| Title | Neural Adaptive Transport Framework for Internet-scale Interactive Media Streaming Services |
| Publication Type | Conference Paper |
| Year of Publication | 2019 |
| Authors | Xu, Y., Chen, H., Zhao, Y., Zhang, W., Shen, Q., Zhang, X., Ma, Z. |
| Conference Name | 2019 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB) |
| Keywords | adaptive real-time streaming, adaptive real-time streaming strategy, ARS strategy, bandwidth fluctuation, cloud computing, composability, COR scheme, CVP system, deep reinforcement learning, Human Behavior, Internet, Internet-scale Computing Security, Internet-scale interactive media streaming services, learned resolution scaling, learning (artificial intelligence), learning based cloud overlay routing scheme, maximal QoE, media services, Metrics, minimal end-to-end latency, NAT system, network dynamics, neural adaptive transport, neural adaptive transport framework, neural nets, Overlay routing, policy governance, pubcrawl, QoE improvement, quality of experience, residual neural network based collaborative video processing system, Resiliency, resolution scaling, telecommunication network routing, video bitrate, video signal processing, video streaming |
| Abstract | Network dynamics, such as bandwidth fluctuation and unexpected latency, hurt users' quality of experience (QoE) greatly for media services over the Internet. In this work, we propose a neural adaptive transport (NAT) framework to tackle the network dynamics for Internet-scale interactive media services. The entire NAT system has three major components: a learning based cloud overlay routing (COR) scheme for the best delivery path to bypass the network bottlenecks while offering the minimal end-to-end latency simultaneously; a residual neural network based collaborative video processing (CVP) system to trade the computational capability at client-end for QoE improvement via learned resolution scaling; and a deep reinforcement learning (DRL) based adaptive real-time streaming (ARS) strategy to select the appropriate video bitrate for maximal QoE. We have demonstrated that COR could improve the user satisfaction from 5% to 43%, CVP could reduce the bandwidth consumption more than 30% at the same quality, and DRL-based ARS can maintain the smooth streaming with \textbackslashtextless; 50% QoE improvement, respectively. |
| DOI | 10.1109/BMSB47279.2019.8971955 |
| Citation Key | xu_neural_2019 |
Neural Adaptive Transport Framework for Internet-scale Interactive Media Streaming Services