Cloud computing platforms are well established as the reference infrastructure for flexibility allowing business to scale according to user demands. However, several challenges remain to be addressed. Scaling up the infrastructure to match up the resource demand of the users is relatively straight forward. However in order to save up on power consumption, cloud providers have to dynamically consolidate the virtual machines (VM), so that only a reduced subset of hosts remains powered on. To solve this issue, the cloud scheduler, which handles the VM allocations, has to balance between providing enough resource to each user, and reducing the overall power consumption of the cloud. In this paper we investigate the VM allocation and reallocation inside a cloud in order to save energy while maintaining the resources required by users. Such actions have to be made in order to minimize the number of hosts powered on, while limiting concurrent migrations of virtual machines, and in a reasonable computational time. We propose to effectively consolidate virtual machines with an approach handling the reallocation, migration and host management problems. Our approach has been implemented in OpenNebula, and experimentally compared with its default approach.