Energy-aware and Carbon-efficient VM Placement Optimization in Cloud Datacenters using Evolutionary Computing Methods

In this research, we use two well-known evolutionary algorithms, the genetic algorithm, and the memetic algorithm, for the dynamic placement of VMs. The proposed method can reduce energy and carbon costs while reducing resource allocation time. In this method, the Power Usage Effectiveness (PUE) is used to evaluate the efficiency of cloud datacenters. Also, three types of energy supply sources have been considered for cloud data centers, among which, renewable energy sources are given higher priority to reduce carbon production and reduce overall costs.

在本项研究中，我们采用两种著名的进化算法——遗传算法和 memes 算法，以实现虚拟机的动态部署。所提出的方法能够在缩短资源分配时间的同时，降低能源和碳排放成本。在该方法中，我们运用功率使用效率（PUE）来评估云数据中心的高效性。此外，针对云数据中心，我们还考虑了三种能源供应来源，其中，可再生能源因其有助于降低碳排放和整体成本而被赋予更高的优先级。