Understanding Unexpected Behaviors in Exploratory Simulations (original) (raw)
Related papers
Explanation exploration: Exploring emergent behavior
Proceedings of the 21st …, 2007
Understanding emergent behavior(s) exhibited in simulations poses an interesting challenge. Emergence can represent a valid behavior arising from seemingly unrelated phenomena, or it can reflect an error in a model or its implementation. We propose a new method for gathering insight into emergent behavior in simulations using the model adaptation technique, COERCE. COERCE allows a user to efficiently adapt a model to meet new requirements and can be employed to explore emergent behavior exhibited in a simulation. A subject matter expert (SME) can coerce a simulation to gather insight into characteristics of the emergent behavior as the simulated phenomenon is driven toward conditions of interest.
Automatic Support for Understanding Complex Behaviour
To facilitate reasoning about the execution of massively parallel and distributed applications and systems, researchers at the University of Waterloo are developing a visualization tool that displays behaviour using process-time diagrams. One of the research goals is the development and implementation of abstraction facilities to handle large numbers of processes and events. A related presentation describes one abstraction technique, grouping processes into process clusters. This paper starts with the introduction of a second abstraction technique, grouping events into abstract events. Both abstraction techniques have been implemented in the current visualization tool, supporting abstract visualizations in a top-down manner. For complex systems, however, manually forming appropriate abstractions and building complete abstraction hierarchies is infeasible. This presentation therefore outlines two tools that build multi-level abstraction hierarchies automatically. The rst tool combines information obtained by a static source code analysis with runtime information to cluster processes based on speci c interprocess communication patterns. The second tool combines static and dynamic information to derive abstract events that represent meaningful \units of work" within the context of the application domain.
Simod: A Tool for Automated Discovery of Business Process Simulation Models
2019
Business process simulation is a widespread approach for quantitative analysis of business processes. However, the creation of accurate business process simulation models is a laborious and error-prone task, due to the numerous parameters that need to be carefully tuned. Additionally, the accuracy of a simulation model is inherently limited by the accuracy of the process model that is used as a starting point. This paper presents Simod: A tool to automatically generate simulation models from event logs. Simod uses an automated process discovery technique to extract a process model from an event log and then enhances this model with simulation parameters extracted via a combination of trace alignment, replay, and curve-fitting techniques. The tool incorporates a Bayesian hyperparameter optimization technique to fine-tune the accuracy of the resulting simulation model.
Evaluating simulation-derived scenarios for effective decision support
Technological Forecasting and Social Change, 2014
Scenario planning traditionally relies on qualitative methods to choose its scenarios. Recently, quantitative decision support tools have also begun to facilitate such choices. This study uses behavioral experiments and structured decision-maker interviews to evaluate the results of "scenario discovery," a quantitative method that defines scenarios as sets of future states of the world in which proposed policies fail to meet their goals. Statistical cluster-finding and principal component algorithms applied to large databases of computer simulation model results then help users to identify such scenarios. The two experiments examine the results of this process and demonstrate a user preference for increased accuracy and simplicity achieved through rotating the space of uncertain model input parameters, but primarily when the rotated parameters are conceptually similar. Interviews with experts suggest utility for both qualitatively-and quantitatively-derived scenarios. The former were easier to understand and had the most utility for scoping. The latter were perceived as containing more relevant information and having more utility for understanding tradeoffs and making choices among them. Overall, this study suggests the value of quantitative tools for facilitating scenario choice, while also highlighting the importance of formal evaluation in judging the utility of new methods for decision support.
Scenario-Based Modeling in Industrial Information Systems
2010
This manuscript addresses the creation of scenario-based models to reason about the behavior of existing industrial information systems. In our approach the system behavior is modeled in two steps that gradually introduce detail and formality. This manuscript addresses the first step, where text-based descriptions, in the form of structured rules, are used to specify how the system is or should be regulated. Those rules can be used to create behavioral snapshots, which are collections of scenario-based descriptions that represent different instances of the system behavior. Snapshots are specified in an intuitive and graphical notation that considers the elements from the problem domain and permit designers to discuss and validate the externally observable behavior, together with the domain experts. In the second step (not fully covered in this manuscript), the system behavior is formalized with an executable model. This formal model, which in our approach is specified using the Colored Petri Net (CP-nets) language, allows the system internal behavior to be animated, simulated, and optimized. The insights gained by experimenting with the formal model can be subsequently used for reengineering the existing system.
