Intent-based Control Loop for DASH Video Service Assurance using ML-based Edge QoE Estimation

Intent-Based Networking (IBN) proposals are based on autonomous closed-loop orchestration architectures that monitor and tune network performance. To this end, IBN defines high-level policies and actions implemented by a closed-loop system. This work demonstrates a Closed Control Loop (CCL) architecture for video service assurance using Machine Learning (ML) based Quality of Experience (QoE) estimation at edge nodes. As part of the solution, network-level Quality of Service (QoS) metrics patterns (e.g., RTT, Throughput) collected through flow-level monitoring are used to build a QoS-to-QoE correlation model tailored to specific target network regions, user groups, and services, in our case DASH video streaming. The demo will showcase the CCL workflow triggering the Orchestrator to take appropriate network-level actions to overcome network QoS degradations and restore the QoE target based on the intent associated with the video service.