END3942 SIMULATION

CHAPTER 2
FUNDAMENTAL CONCEPTS ON MODELING
AND SIMULATION

Prof.Dr. Nezir AYDIN

Yıldız Technical University
Industrial Engineering

1
What is a Simulation? (1/3)
• A simulation is one of the strongest method to design and
analyze complex systems.
• In other words, simulation – very broad term – is a
method to imitate or mimic real systems, usually via
computer
• Applies in many fields and industries
• Changes in behavior of a system over a time is analyzed
by a simulation model. This model consists a set of
assumptions.
• These admissions are developed based on
mathematical, logical and symbolic relations between
entities of the system.

2
What is a Simulation? (2/3)
• Furthermore, once the simulation model is
developed and validated, it starts analyzes the
system by what-if questions.
• It helps finding out :
• The effects of the changes on a real system,
• The performance of a newly constructed system.
• Therefore it is;
• An analyzing tool
• Designing tool

3
What is a Simulation? (3/3)
• In real world most of the systems are complex
and it is either impossible (based on technical
requirements) or very difficult to solve.
• In that case simulation is a very good candidate
to use.
• In simulation, collected data from a real world
system is used to forecast the parameters of the
developed simulation model.

4
4
AIMS OF SIMULATION
• Assessment: Determines/presents the
performance of the proposed system.
• Comparison: Compares the proposed designs
and policies.
• Forecast: Forecast the performance of the
system.
• Sensitivity Analysis: Determines the factors that
effect the performance of the system.
• Optimization: Provides good combinations of
factors.
• Bottleneck Analysis: Determines bottlenecks.
5
5
When to use Simulation?
• Simulation can be used for the purposes of:
• Study and experiment with internal interactions of a complex
system.
• Observe the effect of system alterations on model behavior.
• Gain knowledge about the system through design of simulation
model.
• Using as a pedagogical device to reinforce analytic solution
methodologies, also to verify analytic solutions.
• Experiment with new designs or policies before implementation.
• Determine machine requirements through simulating different
capabilities.
• For training and learning.
• Show animation.
• Model complex systems.

6
6
When Not to Use Simulation? (1/3)
• Problem can be solved by common sense.
• On average 100 customers arrive at a bank per hour to pay
their insurance and on average it takes 5 mins to serve.
In order to keep the system under control how
many servers are needed?
• 5*100/60 = 9
• At least 9 servers are needed to keep the system
under control.
• You could use simulation but do you really need it?

7
7
When Not to Use Simulation? (2/3)
Problem can be solved analytically.
• If you are able to write close form of a problem and solve with
mathematics (differential equations…). i.e., inventory problems.
If it is easier to perform direct experiments.
If the costs exceed the savings.
• If the cost of applying simulation exceeds the profit it provides.
If the resources or time to perform simulation studies
are not available.
• Labor (personnel)- computer language (program)- Computer itself-
capital
• The detail level is very important and it is determined by human (labor).

8
When Not to Use Simulation? (3/3)
• If there is not enough time or personnel to
verify/validate the model.
• Applying simulation takes longer than the projects time.
• A simulation model should be able to answer only required
answer(s).
• Not less not more!

If no data, not even estimates, is available.

• At the design stage of a simulation project the data needed
should be available, if not look for it!
If managers have unreasonable expectations:
overestimate the power of simulation.
If system behavior is too complex or cannot be defined.

9
Advantages and Disadvantages of Simulation
• Simulation is frequently used in problem solving.
• It mimics what happens in a real system.
• It is possible to develop a simulation model of a system without
dubious assumptions of mathematically solvable models.
• In contrast to optimization models, simulation models are
“run” rather than “solved”.
• Advantages:
• Explore new policies or procedures without disrupting ongoing
operations of the real system.
• Test new hardware or physical systems without committing to
acquisition.
• Test hypotheses about how or why certain phenomena occur.
• Study speed-up or slow-down of the phenomena under
investigation.

