Efficient service scheduling is an important technique to support collaborative manufacturing platforms such as IoT-enable manufacturing systems and cloud manufacturing. In the past few years, optimization problems for processing services have attracted the most attention of researchers and practitioners in terms of task matching, service selection, and scheduling. Logistics services, as another important kind of services in the cloud manufacturing environment, need to be explored further, beyond parameters of costs and time, in order to obtain more efficient task execution and more timely product delivery. In this paper, we consider the problem of synchronous scheduling of logistics services and processing services in cloud manufacturing. Based on the mathematical description, we present a collaborative optimization algorithm for logistics and processing services which we call COOPS to generate scheduling solutions for both processing tasks and logistics tasks at the same time. Typical optimization algorithms such as pattern search, particle swarm optimization and simulated annealing are compared with the proposed algorithm to show their performance on the average completion time of all manufacturing tasks. Results show that the proposed method obtains a shorter average completion time for all tasks in different scenarios.

高效的服务调度是支持协作制造平台（例如支持IoT的制造系统和云制造）的一项重要技术。在过去的几年中，处理服务的优化问题在任务匹配，服务选择和调度方面引起了研究人员和从业人员的最大关注。物流服务，作为云制造环境中另一种重要的服务，需要超越成本和时间参数来进一步探索，以便获得更高效的任务执行和更及时的产品交付。在本文中，我们考虑了云制造中物流服务和处理服务的同步调度问题。根据数学描述，我们提出了一种针对物流和加工服务的协作优化算法，我们将其称为COOPS，以同时为加工任务和物流任务生成调度解决方案。将典型的优化算法（例如模式搜索，粒子群优化和模拟退火）与提出的算法进行比较，以显示其在所有制造任务的平均完成时间上的性能。结果表明，所提出的方法在不同情况下为所有任务获得了较短的平均完成时间。将粒子群优化算法和模拟退火算法与提出的算法进行比较，以显示它们在所有制造任务的平均完成时间上的性能。结果表明，所提出的方法在不同情况下为所有任务获得了较短的平均完成时间。将粒子群优化算法和模拟退火算法与提出的算法进行比较，以显示它们在所有制造任务的平均完成时间上的性能。结果表明，所提出的方法在不同情况下为所有任务获得了较短的平均完成时间。