Efficient allocation of VMs in servers of data center to reduce energy consumption
Djouhra Dad, Ghalem Belalem · 2017
Cloud computing has become over the last years an important paradigm in the computing landscape. Its principle is to provide decentralized services and allows client to consume resources on a pay-as you-go model. The growing demand for this type of service brings providers service clouds to increase the size of their infrastructure to the point that the energy consumption and associated costs become very important. This cloud infrastructure comprises several components such as servers, cooling systems, etc. In this paper, we present three policies (FDT, DDT and DRT) each one with two phases. The selection phase which is based on physical resources thresholds (one or two physical resources) and the allocation phase to place the migrated VMs on hosts. We simulate the proposed approaches on CloudSim simulator and compare them with two existed approaches. Our proposal allows reducing energy consumption, number of migrations, the number of SLA violations and thus minimizing the CO2emission.