10
10
Advantages and Disadvantages of the Simulation

• Advantages (cont.):
• Study interactions of variables, and their importance to system
performance.
• Perform bottleneck analysis.
• Understand how the system operates.
• Test “what if” questions.
• Disadvantages:
• Model building requires special training.
• Simulation results can be difficult to interpret.
• Simulation modeling and analysis can be time consuming and
expensive.
• Simulation is used in some cases when an analytical solution is
possible (or even preferable).

11
11
Areas of Application
• The applications of simulation are vast.
• The Winter Simulation Conference: an excellent way to
learn more about the latest in simulation applications and
theory.
• Some areas of applications:
• Manufacturing
• Construction engineering and project management.
• Military.
• Logistics, supply chain, and distribution.
• Transportation modes and traffic.
• Business process simulation.
• Healthcare.
• Computer and communication systems.

12
12
Areas of Application
• Some general trends:
• Risk analysis, e.g. pricing, insurance.
• Call-center analysis.
• Large-scale systems, e.g., internet backbone, wireless networks.
• Automated material handling systems as test beds for the
development and functional testing of control-system software.
• Production
• Banks
• Airports
• Biology,
• Sociology,
•

13
13
 Lets go back to systems

Systems and System Environment

• A system is a group of objects joined
together in some regular interaction or
interdependence to accomplish some
purposes.
• i.e., a production system: machines,
component parts & workers operate jointly
along an assembly line to produce vehicle.
• Affected by changes occurring outside the
system.

System environment: “outside the system”, defining

the boundary between system and its environment is
important.
14
14
Components of a System (1/2)
• An entity: an object of interest in the system, e.g.,
computing jobs in a queue. Patient, customer, e-mail…
• An attribute: a property of an entity, e.g., priority class,
or vector of resource requirements.
• An activity: represents a time period of a specified
length, e.g. job receiving service.
• The state of a system: collection of variables
necessary to describe the system at any time, relative
to the objectives of the study, e.g. the number of busy
servers, the number of jobs in queue, the number of
people in the queue.

15
15
Components of a System (2/2)
• An event: an instantaneous
occurrence that may change the
system state, can be endogenous
or exogenous, e.g. a new job
arrival, or service time completion.
• Resources: Personnel, tools,
energy, time, capita.
• Control: Programs when/ how
/where the activities occur..

16
16
 System Examples
System Entity Attribute Activity Event State Variable
Banking customer Checking Making deposit Arrival; # of busy
account departure tellers; # of
balance customers
waiting
Train
Manufactu
ring
Communi
cation
Stock

17
 System Examples
System Entity Attribute Activity Event State Variable
Banking customer Checking Making deposit Arrival; # of busy
account departure tellers; # of
balance customers
waiting
Train Passengers Departure Traveling Train arrivals to # of Waiting
city; the station or to passengers, #
destination the destination of traveling
passengers
Manufactu Machines Speed, Press, molding.. failure Failed, busy,
ring capacity, idle
prob. of
failure
Communi Messages # of words, Sending Arrival # of messages
cation destination in queue
Stock Depot Capacity Accepting Demand Stock level;
materials unsatisfied
demand

18
Model of a System
• Studies of systems are often accomplished with a model
of a system.
• A model: a representation of a system for the purpose of
studying the system.
• A simplification of the system.
• Should be sufficiently detailed to permit valid conclusions to be
drawn about the real system.
• Should contain only the components that are relevant to the study.
Simplification
Real System Condensation Model
Assumptions

19
19
MODELS - representation
Mathematical
Iconic models Analog models
models

BEGIN;
EI=BI+PROD-DEMAND
.
END;

SIMULATION

20
MODELS – representation cont’d
• Iconic models: 3D maps; plane maquette.
• Analog models: represents some specifications of an
event or object and plotted by lines. electricity circuit,
speedometer, thermometer.
• Mathematical models: Representation of an object
by characters symbols and numbers. Words, formulas,
equations.

21
MODELS- Type of use
Prescriptive Descriptive
models models

• Subject to constraint • Defines output as a

optimizing models. combination of inputs.
Provides a final Describes real case.
(optimized) solution. There is no forecast,
comments, or
recommendations based
on findings.
• Flow charts, organization
charts, financial
statements..
22
Where simulation stands?
• Two types of models: mathematical or physical.
• Mathematical model: uses symbolic notation and
mathematical equations to represent a system.
• Simulation is a type of mathematical model.

