Quality-of-Service assessment on YouTube video streaming on encrypted network traffic and machine learning approach to classify key quality indicators

Abstract

Video streaming applications generate the most internet traffic today. Consequently, monitoring and management of video streaming quality has gained a significant importance in the recent years. The disturbances in the video, such as, amount of buffering and bitrate adaptations affect user Quality of Service (QoS). Network operators usually monitor such events from network traffic with the help of Deep Packet Inspection (DPI). However, it is becoming difficult to monitor such events due to the traffic encryption. To address this challenge, this thesis work makes the key contribution to present a test-bed, which performs automated video streaming tests under controlled time-varying network conditions and measures performance at network and application level. In other words, the objective is to monitor encrypted YouTube traffic (in HTTPS/QUIC) and extract information about the Key Quality Indicators (KQIs), such as startup delay, re-buffering time and events, quality changes.