SNE T ECHNICAL N OTE SNE 32(3) – 9/2022 121 Development of an Integrated Solution for Data Farming and Knowledge Discovery in Simulation Data Jonas Genath 1* , Sören Bergmann 1 , Niclas Feldkamp 1 , Sven Spieckermann 2 , Stephan Stauber 2 1 Group for Information Technology in Production and Logistics, Ilmenau University of Technology, Ehrenbergstraße 29, 98693 ilmenau, Germany; * jonas.genath@tu-ilmenau.de 2 SimPlan AG, Sophie-Scholl-Platz 6, 63452 Hanau, Germany Abstract. Simulation is an established methodology for planning and evaluating manufacturing and logistics sys- tems. In contrast to classical simulation studies, the method of knowledge discovery in simulation data uses a simulation model as a data generator (data farming). Sub- sequently, hidden, previously unknown and potentially useful cause-effect relationships can be uncovered on the generated data using data mining and visual analytics methods. So far, however, there was a lack of integrated, easy-to-use software solutions for the application of the data farming in operational practice. This paper presents such an integrated solution, which allows generating ex- periment designs, implements a method to distribute the necessary experiment runs, and provides the user with tools to analyze and visualize the result data. Introduction Simulation is an established tool for planning and con- trolling complex production and logistics systems and has proven to be an important key component, among other things, in solving challenges in the context of In- dustry 4.0 [8]. Traditional simulation studies are usually designed to cover a previously defined project scope or to achieve a concrete project goal through manual exper- imentation. This includes, for example, the optimisation of a production layout [9]. With increasing computing power and the general availability of Big Data infrastructures and cloud-based solutions, as well as considerable progress in the field of data mining, another possible application for simulation models arises: conducting a very wide range of experi- ments to uncover hidden, previously unknown and poten- tially useful cause-effect relationships. Particularly in complex systems, there may be relationships, problems or even solutions that go beyond the defined goal of a traditional simulation project and can therefore contrib- ute to decision support. The basis for this approach is the methodology of data farming [5]. Based on data farming, Feldkamp et al. [4] developed a method named Knowledge Discovery in Simulation Data, which supplements data farming with methods from data mining and visual analytics, specifically suited for the analysis of production and logistic systems. Initial case studies have proven its potential [1, 2]. However, a broad transfer into operational practice was so far held back due to the lack of an integrated soft- ware solution that also enables non-simulation or data farming experts to conduct knowledge discovery in sim- ulation projects. This paper presents such an integrated solution, which initially extends the existing software solution SimAssist (cf. [13]) as a prototype. The development was carried out within the framework of the German Federal Ministry of Education and Research (FMER) project "Development of an integrated solution for data farming and knowledge discovery in simulation data (DaWiS)". The sub-aspects to be considered here are procedures of intelligent experiment design, methods for the (cloud- based) distribution of experiments as well as the selection SNE 32(3), 2022, 121-126, DOI: 10.11128/sne.32.tn.10611 Selected ASIM SPL 2021 Postconf. Publication: 2022-01-18; Received English version: 2022-03-14; Accepted: 2022-05-09 SNE - Simulation Notes Europe, ARGESIM Publisher Vienna ISSN Print 2305-9974, Online 2306-0271, www.sne-journal.org