SIMULATION MODELLING & ANALYSIS LAB

MANUAL
(L-T-P: 0-0-2)

Instructor: Dr. Rashmi Singh

Department of Management Studies
IIT(ISM)-Dhanbad
Lab Location: Systems Lab (Ground Floor, DMS)
S.No. Simulation Models of Distinct System
1. A Simple Processing System
2. Case Study: Serial/Parallel Processing
3. An Electronic Assembly & Test System
4. Exercise: Input Probability Distribution/Fitting Distribution
5. A Simple Call Centre & Output Analysis
6. An Inventory System
7. A Small Manufacturing System
Course: Simulation Modeling & Analysis Lab (MSC517)

Course Course
Name of Course L T P Credit
Type Code
DP MSC517 Simulation Modeling & Analysis Lab 0 0 2 2

Course Objective
In this course, one will be introduced to the foundations of simulation modeling along with some popular software.
This will also give you insights on how and when to apply simulation modeling to solve a variety of business-related
problem that exist in manufacturing/healthcare/bank/transportation/logistics/supply chain sectors. The course will be
taught with popular software Arena.
Learning Outcomes
 To understand the concept of simulation modeling & various types of simulation models
 To develop the skill in application software like Arena for solving business application problems through
simulation modeling technique
 To build valid, credible, and appropriately detailed simulation models using Arena software for solving real-life
business problems

Unit Topics to be Covered Lectures Learning Outcome

1. Fundamental Simulation Concepts: System,
simulation modeling, Applications, & Challenges.
2. A Guided Tour Through Arena: Arena Window,
Elements of simulation model, developing a simple
processing system and analyzing its behavior.
3. Basic Operations and Inputs: Developing an
electronic assembly & test system, input analysis,
selecting Input Probability Distribution, fitting input
distributions via input analyzer.
4. Modeling Detailed Operations: A simple call center
system, modeling issues, building the model, system
exit and run setup, and detailed output analysis.
5. Case Study: Development of various simulation
models such as, specialized serial processing Vs.
generalized parallel processing, an inventory system,
and a small manufacturing system
[2L] Students will learn the fundamental
concepts of simulation modeling, types of
simulation models and their challenges.
[4L] Students will be exposed to the Arena
software and they will develop the
simulation model of a simple processing
system through Arena software.
[6L] Students will learn to find the patterns in
the data and appropriately model that data
with the best fit distribution.
[6L] Students will learn to develop simulation
models with different configurations and
will analyze its impact on the system
performance measures.
[8L] Students will get to learn the
implementation of different types of
simulation models for real-life problems
using software.

Evaluation Components 100 Marks

30 Marks
2 Quizzes (subjective/multiple-choice question)
Project & Viva 70 (40 + 30) Marks

References for Reading

Text Books:
1. Law, A. M., Kelton, W. D., & Kelton, W. D. (1991). Simulation modeling and analysis (Vol. 2). New
York: McGraw-Hill.
2. Kelton, W. D. (2002). Simulation with ARENA. McGraw-Hill.
 SIMULATION MODELING & ANALYSIS LAB

Simulation: It is a method to imitate or mimic real systems, usually via computer and it can
be applied in many fields and industries.
Examples:
 Manufacturing facility
 Bank or other personal-service operation
 Transportation/logistics/distribution operation
 Hospital facilities (emergency room, operating room, admissions)
 Computer network
 Freeway system
 Business process (insurance office)
 Criminal justice system
 Chemical plant
 Fast-food restaurant
 Supermarket
 Theme park
 Emergency-response system

