Many-Objective Resource Allocation in Cloud Computing Datacenters

Abstract

Cloud computing datacenters dynamically provide millions of virtual machines in actual cloud computing markets and several challenging problems have to be addressed towards an efficient resource management of these infrastructures. In the context of resource allocation, Virtual Machine Placement (VMP) is one of the most studied problems with several possible formulations and a large number of existing optimization criteria. This paper summarizes a doctoral dissertation focused on studying for the first time Many-Objective Virtual Machine Placement (MaVMP) problems. First, novel taxonomies were proposed for the VMP problem in order to gain a systematic understanding of the existing approaches and formulations. Next, MaVMP problems were formulated for the first time and algorithms were designed to effectively address particular challenges associated to the solution of Many-Objective Optimization Problems (MaOPs). Experimental results prove the correctness, effectiveness and scalability of the proposed algorithms in different experimental environments. Finally, preliminary conclusions and future work for completion of the doctoral dissertation are presented.