As a new form of computing based on the core technology of cloud computing and built on edge infrastructure, edge computing can handle computing-intensive and delay-sensitive tasks. In mobile edge computing (MEC) assisted by 5G technology, offloading computing tasks of edge devices to the edge servers in edge network can effectively reduce delay. Designing a reasonable task offloading strategy in a resource-constrained multi-user and multi-MEC system to meet users’ needs is a challenge issue. In industrial internet of things (IIoT) environment, considering the rapid increase of industrial edge devices and the heterogenous edge servers, a particle swarm optimization (PSO)-based task offloading strategy is proposed to offload tasks from resource-constrained edge devices to edge servers with energy efficiency and low delay style. A multi-objective optimization problem that considers time delay, energy consumption and task execution cost is proposed. The fitness function of the particle represents the total cost of offloading all tasks to different MEC servers. The offloading strategy based on PSO is compared with the genetic algorithm (GA) and the simulated annealing algorithm (SA) through simulation experiments. The experimental results show that the task offloading strategy based on PSO can reduce the delay of the MEC server, balance the energy consumption of the MEC server, and effectively realize the reasonable resource allocation.

中文翻译：

---

工业物联网边缘计算中使用粒子群优化算法的高效任务卸载

边缘计算作为一种基于云计算核心技术、构建在边缘基础设施之上的新型计算形态，能够处理计算密集型和延迟敏感型任务。在5G技术辅助的移动边缘计算（MEC）中，将边缘设备的计算任务卸载到边缘网络中的边缘服务器，可以有效降低时延。在资源受限的多用户和多 MEC 系统中设计合理的任务卸载策略以满足用户的需求是一个挑战问题。在工业物联网（IIoT）环境中，考虑到工业边缘设备和异构边缘服务器的快速增长，提出了一种基于粒子群优化（PSO）的任务卸载策略，将任务从资源受限的边缘设备卸载到边缘服务器。具有能源效率和低延迟风格。提出了一个考虑时间延迟、能耗和任务执行成本的多目标优化问题。粒子的适应度函数表示将所有任务卸载到不同 MEC 服务器的总成本。通过仿真实验，将基于PSO的卸载策略与遗传算法（GA）和模拟退火算法（SA）进行了比较。实验结果表明，基于PSO的任务卸载策略能够降低MEC服务器的延迟，平衡MEC服务器的能耗，有效实现资源的合理分配。通过仿真实验，将基于PSO的卸载策略与遗传算法（GA）和模拟退火算法（SA）进行了比较。实验结果表明，基于PSO的任务卸载策略能够降低MEC服务器的延迟，平衡MEC服务器的能耗，有效实现资源的合理分配。通过仿真实验，将基于PSO的卸载策略与遗传算法（GA）和模拟退火算法（SA）进行了比较。实验结果表明，基于PSO的任务卸载策略能够降低MEC服务器的延迟，平衡MEC服务器的能耗，有效实现资源的合理分配。