Discrete-Event System Simulation

FOURTH EDITION

Jerry Banks Independent Consultant John S. Carson II Brooks Automation Barry L. Nelson Northwestern University

t,

David M. Nicol
University of Illinois, Urbana-Champaign
PRENTICE-HALL INTERNATIONAL SERIES IN INDUSTRIAL AND SYSTEMS ENGINEERING

I/I/. J. Fabrycky and J. H. Mize, editors

11 Introduction to Simulation When Simulation Is the Appropriate Tool When Simulation Is Not Appropriate Advantages and Disadvantages of Simulation Areas of Application Systems and System Environment Components of a System Discrete and Continuous Systems Model of a System Types of Models Discrete-Event System Simulation Steps in a Simulation Study References Exercises Simulation Examples 1 3 4 4 5 7 9 9 11 12 13 13 14 18 19 21 22 39 Chapter 2 2.Contents Preface About the Authors xiii xv I Introduction to Discrete-Event System Simulation Chapter 1 1.2 Simulation of Inventory Systems .7 1.1 1.6 1.8 1.9 1.5 1.10 1.3 1.1 Simulation of Queueing Systems 2.2 1.4 1.

9 WITNESS .4 Other Examples of Simulation Summary References Exercises General Principles _ _ 46 57 57 57 67 68 71 74 77 86 87 88 90 92 92 92 93 95 96 97 97 97 98 98 99 99 102 104 112 117 120 122 123 124 124 125 125 126 127 128 Chapter 3 3.6 4.8 SIMUL8 4.1.7 Historjt of Simulation Software 4.1 3.4 The Expansion Period (1971-78) 4.1.2 AutoMod 4.1 The Event Scheduling/Time Advance Algorithm 3.1.4 4.2 The Advent (1961-65) 4.3 The Formative Period (1966-70) 4.6 ProModel 4.3 Extend 4.1 Arena 4.3 Concepts in Discrete-Event Simulation 3.5 4.7 QUEST 4.7.7.4 Flexsim 4.1.VI Contents 2.3 4.6 Integrated Environments (1987-Present) Selection of Simulation Software An Example Simulation Simulation in Java Simulation in GPSS Simulation in SSF Simulation Software 4.2 4.2.2 World Views 3.1.5 Consolidation and Regeneration (1979-86) 4.1.3 Using Dynamic Allocation and Linked Lists 3.3 2.4 Advanced Techniques Summary References /' Exercises Simulation Software Chapter 4 4.7.7.1 4.7.1 The Period of Search (1955-60) 4.2.1.1.2.1.7.3 Manual Simulation Using Event Scheduling List Processing 3.2 3.5 Micro Saint 4.7.2.7.1 Lists: Basic Properties and Operations 3.7.2 Using Arrays for List Processing 3.

1 The Calling Population 6.8 Experimentation and Statistical-Analysis Tools 4.5.3 Long-Run Measures of Performance of Queueing Systems 6.3 5.3 The Conservation Equation: L — Xw 6.3 Multiserver Queues with Poisson Arrivals and Limited Capacity: M/M/c/N/oo 6.4 5.CONTENTS VII 4.7 Chapter 6 6.3.2 System Capacity 6.1.8.4.6 5.4 Server Utilization 6.5.5 Costs in Queueing Problems 6.1 Single-Server Queues with Poisson Arrivals and Unlimited Capacity: M/G/l 6.8.2 Queueing Notation 6.3.2 Multiserver Queue: M/M/c/oo/oo 6.1 Characteristics of Queueing Systems 6.4.4 Queue Behavior and Queue Discipline 6.2 Average Time Spent in System Per Customer w 6.1 5.1.5 Statistical Models in Simulation Review of Terminology and Concepts Useful Statistical Models Discrete Distributions Continuous Distributions Poisson Process 5.3.2 Nonstationary Poisson Process /' Empirical Distributions Summary References Exercises Queueing Models 147 149 150 156 160 166 186 188 189 190 193 193 193 201 202 202 204 204 205 206 208 208 209 111 212 213 218 220 221 227 233 235 5.1 Common Features 4.1.5 Service Times and the Service Mechanism 6.4 Steady-State Behavior of Infinite-Population Markovian Models 6.2 5.3.1 Properties of a Poisson Process 5.4.3 The Arrival Process 6.5 Steady-State Behavior of Finite-Population Models (M/M/c/K/K) .1 Time-Average Number in System L 6.1.2 Products References Exercises 128 128 129 131 132 II Mathematical and Statistical Models Chapter 5 5.3.1.

