection automatically determines whether every service in your application performs within the acceptable performance limits. It uses machine learning capabilities to continuously monitor latency, error, and throughput of services to identify abnormal behavior. This helps reduce the Mean Time To Detection (MTTD) for application performance problems.
From Observe >Application Performance Monitoring>Services, select a service to view the detected anomaly details for that service. The color-coded status symbol next to Anomaly Detection in the Health and Alerting section depicts the overall status of the service.
Icon
Description
Indicates the detected anomalies are in critical state. You may want to take corrective actions.
Indicates the detected anomalies are in unknown state. An anomaly is rendered to an unknown state when there is not enough data to deterministically evaluate it.
Indicates the detected anomalies are in warning state.
No indicator implies that the service is performing within the expected range.
You can view the relationship between the selected service and other services as a flow map or a list.
Anomaly Detection is enabled by default for all services in the application. It takes 48 hours for machine learning to model train on the services in your application. Click Configure>Anomaly Detectionto view the model training status and other details of all the services. SeeModel Training.
