AI and the World's Hard Problems · Theoretical computer science · arXiv · 2026-10-20
Dynamic Control of a Make-to-Order Manufacturing System under Throughput Time Constraints: An Effective Computational Method in the High-Dimensional Case
This work models a make-to-order production system serving price- and delay-sensitive customers as a multiclass queueing network with throughput-time constraints. The authors develop a neural network-based computational method for the high-dimensional control problem and derive an integrated policy combining dynamic pricing, scheduling, and outsourcing. Simulation studies on two test problems from the literature show the policy is effective.