In this project, we present state-of-the-art bitrate adaptation algorithms for HTTP adaptive streaming (HAS) over the last several years.

In streaming media, it is imperative to deliver a good viewer experience to preserve customer loyalty. Prior research shows that this is rather diffcult when shared Internet resources struggle to meet the demand from streaming clients that are largely designed to behave in their own self-interest. To date, several schemes for adaptive streaming have been proposed to address this challenge with varying success. In this project, we take a different approach and develop a game theoretic approach. We present a practical implementation integrated in the dash.js reference player and provide substantial comparisons against the state-of-the-art methods using trace-driven and real-world experiments. Our approach outperforms its competitors in the average viewer experience by 38.5%, and in video stability by 62%.

HTTP adaptive streaming (HAS) is being adopted with increasing frequency and becoming the de-facto standard for video streaming. However, the client-driven, on-off adaptation behavior of HAS results in uneven bandwidth competition and this is exacerbated when a large number of clients share the same bottleneck network link and compete for the available bandwidth. With HAS each client independently strives to maximize its individual share of the available bandwidth, which leads to bandwidth competition and a decrease in end-user quality of experience (QoE). The competition causes scalability issues, which are quality instability, unfair bandwidth sharing and network resource underutilization. In this project, we propose a new software defined networking (SDN) based dynamic resource allocation and management architecture for HAS delivery systems, which aims to alleviate these scalability issues and improve the per-client QoE.

Originally proposed by Google, QUIC is a low-latency transport protocol currently being developed and specified in the IETF. QUIC's low-latency, improved congestion control, multiplexing features are promising and may help improve viewer experience in HTTP adaptive streaming applications. To investigate what issues due to running HTTP over TCP can be alleviated by using HTTP over QUIC. In this project, we measured QUIC's streaming performance on wireless and cellular networks. Specifically, we examined QUIC’s performance during network interface changes due to viewer's mobility and under unstable network conditions. Results show that QUIC starts media streams more quickly, providing a better streaming and seeking experience, in particular, when there is more congestion in the network, and outperforms TCP when the viewer is mobile and switches between the networks.

HTTP adaptive streaming with chunked transfer encoding can be used to offer low-latency streaming without sacrificing the coding efficiency. While this allows a media segment to be generated and delivered at the same time, which is critical in reducing the latency, the conventional bitrate adaptation schemes make often grossly inaccurate bandwidth measurements due to the presence of idle periods between the chunks. These wrong measurements cause the streaming client to make bad adaptation decisions. To this end, in this porject, we designed a new bitrate adaptation schemes for low-latency chunked streaming.