1.1.3.1.5 Chapter 8 8.7 Discrete Distributions Acceptance—Rejection Technique 8.4. 7.5 Empirical Continuous Distributions 8.3 Random-Number Generation Properties of Random Numbers Generation of Pseudo-Random Numbers Techniques for Generating Random Numbers 7.3 Gamma Distribution Special Properties 8.1 7.1.4 Triangular Distribution 8. References Exercises .1 Poisson Distribution 8.1.3.3 Weibull Distribution 8.4 Inverse-Transform Technique 8.2 7.4 7.3.1.1.1 8.2.3 8.1 Exponential Distribution 8.3.VIII Contents 6.2 8.2 Uniform Distribution 8.1 Frequency Tests 7.6 6.6 Continuous Distributions without a Closed-Form Inverse 8.2 Convolution Method 8.1 Linear Congruential Method 7.3.2.7 Networks of Queues Summary References Exercises ^ 239 241 242 243 III Random Numbers Chapter 7 7.3 Random-Number Streams Tests for Random Numbers /.3 More Special Properties Summary .1 Direct Transformation for the Normal and Lognormal Distributions 8.2 Nonstationary Poisson Process 8.2.2 Combined Linear Congruential Generators 7.4.2 Tests for Autocorrelation Summary References Exercises Random-Variate Generation 249 251 251 252 253 254 257 259 260 261 265 267 268 269 272 273 273 276 277 278 279 283 284 289 290 293 294 296 296 298 299 299 299 300 7.3.

3 Calibration and Validation of Models 10.3.1 Histograms 9.6 9.2 Chi-Square Test with Equal Probabilities 9.3.5 Input-Output Validation: Using a Turing Test 10.2 Stochastic Nature of Output Data .1 Chi-Square Test 9.1 Types of Simulations with Respect to Output Analysis 11.4 Input-Output Validation: Using Historical Input Data 10.3 Time-Series Input Models 9.7.3 Validating Input-Output Transformations 10.5 9.4 ^-Values and "Best Fits" Fitting a Nonstationary Poisson Process Selecting Input Models without Data Multivariate and Time-Series Input Models 9.2.3.7 9.3.4.2.4 The Normal-to-Anything Transformation Summary References Exercises 305 307 308 310 310 313 316 319 319 321 326 327 329 331 333 334 335 337 337 338 340 342 344 345 346 354 355 356 361 362 362 363 374 378 379 379 381 383 384 387 9.4. Verification. and Validation 10.3 9.CONTENTS iX IV Analysis of Simulation Data Chapter 9 9.1 9.4 Summary References Exercises Chapter 11 Output Analysis for a Single Model 11.7.1 Preliminary Statistics: Sample Mean and Sample Variance 9.3 Quantile-Quantile Plots Parameter Estimation 9.2 Input Modeling Data Collection Identifying the Distribution with Data 9.1 Model-Building.3.3.4 9.2 Verification of Simulation Models 10.2 Suggested Estimators Goodness-of-Fit Tests 9.2 Validation of Model Assumptions 10.7.7.1 Face Validity 10.3.4.1 Covariance and Correlation 9.2 Multivariate Input Models 9.2 Selecting the Family of Distributions 9.2.8 Chapter 10 Verification and Validation of Simulation Models 10.4.3 Kolmogorov-Smirnov Goodness-of-Fit Test 9.