Simulation languages
 GPSS, SIMSCRIPT, SLAM, SIMAN

Arena Software: Arena software will be used to take this lab and it basically fits in the
hierarchical structure where it uses concepts of multiple levels of modeling and can mix
different modeling levels together in the same model, it often, start high then go lower as
needed. It provides ease-of-use that is advantage of simulators without sacrificing modeling
flexibility.
Pieces of Simulation Model
 Entities: It is the dynamic object that get created, move around, and then leave the
system (may be). It can change status, get affected or can affect other entities.
 Attributes: It describe the characteristics of all entities that helps in their differentiation.
It can be treated as local variables.
 Global Variables: It reflects a characteristic of the entire system instead of a specific
entity.
 Resources: It can be a person, equipment, or space for which entities will be competing
in the system. An entity seizes a resource, uses it and then releases it after completing
the operation.
 Queues: It is the place for entities to wait when they cannot seize the resource because
it is occupied. It can be of finite or infinite length depending upon the system
characteristic.
 Statistical accumulators: These are the variables that are used in the simulation model
to compute the desired output performance measures at the end of simulation.
 Simulation Clock: It shows the current value of time in the simulation model.
 Event Calendar: It keeps the records of event in increasing order on event time.
 State variables: It describe the current status in the system.
 Starting and Stopping Condition: It is essential to specify an appropriate starting and
stopping rule for a developed simulation model of desired system.
 Replication: The developed simulation model uses the same input parameter and
provide same starting and stopping condition and run the model multiple times to get
statistically identical models which uses separate random numbers (i.e. independent)
for analyzing the behavior of the desired system.

Different Types of Simulation Models

 Static Vs. Dynamic: The variable “time” does not play any role in static
simulation model.

 Continuous Vs. Discrete: It depends on the fact that whether the “state” in the
system can change “continuously” or only at “discrete points” in time.

 Deterministic Vs. Stochastic: It basically depend on the “presence or absence

of a random variable” in the simulation model.

Events for the Simulation Models

 Event: An activity that happen at an instant of time which might change

variables, attributes and statistical accumulators value in the system.
 Arrival: It describe the “arrival” of a new entity in the system.
 Departure: It indicate the “service” is completed in the developed simulation
model.
 End: It defines the stopping condition in the simulation model and indicate the
time the system stopped its activity.

Important Output Performance Measures

o Total Production
o Average Waiting Time
o Maximum waiting time of parts in queue
o Time-average number of parts in queue
o Maximum number of parts in queue
o Average and maximum total time in system of parts (a.k.a. cycle time)
o Utilization of the machine (proportion of time busy)
ARENA WINDOW
Project
Bar

Flow-
Chart
Model

Spread-
Sheet
Model

Status
Bar

ARENA EXAMPLES

1. A Simple Processing System: The parts are coming into the system with an
exponential distribution with mean value of 5 minutes. It is going to the drilling
machine for drill operation and the machine is providing the service to the parts with
the triangular distribution with the minimum value equal to 1 minutes, maximum value
equal to 6 minutes and most likely value equal to 3 minutes. After finishing the
processing at drilling machine the parts are coming out from the system as the finished
product. To provide the drilling service at drill station, there is only one machine that
is available in the system. The simulation run time is 20 minutes and the base time unit
is minutes. Develop the simulation model for a simple processing system using the
ARENA software and run it for a sample of one unit i.e. replication = 1.

Machine
(Server)
Arriving Departing
Blank 7 6 5 4 Finished
Parts Parts
Queue Part in
(FIFO) Service
A Simple Processing System in ARENA

create arriv als Drilling

Dispose parts
f or parts station
0
0
0

Step 1: Use “Create” Module from discrete processing template from project bar to create
parts for a simple processing system model.

Step 2: Use “Process” Module from discrete processing template from project bar to represent
drilling station that has one drilling machine to provide the drilling operation for the parts that
will arrive in the system.
Step 3: Use “Dispose” Module from discrete processing template from project bar to dispose
the parts that has finish the drilling operation and thus will come out from the system as finished
product.

Step 4: Go to Run setup dialog and give project information.

Step 5: Go to Run setup dialog and give simulation parameter details for the developed
simulation model.
Step 6: Model look after simulation run time of 20 minutes.

Step 7: Dynamic plot for showing work-in-process at the drilling station using the
animate/charts/plot/data series (add).

