Nowadays, cloud computing industry has been transformed to a new supply chain between cloud service providers and service requesters. To this end, cloud service provisioning in datacenters is procured via virtualization platforms in which it can potentially increase the
More
Nowadays, cloud computing industry has been transformed to a new supply chain between cloud service providers and service requesters. To this end, cloud service provisioning in datacenters is procured via virtualization platforms in which it can potentially increase the utilization of computing resources at infrastructure level. Inefficient virtual machine placement (VMP) schemes lead lower system utilization, increase of resource dissipation, and high rate of power consumption. Therefore, this paper formulates VMP problem on physical machines of cloud datacenters to a multi-objective optimization problem with minimization of both power consumption and resource dissipation perspectives which is computationally NP-Hard. Since the most meta-heuristic algorithms are designed for continuous optimization problems and are also susceptible to get stuck in local optimum, to figure out this combinatorial problem an optimization algorithm based on simulated annealing algorithm commensurate with discrete search space of stated problem is extended, so that the possibility of getting stuck in local optimum is reduced. To validate the proposed approach, several scenarios are introduced and conducted. Reported results from simulation of different scenarios show that the proposed approach outperforms against other existing approaches in terms of reduction in power consumption, resource dissipation, and the number of active server in use.
Manuscript profile
