A Bio-inspired Approach to Provisioning of Virtual Resources in Federated Clouds

Abstract

In cloud computing the allocation and scheduling of multiple virtual resources, such as virtual machines (VMs), are still a challenge. The optimization of these processes bring the advantage of improving the energy savings and load balancing in large data centers. Resource allocation and scheduling also impact in federated clouds where resources can be leased from partner domains. This paper proposes a bio-inspired VM allocation method based on Genetic Algorithms to optimize the VM distribution across federated cloud domains. The main contribution of this work is an inter-domain allocation algorithm that takes into account the capacity of the links connecting the domains in order to avoid quality of service degradation for VMs allocated on partner domains. An architecture to simulate federated clouds is also a contribution of this paper.