Discovering unexpected changes in system behavior or performance is satisfied by this use case:

Anomaly detection is the AIOps use case that specifically addresses the discovery of unexpected changes. It involves establishing a dynamic baseline of what constitutes normal system behavior and performance metrics over time. The AIOps platform then continuously monitors the system, automatically identifying and alerting on any significant deviations or outliers from this established baseline. This proactive approach helps find problems before they escalate.

A. Event correlation groups known, related events together; it does not inherently discover new or unexpected patterns of behavior.
C. Root cause analysis is a reactive process performed after an anomaly or failure has already been detected to find its origin.
D. Alert noise reduction focuses on filtering and prioritizing the existing stream of alerts, not on discovering novel behavioral changes within the system data.

1. PeopleCert. (2022). PeopleCert AIOps Foundation Candidate Syllabus. Version 1.0, Section 3.2.1, "Key AIOps Use Cases," explicitly defines Anomaly Detection as the discovery of unusual or unexpected system behavior against a performance baseline.

2. Chandola, V., Banerjee, A., & Kumar, V. (2009). Anomaly detection: A survey. ACM Computing Surveys (CSUR), 41(3), 1-58. https://doi.org/10.1145/1541880.1541882. This foundational academic paper defines anomalies as patterns that do not conform to expected behavior.