Process-Oriented Analysis and Validation of Multi-Agent-Based Simulations

Nicolas Denz

Cite this publication as

Nicolas Denz, Process-Oriented Analysis and Validation of Multi-Agent-Based Simulations (2014), Logos Verlag, Berlin, ISBN: 9783832587741

56
accesses

Descripción / Abstract

In multi-agent-based simulation (MABS) the behavior of individual actors is modeled in detail. The analysis and validation of these models is rated as difficult and requires support by innovative techniques and tools. Problems include model complexity, the amount and often qualitative representation of simulation results, and the typical dichotomy between microscopic modeling and macroscopic observation perspectives.

In recent years, data mining has been increasingly applied as a support technique in this context. A particularly promising approach is found in the field of process mining. Due to its rooting in business process analysis, process mining shares several process- and organization-oriented analysis perspectives and use cases with agent-based modeling.

This thesis proposes a conceptual framework for the systematic application of process mining to the analysis and validation of MABS. As a foundation, agent-oriented analysis perspectives and simulation-specific use cases are identified and complemented with methods, techniques, and results from the literature. A partial formalization of perspectives and use cases is sketched by utilizing concepts from process modeling and software engineering. Beyond the conceptual work, process mining is applied in two case studies related to different modeling and simulation approaches.

Índice

  • BEGINN
  • 1 Introduction
  • 1.1 Motivation
  • 1.2 Objectives and Contributions of the Thesis
  • 1.3 Outline of the Thesis
  • I Foundations and State of the Art
  • 2 Modeling and Simulation
  • 2.1 Basic System Theory
  • 2.2 Computer Simulation
  • 2.3 Modeling Techniques
  • 2.4 Experimentation, Analysis, and Validation
  • 3 Agent-Based Simulation
  • 3.1 Agents and Multi-Agent Systems
  • 3.2 The Agent-Based Simulation World View
  • 3.3 Modeling Techniques for Agent-Based Simulation
  • 3.4 Implementation of Agent-Based Models
  • 3.5 The Problem of Analysis and Validation
  • 4 Data Mining and Process Mining
  • 4.1 Data Mining
  • 4.2 Process Mining
  • 5 Related Work
  • 5.1 Analysis and Validation of MABS
  • 5.2 Data Mining in Multi-Agent Systems and Simulations
  • 5.3 Process Mining in Software Engineering and Simulation
  • 5.4 Scientic Workows for Simulation and Process Mining
  • II Concepts, Tools, and Case Studies
  • 6 Conceptual Framework
  • 6.1 Motivation and Overview
  • 6.2 Analysis Perspectives
  • 6.3 Use Cases within the Model Building Cycle
  • 6.4 Simulation-specic Requirements
  • 6.5 Summary and Contributions
  • 7 Process Mining in PAOSE
  • 7.1 Process Mining and the Mulan Framework
  • 7.2 Reconstruction of Basic Interaction Protocols
  • 7.3 Reconstruction of Higher Order Protocols
  • 7.4 Tool Support
  • 7.5 Summary
  • 8 Process Mining in a Discrete Event Simulation Study
  • 8.1 Courier Service Study
  • 8.2 Application of Process Mining
  • 8.3 Process Mining Experiments and Results
  • 8.4 Integration into an Experimentation Environment
  • 9 Summary, Discussion, and Outlook
  • 9.1 Summary of Contributions
  • 9.2 Discussion
  • 9.3 Outlook

Otros documentos de esta serie

    Títulos relacionados

      Otros títulos del mismo autor