DDA: Cross-Session Throughput Prediction with Applications to Video Bitrate Selection

TL;DR

This paper introduces DDA, a cross-session throughput predictor that leverages session similarity to improve initial video bitrate selection, significantly enhancing user experience in streaming.

Contribution

The paper develops DDA, a novel throughput prediction method that outperforms existing algorithms by utilizing cross-session similarities for better accuracy.

Findings

DDA achieves >50% lower prediction error than other algorithms.

Using DDA enables 4x higher average initial bitrate in video streaming.

Improved prediction accuracy leads to better user experience.

Abstract

User experience of video streaming could be greatly improved by selecting a high-yet-sustainable initial video bitrate, and it is therefore critical to accurately predict throughput before a video session starts. Inspired by previous studies that show similarity among throughput of similar sessions (e.g., those sharing same bottleneck link), we argue for a cross-session prediction approach, where throughput measured on other sessions is used to predict the throughput of a new session. In this paper, we study the challenges of cross-session throughput prediction, develop an accurate throughput predictor called DDA, and evaluate the performance of the predictor with real-world datasets. We show that DDA can predict throughput more accurately than simple predictors and conventional machine learning algorithms; e.g., DDA's 80%ile prediction error of DDA is > 50% lower than other algorithms. We also show that this improved accuracy enables video players to select a higher sustainable initial bitrate; e.g., compared to initial bitrate without prediction, DDA leads to 4x higher average bitrate.