2. Case Study: Serial/Parallel Processing: Consider a loan application office, where

applications arrive with exponentially distributed inter-arrival times with mean 1.25
hours. The first application arrives at time zero and processing each application requires
 four steps: first credit check, then preparing the loan covenant, then pricing the loan
and finally disbursement of funds. For each application, the steps have to be done in
that order. The time for each step is exponentially distributed with mean 1 hour,
independent of the other steps and arrival process. Initially, the system is empty and
idle, we will run it for 160 hours. Compute the average and maximum total number of
applications in process, and the average and maximum total time, from entry to exit,
that application spend in the system as well as their waiting time for the next processing
step to begin. There are four employees available (Alfie, Betty, Chuck, and Doris), all
equally qualified for any of the four steps.

Serial Processing in ARENA

Betty Doris
Applic ation Alie Check Chuck Pric es Applic ation
Prepares Disburses
Arrives Credit Loan Departs
Covenant Funds 0
0
0 0 0 0

Step 1: Use “Create” Module from discrete processing template from project bar to create
applications for a serial processing system model.
Step 2: Use “Process” Module from discrete processing template from project bar to represent
first operation of credit check for loan applications that is being performed by Alie in the
system.

Step 3-5: Use “Process” Module from discrete processing template from project bar to
represent other operations of loan covenant, price check and finally disbursement of funds for
loan applications that is being performed by Betty, Chuck, and Doris in the system.
Step 6: Use “Dispose” Module from discrete processing template from project bar to dispose
the loan applications from the system.

Parallel Processing in ARENA

 One of the
Application f our people Application
Arriv es processes all Departs
f our steps 0
0
0
“PROCESS” MODULE

3. An Electronic Assembly & Test System: This system represents the final operations of the
production of two different sealed electronic units. The arriving parts are cast metal cases that
have already been machined to accept the electronic parts. The first part: Part A is produced in
adjacent department outside the bounds of this model with inter-arrival times to our model
being exponentially distributed with a mean of 5 minutes. Upon arrival, they are transferred to
the Part A prep area. At Part A prep area, the mating faces of the cases are machined to assure
a good seal, and then the part is deburred and cleaned; the process time for the combined
operation at the Part A prep area follows a TRIA (1, 4, 8) distribution. The part is then
transferred to the sealer.

The second unit, named Part B are produced at different building, also outside this models,
bounds, where they are held until a batch of four units is available; the batch is then sent to the
final production area we are modeling. The time between arrivals of successive batches of Part
B to our model is exponential with a mean of 30 minutes. Upon arrival at the Part B prep area,
the batch is separated into the four individual units, which are processed individually from here
on. The processing at the Part B prep area has the same three steps as at the Part A prep area,
except the process time for the combined operation follows a TRIA (3, 5, 10) distribution. The
part is then sent to the sealer.

At the sealer operation, the electronic components are inserted, the case is assembled and sealed
and the sealed unit is tested. The total process time for these operations depends on the part
type: TRIA (1, 3, 4) for part A and WEIB (2.5, 5.3). Ninety-one percent of parts pass the
inspection and are transferred immediately to the shipping department; whether a part passes is
independent of whether any other parts pass. The remaining parts are transferred instantly to
the rework area where they are disassembled, repaired, cleaned, assembled, and re-tested.
Eighty percent of the parts processed at the rework area are salvaged and transferred instantly
to the shipping department as reworked parts, and the rest are transferred instantly to the scrap
area. The time to rework a part follows an exponential distribution with mean of 45 minutes
 and is independent of part type and the ultimate disposition (salvaged or scrapped). We want to
collect statistics in each area on resource utilization, number in queue, time in queue, and the
cycle time separated out by shipped parts, salvaged parts, or scrapped parts. We will initially
run the simulation for four consecutive 8 hour shift or 1920 minutes.

