TOWARDS LOGISTICS SYSTEMS PARAMETER OPTIMISATION THROUGH THE USE OF RESPONSE SURFACES


Katrien Ramaekers and Gerrit K. Janssens, Operations Management and Logistics, Limburgs Universitair Centrum (LUC), Universitaire Campus – Building D, B-3590 Diepenbeek, Belgium
e-mail: {katrien.ramaekers,gerrit.janssens}@luc.ac.be
Hendrik Van Landeghem, Industrial Management, Universiteit Gent (RUG), Technologiepark 903, B-9052 Zwijnaarde (Gent), Belgium
e-mail: hendrik.vanlandeghem@rug.ac.be

ABSTRACT:Logistics systems appear with uncertainties in demand, in lead times, in transport times, in availability of resources and in quality. Management decisions have to take these uncertainties into consideration. An evaluation of decisions may be done by means of simulation. However, not all stochastic phenomena are of equal importance. By design of simulation experiments and making use of response surfaces, the most important phenomena are detected and their influence on performance estimated. Once the influence of the phenomena is known, this knowledge may be used to determine the optimal values of some decision parameters. A model is built in a logistics modelling software. Some parameters are noise parameters but can be defined in order to test robustness. Other parameters are decision parameters: they have to be optimised for a specific objective function. Experiments are run to estimate the response surface. The validity of the response surface with few observations is also tested.

KEYWORDS: Simulation-optimisation, response surface, experimen-tal design, regression, logistics

---

Back to HMS2003 Home Page