3 Bonferroni Approach to Screening 12.2 Bonferroni Approach to Selecting the Best 12. Exercises Chapter 12 Comparison and Evaluation of Alternative System Designs 12.4 Estimating Probabilities and Quantiles from Summary Data 11.3 Multiple Linear Regression 12.2.2.3 Measures of Performance and Their Estimation 11.1.6 Summary References .5.2.2 Error Estimation for Steady-State Simulation 11.1 Simple Linear Regression 12.5 Output Analysis for Steady-State Simulations 11.4 Random-Number Assignment for Regression 12.5.3 Quantiles 11.2 Comparison of Several System Designs 12.5.3.5.1 Bonferroni Approach to Multiple Comparisons 12.2 Confidence Intervals with Specified Precision 11.1 Point Estimation * 11.3 Common Random Numbers (CRN) 12.X Contents 11.2 Testing for Significance of Regression 12.1.1 Comparison of Two System Designs 12.1 What Does 'Optimization via Simulation' Mean? 12.4.3 Replication Method for Steady-State Simulations 11.4.1 Initialization Bias in Steady-State Simulations 11.4 Confidence Intervals with Specified Precision 12.4 Output Analysis for Terminating Simulations 11.2 Independent Sampling with Unequal Variances 12.4.1.3.2 Confidence-Interval Estimation 11.3.4 Optimization via Simulation 12.4 An Illustration: Random Search 390 390 392 393 394 397 399 400 402 403 409 413 417 418 422 423 423 424 432 433 436 438 438 446 -448 449 454 457 458 459 463 466 466 467 468 469 470 473 .4.3 Using Robust Heuristics 12.3.5 Batch Means for Interval Estimation in Steady-State Simulations 11.5.6 Quantiles 11.3.4.LI Independent Sampling with Equal Variances 12.3 Metamodeling 12.4.1 Statistical Background 11.4.3.5.2 Why is Optimization via Simulation Difficult? 12.4 Sample Size in Steady-State Simulations 11.4.

3.4 Case Studies of the Simulation of Manufacturing and Material-Handling Systems 13.2 Simulation Tools 14.1 Modeling Downtimes and Failures 13.2.5.3.2 Virtual-Memory Referencing 14.2.3.2 Goals and Performance Measures 13.5.4 Analysis of Station Utilization 13.CONTENTS Xi 12.6 Memory Simulation 483 485 486 486 487 488 489 490 491 495 496 499 499 502 503 503 504 506 506 506 507 517 517 520 522 524 525 526 528 534 538 543 .1.3 Some Common Material-Handling Equipment 13.1.3 Issues in Manufacturing and Material-Handling Simulations 13.3.1 Models of Manufacturing Systems 13.2 Event Orientation 14.5.1 Process Orientation 14.2 Presimulation Analysis 13.3 Model Input 14.1 System Description and Model Assumptions 13.3 Simulation Model and Analysis of the Designed System 13.5 CPU Simulation 14.5.1 Introduction 14.1 Manufacturing and Material-Handling Simulations 13.2 Models of Material-Handling 13.6 Concluding Words 13.4 High-Level Computer-System Simulation 14.6 Summary References Exercises Chapter 14 Simulation of Computer Systems 14.1.5.5 Summary References Exercises ° 476 476 477 V Applications Chapter 13 Simulation of Manufacturing and Material-Handling Systems 13.5.2 Trace-Driven Models 13.5 Analysis of Potential System Improvements 13.5 Manufacturing Example: A Job-Shop Simulation 13.1 Modulated Poisson Process 14.

1 Introduction 15.6.3 Media Access Control 15.2 Traffic Modeling 15.3.xii Contents o 14.2 Example 15.7 Summary References Exercises Chapter 15 Simulation of Computer Networks 15.3.2 Ethernet 15.1 Construction 15.6 Model Construction 15.7 Summary References Exercises Appendix Index 546 546 547 550 550 552 555 556 559 561 562 569 569 571 573 574 574 576 591 /' .1 Token-Passing Protocols 15.4 Data Link Layer 15.5 TCP 15.6.

Master your semester with Scribd & The New York Times

Special offer for students: Only $4.99/month.

Master your semester with Scribd & The New York Times

Cancel anytime.