Extended version of An Overview of Hierarchical Control Flow Graph Models, contained in Proceedings of 1995 Winter Simualtion Conference.

Download complete paper (87KB gzipped postscript).

This paper proposes a methodology that replaces the usual ad hoc approach to metamodeling. This methodology considers validation of a metamodel with respect to both the underlying simulation model and the problem entity. It distinguishes between fitting and validating a metamodel, and covers four types of goal: (i) understanding, (ii) prediction, (iii) optimization, and (iv) verification and validation. The methodology consists of a metamodeling process with 10 steps. This process includes classic design of experiments (DOE) and measuring fit through standard measures such as R-square and cross-validation statistics. The paper extends this DOE to stagewise DOE, and discusses several validation criteria, measures, and estimators. The methodology covers metamodels in general (including neural networks); it also gives a specific procedure for developing linear regression (including polynomial) metamodels for random simulation.

© European Journal of Operational Research, Vol. 120, 2000, pp. 14-29.

Three useful modeling techniques for specifying discrete event simulation models are discussed. Hierarchical model specification provides for model specification at different levels of abstraction. Scaling of model elements provides for the combination of similarly structured and parallel operating model elements into arrays, of both fixed and dynamic sizes. Reuse of model elements allows for the repeated use of model elements specifications. The Hierarchical Control Flow Graph Model paradigm is used to demonstrate the techniques discussed.

Download complete paper (62 KB gzipped postscript).

Download complete paper (78 KB gzipped postscript).

This paper discusses verification and validation of simulation models. The different approaches to deciding model validity are presented; how model verification and validation relate to the model development process are discussed; various validation techniques are defined; conceptual model validity, model verification, operational validity, and data validity are described; ways to document results are given; and a recommended procedure is presented.

Download complete paper (78 KB gzipped postscript).

Download complete paper (136 KB gzipped postscript).

The portion of the Hierarchical Modeling And Simulation System-Java (HiMASS-j) used for specifying Hierarchical Control Flow Graph (HCFG) Models is described. The specification of HCFG Models in HiMASS-j is by visual interactive modeling through the use of graphical user interfaces and dialog boxes. HCFG Models are specified using two complementary hierarchical specification structures, one to specify the components that comprise a model and how these components are interconnected, and the other to specify the behaviors of the individual atomic components.

Download complete paper (93KB gzipped postscript).
 

The specification of a simulation model of a complex traffic intersection using the Hierarchical Modeling And Simulation System-Java (HiMASS-j) is presented. HiMASS-j is an object-oriented Java 1.1 based simulation software system that uses the Hierarchical Control Flow Graph (HCFG) Model paradigm. Models specified in this paradigm use two complementary hierarchical specification structures, one to specify the model components and their interconnections and the other to specify the behaviors of the individual components. Models are specified in HiMASS-j via visual interactive modeling.

Download complete paper (151KB gzipped postscript).

The building of Hierarchical Control Flow Graph (HCFG) Models of queueing systems is described by developing different model elements of queueing subsystems and then combining them into HCFG Models. A brief overview of HCFG Models, which is a new modeling paradigm for discrete event simulation, is presented. Conceptually, HCFG Models consist of a set of independent, encapsulated, concurrently operating model components where each component has its own thread of control and the components interact with each other solely via message passing. HCFG Models have two complementary types of hierarchical model specification structures to specify models, one to specify components and their interconnections and the other to specify component behaviors.

Download complete paper (58KB gzipped postscript).

Hierarchical Flow Graph Model define a modeling paradigm for discrete event simulation modeling based upon hierarchical extensions to Control Flow Graph Models. Conceptually, models consist of a set of independent, encapsulated, concurrently operating model components where each component has its own thread of control and the components interact with each other solely via message passing. Two primary objectives for Hierarchical Flow Graph Models are: (1) to facilitate model development by making it easier to develop, maintain, and reuse models and model elements and (2) to support the flexible and efficient excution of models. Hierarchical Flow Graph Models use two complimentary types of hierarchical model specification structures, one to specify components and interconnections and the other to specify component behaviors.

Download complete paper (46KB gzipped postscript).

The Hierarchical Modeling and Simulation System (HI-MASS) is a prototype modeling and simulation system that supports modeling based on the Hierarchical Flow Graph Modeling paradigm and simulation execution using a synchronous simulation algorithm. The prototype is an object-oriented C++ based system for a Unix environment and implemented using freely available software tools. Models are specified using two complimentary hierarchical model specification structures, one to specify the components which comprise a model and how those components are interconnected, and the other to specify the behaviors of the individual components. A graphical user interface provides for component and interconnection specification using visual interactive modeling.Behavior specifications are constructed using C++ classes and functions provided by HI-MASS.

Download complete paper (53 KB gzipped postscript).
 

This paper discusses the model specification, construction of the executable model, model execution, and the simulation results of a simulation model of a surveillance radar data processing system that was developed using the Hierarchical Modeling and Simulation System (HI-MASS). HI-MASS is an object-oriented C++ based system that supports model specification (modeling) using the Hierarchical Flow Graph Modeling paradigm and executes simulation models using the sequential synchronous simulation execution algorithm. Models specified in this model paradigm use two complimentary hierarchical specification structures, one to specify the model components and their interconnections and the other to specify the behaviors of the individual components. The components and their interconnections are specified in HI-MASS via visual interactive modeling.

Download complete paper (55 KB gzipped postscript).