Adaptive Video Streaming with Transport Layer Information

Adaptive Bitrate (ABR) is an essential method for enhancing the user Quality of Experience (QoE) in online video streaming. Existing ABR algorithms rely on network characteristics observed at the application layer for bitrate decisions. However, this approach has limitations: accurate video chunk download times cannot be fully derived from application layer observations. Specifically, these algorithms overlook factors such as round-trip time (RTT) and packet loss rate, which impact video chunk transmission, and their real-time responsiveness is often limited. To address this, we propose Prophet, a bitrate adaptation algorithm based on transport layer information. Unlike traditional ABR algorithms, Prophet calculates network parameters such as bandwidth, packet loss rate, and RTT at the transport layer, enabling a more accurate assessment of network conditions. Additionally, we developed a video chunk download time prediction model that incorporates transport-layer insights, taking into account factors like packet loss retransmission and tail latency to achieve precise download time predictions. Experiments conducted in real-world network environments demonstrate that the Prophet algorithm performs well under various network conditions, effectively balancing Quality of Experience metrics while avoiding excessive bitrate increases or reductions in buffering time. Compared to existing ABR algorithms, Prophet achieves an average QoE improvement of 0.3%-117.9%, with a notable average QoE increase of 31.7%-118.0% in cellular network conditions.