Scholarlink

<p>The exponential growth of the Internet of Things (IoT) has resulted in the widespread deployment of interconnected devices that frequently depend on external fog nodes for computational support due to limitations in battery life, processing power, and storage capacity. In such environments, ensuring efficient and reliable task offloading and scheduling mechanisms is critical to maintain system performance and service quality. However, the task scheduling problem—especially within dynamic logistics scenarios involving mobile IoT devices, is NP-hard and computationally intensive, due to the continuous movement and heterogeneity of devices. To address these challenges, this study proposes a novel Fault-Tolerant and Mobility-Aware Task Offloading and Scheduling Model (FTM-TOSM) tailored for IoT-enabled logistics systems. The model introduces mobility awareness by dynamically assessing the relative proximity of mobile IoT devices (e.g., vehicles, drones) to fog nodes using Euclidean distance, enabling location-optimized task assignments. A multi-criteria decision-making approach, based on the Analytic Hierarchy Process (AHP), is employed to determine task priorities. Tasks are then categorized as follows: low-priority tasks are executed locally on IoT devices, Medium-priority tasks are offloaded to nearby fog nodes, and High-priority tasks are routed to cloud servers for advanced processing. To enhance fault tolerance, the model incorporates dynamic re-clustering techniques, allowing the system to recover from node failures during offloading operations. Furthermore, Virtual Machine (VM) selection for task execution is guided by a multi-criteria strategy that considers execution cost, energy consumption, and available resources. Performance assessments conducted using the iFogSim2 simulation platform reveal that the FTM-TOSM framework substantially outperforms traditional approaches like Ant Colony Optimization (ACO). Specifically, the model delivers up to a 10.4% reduction in energy usage, a 25.2% drop in SLA violations, a 16.28% enhancement in response time, and a 22.1% decrease in task failure rates. These findings confirm the model’s capability to improve the reliability, operational efficiency, and flexibility of fog-based IoT logistics environments.</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

Fault tolerant and mobility-aware task offloading and scheduling model for IoT logistics

  • 期刊论文

  • 发表日期：

    2025年7月30日

查看全文
  • Asif Umer,
  • Mushtaq Ali,
  • Ali Imran Jehangiri

摘要

The exponential growth of the Internet of Things (IoT) has resulted in the widespread deployment of interconnected devices that frequently depend on external fog nodes for computational support due to limitations in battery life, processing power, and storage capacity. In such environments, ensuring efficient and reliable task offloading and scheduling mechanisms is critical to maintain system performance and service quality. However, the task scheduling problem—especially within dynamic logistics scenarios involving mobile IoT devices, is NP-hard and computationally intensive, due to the continuous movement and heterogeneity of devices. To address these challenges, this study proposes a novel Fault-Tolerant and Mobility-Aware Task Offloading and Scheduling Model (FTM-TOSM) tailored for IoT-enabled logistics systems. The model introduces mobility awareness by dynamically assessing the relative proximity of mobile IoT devices (e.g., vehicles, drones) to fog nodes using Euclidean distance, enabling location-optimized task assignments. A multi-criteria decision-making approach, based on the Analytic Hierarchy Process (AHP), is employed to determine task priorities. Tasks are then categorized as follows: low-priority tasks are executed locally on IoT devices, Medium-priority tasks are offloaded to nearby fog nodes, and High-priority tasks are routed to cloud servers for advanced processing. To enhance fault tolerance, the model incorporates dynamic re-clustering techniques, allowing the system to recover from node failures during offloading operations. Furthermore, Virtual Machine (VM) selection for task execution is guided by a multi-criteria strategy that considers execution cost, energy consumption, and available resources. Performance assessments conducted using the iFogSim2 simulation platform reveal that the FTM-TOSM framework substantially outperforms traditional approaches like Ant Colony Optimization (ACO). Specifically, the model delivers up to a 10.4% reduction in energy usage, a 25.2% drop in SLA violations, a 16.28% enhancement in response time, and a 22.1% decrease in task failure rates. These findings confirm the model’s capability to improve the reliability, operational efficiency, and flexibility of fog-based IoT logistics environments.