An energy-aware virtual machine placement method in cloud data centers based on improved Harris Hawks optimization algorithm

The escalating adoption of cloud computing has presented a significant environmental and economic challenge because of the corresponding surge in energy consumption within cloud data centers. Virtualization technology is widely recognized as a popular method for mitigating energy consumption in data centers. Providing an optimal and method for virtual machine placement (VMP) contributes crucially to server integration. This article introduces a novel VMP algorithm that combines the Harris Hawk and Genetics Optimization algorithms, along with resource-aware allocation. This algorithm primarily minimizes the energy consumed by cloud data centers. Despite heuristic and meta-heuristic algorithms, including IGA POP, the energy-aware VMP strategy proposed in this study aims to minimize energy consumption by optimizing the allocation of physical machines (PMs). The introduced strategy achieves a balanced utilization of resources, comprising CPU, RAM, and bandwidth, decreasing the number of active servers required. The proposed VMP algorithm yields efficiency scores of 2.95 for datasets comprising 50 and 300 virtual machines, respectively. The data show a decrease in energy consumption by 1.83%, as well as reductions of 3.84 and 2.17% in the number of active PMs.