Scholarlink

<p> <!--Query ID="Q1" Text="Please provide the MSC classification code for this article." Resolved="yes"-->In this paper, we address the multi-objective task scheduling problem in cloud computing environments for IoT-generated tasks, focusing on minimizing makespan, load imbalance, energy consumption, and CO<sub>2</sub> emissions. We propose a novel load imbalance metric tailored for this specific context and introduce an enhanced Equilibrium Optimizer (EO) algorithm, termed CEEO. The CEEO integrates a Coulomb operator inspired by Coulomb’s law to improve exploration and escape local optima in multimodal optimization problems. The algorithm’s performance is evaluated using standard benchmark functions from CEC2017, where it demonstrates significant improvements over existing optimization algorithms in terms of convergence speed and solution quality. In addition, the CEEO is applied to a simulated cloud computing task scheduling environment, considering varying numbers of tasks and virtual machines. The results reveal that CEEO consistently outperforms other scheduling algorithms, reducing makespan and improving load balancing, energy consumption, and CO<sub>2</sub> emissions. Statistical analysis using the Friedman test confirms the statistical significance of these improvements. This research provides an efficient and robust solution for multi-objective task scheduling in cloud computing, offering substantial improvements in operational costs, execution time, and overall service quality.</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

CEEO: an innovative Coulomb-enhanced Equilibrium Optimizer for task scheduling of cloud services in IoT environments

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年5月26日

查看全文
  • Sepehr Ebrahimi Mood,
  • Alireza Souri,
  • Nihat İnanç,
  • Kuan-Ching Li

摘要

In this paper, we address the multi-objective task scheduling problem in cloud computing environments for IoT-generated tasks, focusing on minimizing makespan, load imbalance, energy consumption, and CO2 emissions. We propose a novel load imbalance metric tailored for this specific context and introduce an enhanced Equilibrium Optimizer (EO) algorithm, termed CEEO. The CEEO integrates a Coulomb operator inspired by Coulomb’s law to improve exploration and escape local optima in multimodal optimization problems. The algorithm’s performance is evaluated using standard benchmark functions from CEC2017, where it demonstrates significant improvements over existing optimization algorithms in terms of convergence speed and solution quality. In addition, the CEEO is applied to a simulated cloud computing task scheduling environment, considering varying numbers of tasks and virtual machines. The results reveal that CEEO consistently outperforms other scheduling algorithms, reducing makespan and improving load balancing, energy consumption, and CO2 emissions. Statistical analysis using the Friedman test confirms the statistical significance of these improvements. This research provides an efficient and robust solution for multi-objective task scheduling in cloud computing, offering substantial improvements in operational costs, execution time, and overall service quality.