Scholarlink

<p>Task scheduling in Fog-Cloud-IoT systems presents difficulties due to fluctuating workloads, task interdependencies, and resource limitations. Fog and cloud computing, when combined with the Internet of Things, create a robust framework for distributed processing. The dynamic characteristics of these environments, along with diverse job interdependencies, necessitate new solutions to guarantee maximum performance. This work tackles the job scheduling issue by using an innovative Deep Reinforcement Learning (DRL) model to improve the efficiency and scalability of task management in Fog-Cloud-IoT settings. We present a DRL model to efficiently manage interdependent activities in these contexts by dynamically scheduling them according to their execution duration, synchronization needs, and communication expenses. In contrast to conventional meta-heuristic methods, the suggested DRL model adaptively learns to reduce execution time, energy consumption, and task failure rates in unpredictable IoT contexts. Comprehensive simulations across several scenarios demonstrate that the suggested model decreases the average execution time by 25% and enhances the task success rate by 15% relative to the baseline algorithms. This methodology rectifies significant deficiencies in current techniques, such as restricted adaptability to fluctuating settings and the neglect of synchronization expenses. This study enhances effective and scalable job scheduling, presenting considerable implications for real-time IoT applications, including smart healthcare and autonomous 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

Reinforcement learning-based framework for real-time task scheduling in IoT-Fog-Cloud environments

  • 期刊论文

  • 发表日期：

    2025年9月29日

查看全文
  • Zhixin Xie,
  • Ying Su,
  • Guangbiao Liu,
  • Yishi Yang

摘要

Task scheduling in Fog-Cloud-IoT systems presents difficulties due to fluctuating workloads, task interdependencies, and resource limitations. Fog and cloud computing, when combined with the Internet of Things, create a robust framework for distributed processing. The dynamic characteristics of these environments, along with diverse job interdependencies, necessitate new solutions to guarantee maximum performance. This work tackles the job scheduling issue by using an innovative Deep Reinforcement Learning (DRL) model to improve the efficiency and scalability of task management in Fog-Cloud-IoT settings. We present a DRL model to efficiently manage interdependent activities in these contexts by dynamically scheduling them according to their execution duration, synchronization needs, and communication expenses. In contrast to conventional meta-heuristic methods, the suggested DRL model adaptively learns to reduce execution time, energy consumption, and task failure rates in unpredictable IoT contexts. Comprehensive simulations across several scenarios demonstrate that the suggested model decreases the average execution time by 25% and enhances the task success rate by 15% relative to the baseline algorithms. This methodology rectifies significant deficiencies in current techniques, such as restricted adaptability to fluctuating settings and the neglect of synchronization expenses. This study enhances effective and scalable job scheduling, presenting considerable implications for real-time IoT applications, including smart healthcare and autonomous systems.