Proceedings of the ACM SIGCOMM 2021 Workshop on Network-Application Integration | 2021
Characterizing the Relationship Between Application QoE and Network QoS for Real-Time Services
Abstract
Real-time services require a good interplay between network and application dynamics in order to deliver a satisfactory user experience. The traditional monitoring and optimization of Quality of Service (QoS) parameters in the network lacks of knowledge of user s Quality of Experience (QoE) and, as a result, of efficiency in improving user experience. In this paper, we aim at providing a characterization of the relationship between QoS parameters and QoE indicators to drive in-network learning and online QoE inference. To do so, we consider three complementary RTC QoE metrics and conduct an extensive study on Cisco Webex of the impact of network impairments on application performance. Our analysis takes into account the effects of different monitoring vantage points on the inference and allows to define inference models accordingly. Finally, the application of learned models in-the-wild shows promising results illustrating the potential of the approach.