Representation of an Electronic Assembly and Test System

Model Requirements:

• Produce two different sealed elect. units (A, B)

• Arriving parts: cast metal cases machined to accept the electronic parts
• Part A, Part B – separate prep areas
• Both go to Sealer for assembly, testing – then to Shipping (out) if OK, or else to Rework
• Rework – Salvage (and Shipped), or Scrap
PART “A’
• Inter-arrivals: expo (5) minutes
• From arrival point, proceed immediately to Part A Prep area
• Process = (machine + deburr + clean) ~ TRIA (1,4,8) minutes
• Go immediately to Sealer
• Process = (assemble + test) ~ TRIA (1,3,4) min.
• 91% pass, go to Shipped; Else go to Rework
• Rework: (re-process + testing) ~ expo (45)
• 80% pass, go to Salvage/Ship; Else go to Scrap

PART “B’
• Inter-arrivals: batches of 4, expo (30) min.
• Upon arrival, batch separates into 4 individual parts
• From arrival point, proceed immediately to Part B Prep area
• Process = (machine + deburr +clean) ~ TRIA (3,5,10)
• Go to Sealer
• Process = (assemble + test) ~ WEIB (2.5, 5.3) min., different from Part A, though at
same station
• 91% pass, go to Shipped; Else go to Rework
• Rework: (re-process + test) = expo (45) min.
• 80% pass, go to Salvage/Ship; Else go to Scrap

Run Conditions, Output

• Start empty & idle, run for four 8-hour shifts (1,920 minutes)
• Collect statistics for each work area on
 Resource utilization
 Number in queue
 Time in queue
• For each exit point (Shipped, Salvage/Shipped, Scrap), collect total time in system
(a.k.a. cycle time)

ARENA MODEL

0 Tr ue Re c o rd s c ra p p e d Dis p o s e s c ra p p e d
re wo rk p ro c e s s failed ins pection
0
As s ig n p a rt A
Pa rt A Arriv a l Se a le r a n d a rriv a l Pre p A p ro c e s s
tim e 0
0 0 Fals e
0 Tr ue
0
Se a le r Pro c e s s Failed s ealer ins pec tion

As s ig n p a rt B
Pa rt B Arriv a l s e a le r tim e a n d
a rriv a l tim e
0
0 Re c o rd s a lv a g e d Dis p o s e s a lv a g e d
0 Fals e
Pre p B p ro c e s s 0
0
Re c o rd s h ip p e d Dis p o s e s h ip p e d

0
 Entity Transfer through station & Route Module

R oute to
scrapped
part A arrival 0
Arrival of part A Assign for part A R oute to prep A rew ork arrival Tr ue
station rework rew ork inspection
station
0
0 R oute to
0 False
salavaged
Arrival of part B Assign for part B part B arrival
R oute to prep B
station
0

scrapped arrival
Record scrapped Dispose scrapped
prep A arrival station
Process A Prep
station 0

0 R oute to sealer

salavaged arrival Record salvaged Dispose salvaged

prep B arrival station
station Process B Prep 0

0 R oute to rework Dispose shipped

station shipped arrival Record shipped parts
0 station
sealer arrival
Tr ue 0
sealer process failed inspection
station

0 R oute to shipped
0 False
station

Model 4: A Small Manufacturing System

Specification:

• System to be modeled consists of part arrivals

• Four manufacturing cells and part departures
• Cells 1, 2, and 4 have a single machine
• Cell 3 has two machines
• One of these machine is a newer model that can process parts in 80% of the time
required by the older machine
• System produces three part types and each visiting a different sequence of stations
• Part steps and process time is given below:

Part Cell/Time Cell/Time Cell/Time Cell/Time Cell/Time

Type

1 1, 2, 3, 4,
TRIA (6, 8, TRIA (5, 8, TRIA (15, TRIA (8, 12,
10) 10) 20, 25) 16)

2 1, 2, 4, 2, 3,
TRIA (11, TRIA (4, 6, TRIA (15, TRIA (6, 9, TRIA (27,
13, 15) 8) 18, 21) 12) 33, 39)

3 2, 1, 3,
TRIA (7, 9, TRIA (7, TRIA (18,
11) 10, 13) 23, 28)
• The inter-arrival times between successive part arrivals (all types combined) are
exponentially distributed with mean of 13 minutes
• The distribution by type is 26% part 1, 48% part 2, and 26% part 3
• We will assume that the time to move between any pair of cells is two minutes
• We want to collect statistics on resource utilization, time, and number in queue, as well
as cycle time
• We will run simulation for 32 hours

