Adaptation Logic for HTTP Dynamic Adaptive Streaming using Geo-Predictive Crowdsourcing

TL;DR

This paper introduces a crowd-based adaptation algorithm for HTTP streaming that leverages a large crowdsourcing dataset to improve Quality of Experience (QoE) over existing methods.

Contribution

It presents a novel crowd-informed adaptation algorithm and demonstrates how to integrate crowd knowledge into existing streaming algorithms.

Findings

Our algorithm outperforms state-of-the-art methods in QoE metrics.

Utilizing crowd data significantly improves streaming adaptation decisions.

Large real-life dataset validates the effectiveness of the proposed approach.

Abstract

The increasing demand for video streaming services with high Quality of Experience (QoE) has prompted a lot of research on client-side adaptation logic approaches. However, most algorithms use the client's previous download experience and do not use a crowd knowledge database generated by users of a professional service. We propose a new crowd algorithm that maximizes the QoE. Additionally, we show how crowd information can be integrated into existing algorithms and illustrate this with two state-of-the-art algorithms. We evaluate our algorithm and state-of-the-art algorithms (including our modified algorithms) on a large, real-life crowdsourcing dataset that contains 336,551 samples on network performance. The dataset was provided by WeFi LTD. Our new algorithm outperforms all other methods in terms of QoS (eMOS).