For years computer-based stochastic simulation has been a commonly used tool in the performance evaluation of various systems. Unfortunately, the results of simulation studies quite often have little credibility, since they are presented without regard to their random nature and the need for proper statistical analysis of simulation output data.This paper discusses the main factors that can affect the accuracy of stochastic simulations designed to give insight into the steady-state behavior of queuing processes. The problems of correctly starting and stopping such simulation experiments to obtain the required statistical accuracy of the results are addressed. In this survey of possible solutions, the emphasis is put on possible applications in the sequential analysis of output data, which adaptively decides about continuing a simulation experiment until the required accuracy of results is reached. A suitable solution for deciding upon the starting point of a steady-state analysis and two techniques for obtaining the final simulation results to a required level of accuracy are presented, together with pseudocode implementations.

/pdf/steady-state-simulation-of-queueing-processes-survey-of-kbkfd6opp2.pdf

Steady-state simulation of queueing processes: survey of problems and solutions

PRINCIPLES. Bond-Graph Representation of Elementary Systems. Causality. System Representations and Transformations. System Approximation. System Inversion. APPLICATIONS. An Extrusion Process. Process Systems. Pharmacokinetics. Mechanical and Robotic Systems. Control Systems.

Metamodelling: for bond graphs and dynamic systems

Systems simulation - the art and science

New Experimentalism Applied to Evolutionary Computation

Le premier but de ce travail est d'obtenir un modele de comprehension de la dynamique mecano-chimique du ventricule gauche. Le niveau de complexite de ce modele doit permettre son emploi dans des applications dans l'enseignement et son insertion dans un modele de la boucle cardiovasculaire complete. Ce modele doit aussi permettre une premiere etude d'optimisation pour formuler et tester des hypotheses concernant la nature de l'efficacite ventriculaire resultant de l'evolution naturelle. Pour atteindre ces objectifs, nous avons choisi un niveau de complexite intennediaire (modeles "en boites grises") qui nous permet d'adapter des approches a parametres localises et d'eviter l'emploi des modeles a derivees partielles ou a elements finis qui sont trop lourds. Cette approche nous permet egalement de focaliser notre interet sur les mecanismes physico-chimiques actuellement etudies par les experimentateurs tout en adoptant des sous modeles plus simples pour les autres parties du systeme.

Etude des conditions d'efficacite du ventricule gauche par optimisation teleonomique d'un modele de son fonctionnement

INTRODUCTION 5. Model verification 6. Model validation Effective execution of managerial responsibility is a perplexing task of ever increasing complexity. This is the result of unpredictable world, national and local economies, the pervasive impact of federal and state regulation, the capricious nature of the consuming public and the relentless and accelerating advance of modern. technology. The contribution of each of these elements of business life has led to the perceived need for larger and more complicated organizational structures to effectively carry on business activity. Consequently the manager is forced to recognize and understand the interaction of an increasing number of components within his own organization and its environment. With that recognition and understanding effective management is certainly not assurred. But the manager who does not recognize and understand the forces which should affect and are affected by his decisions has little hope of effectively discharging the responsibilities of a managerial position.

/pdf/introduction-to-systems-analysis-modeling-and-simulation-53neo3g3nr.pdf

Introduction to systems analysis, modeling and simulation

This paper presents an algorithm to determine where the correlation of data sequence has died out This algorithm can be used to collect essentially uncorrelated observations from a sequence of correlated observations The final purpose is to use such observations to derive statistical inferential procedures for the parameters concerned Examples of M/M/1 queues are presented

/pdf/an-algorithm-for-testing-serial-dependence-of-simulation-2t0xeoh0dh.pdf

J. W. Schmidt

Papers

Introduction to systems analysis, modeling and simulation

An algorithm for testing serial dependence of simulation output data