Cloud Resource Management with a Hybrid Virtual Machine Consolidation Approach

Modern cloud data centers must effectively deliver a wide range of IT services to clients ensuring preassigned performance and availability. But the rapid growth of large-scale IT services results in the necessity of developing new methods for resource management in the cloud data center. This paper presents a hybrid virtual machine consolidation approach that aims at minimization of energy consumption and SLA violation by applying modified Best Fit Decreasing heuristic to initial virtual machine (VM) placement and by applying the adopted beam search algorithm to manage VM migrations. The heuristics of the proposed approach, the assessment functions, and the stop functions of the algorithms are developed. The proposed methods are programmed in C# and evaluated using Bitbrains workload traces. The simulation results show that the proposed approach outperforms a plain Best Fit heuristic in terms of the SLA violation, the number of active physical machines, and the number of VM migrations.