Approximation of dispatching rules for manufacturing simulation using data mining methods. - In: Proceedings of the 2015 Winter Simulation Conference, ISBN 978-1-4673-9743-8, (2015), S. 2329-2340
Discrete-event simulation is a well-accepted method for planning, evaluating, and monitoring processes in production and logistics contexts. In order to reduce time and effort spent on creating the simulation model, automatic simulation model generation is an important area in modeling methodology research. When automatically generating a simulation model from existing data sources, the correct reproduction of the dynamic behavior of the modelled system is a common challenge. One example is the representation of dispatching and scheduling strategies of production jobs. When generating a model automatically, the underlying rules for these strategies are typically unknown but yet have to be adequately emulated. In previous work, we presented an approach to approximate the behavior through artificial neural networks. In this paper, we investigate the suitability of various other data mining and supervised machine learning methods for emulating job scheduling decisions with data obtained from production data acquisition.
HLA-based optimistic synchronization with SLX. - In: Proceedings of the 2015 Winter Simulation Conference, ISBN 978-1-4673-9743-8, (2015), S. 1717-1728
The High Level Architecture for Modeling and Simulation (HLA) comes with the promise of facilitating interoperability between a wide variety of simulation systems. HLA's time management offers a unique support for heterogeneous time advancement schemes and differentiates HLA from other general interoperability standards. While it has been shown that HLA is applicable for connecting commercial off-the-shelf simulation packages (CSPs), the usage of HLA time management in this application area is virtually always limited to conservative synchronization. In this paper, we investigate HLA's capabilities concerning optimistic synchronization. For the first time, we show its use in combination with a commercial-off-the-shelf simulation package (CSP), namely the simulation system SLX. We report on implementation details, performance results, and potential limitations in the current HLA 1516.1-2010 standard and its interpretation by runtime infrastructure (RTI) software vendors.
Visual analytics of manufacturing simulation data. - In: Proceedings of the 2015 Winter Simulation Conference, ISBN 978-1-4673-9743-8, (2015), S. 779-790
Discrete event simulation is an accepted technology for investigating the dynamic behavior of complex manufacturing systems. Visualizations created within simulation studies often focus on the animation of the dynamic processes of a single simulation run, supplemented with graphs of certain performance indicators obtained from replications of a simulation run or a few manually conducted simulation experiments. This paper suggests a much broader visually aided analysis of simulation input and output data and their relations than it is commonly applied today. Inspired from the idea of visual analytics, we suggest the application of data farming approaches for obtaining datasets of a much broader spectrum of combinations of input and output data. These datasets are then processed by data mining methods and visually analyzed by the simulation experts. This process can uncover causal relationships in the model behavior that were previously not known, leading to a better understanding of the systems behavior.
Optimistic synchronization in the HLA 1516.1-2010: interoperably challenged. - Ilmenau : Univ.-Bibliothek. - Online-Ressource (PDF-Datei: 9 S.)Druck-Ausgabe: Fall Simulation Interoperability Workshop (2015 Fall SIW) : Orlando, Florida, USA, 31 August-4 September 2015 / SISO - Simulation Interoperability Standards Organization. - Red Hook, NY : Curran Associates, Inc., 2016. - Seite 167-175
Time Management can be considered as one of the key achievements of the High Level Architecture for Modeling and Simulation (HLA). While HLA's time management is supposed to offer a unique support for heterogeneous time advancement schemes, its practical use is often limited to conservative time advancement (e.g. using services such as nextMessageRequest/nextMessageRequestAvailable) or time stepped time advancement (e.g. using services such as timeAdvanceRequest/timeAdvanceRequestAvailable). In this paper, we investigate HLA's capabilities for supporting optimistic time advancement and the interoperability between optimistic and conservative federates. The results are strikingly disappointing. While HLA had initially taken off with the noble vision of federations including both optimistic and conservative federates within a single federation execution, the current implementations of two leading RTI vendors fall short of achieving this objective. Neither do they enable the efficient execution of federations consisting of purely optimistically synchronized federates nor do they facilitate interoperability between optimistic and conservative federates. This paper documents the observed problems and discusses potential limitations in the IEEE HLA 1516.1-2010 specification and its interpretation by RTI vendors.
