Virtual Machine Resource Allocation for Multimedia Cloud: A Nash Bargaining Approach

Recently, multimedia cloud is being considered as a new effective serving mode in multimedia domain. It can provide a flexible stack of powerful Virtual Machine (VM) resources of cloud like CPU, memory, storage, network bandwidth etc. on demand to manage media services and applications (e.g. image/video retrieval, video transcoding, streaming, video rendering, sharing and delivery) at lower cost. However, one major issue here is how to efficiently allocate VM resources dynamically based on applications’ QoS demands and support energy and cost savings by optimizing the number of servers in use. In order to solve this problem, we propose a cost effective and dynamic VM allocation model based on Nash bargaining solution. With various simulations it is shown that the proposed mechanism can reduce the overall cost of running servers while at the same time guarantee QoS demand and maximize resource utilization in various dimensions of server resources.