With the development of new generation information technology, many traditional factories begin to transform to smart factories. How to process the huge volume data in the smart factories so as to improve the production efficiency is still a serious problem. Based on the characteristics of smart factory, a fog computing framework suitable for smart factory is proposed, and Kubernetes is used to automatically deploy containerized smart factory applications. First, in the scene of fog computing, an improved interval division genetic scheduling algorithm IDGSA (Interval Division Genetic Scheduling Algorithm) based on genetic algorithm is proposed to schedule and allocate tasks in smart factory. We consider the optimization of task execution time and resource balance at same time and combined with IDGSA, the optimized scheduling decision is given. Second, we further design an architecture of cloud and fog collaborative computing. In this scenario, we propose the IDGSA-P (Interval Division Genetic Scheduling Algorithm with Penalty factor) for optimization based on IDGSA. Finally, we carry out simulation experiments to verify the performance of the proposed algorithms. The simulation results show that compared with Kubernetes default scheduling algorithm, IDGSA can reduce data processing time by 50% and improve the utilization of fog computing resources by 60%. Compared with traditional genetic algorithm, with fewer iterations, IDGSA can reduce data processing time by 7% and improve the utilization of fog computing resources by 9%. And compared with the conventional Joines&Houck method, the proposed IDGSA-P algorithm can converge much faster and archived better optimization results. Further, the simulation shows that IDGSA-P in cloud and fog collaborative computing can reduce the total task delay by 18% and 7%, respectively, when compare to only-cloud and only-fog computing.

随着新一代信息技术的发展，许多传统工厂开始向智能工厂转型。如何处理智能工厂中的海量数据以提高生产效率仍然是一个严峻的问题。基于智能工厂的特点，提出了适用于智能工厂的雾计算框架，利用Kubernetes自动部署容器化的智能工厂应用。首先，在雾计算场景下，提出一种基于遗传算法的改进的区间划分遗传调度算法IDGSA（Interval Division Genetic Sc​​heduling Algorithm），用于智能工厂的任务调度和分配。我们同时考虑任务执行时间和资源平衡的优化，结合IDGSA，给出了优化的调度决策。其次，我们进一步设计了云雾协同计算的架构。在这种情况下，我们提出了基于 IDGSA 的 IDGSA-P（带惩罚因子的区间划分遗传调度算法）进行优化。最后，我们进行了仿真实验，以验证所提出算法的性能。仿真结果表明，与 Kubernetes 默认调度算法相比，IDGSA 可以通过以下方式减少数据处理时间：50%，将雾计算资源的利用率提高60%。与传统遗传算法相比，IDGSA可以减少7%的数据处理时间，减少7%的迭代次数，提高雾计算资源的利用率9%。与传统的Joines&Houck方法相比，所提出的IDGSA-P算法收敛速度更快，优化结果更好。此外，仿真表明，与仅云和仅雾计算相比，IDGSA-P 在云和雾协同计算中的总任务延迟分别降低了18%和7% 。