A mathematical model for optimizing containerized deployment in energy-efficient virtualized data centers: SAP HANA datacenter simulation

Abstract This study addresses the challenge of efficient resource management in data centers through pod and virtual machine (VM) migration. The objective is to prevent resource shortages while improving power efficiency in cloud environments. To this end, we formulate a multi-objective mixed-integer linear programming (MILP) model for optimizing pod and VM replacement and complement it with a specialized algorithm that dynamically migrates pods and VMs from overutilized to underutilized hosts. Simulation results show that the proposed approach reduces estimated server-power consumption and improves resource allocation compared with the evaluated benchmark configurations. Statistical analyses further indicate that the proposed model and algorithm outperform the benchmark approaches. Building on our previous work on VM and software container replacement, this study contributes to the development of more energy-efficient and resource-aware cloud computing systems.