Practical Performance Modeling: Application of the Mosel LanguagePractical Performance Modeling: Application of the MOSEL Language introduces the new and powerful performance and reliability modeling language MOSEL (MOdeling, Specification and Evaluation Language), developed at the University of Erlangen, Germany. MOSEL facilitates the performance and reliability modeling of a computer, communication, manufacturing or workflow management system in a very intuitive and simple way. The core of MOSEL consists of constructs to specify the possible states and state transitions of the system under consideration. This specification is very compact and easy to understand. With additional constructs, the interesting performance or reliability measures and graphical representations can be specified. With some experience, it is possible to write down the MOSEL description of a system immediately only by knowing the behavior of the system under study. There are no restrictions, unlike models using, for example, queueing networks, Petri nets or fault trees. MOSEL fulfills all the requirements for a universal modeling language. It is high level, system-oriented, and usable. It is open and can be integrated with many tools. By providing compilers, which translate descriptions specified in MOSEL into the tool-specific languages, all previously implemented tools with their different methods and algorithms (including simulation) can be used. Practical Performance Modeling: Application of the MOSEL Language provides an easy to understand but nevertheless complete introduction to system modeling using MOSEL and illustrates how easily MOSEL can be used for modeling real-life examples from the fields of computer, communication, and manufacturing systems. Practical Performance Modeling: Application of the MOSEL Language will be of interest to professionals and students in the fields of performance and reliability modeling in computer science, communication, and manufacturing. It is also well suited as a textbook for university courses covering performance and reliability modeling with practical applications. |
Contents
INTRODUCTION | |
12 The State of Evaluation Methods and Tools | |
14 Implementation of the Idea | 2 |
15 Overview | 4 |
THEORETICAL BACKGROUND | 7 |
23 Some Useful Distribution Functions | 14 |
231 Discrete Distribution Functions | 15 |
232 Parameters of Continuous Distributions | 21 |
43 Restrictions for the Different Tools | 141 |
432 Rules and Restrictions for CSPL | 142 |
MODELING USING MOSEL | 145 |
512 Fault Trees | 150 |
513 Reliability Graphs | 154 |
514 Markov Chains | 157 |
515 Generalized Stochastic Petri Nets GSPNs | 166 |
516 Stochastic Process Algebras | 169 |
24 Stochastic Processes | 33 |
242 Classification of Stochastic Processes | 34 |
25 DiscreteTime Markov Chains | 37 |
251 Classification of States | 39 |
252 Limiting Probability Distributions | 41 |
253 Distribution of Holding Times | 42 |
254 DiscreteTime BirthDeath Processes | 43 |
26 ContinuousTime Markov chain | 44 |
261 Introduction | 45 |
262 Limiting Behavior of Homogeneous CTMC | 48 |
263 ContinuousTime BirthDeath Processes | 50 |
264 Pure Birth Processes | 52 |
265 The MM1 Queue | 54 |
266 Finite Queue MM1K | 57 |
MODEL TYPES | 59 |
32 Queuing Networks | 60 |
33 SeriesParallel Acyclic Directed Graphs | 63 |
34 NonSeriesParallel Task Precedence Graphs | 64 |
35 SeriesParallel Reliability Block Diagrams | 66 |
36 Fault Trees | 67 |
37 Reliability Graphs | 68 |
39 Generalized Stochastic Petri Nets | 70 |
310 Stochastic Process Algebras | 75 |
311 Performability Models Reward Models | 85 |
MOSEL AN UNIVERSAL MODELING LANGUAGE | 87 |
412 The General Structure of a MOSEL Description | 92 |
413 Parameter Declaration Part | 93 |
414 System State Definition Part | 96 |
415 Transition Definition Part | 98 |
416 Result Part | 107 |
417 Picture Part | 108 |
418 Rewards | 119 |
419 Comments | 126 |
4110 Shortcuts in MOSEL | 128 |
4111 Preprocessor Directives | 132 |
4112 Multidimensional Nodes | 134 |
42 Command Line Syntax of MOSEL Program | 138 |
52 Program Performance Analysis | 170 |
522 Task Precedence Graphs | 179 |
53 System Performance Analysis | 181 |
532 MMNK Queuing Systems | 187 |
533 Markov Chains | 192 |
534 Generalized Stochastic Petri Nets GSPNs | 196 |
535 Stochastic Process Algebras | 201 |
54 Performability Analysis | 203 |
542 Determination of Reward Rates | 205 |
543 Modeling Perforrnability without Rewards | 208 |
55 Special Techniques of Analysis | 210 |
551 Distinction of particular jobs in a model | 211 |
552 Modeling NonExponential Distributions | 213 |
553 Modeling of MultiClass Networks | 226 |
554 Modeling Distribution Functions and Probability Density Functions as Results | 231 |
555 Technique to avoid Explosion of Markov State Space | 234 |
REALLIFE EXAMPLES | 239 |
612 Polling Systems | 259 |
613 ForkJoin systems | 265 |
614 NonHomogeneous Terminal System | 272 |
615 Multithreaded Architectures | 279 |
62 Communications Examples | 292 |
622 Cellular Mobile Networks | 315 |
623 Performance Model of an ATM Multiplxer | 333 |
63 Manufacturing Examples | 338 |
632 Wafer Production System | 340 |
633 Cluster Tools for SingleWafer Processing | 344 |
MOSEL and IGL Reference | 350 |
A12 Semantics of the language MOSEL | 355 |
A13 Keywords and Tokens of the language MOSEL | 361 |
A2 IGL Graphical Editing of the Results | 363 |
A23 The Intermediate Graphic Language IGL | 376 |
A3 Technical data of the MOSEL program suite | 378 |
A32 The program igl | 380 |
Bibliography | 382 |
394 | |
Other editions - View all
Practical Performance Modeling: Application of the MOSEL Language Khalid Begain,Gunter Bolch,Helmut Herold No preview available - 2012 |
Common terms and phrases
arrival ARROWTEXT Balloon Help batch birth-death process buffer cell client-server Clients 4 Kbytes components cpu_state CSMA/CD CURVE define described in MOSEL DIFF disk driver enum Erlang distribution example exponentially distributed failure rate FROME function graph GRID GSPN model handover HELP double idle IGL interpreter ISDN kernel keywords lambda Markov chain MEAN REWARDSS mean_qlength memory modules model from Figure mono-processor MOSEL as shown MOSEL compiler MOSEL listing MOSEL program mtbf mttf multiprocessor NODE node_1 number of jobs number of memory Offered Load packets parameters performance Petri nets picture Poisson process Polling System precedence graph PROB probability proc_down proc_up queue length queuing network random variables reliability request result file sc_request server server_idle shown in Figure specified SPNP station stochastic process super switch terminals throughput token token ring tool transient analysis transition UNIX userq UTIL util_server values wafer XSCALE YSCALE LOOKOUT