Scholarlink

<p>The Internet of Medical Things (IoMT) employs IEEE 802.15.4/6LowPan-based wearable sensors to facilitate continuous health monitoring, generating critical data that demands low-latency and energy-efficient processing. However, the constrained bandwidth and energy budgets of these sensors render direct cloud offloading inefficient, leading to increased latency and network congestion. To address these challenges, this study introduces a novel metadata-driven task allocation framework for IoMT systems integrated with fog computing. In this approach, sensors transmit lightweight metadata (e.g., data size, task type, priority) to a fog broker, which employs the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) to optimally assign tasks to fog nodes or the cloud. This strategy balances latency, energy efficiency, computational load, and bandwidth utilization, adhering to the stringent Quality of Service (QoS) requirements of healthcare applications. Evaluated through an integrated simulation environment (NS-3 and Mininet), the proposed framework significantly outperforms traditional approaches, achieving reduced latency, lower energy consumption, optimized backhaul bandwidth, and higher task completion rates. By leveraging the low-power capabilities of IEEE 802.15.4/6LowPan and the multi-criteria decision-making of TOPSIS, this framework enhances scalability, reliability, and sustainability for next-generation IoMT healthcare 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

Resource efficient task scheduling in fog assisted IoMT using low rate wireless personal area networks

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月24日

查看全文
  • Reza Mohammadi

摘要

The Internet of Medical Things (IoMT) employs IEEE 802.15.4/6LowPan-based wearable sensors to facilitate continuous health monitoring, generating critical data that demands low-latency and energy-efficient processing. However, the constrained bandwidth and energy budgets of these sensors render direct cloud offloading inefficient, leading to increased latency and network congestion. To address these challenges, this study introduces a novel metadata-driven task allocation framework for IoMT systems integrated with fog computing. In this approach, sensors transmit lightweight metadata (e.g., data size, task type, priority) to a fog broker, which employs the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) to optimally assign tasks to fog nodes or the cloud. This strategy balances latency, energy efficiency, computational load, and bandwidth utilization, adhering to the stringent Quality of Service (QoS) requirements of healthcare applications. Evaluated through an integrated simulation environment (NS-3 and Mininet), the proposed framework significantly outperforms traditional approaches, achieving reduced latency, lower energy consumption, optimized backhaul bandwidth, and higher task completion rates. By leveraging the low-power capabilities of IEEE 802.15.4/6LowPan and the multi-criteria decision-making of TOPSIS, this framework enhances scalability, reliability, and sustainability for next-generation IoMT healthcare systems.