• Simulation models:
• Static or dynamic.
• Deterministic or stochastic.
• Discrete or continuous.

• Our focus: discrete, dynamic, and stochastic models.

23
23
Discrete Event System Simulation
• This course is about discrete-event system simulation.
• Simulation models are analyzed by numerical methods
rather than by analytical methods.
• Analytical methods: deductive reasoning of mathematics to
“solve” the model.
• Numerical methods: computational procedures to “solve”
mathematical models.

24
24
 25

What this course covers

25
How are we going to do?
• Manuel ✓
• On spreadsheets of MS Excel and its addings ✓
• Other computer languages X
• C++, C#, JAVA, etc.. (ask your computer programming instructor)

• Simulation languages ✓
• SIMAN, GPSS, SLAM etc..

• Simulation package programs ✓

• ARENA, ProModel, AutoMod, AnyLogic, etc.. ✓
26
26
 Deterministic vs Stochastic simulation models

• Deterministic • Stochastic
• Free of stochastic • Includes at least one
parameter. Providing an stochastic parameter.
input set provides an Provides random output
output set. Since it is free and forecasts
of stochasticity it provides characteristics of the
the same results all the system statistically.
times (given that you • For instance: Interarrival
provide the same input time or service time in the
set). banking example.
• For instance: All patient
show up ontime for treatment.

27
Static vs Dynamic simulation models
• Static simulation • Dynamic simulation
models: models:
• Represents the state of • Represents the state of
the system at a certain the system for a time
time. period or the whole
• For instance: Monte-Carlo process time. This means
simulation models (coin- it changes over time.
tossing). • For instance: Consider 8
hours in a bank. Represent
the changes over time.

28
Discrete vs Continuous Systems
• Discrete system: in which state variable(s) change only at a
discrete set of points in time.
• e.g., the number of jobs in queue changes when a new job arrives or
when service is completed for another
• Continuous system: in which state variable(s) change
continuously over time.
• e.g., the head of water behind a dam.

Discrete System Continuous System

29
29
STEPS OF A SIMULATION (1/2)

30
STEPS OF A SIMULATION (2/2)
A simulation study should be accomplished in 4 phases:
• Describe the problem, Define an achievable goal (steps
1-2)
• Gathering the data and construct the model at an
appropriate level(s) of detail (steps 3-7)
• Run the model (steps 8-10)
• Application (steps 11-12)

31
PHASE I (1/3)

32
PHASE I (2/3)
Step 1: Problem description (formulation) :
• Every study should begin with a statement of the
problem
• Problem should be explained and defined clearly
• If analyst and decision maker are different people then
analyst should make sure the problem is understood clearly.
• If analyst defines the problem, again, analyst should make
sure that decision maker understand it clearly.
• All should agree!

33
PHASE I (3/3)
Step 2: Setting of objectives and overall project plan:
• The objectives indicate the questions to be answered by
simulation. A determination should be made concerning whether
simulation is the appropriate methodology for the problem as
formulated and objectives as stated.
• Project proposal
• Questions need answers (goals)
• Is simulation a right methodology?
• Alternative system designs
• Performance measures
• Required inputs
• Software, hardware and personnel
• Time schedule
• Results aimed to achieve after each steps
• Cost plans (expenses) 34
PHASE II (1/11)

35
PHASE II (2/11)
Step 3: Model conceptualization:
• Develop the conceptual model
Real System

Virtual
system

Conceptual System

Logical System

36
 PHASE II (3/11)
Step 3: Model conceptualization :
• The construction of a model of a system is probably as much art as
science. The art of modeling is enhanced by an ability to abstract the
essential features of a problem, to select and modify basic
assumptions that characterize the system, and then to enrich and
elaborate the model until useful approximation results are obtained.
• Condensate fundamental properties of the system
• Entities, events, activities, resources, variables and their relationships,
• Performance measures,
• Data requirements

• Determine correct detail level

• Low detail level: If it is not detailed enough, real performance measures
will not be achieved, and will cause info loses,
• High detail level: Will cause time wasting and might cause errors.

