An Augmented Autoregressive Approach to HTTP Video Stream Quality Prediction

TL;DR

This paper introduces an augmented autoregressive model for predicting continuous-time video quality in HTTP streaming, leveraging multiple inputs and ensemble techniques to enhance accuracy and reduce errors.

Contribution

It proposes a novel non-linear autoregressive approach that incorporates multiple video quality models and ensemble averaging for improved quality prediction.

Findings

Enhanced prediction accuracy with multiple inputs.

Reduced forecasting errors through ensemble techniques.

Improved quality of experience optimization.

Abstract

HTTP-based video streaming technologies allow for flexible rate selection strategies that account for time-varying network conditions. Such rate changes may adversely affect the user's Quality of Experience; hence online prediction of the time varying subjective quality can lead to perceptually optimised bitrate allocation policies. Recent studies have proposed to use dynamic network approaches for continuous-time prediction; yet they do not consider multiple video quality models as inputs nor consider forecasting ensembles. Here we address the problem of predicting continuous-time subjective quality using multiple inputs fed to a non-linear autoregressive network. By considering multiple network configurations and by applying simple averaging forecasting techniques, we are able to considerably improve prediction performance and decrease forecasting errors.