An event-triggered dynamic scheduling method for randomly arriving tasks in cloud manufacturing

摘要

Cloud manufacturing (CMfg) is a service-oriented manufacturing mode and provides customers with on-demand manufacturing services via network. To solve the task scheduling problem in the dynamic CMfg environment with randomly arriving tasks, this article presents an event-triggered dynamic task scheduling (EDS) method. The event-triggered strategy is designed by considering arrival of new tasks and completion of first or middle subtasks in the subtask sequences to improve the timeliness of the service scheduler. The subtask-oriented strategy is applied to avoid service pre-emption so that the timely and effective task schedules can be obtained. The service time, logistic time and earliest available time of the candidate services are combined to choose the optimal services for triggered subtasks. Based on a case study of numerical control machining, the experimental results demonstrate that the average task execution time of the task schedules obtained through EDS was shorter than the other three task scheduling methods as tasks arrive randomly over time, and the total amount of occupied services during the scheduling period was not high.