37
PHASE II (4/11)
Step 3: Model conceptualization :
Accuracy of the model

Cost of the model

Content and detail level

Content and detail level

38
PHASE II (5/11)
Step 3: Logical Model: a flow model which shows
relationships between entities
Exit event

L(t)=L(t)-1
No Yes
B(t)=0 Q(t)>0? Q(t)=Q(t)-1

Start serving

Collect
statistical data

39
PHASE II (6/11)

40
PHASE II (6/11)

Step 4: Data collection:

• There is a constant interplay between the construction of the
model and the collection of the needed input data
• Required data collection for input analyzes.
• In banking example, if the goal is to determine number of
servers, the needed data are interarrival times and service
times. Furthermore, existing ferformance measures should be
evaluated.
• Analyzing the data
• Determination of random variables
• Determination of appropiate distributions

41
PHASE II (7/11)

42
PHASE II (7/11)
Step 5: Model translation:
Most real-world systems result in models that
require a great deal of information storage and
computation, so the model must be entered into a
computer-recognizable format. General purpose or
special purpose simulation languages or packages to be
used is determined here.

43
PHASE II (8/11)
Step 5: Model translation:
Logical model, is coded either using an
appropiate computer language (Fortran, Pascal,
C++, …) or a simulation language (SIMAN,
GPSS, SLAM, …)
Software

Other general computer

Simulation languages
languages

For instance For instance

JAVA, C++, VBA, … SIMAN, ARENA, GPSS …

44
PHASE II (9/11)

45
PHASE II (9/11)
Step 6: Model Verification: Did I build the model
right?
Verification pertains to the computer program prepared for the
simulation model. Is the computer program performing properly?

• Verification relates to the computer language selected.

• It is tested to check whether it works or not.
• If conceptualization of the model and input parameter are
designed correctly then model verification is completed.

46
PHASE II (10/11)

47
PHASE II (10/11)
Step 7: Model Validation: Did I build the right
model?
• Validation usually is achieved through the calibration of the
model, an iterative process of comparing the model against
actual system behavior and using the discrepancies between
the two, and the insights gained, to improve the model.

• Model validation relates to the behavior of the model developed.

• Real world system’s behavior and designed model’s behavior
should be accurate.
• Output of the model and the data gathered from real system
should be compared statistically,
• If H0 is failed to reject then the model is valid (No significant
difference). If not, the model should be revised.
48
 PHASE II (11/11)

Real System

Conceptual system
VALIDATION

Logical Model

VERIFICATION

Simulation model

49
PHASE III (1/3)

50
PHASE III (2/3)
Step 8: Experimental Design:
• The alternatives that are to be simulated must be
determined.
• Often, the decision concerning which alternatives to
simulate will be a function of runs that have been
completed and analyzed.
• For each system design that is simulated, decisions
need to be made concerning the length of the
initialization period, the length of simulation runs, and
the number of replications to be made of each run.

51
PHASE III (3/3)
Step 9: Production runs and analyses:
• Production runs, and their subsequent analyses, are used to
estimate measures of performance for the system designs that
are being simulated.
• The aim here is to determine the confidence intervals of
performance measures and select the best performed design.
Step 10: More runs?:
• Given the analyses of runs that have been completed, the
analyst determines whether additional runs are needed and
what design those additional experiments should follow.

52
PHASE IV (1/3)

53
PHASE IV (2/3)
Step 11: Documentation and reporting:
• There are two types of documentation: program and progress.
• Program documentation is necessary for numerous reasons. If
the program is going to be used again by the same or different
analysts, it could be necessary to understand how the program
operates and what parameters used.
• The result of all the analysis should be reported clearly and
concisely in a final report. This will enable the model users (now,
the decision makers) to review the final formulation, the
alternative systems that were addressed, the criterion by which
the alternatives were compared, the results of the experiments,
and the recommended solution to the problem.

54
PHASE IV (3/3)
Step 12: Implementation:
• It depends on the performance, correctness and accuracy of the
11 steps abovementioned.
• If implementation is not satisfying then something is wrong with
the previous steps!!!

55
See you at the next lecture ☺

56