Process mining is a tool to extract non-trivial and useful information from process execution logs. These so-called event logs (also called audit trails, or transaction logs) are the starting point for various discovery and analysis techniques that help to gain insight into certain characteristics of the process. In this paper we use a combination of process mining techniques to discover multiple perspectives (namely, the control-flow, data, performance, and resource perspective) of the process from historic data, and we integrate them into a comprehensive simulation model. This simulation model is represented as a Coloured Petri net (CPN) and can be used to analyze the process, e.g., evaluate the performance of different alternative designs. The discovery of simulation models is explained using a running example. Moreover, the approach has been applied in two case studies; the workflows in two different municipalities in the Netherlands have been analyzed using a combination of process mining and simulation. Furthermore, the quality of the CPN models generated for the running example and the two case studies has been evaluated by comparing the original logs with the logs of the generated models. for drawing conclusions from a simulation run. Therefore, we propose to use process mining techniques to (semi-)automatically discover a simulation model based on information that was recorded during process enactment. This way, we can much quicker arrive at a first simulation model (to be further evaluated and potentially modified) than with the traditional approach. In addition, it is likely to better represent reality as it is based on objective information.
Computers in Industry, 1987
With the increasing levels of automation in factories, production management systems need increasingly sophisticated models of manufacturing processes. A framework is presented for the design and implementation of process reasoning modules which characterize processes within a manufacturing environment. Each reasoning module describes a process in terms of its effects, constraints, and process parameters. The effects include intended objectives, such as material removal, and side effects such as burr production. Constraints include specific limits on process parameters, and preconditions to the invocation of a process. These preconditions can require the execution of several other processes, leading to the chaining of events. The process parameters provide qualitative and quantitative information necessary to execute a process.
Petra: A Tool for Analysing a Process Family
When looking for the best model, simulation is often used for "what-if" analysis. The properties of a modelled process are explored by repeatedly executing the model. Based on the outcomes, parts of the model may be manually modified to improve the process. This is iteratively done to obtain the model best suited to a user's requirements. In most cases, this is a labour-intensive and time-consuming task. To improve on the state of the art, we propose a framework where the user defines a space of possible process models with the use of a configurable process model. A configurable process model is a compact representation of a family of process models, i.e., a set of process models related to each other. Within the framework, different tools can be used to automatically compute characteristics of a model. We show that, when used on data from multiple real-life models, our framework can find better models in an automated way. ? This research has been carried out as part of the Configurable Services for Local Governments (CoSeLoG) project (http://www.win.tue.nl/coselog/).
Comparative Analysis of Software tools Available for BPR
2015
This paper start with the overview of Business process reengineering (BPR). The next session focus on BPR tools-DEC model and SHAMASH. The paper continues with the description of a methodology that can be used to compare different BPR software tools. This methodology is then used to compare the four BPR software tools described earlier in the paper. This methodology should provide a basis for assessing the strengths and weaknesses of other software tools in the BPR domain while helping BPR practitioners to assess how a particular BPR software tool will "fit" a particular process or industry sector. SHAMASH, a process modelling tool for business process reengineering. The main features that differentiate it from most current related tools are its ability to define and use organisation standards, and functional structure, and make automatic model simulation and optimisation of them. SHAMASH is a knowledge-based system, and we include a discussion on how knowledge acquisition...
Deriving In-Depth Knowledge from IT-Performance Data Simulations
International Journal of Knowledge Society Research, 2012
Knowledge of behavioral patterns of a system can contribute to an optimized management and governance of the same system, or of similar systems. While human experience often manifests itself as intuition, intuition can be notoriously misleading, particularly in the case of quantitative data and subtle relations between different data sets. This article augments managerial intuition with knowledge derived from a specific byproduct of automated transaction processing performance and log data of the processing software. More specifically, the authors consider data generated by incident management and ticketing systems within IT support departments. The authors’ approach utilizes a rigorous analysis methodology based on System Dynamics. This allows for identifying real causalities and hidden dependencies between different datasets. The authors can then use them to derive and assemble knowledge bases for improved management and governance in this context. This approach is able to provide...