Towards Automated Simulation of Multi Agent Based Systems

Abstract

The simulation of systems offers a viable approach to find the optimal configuration of a system with respect to time, costs or any other utility function. In order to speed up the development process and to relieve developers from doing cumbersome work that is related to the execution of simulation runs, i.e. doing the simulation management manually, it is desirable to have a framework that provides tools which perform the simulation management automatically. Therefore, this work addresses this issue and presents an approach that reduces the effort to manage simulations, i.e. it eases and automates the execution, observation, optimization and evaluation. The approach consists of a declarative simulation description language and a framework that is capable of automatically managing simulations. Thereby, this approach reduces the costs, i.e. with respect to time and money, to perform simulations. Furthermore, this work targets a special subset of simulations, i.e. multi agent based simulation, that has grown large attention in many areas of science as well as in commercial applications in the last decade. The applicability of the approach is proven by a case study called "mining ore resources" that has been conducted.