Scholarlink

<p>Cloud computing refers to the technique of applying scalable and in many cases virtualized resources as services over the internet. The sharp increase in cloud data centers presents a significant challenge in power management. This research investigates two metaheuristic optimization methods—Genetic Algorithm (GA) and Particle Swarm Optimization (PSO)—to reduce energy consumption by optimizing virtual machines (VMs) placement on physical machines (PMs). These approaches were evaluated using the CloudSim Plus simulator and compared with a baseline First Fit (FF) allocation method. Experimental results show that GA and PSO efficiently consolidate VMs onto fewer active hosts, thereby reducing overall energy consumption. CPU utilization and VM migration costs are taken into account by the algorithms to ensure service quality. These findings demonstrate the efficacy of metaheuristic-based approaches in resource management with emphasis on energy for cloud data centers as a solid foundation to support future research on sustainable cloud computing.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

GA and PSO-based heuristic approach for energy-optimized VM scheduling in CloudSim plus

  • 期刊论文

  • 发表日期：

    2025年12月23日

查看全文
  • Sarita Kumari,
  • Deepak Kumar,
  • Ahmad T. Al-Taani

摘要

Cloud computing refers to the technique of applying scalable and in many cases virtualized resources as services over the internet. The sharp increase in cloud data centers presents a significant challenge in power management. This research investigates two metaheuristic optimization methods—Genetic Algorithm (GA) and Particle Swarm Optimization (PSO)—to reduce energy consumption by optimizing virtual machines (VMs) placement on physical machines (PMs). These approaches were evaluated using the CloudSim Plus simulator and compared with a baseline First Fit (FF) allocation method. Experimental results show that GA and PSO efficiently consolidate VMs onto fewer active hosts, thereby reducing overall energy consumption. CPU utilization and VM migration costs are taken into account by the algorithms to ensure service quality. These findings demonstrate the efficacy of metaheuristic-based approaches in resource management with emphasis on energy for cloud data centers as a solid foundation to support future research on sustainable cloud computing.