Simulation & Optimization Research Group
Markets, company structures and processes are not only complex, but are also changing ever more rapidly. Shorter cycles require rapid redesign and adjustment of internal and external structures and dependencies.
Our applied research transfers the newest methods from theory to practice. This enables us to develop individual and innovative solutions with our partners.
We enable you to recognize potential for rationalization and quantify it more effectively. We also help you achieve better understanding and control of dynamic and complex processes. Your planning quality improves significantly as we support you in asking the correct questions.
Thanks to user-friendly simulation tools, you can easily change your system parameters whenever necessary. In this way you adopt the best possible solution to your problem efficiently and without risk.
We all want to
- use resources efficiently
- avoid risks
- disentangle processes
- understand dependencies
- work out quantified (and qualified) bases for decisions
«We achieve your goals innovatively and sustainably at the interface of research and practice.»
We support you by
- analyzing your complex processes and systems
- reducing intricate relationships to the essentials
- developing dynamic models
- visualizing processes
- using optimization methods
«We solve complex problems through simulation and optimization.»
Your benefits from our projects:
- analysis of your current situation and recommendations for action
- simulation models to quantitatively support your decisions
- visualizations for a better understanding of processes
- tools to support strategic and operational planning and innovative solutions
«We experiment with you in the simulator to find a predictable and economically viable reality.»
End-to-End Data Driven Design of After-Sales-Services for Digital Cutters
Reinforcement Learning Analysis Framework
The aim of this project is to implement a framework that facilitates the development of RL solutions for real-world applications. This is necessary since the academic literature usually focuses on specific algorithms and approaches differ widely for different regions in the highly complex RL problem space. ...