Online Cloud Transcoding and Distribution for Crowdsourced Live Game Video Streaming

摘要

In recent years, empowered by rich media generation devices and convenient Internet access, Crowdsourced Live Game Video Streaming (CLGVS) has become one of the most popular Internet services. Twitch.tv, the most well-known CLGVS platform in the world, allows gamers to broadcast their gaming videos over the Internet. With the prevalence of mobile devices, viewers can watch gamers playing video games anywhere, anytime, on any devices (e.g., smartphones, tablets, or personal computers). However, the heterogeneity of user devices makes conventional solutions hard to ensure user-perceived quality. In this paper, we address the problem of cost-effective adaptive live game video streaming from the perspective of CLGVS service providers. Our purpose is to minimize the operational cost for CLGVS service providers by making live transcoding decisions, bit-rate adaptation decisions, and datacenter assignment decisions dynamically. Meanwhile, our algorithm also ensures good-enough service quality for viewers. Due to the diversity of game genres, we also consider game genres when designing our algorithm. To achieve the above purpose, we formulate the problem into a constrained stochastic optimization problem. By leveraging the Lyapunov optimization framework, we derive the online strategy with provable performance bound. To evaluate the effectiveness of our proposed algorithm, we further conduct a series of trace-driven simulations. The experimental results demonstrate the effectiveness of our algorithm in terms of operational cost and service quality. Our proposed algorithm can reduce operational cost by up to 50% while achieving good-enough viewer QoE compared with other alternatives.