A digital twin framework for online optimization of supply chain business processes

Abstract

We present an integrated digital twin framework for supply chain business processes. The framework models supply chain processes as queueing networks where agents perform tasks on orders flowing through the process. The modeling approach captures the routing dynamics and stochasticity in both the task durations and order arrivals that are observed in practice. The digital replica creates value by providing a flexible digital environment that can be used to evaluate policies, mitigate bottlenecks, quote more accurate lead times, and forecast and mitigate disturbances. The digital twin model is updated in real-time using the live process data. Optimization models can be deployed in either offline or online mode. In the offline mode, a deterministic optimization model is executed using the most-recent system parameters at expectation. In the online mode, the framework creates a stochastic simulation environment where online optimization can be performed in a feedback loop.