University of Twente Student Theses

Login
As of Friday, 8 August 2025, the current Student Theses repository is no longer available for thesis uploads. A new Student Theses repository will be available starting Friday, 15 August 2025.

Dynamic Production Policies for ASML’s General Supply Network

Ochoa Barnuevo, Marco Luis (2025) Dynamic Production Policies for ASML’s General Supply Network.

[img] PDF
14MB
Abstract:This thesis presents the first scalable and interpretable approach to optimizing inventory and production decisions in a capacitated, general multi-echelon supply network. Focusing on ASML's complex environment characterized by volatile demand and shared capacity constraints, it proposes a capacity-aware base-stock policy combined with adaptive allocation rules, significantly outperforming traditional methods. Additionally, we introduce a lightweight Deep Reinforcement Learning (DRL) method to dynamically refine decisions further. Extensive results, in our non-trivial cases, show that our heuristic approach alone captures 90–95% of possible cost savings, reduces inventory by up to 30%, and runs efficiently (under 30 seconds for larger systems). The DRL enhancement provides an extra 1–5% cost reduction and improved service levels with smart insights for inventory planners. This research thus delivers practical, state-of-the-art tools for managing complex supply chains, bridging theoretical insights with real-world applicability.
Item Type:Essay (Master)
Clients:
ASML, Veldhoven, Netherlands
Faculty:BMS: Behavioural, Management and Social Sciences
Subject:31 mathematics, 50 technical science in general, 54 computer science, 85 business administration, organizational science
Programme:Industrial Engineering and Management MSc (60029)
Link to this item:https://purl.utwente.nl/essays/106969
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page