Out-of-Order Architecture for Real-Time Data-Driven Resilient Planning and Scheduling of Cyber-Physical Manufacturing Systems

The intrinsic stochasticity of manufacturing is one of the main factors that hinder system resilience. Planning and scheduling problems are typical examples plagued by uncertainties such as stochastic processing time, arrivals of new orders, and breakdowns of workstations. Frequent uncertainties disturb the workflow, and their cascading effects create chaos in the whole system. The transparency and traceability analytics in Cyber-Physical Manufacturing Systems (CPMS) bring new hope to tackle uncertainties. Inspired by the core spirit of Out-of-Order (OoO) Execution in CPU, this paper proposes a novel OoO architecture for resilient planning and scheduling in CPMS with real-time data analytics. Following OoO principles, multi-level instruction queues are constructed, under which manufacturing operations (instructions) are sequenced and performed by analyzing real-time dependencies and executability. This study contributes a new perspective to enhance decision resilience using real-time data in CPMS. Results validate the effectiveness and resilience of OoO under different levels of uncertainty, showing improvements in the on-time delivery rate and reductions in the average order flow time.