Towards User-level QoE: Large-scale Practice in Personalized Optimization of Adaptive Video Streaming

TL;DR

This paper introduces LingXi, a large-scale personalized adaptive video streaming system that optimizes user experience by analyzing engagement metrics and dynamically adjusting streaming parameters, leading to measurable improvements in viewing time and stall reduction.

Contribution

LingXi is the first large-scale deployed system for user-level QoE optimization in adaptive streaming, using engagement-based metrics and Bayesian optimization for personalized parameter tuning.

Findings

Achieved a 0.15% increase in total viewing time.

Reduced stall time by 1.3% overall, 15% for low-bandwidth users.

Demonstrated superior performance through large-scale A/B testing on Kuaishou.

Abstract

Traditional optimization methods based on system-wide Quality of Service (QoS) metrics have approached their performance limitations in modern large-scale streaming systems. However, aligning user-level Quality of Experience~(QoE) with algorithmic optimization objectives remains an unresolved challenge. Therefore, we propose \texttt{LingXi}, the first large-scale deployed system for personalized adaptive video streaming based on user-level experience. \texttt{LingXi} dynamically optimizes the objectives of adaptive video streaming algorithms by analyzing user engagement. Utilizing exit rate as a key metric, we investigate the correlation between QoS indicators and exit rates based on production environment logs, subsequently developing a personalized exit rate predictor. Through Monte Carlo sampling and online Bayesian optimization, we iteratively determine optimal parameters. Large-scale A/B testing utilizing 8\% of traffic on Kuaishou, one of the largest short video platforms, demonstrates \texttt{LingXi}'s superior performance. \texttt{LingXi} achieves a 0.15\% increase in total viewing time, a 0.1\% improvement in bitrate, and a 1.3\% reduction in stall time across all users, with particularly significant improvements for low-bandwidth users who experience a 15\% reduction in stall time.