QoE-Oriented Resource Optimization for Mobile Cloud Gaming: A Potential Game Approach

Cloud gaming is a novel service provisioning paradigm, which hosts video games in the cloud and transmits interactive game streaming to players via the Internet. In this model, the cloud is required to consume tremendous resources for video rendering and streaming, especially when the number of concurrent players reaches a certain level. On the other hand, different players may have distinct requirements on Quality-of-Experience, such as high video quality, low delay, etc. Under this circumstance, to ensure an overall satisfaction for all players with finite cloud resources becomes a major challenge to existing cloud services. This paper employs game theory to the cloud gaming scenario and proposes a model to meet players' overall requirements with low cost. This game is proved to be a potential game with determining a devised potential function. Our experiment has shown that, with our algorithm, players can achieve a mutually satisfactory steady state, and the system will reduce the overhead up to 50% within the time complexity of O(Mlog M), where M is the number of physical servers.