Scholarlink

<p>Task scheduling has become a significant research focus in cloud computing because of the growing need for efficient resource utilization. This paper explores an innovative scheduling approach harnessing Human Memory Optimization (HMO) and Fuzzy Adaptive Human Memory Optimization (FAHMO). Such techniques are inspired by human cognitive principles and employ an adaptive search strategy that maintains an effective trade-off between exploration and exploitation. By maintaining a history of successful and unsuccessful scheduling decisions, HMO enables continuous enhancement of scheduling efficiency. Integrating fuzzy logic into FAHMO improves the decision-making process by effectively managing uncertainty and ambiguity in task scheduling, thereby producing more flexible and efficient solutions. Comparative analysis demonstrates that HMO and FAHMO outperform conventional metaheuristic algorithms, including PSO-PGA, in terms of convergence speed and task completion time. The results confirm that the proposed approach significantly reduces makespan and enhances overall cloud task scheduling performance. Specifically, FAHMO achieved up to 67.46% improvement in makespan and 63.18% in convergence accuracy compared to PSO-PGA.</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

Fuzzy adaptive human memory optimization based optimal task scheduling in cloud computing

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月7日

查看全文
  • Padmaja Patel,
  • K. Murali Gopal,
  • Nimai Charan Patel,
  • Binod Kumar Sahu,
  • Siba Prasada Tripathy,
  • Muneera Altayeb,
  • Mykhailo Panchyk,
  • Ezzeddine Touti

摘要

Task scheduling has become a significant research focus in cloud computing because of the growing need for efficient resource utilization. This paper explores an innovative scheduling approach harnessing Human Memory Optimization (HMO) and Fuzzy Adaptive Human Memory Optimization (FAHMO). Such techniques are inspired by human cognitive principles and employ an adaptive search strategy that maintains an effective trade-off between exploration and exploitation. By maintaining a history of successful and unsuccessful scheduling decisions, HMO enables continuous enhancement of scheduling efficiency. Integrating fuzzy logic into FAHMO improves the decision-making process by effectively managing uncertainty and ambiguity in task scheduling, thereby producing more flexible and efficient solutions. Comparative analysis demonstrates that HMO and FAHMO outperform conventional metaheuristic algorithms, including PSO-PGA, in terms of convergence speed and task completion time. The results confirm that the proposed approach significantly reduces makespan and enhances overall cloud task scheduling performance. Specifically, FAHMO achieved up to 67.46% improvement in makespan and 63.18% in convergence accuracy compared to PSO-PGA.