A Resource Allocation Strategy for Multimedia Cloud Using Game Theory

Multimedia services have the characteristics of large volumes of data, significant differences between types and high complexity of input and output, and therefore the solution of resource allocation for multimedia services would meet higher requirements. In accordance with those characteristics of multimedia services, this paper presents a resource allocation strategy for handling multimedia tasks in the cloud. With the introduction of multiple QoS requirements of users and cloud service providers, the virtual resource allocation problem should be considered from three aspects, i.e. Completion time, cost and energy consumption. The proposed strategy builds a new utility function and uses game theory to solve the problem of resource competition and reuse. Compared with the traditional method, the experimental results show that the proposed resource allocation strategy can reduce the completion time of multimedia tasks nearly 40%, save the users´ cost about 25%, and cut down the energy consumption of the cloud approximately 30%. The proposed strategy can optimize resource utilization and allocation while ensuring the quality of services and videos.