PI: Sejun Song

Traditional application-driven (i.e., fault, SLA, or DoS attack detection) “pull” model (SNMP) based network management is expensive and slow for network problem detection, isolation, and root cause analysis. Especially, the recent federation of novel softwareisation and virtualization architectures, as well as Internet of Things (IoT) technologies, require better management over the heterogeneous systems and services. The project adopts “push” based open source forwarding (streaming) network management technologies by using P4 (Programming Protocol-Independent Packet Processors) Inband Network Telemetry (INT). For the scalable and real-time network service management, multi-source information fusion on the intelligent edge plays one of the most critical roles. This project 1) pioneers INT methods to facilitate efficient system information and packet-level data, and 2) designs and develops real-time information fusion algorithms on the intelligent edge that correlates multi-source micro and macro streaming telemetry data. The success of this project will lead to the learning-based data-driven network management for the next-generation virtualized networks and infrastructure.