云边协同计算架构下大规模工厂接入的任务调度

Task scheduling method for large-scale factory access in cloud and edge collaborative computing architecture

针对大型制造业企业生产车间业务流程复杂,传统的任务调度方法无法适配云边协同的业务模式,导致负载不均衡的问题,提出云边协同任务调度算法。首先将云端服务器和边缘端服务器上的有向无环图(DAG)合并,然后采用基于关键路径的分割策略划分任务,以有效提高分配的准确性,最后通过合理分配处理器实现负载均衡。实验结果表明,所提方法通过提高计算资源利用率来缩短处理时间,并采用异构分布式系统使得处理大规模任务集时仍具有较高的计算性能。

Large-scale manufacturing enterprises have complex business processes in their production workshops,and traditional task scheduling methods cannot adapt to the cloud and edge collaborative business model,which leads to the problem of unbalanced load.Aiming at this problem,a Cloud and Edge Collaborative Task Scheduling(CECTS)algorithm was proposed.The method merged Directed Acyclic Graph(DAG)on cloud server and edge server,then the tasks was divided by critical path-based segmentation strategy,which could improve the accuracy of allocation effectively.Through processor allocation,the load balancing was achieved.Experimental results showed that the method reduced the processing time by improving the utilization of computing resources,and used a heterogeneous distributed system to achieve high computing performance when processing large-scale task sets.