A Cloud-Edge-Based Multi-Objective Task Scheduling Approach for Smart Manufacturing Lines

Abstract

The number of task demands created by smart terminals is rising dramatically because of the increasing usage of industrial Internet technologies in intelligent production lines. Speed of response is vital when dealing with such large activities. The current work needs to work with the task scheduling flow of smart manufacturing lines. The proposed method addresses the limitations of the current approach, particularly in the context of task scheduling and task scheduling flow within intelligent production lines. This study concentrates on solving the multi-objective task scheduling challenge in intelligent manufacturing by introducing a task scheduling approach based on job prioritization. To achieve this, a multi-objective task scheduling mechanism was developed, aiming to reduce service latency and energy consumption. This mechanism was integrated into a cloud-edge computing framework for intelligent production lines. The task scheduling strategy and task flow scheduling were optimized using Particle Swarm Optimization (PSO) and Gravitational Search Algorithm (GSA). Lastly, thorough simulation studies evaluate Multi-PSG, demonstrating that it beats every other algorithm regarding job completion rate. The completion rate of all tasks is greater than 90% when the number of nodes exceeds 10, which satisfies the real-time demands of the related tasks in the smart manufacturing processes. The method also performs better than other methods regarding power usage and maximum completion rate.