Abstract

With the amount of global network traffic steadily increasing, mainly due to video streaming services, network operators are faced with the challenge of efficiently managing their resources while meeting customer demands and expectations. A prerequisite for such Quality-of-Experience-driven (QoE) network traffic management is the monitoring and inference of application-level performance in terms of video Key Performance Indicators (KPIs) that directly influence end-user QoE. Given the persistent adoption of end-to-end encryption, operators lack direct insights into video quality metrics such as start-up delays, resolutions, or stalling events, which are needed to adequately estimate QoE and drive resource management decisions. Numerous solutions have been proposed to tackle this challenge on individual use-cases, most of them relying on machine learning (ML) for inferring KPIs from observable traffic patterns and statistics. In this paper, we summarize the key findings in state-of-the-art research on the topic. Going beyond previous work, we devise the concept of a generic framework for ML-based QoE/KPI monitoring of HTTP adaptive streaming (HAS) services, including model training, deployment, and re- evaluation. Components of the framework are designed in a generic way, independent of a particular streaming service and platform. The methodology for applying different framework components is discussed across various use-cases. In particular, we demonstrate framework applicability in a concrete use-case involving the YouTube service delivered to smartphones via the mobile YouTube app, as this presents one of the most prominent examples of accessing YouTube. We tackle both QoE/KPI estimation on a per-video-session level (utilizing the validated ITU-T P.1203 QoE model), as well as “real-time” KPI estimation over short time intervals. Obtained results provide important insights and challenges related to the deployment of a generic in-network QoE monitoring framework for encrypted video streams.

Highlights

  • With the rapid growth of global mobile Internet traffic, it has become critical to manage network traffic flows in such a way as to provide a satisfactory experience to end users, while efficiently using limited resources

  • We further present a methodology for session-level Quality of Experience (QoE)/Key Performance Indicators (KPIs) estimation model training relying on simple packet-size–based features applicable for any HTTP adaptive streaming (HAS) use-case, regardless of used protocols and streaming algorithm

  • With the adoption of encryption, such solutions were for the most part no longer viable, which opened up new research questions related to in-network QoE estimation based on the analysis of encrypted video traffic

Read more

Summary

INTRODUCTION

With the rapid growth of global mobile Internet traffic, it has become critical to manage network traffic flows in such a way as to provide a satisfactory experience to end users, while efficiently using limited resources. Due to the adoption of traffic encryption and the dynamics introduced by HAS, it is becoming increasingly challenging for network operators to monitor service performance at the application level, which is crucial when aiming to estimate end users’ QoE. New application-level ground truth data can be collected to re-evaluate models over time and detect the need for a model update Such updates may be necessary in response to changes such as those related to Over The Top (OTT) service quality adaptation logic, or changes in underlying protocols (e.g., move from TCP/TLS to UDP/QUIC). We propose a generic, flexible, and extensible framework for in-network QoE/KPI monitoring of encrypted video streams, consisting of components related to model training, deployment, and re-evaluation.

AND RELATED WORK
DATASETS AND ADDRESSED RESEARCH TOPICS
Findings
CONCLUSIONS AND FUTURE RESEARCH
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call