On the use of the Core Manufacturing Simulation Data (CMSD) standard: experiences and recommendations. - Ilmenau : Univ.-Bibliothek. - Online-Ressource (PDF-Datei: 11 S.)Druck-Ausgabe: Fall Simulation Interoperability Workshop (2015 Fall SIW) : Orlando, Florida, USA, 31 August-4 September 2015 / SISO - Simulation Interoperability Standards Organization. - Red Hook, NY : Curran Associates, Inc., 2016. - Seite 119-129
The Core Manufacturing Simulation Data (CMSD) information model is defined by SISO standards SISO-STD-008-01-2012 and SISO-STD-008-2010. The main objective of CMSD is to facilitate interoperability between simulation systems and other information systems in the manufacturing domain. While CMSD is mainly intended as standardized data exchange format, its capabilities go beyond simple data exchange. Frequently CMSD based system descriptions are used for purposes of automatic simulation model generation. In this paper, we report on practical experiences using the CMSD standard for such purposes as well as for purposes of simulation model initialization and simulation output data collection. Based on our experiences we suggest potential enhancements for a future revision of the standard.
Emulation of control strategies through machine learning in manufacturing simulations :
Abbildung von Steuerungslogiken durch maschinelles Lernen für die Simulation von Produktionssystemen. - In: Simulation in production and logistics 2015, (2015), S. 481-490
In the context of discrete-event simulation of production and logistics systems, modelling an exact representation of the real system is needed for obtaining sound and reliable results. The automatic generation of simulation models is an approach for saving time and effort for creating models and, therefore, it is a recurring issue in modelling methodology research. In automatic model generation, the approximation of dynamic behaviour is a challenging problem. This is for example the case when the dispatching and scheduling of production jobs needs to be adequately emulated, but the underlying rules are unknown. In previous work, we presented an approach for approximating dynamic behaviour through artificial neural networks. In this paper, we propose an improved approach and investigate its suitability again with artificial neuronal networks as well as with other data mining and supervised machine learning methods.
Knowledge discovery in manufacturing simulations. - In: SIGSIM PADS'15, ISBN 978-1-4503-3565-2, (2015), S. 3-12
Discrete event simulation studies in a manufacturing context are a powerful instrument when modeling and evaluating processes of various industries. Usually simulation experts conduct simulation experiments for a predetermined system specification by manually varying parameters through educated assumptions and according to a prior defined goal. Moreover, simulation experts try to reduce complexity and number of simulation runs by excluding parameters that they consider as not influential regarding the simulation project scope. On the other hand, today's world of big data technology enables us to handle huge amounts of data. We therefore investigate the potential benefits of designing large scale experiments with a much broader coverage of possible system behavior. In this paper, we propose an approach for applying data mining methods on simulation data in combination with suitable visualization methods in order to uncover relationships in model behavior to discover knowledge that otherwise would have remained hidden. For a prototypical demonstration we used a clustering algorithm to divide large amounts of simulation output datasets into groups of similar performance values and depict those groups through visualizations to conduct a visual investigation process of the simulation data.
Towards HLA-based optimistic synchronization with CSPs. - In: SIGSIM PADS'15, ISBN 978-1-4503-3565-2, (2015), S. 97-98
The High Level Architecture for Modeling and Simulation (HLA) comes with the promise of facilitating interoperability between a wide variety of simulation systems. HLA's time management offers a unique support for heterogeneous time advancement schemes and differentiates HLA from other general interoperability standards. While it has been shown that HLA is applicable for connecting commercial off-the-shelf simulation packages (CSPs), the usage of HLA time management in this specific application area is virtually always limited to conservative synchronization. In this paper, we investigate HLA's capabilities concerning optimistic synchronization and the imposed requirements on CSPs. For the first time, we outline its use in combination with a CSP, namely the Simulation Language with Extensibility (SLX). We report on initial performance results and potential limitations in the current HLA 1516.1-2010 standard and its interpretation by RTI vendors.
Automatic generation of route networks for microscopic traffic simulations. - In: Winter Simulation Conference (WSC), 2014, ISBN 978-1-4799-7487-0, (2014), S. 2848-2859
Microscopic traffic simulation is a well-accepted simulation approach for simulation problems where the effects of individual driver behavior and/or vehicle interactions need to be taken into account at a fairly detailed level. Such problems include the optimization of traffic light controls patterns or the design of lane layouts at intersections. Such simulation models typically require very detailed and accurate models of the underlying road networks. The manual creation of such networks constitutes a high effort, limiting the simulated area in practical applications to the absolutely necessary. With the increased availability of satellite based geographical data we investigate, if and how such data can be automatically transformed into route networks with adequate level of detail for microscopic traffic simulation models. We further outline the design of data structures for an extensible simulation framework for microscopic traffic simulation which is capable of including different types of publically available data sources.
Webbasierte Animation von Simulationsläufen auf Basis des Core Manufacturing Simulation Data (CMSD) Standards. - In: ASIM 2014, 22. Symposium Simulationstechnik, 3. bis 5. September 2014, HTW Berlin; Tagungsband, (2014), S. 63-70