MM-ABR: an Enhanced ABR Algorithm with Multi-Metric Information for QUIC-based Video Streaming
Changjiang Cui, Yifei Lu, Zhen Wang, Zeqi Ruan, Hongxiang Wang · 2023
DASH is becoming the unified adaptive bitrate (ABR) streaming open-source standard in video streaming. However, existing ABR algorithms lack accuracy and real-time performance in bandwidth estimation. Incorporating a wider range of information can enhance ABR algorithm performance. Positioned at the application layer, QUIC offers high scalability and can provide richer decision-making information for ABR algorithms. In this paper, we introduce an enhanced ABR algorithm enriched with multi-metric information, referred to as MM-ABR. MM-ABR surpasses the capabilities of existing ABR algorithms by additionally predicting network congestion, thereby improving the smoothness of video playback. To obtain the multi-metric information required for MM-ABR, we extend the implementation of the QUIC protocol, which allows us to integrate not only more accurate bandwidth data but also RTT and packet loss information into the DASH client application. We conduct simulations using NS-3 and compare MM-ABR with traditional ABR algorithms. The results demonstrate that MM-ABR offers higher video quality and Quality of Experience (QoE).