A framework for scheduling in cloud manufacturing with deep reinforcement learning

Abstract

Cloud manufacturing is a novel service-oriented networked manufacturing paradigm that aims to provide on-demand manufacturing cloud services to consumers. Scheduling is a critical means for achieving that aim. Currently, research on scheduling in cloud manufacturing is still in its infancy, and current frequently adopted meta-heuristic algorithm-based approaches have some shortcomings, e.g. they require complex design processes and lack adaptability to dynamic environments. Deep reinforcement learning (DRL) that combines advantages of reinforcement learning and deep learning provides an efficient, adaptive and intelligent approach for solving scheduling problems in cloud manufacturing. However, to the best of our knowledge, there has been no application of DRL to scheduling in cloud manufacturing. This work conducts a preliminary exploration over this issue. First, a DRL-based framework for scheduling in cloud manufacturing is proposed. Then a DRL model for online single-task scheduling in cloud manufacturing is presented to demonstrate the effectiveness of the framework. DRL as a promising technique will find wide applications in cloud manufacturing, and this work can provide some reference for future research on this.