A Matrix Transformation Algorithm for Virtual Machine Placement in Cloud

The virtual machine (VM) placement is an important problem of cloud data center resource management. There have been many research efforts to address this problem. However, existing research is mainly concerned with single objective such as the number of the physical machine (PM) used, and few research consider the resource utilization rate of PM´s different dimensions. In this paper, we present a two-objective optimization model such that the number of required PM is minimized and the resource utilization of occupied PM is optimum. We further provide an algorithm based on matrix transformation. In the algorithm, we define cluster matrix of VM request sequence and VM placement initial matrix to generate the optimum solution of VM placement optimization model. Finally, we compare our algorithm with the other VM placement strategy, the experimental results demonstrate the good performance of our algorithm.