Speaker
Description
As networks grow in scale and complexity, traditional monitoring tools struggle to track subtle deviations and manage increasing incident volumes. Modern applications depend on stable latency, packet loss, and jitter, where small variations can degrade user experience. Machine Learning offers an intelligent approach to anomaly detection by learning baseline behavior and identifying deviations without static thresholds. By analyzing large sets of measurements, ML enhances situational awareness, accelerates troubleshooting, and improves reliability. This presentation discusses how ML techniques support anomaly detection in RNP network operations.
What will the TNC audience take away from your talk?
How to integrate Machine Learning into network operations without compromising reliability.
Which data sources (telemetry, NetFlow, synthetic tests, syslog) matter most for anomaly detection.
Practical benefits: fewer false positives, smarter alert prioritization, and adaptive detection.
Real-world challenges: anomaly classification, alert filtering, and root cause correlation.
A roadmap toward AIOps—moving from detection to intelligent automation.
| Are you a first time speaker at TNC? | Yes |
|---|
