GUIDE: Detect and monitor anomalies in systems and applications

[OdysLam]

The first Proof-of-Concept of local, distributed anomaly detection is here. Read the guides and learn how you not only detect anomalies in your system but also receive alarms whenever an anomalous behaviour is detected.

Kudos to @joel for these awesome guides.

Don’t forget the Megathread we have created to discuss and receive feedback about our anomaly detection:

Anomalies collector feedback megathread!

Hi @Morne_Supra thanks for trying it out! It will just drop and retrain a new model based on last 4 hours every 30 minutes. So if your system has very strong time patterns each day then this could be a limiting factor in how well the model could ever do (since only knows about last 4 hours). For some systems you might actually want this - you want the model to evolve and adapt as the system changes and new workloads come onto it etc. But for others, maybe web servers perhaps, you want to try …

Guides

Machine learning (ML) powered anomaly detection | Learn Netdata

Anomaly Advisor | Learn Netdata