An energy-aware ant colony optimization strategy for virtual machine placement in cloud computing

Abstract

Virtual machine placement (VMP) directly impacts the energy consumption, resource utilization, and service quality of cloud data centers (CDCs), and it has become an active research topic in cloud computing. Inspired by the ant colony system (ACS) which has been proven effective metaheuristic approach for solving NP-hard problems, this paper proposes an improved ACS-based energy efficiency strategy (EEACS) for VMP problems. Our approach considers each virtual machine (VM) as an energy-consuming block, taking into account its individual energy requirements. EEACS ranks the physical machines (PMs) in a CDC in descending order based on their energy efficiency and optimizes both server selection and pheromone updating rules within the ACS. By guiding artificial ants towards promising solutions that balance energy consumption and resource utilization, EEACS ensures that VMs are placed efficiently based on pheromone and heuristic information. Extensive simulations in both homogeneous and heterogeneous computing environments demonstrate the effectiveness of our proposed strategy. The experimental results show that the EEACS enhances the resource utilization and achieves a notable reduction in energy consumption in comparison to conventional heuristic and evolutionary-based algorithms.