A Weighted PageRank-Based Algorithm for Virtual Machine Placement in Cloud Computing

Abstract

Virtualization makes virtual machine placement (VMP) one of the most important technology in cloud computing. An effective VMP algorithm can significantly improve resource utilization of physical machines (PMs) in cloud datacenters. In this paper, we propose a VMP algorithm based on weighted PageRank (WPRVMP), which pursued to minimize the number of active PMs and improve the total resource utilization of all PMs in cloud datacenters. The impact of unplaced virtual machines (VMs) in the VMP process on the placement results, and the impact of VMP on the total resource utilization of all PMs are considered in this algorithm, to avoid the algorithm to fall into local optimal solution. In the process of selecting PM for each VM, the number of unplaced VMs of different types in the VMP process is considered in WPRVMP by weighted. The weighted PageRank algorithm is used to measure the possibility of a PM making full use of resources under different VMP conditions. The algorithm then ranks PMs according to the impact of the given VM is placed on each PM on the maximum resource utilization of all PMs, and places the VM based on the ranking results. Experimental results show that our algorithm is superior to other algorithms in reducing the number of active PMs and improving the resource utilization of PMs.