A Hybrid Edge-Cloud Architecture for Reducing On-Demand Gaming Latency
Résumé
The cloud was originally designed to provide general-purpose computing using commodity hardware and its focus was on increasing resource consolidation as a means to lower cost. Hence, it was not particularly adapted to the requirements of multimedia applications that are highly latency sensitive and require specialized hardware, such as graphical processing units. Existing cloud infrastructure is dimensioned to serve general-purpose workloads and to meet end-user requirements by providing high throughput. In this paper, we investigate the effectiveness of using this general-purpose infrastructure for serving latency-sensitive multimedia applications. In particular, we examine on-demand gaming, also known as cloud gaming, which has the potential to change the video game industry. We demonstrate through a large-scale measurement study that the existing cloud infrastructure is unable to meet the strict latency requirements necessary for acceptable on-demand game play. Furthermore, we investigate the effectiveness of incorporating edge servers, which are servers located near end-users (e.g., CDN servers), to improve end-user coverage. Specifically, we examine an edge-server-only infrastructure and a hybrid infrastructure that consists of using edge servers in addition to the cloud. We find that a hybrid infrastructure significantly improves the number of end-users served. However, the number of satisfied end-users in a hybrid deployment largely depends on the various deployment parameters. Therefore, we evaluate various strategies that determine two such parameters, namely, the location of on-demand gaming servers and the games that are placed on these servers. We find that, through both a careful selection of on-demand gaming servers and the games to place on these servers, we significantly increase the number of end-users served over the basic random selection and placement strategies.