QOE enhancement through cost-effective adaptation decision process for multiple-server streaming over HTTP

Abstract

Single-source HTTP Adaptive Streaming protocols (HAS), such as MPEG-DASH, have become the de-facto solutions to deliver video over the Internet. By avoiding buffer stalling events that are mainly caused by the lack of throughput at client or at server side, HAS protocols increase end-user's Quality of Experience (QoE). We propose to extend HAS capabilities to a pragmatic DASH-compliant Multiple-Source Streaming solution (MS-Stream) that simultaneously utilizes several servers. MS-Stream offers the opportunity to obtain higher QoE by exploiting expanded bandwidth and link diversity in heterogeneous distributed streaming infrastructures, such as distributed home-gateways or geographically distributed set-topboxes belonging to Over-The-Top video service providers. This paper exposes a cost-effective two-phase adaptation process with dual (i.e., bitrate and number of sources) adaptation decisioning prior segment request and in-segment download adaptation. Our approach was empirically evaluated for on-demand video streaming over the Internet. An online demonstration is also made available [1].

A Hybrid P2P/Multi-Server Quality-Adaptive Live-Streaming Solution Enhancing End-User's QoE

“…In order to address the issues of low QoE in P2P systems, lack of server-side throughput, and high scalability costs, we exploit the advantages of quality adaptation for hybrid P2P/multi-server live streaming. Deriving from the work [1][2][3][4][5], we demonstrate our solution for cost-and quality-adaptive hybrid P2P/multi-server livestreaming trading the system scalability and its QoE. We consider the use-case of a streaming provider delivering a live video at Q max qualities to N (t ) clients.…”