摘要
Cloud manufacturing can manage mass manufacturing resources and capabilities, and provide them as services via the Internet. Undoubtedly, multiple manufacturing clouds (MCs) will have extremely abundant services in terms of function, price, reliability, location, etc. Selecting and using services from multiple MCs is a natural evolution in the best interests of service consumers. On the other side, various uncertainties in today’s highly-dynamic business environment can easily disrupt manufacturing activities, rendering original schedules obsolete. However, little work has been done to take advantages of abundant services from MCs and to effectively deal with uncertainties. To address this requirement, we propose a dynamic service selection (SS) method across multiple MCs. The proposed method uses IoT’s real-time sensing ability on service execution, Big-Data’s knowledge extraction ability on services in MCs, and event-driven dynamic SS optimization to deal with disturbances from users and service market and to continuously adjust SS to be more effective and efficient.