Document Type

Conference Paper

Rights

Available under a Creative Commons Attribution Non-Commercial Share Alike 4.0 International Licence

Disciplines

Computer Sciences

Abstract

To guarantee quality of delivery for video streaming over software defined networks, efficient predictors and adaptive routing frameworks are required. We demonstrate an agent that predicts video quality of delivery metrics in a scalable way using a bespoke codec-aware learning model. We also demonstrate the integration of this agent with an adaptive framework for centrally controlled software-defined networks that re-configures network operational paths in response to the learning agent, ensuring that good quality of delivery of video is maintained during periods of congestion. The demo scenario highlights the feasibility, scalability and accuracy of the framework

DOI

https://doi.org/10.21427/4vmv-g820

Download


Share

COinS