Scholarlink

<p>The rapid expansion of mobile devices and IoT sensors has led to a surge in real-time data processing demands, which Edge computing (EC) seeks to address by bringing computation closer to data sources. However, effectively scheduling tasks in EC environments remains a significant challenge due to the complexity and dynamic nature of resource constraints. Task scheduling is classified as an NP-hard problem, where conventional algorithms struggle to deliver optimal solutions efficiently. As a result, metaheuristic algorithms have gained prominence for their ability to provide near-optimal solutions within reasonable time frames. This study conducts a comprehensive systematic review of task scheduling approaches in Edge Computing (EC) that utilize metaheuristic algorithms, with particular emphasis on Particle Swarm Optimization (PSO), Genetic Algorithms (GA), and Ant Colony Optimization (ACO). A total of 103 relevant publications, spanning the period from 2015 to 2024, were examined and compared based on essential quality-of-service (QoS) metrics, including energy consumption, completion time, execution time, delay, cost, and makespan. The findings indicate that while these algorithms offer substantial improvements, challenges persist in areas such as task relocation, network awareness, and adaptability to dynamic environments. The study identifies critical research gaps and proposes future directions, emphasizing the potential of hybrid models and the integration of artificial intelligence with metaheuristics to develop more intelligent, scalable, and adaptive task scheduling strategies for next-generation EC systems.</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

Systematic review of metaheuristic-based task scheduling strategies in edge computing environments

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月15日

查看全文
  • Jafar Aminu,
  • Rohaya Latip,
  • Zurina Mohd Hanafi,
  • Shafinah Kamarudin,
  • Danlami Gabi

摘要

The rapid expansion of mobile devices and IoT sensors has led to a surge in real-time data processing demands, which Edge computing (EC) seeks to address by bringing computation closer to data sources. However, effectively scheduling tasks in EC environments remains a significant challenge due to the complexity and dynamic nature of resource constraints. Task scheduling is classified as an NP-hard problem, where conventional algorithms struggle to deliver optimal solutions efficiently. As a result, metaheuristic algorithms have gained prominence for their ability to provide near-optimal solutions within reasonable time frames. This study conducts a comprehensive systematic review of task scheduling approaches in Edge Computing (EC) that utilize metaheuristic algorithms, with particular emphasis on Particle Swarm Optimization (PSO), Genetic Algorithms (GA), and Ant Colony Optimization (ACO). A total of 103 relevant publications, spanning the period from 2015 to 2024, were examined and compared based on essential quality-of-service (QoS) metrics, including energy consumption, completion time, execution time, delay, cost, and makespan. The findings indicate that while these algorithms offer substantial improvements, challenges persist in areas such as task relocation, network awareness, and adaptability to dynamic environments. The study identifies critical research gaps and proposes future directions, emphasizing the potential of hybrid models and the integration of artificial intelligence with metaheuristics to develop more intelligent, scalable, and adaptive task scheduling strategies for next-generation EC systems.