Approaches to High Resolution Network Telemetry & Analytics with Machine Learning

Tags:
Network measurement and analytics are key to the overall operations, planning and root-cause analysis of issues within network infrastructure. The increased line rate (100+Gbps) of network connections along with the explosion in data transfer needs for scientific datasets has changed the methodology of effectively monitoring network infrastructure. Network measurement utilizing 5 minute polling intervals with binary threshold based alerting has proven to be unreliable for accurate measurement and alerting of critical network systems. This presentation will discuss the ongoing efforts at NCSA to gather high resolution (< 10s polling period) network telemetry data utilizing SNMP and YANG with machine learning being utilized to analyze and generate alerts on the data being collected.