Approach of glowworm swarm optimization based virtual machine placement.

In a cloud data center, one of the most important problems is using novel virtual machine placement strategy to promote the physical resource utilization. An approach of glowworm swarm optimization based virtual machine placement for cloud data centers called GSO-VMP was proposed. In the virtual placement, GSO algorithm was used to find a near-optimal solution. Each physical host had a luciferin value which represented the available CPU utilization. Whenever a VM was placed to a physical host, luciferin value of this physical host was updated. GSO-VMP algorithm could search the more available physical host within local range and thus the virtual migration numbers had been decreased and low energy consumption had been obtained. GSO-VMP had been evaluated using CloudSim with real-world workload data. The experimental results show that GSO-VMP has good performance in resource wastage and energy consumption. [ABSTRACT FROM AUTHOR]