1. CS433: Modeling and Simulation Dr. Anis Koubâa Al-Imam Mohammad Ibn Saud University 27 February 2010 Lecture 01: Introduction

2. 2 Who I Am?  Dr. Anis Koubâa  Assistant Professor at CS Dept.  Research Associate at ISEP/IPP-HURRAY! (Portugal)  Email (Teaching): anis.koubaa.ccis@gmail.com  Phone: 25 81 921  Background  PhD from INPL/LORIA, Nancy (France)  Master from UHP Nancy I (France)  My Research  Main: Wireless Sensor Networks, Cyber-Physical Systems, Real-Time Embedded Systems, Quality-of-Service, Performance Evaluation  Other: Security

3. 3 Teaching Assistant  Basmah Al-Soli  Office no. 4034/8  Office phone: 2589128  E-mail: basmah.cs@gmail.com

4. 4 Texbook  Tayfur Altiok, Benjamin Melamed,  SIMULATION MODELING AND ANALYSIS WITH ARENA  Hardbound, 456 pages,  publication date: JUN-2007 ISBN-13: 978-0-12-370523-5 ISBN-10: 0-12-370523-1 Imprint: ACADEMIC PRESS

5. 5 Grading (may be changed)  Grading: Grades will be determined roughly as follows: (Grading may be changed)  One Mid-term, 20% total  One Final Exam, 40% total  Project 1, 151% total  Project 2, 10% total  Lab Exams, 15%

6. 6 For more information …  Official course website  http://www.aniskoubaa.net/ccis/cs433/ http://www.aniskoubaa.net/ccis/cs433/  All announcements will be posted on the website  Interaction with students  Mailing list:  ccis-cs433-spring2009@googlegroups.com  To register:  http://groups.google.com/group/ccis-cs433-fall2009

7. 7 Goals of today  Understand what is simulation and what is modelling  Some applications of simulation and modelling  What is the Life Cycle of the Modelling Process

8. 8 Some keywords to know …  System  It is a collection of entities that act and interact together toward the accomplishment of some logical end (computer, network, communication systems, queuing systems etc.)  Simulation  It is an experiment in a computer where the real system is replaced by the execution of the program  It is a program that mimics (imitate) the behaviour of the real system

9. 9 Some keywords to know …  Model  It is a simplification of the reality  A (usually miniature) representation of something; an example for imitation or emulation  A model can be Analytical (Queuing Theory) or by Simulation.  Performance evaluation (of a system)  It means quantifying the service delivered by the System  Experimental, Analytical, or by simulation

10. 10 Some keywords to know …  Queuing System  It is a system where entities ask service from a shared resource(s) and have to wait for service until resource is available.  Examples  Customers waiting in a bank  Packets waiting in a network router/switch  Travelers waiting in airport for flight registration  Tasks requesting execution in a processor (semaphors)  Bank Transactions requesting access to a database

11. 11 A Simple Queuing Model  Use Queuing models to:  Describe the behavior of queuing systems  Evaluate system performance  A Queue System has:  Queue (Buffer): with a finite or infinite size  Server: with a given processing speed  Customers: Entities requesting the shared resource (i.e. server).  Events: Arrival/Departure (with given rates) Queue Server Queuing System

12. 12 Examples Real System (Motherboard) Models of the system

13. 13 Simulation models of the system Examples

14. 14 Models of the System Examples

15. 15 Example Models of the System

16. 16 Examples Circuit Simulator Models of the system

17. What is Computer Simulation? ماهي المحاكاة عن طريق الحاسب؟

18. 18 Computer Simulation  A Computer Simulation is a computer program  that attempts to simulate an abstract model of a particular system.  that describes the behavior of a real (physical) system and its evolution in time  How it works?  The behavior of the system is described by state variables  The simulation program modifies the states variables to emulate the evolution

19. 19 Why we need simulation? It may be too difficult, risky, or expensive to observe a real, operational system Parts of the system may not be observable (e.g., internals of a silicon chip or biological system) Minimize production risk Analyze systems (performance, behavior) before they are built Reduce the number of design errors Optimize design to improve the behavior Analyze operational systems Create virtual environments for training, entertainment Make design more efficient

20. 20 System Analysis Telecommunication Networks (ATM, IP, TCP, UDP, …) Transportation systems (Traffic, Urban planning, Metro Planning, …) Electronic systems (e.g., microelectronics, computer systems) Battlefield simulations (blue army vs. red army) Ecological systems, Manufacturing systems, Logistics … Virtual Environments Physical phenomena (e.g. Trajectory of projectiles) training and entertainment (e.g., military, medicine, emergency planning, flight simulation) Applications of Simulation

21. 21 War gaming: test strategies; training Flight Simulator Transportation systems: improved operations; urban planning Computer communication network: protocol design Parallel computer systems: developing scalable software Games A few more applications …

22. 22 Why Modeling and Simulation? Why to use models? Implementation on real systems is very complex and costly, Experimentation on real systems may be dangerous (e.g. chemical systems) If models adequately describes the reality, experimenting with them can save money and time, and reduce the development complexity When to use simulations? Analytic models may be very complex to evaluate, and may lead to over implication of the real system Simulation can be a good alternative to evaluate the system behavior very close to reality

23. تقييم الأداء Performance Evaluation

24. 24 Performance Metrics The delay metric how much time do I need to wait? The throughput metric how much customer the system is able to serve per time unit? Performance Metrics

25. 25 The Queuing Times Queue Server Queuing System Queuing TimeService Time Response Time (or Delay)

26. 26  The Performance Metric is a measurable quantity that precisely captures what we want to measure (response time, throughput, delay, etc.). Performance Metrics

27. 27  For example, in computer systems, we might evaluate  The response time of a processor to execute a given task.  The execution time of two programs in a multi-processor machine.  In network systems, we might evaluate  The (maximum/average) delay experienced by a voice packet to reach the destination  The throughput of the network  The required bandwidth to avoid congestion Performance Metrics

28. 28 What does affect the performance?  The performance of a system is dramatically affected by the Workload.  The Workload: it characterizes the  Quantity: e.g. number of cars  Nature: type of cars (cars, trucks, motocycle, etc.)

29. 29  In the context of Web Servers, system inputs are http requests (GET or POST requests). The workload characterizes:  The intensity of the requests: how many requests are received by the web server. High intensities deteriorate the performance.  The nature of the requests: the request can be simple GET request or a request that require the access of a remote database. The performance will be different for different request types. What does affect the performance?

30. 30 Benchmarks  Benchmarks: used to generate loads that is intended to mimic a typical user behaviour.  Wikipedia definition:  In computing, a benchmark is the act of running a computer program, a set of programs, or other operations, in order to assess the relative performance of an object, normally by running a number of standard tests and trials against it.  Benchmarking is usually associated with assessing performance characteristics of computer hardware:  Example: the floating point operation performance of a CPU.  Software benchmarks: run against compilers or database management systems.