Research Project GrEASE

Towards Generating and Executing Automatically Simulation Experiments


     Runtime:

     Project coordination:

     Scientific staff:

     Student staff:

     Source of funding:

Jan 01 2017 until  Dec 31 2018

Prof. Dr.  Adelinde M. Uhrmacher

M.Sc. Andreas Ruscheinski
M.Sc. Tom Warnke

Marcus Dombrowsky

DFG  (DFG GEPRIS Link)

Abstract

 

In this project we will develop methods for conducting simulations by automatically generating and executing simulation experiments.

Simulation studies are becoming more and more an indispensable tool in many application areas. However, executing simulation studies requires not only in-depth knowledge about the system to be modeled and analyzed, but also detailed knowledge about the design of simulation experiments and the involved methods. Developing a model implies the execution of diverse simulation experiments, intertwined with phases of model refinement and enrichment. Each of the experiments consists of different tasks for which different methods are available. The goal of the project is to support conducting discrete event stochastic modeling and simulation studies by automatically generating and executing simulation experiments. The basis is a clear separation of concerns in modeling and simulation and an explicit specification of simulation experiments. To automatically determine the next simulation experiments, to generate and execute individual experiments, and to select and configure suitable methods for the simulation tasks, different methodological approaches shall be explored and developed. The evaluation will be based on concrete simulation studies.