Arena Model for Manufacturing System

Assign part type order release Exit system

Create parts Dispose parts
and sequence start sequence station
staion
0 0

Route from cell

cell 1 station cell 1 process
1

Route from cell

cell 2 station cell 2 process
2

Route from cell

cell 3 station cell 3 process
3

Route from cell

cell 4 station cell 4 process
4

Model 5: A Generic Call Center System

Our generic call center system provides a central number in an organization that
customers call for technical support, sales information, and order status. This central
number feeds 26 trunk lines. If all 26 lines are in use, a caller gets a busy signal;
hopefully, the caller will try again later. An answered caller hears a recording describing
three options: transfer to technical support, sales information, or order-status inquiry
(76%, 16%, and 8%, respectively). The estimated time for this activity is UNIF (0.1,
0.6); all times are in minutes.

If the caller chooses technical support, a second recording requests which of three
product types the caller is using, which requires UNIF (0.l,0.5) minutes. The percentage
of requests for product types 1, 2, and 3 are 25%, 34%, and 41 %, respectively. If a
qualified technical support person is available for the selected product type, the call is
automatically routed to that person. If none are currently available, the customer is
placed in an electronic queue where he is subjected to annoying rock music until a
support person is available. The time for all technical support calls is estimated to be
TRIA (3, 6, 18) minutes regardless of the product type. Upon completion of the call,
the customer exits the system.
Sales calls are automatically routed to the sales staff. If a sales person is not available,
the caller is treated to soothing new-age space music (after all, we’re hoping for a sale).
Sales calls are estimated to be TRIA (4, 15, 45)-sales people tend to talk a lot more than
technical support people! Upon completion of the call, the happy customer exits the
system. Callers requesting order-status information are automatically handled by the
phone system, and there is no limit on the number the system can handle (except that
there are only 26 trunk lines, which is itself a limit, since an ongoing order-status call
occupies one of these lines).

The estimated time for these transactions is TRIA (2, 3, 4) minutes, with 15% of these
callers opting to speak to a real person after they have received their order status. These
calls are routed to the sales staff where they wait with the lower priority as sales calls.
These callers then exit the system. The call system hours are from 8 AM until 6 PM.
Although the system closes to new calls after 6 PM, all calls that enter the system by
that time are answered. The call arrival rate to this system varies over the course of the
day, which is typical of these types of systems, and is ex pressed exponentially with
mean value equal to 0.857 minutes.

Arrival Section for Incoming Calls

In c re m e n t To ta l
Delay for Initial
Seiz e trunk line rec ording
0 Tr ue WIP
Cre a te In c o m i n g Re c o rd Dec ide the fate of
c alls In c o m i n g c a l l s Inc oming Calls
0
Re c o rd re j e c te d Dis p o s e re je c te d
0 False c alls c alls
0

Technical Support Logic Section Pro d u c t 1 Te c h

Pe rs o n
Calls Cut-off Logic Section
As s i g n te c h Au to m a ti c
Dec ide call Type c a l l ty p e a n d Te c h Ca l l s Dec ide product type 0
p ic tu re Re c o rd i n g
Pro d u c t 2 Te c h
0 Pe rs o n Re a s s i g n
Els e v a ri a b l e s c a l l s Dis p o s e fa k e
Els e Cre a te fa k e e n ti ty
25 p e r a rri v a l a n d e n ti ty
76
34
0 m a x a rriv a ls
16
0 0
Pro d u c t 3 Te c h
Pe rs o n

Sales Support Logic Section

As s i g n s a l e s Sa l e s Pro c e s s
c a l l ty p e a n d c alls
p ic tu re

Order Status Support Logic Section

As s i g n o rd e r
0
Dec ided not to s peak Tr ue
s ta tu s c a l l ty p e Delay
to Sales Rep
a n d p i c tu re
TRIA (2 , 3 , 4 )
0 False
Delay Sales Releas e s ales
As s i g n p ri o ri ty Seiz e s ales rep pers on for order rep
fo r s a l e s re p s tatus

Departure Logic Section

Releas e Trunk De c re m e n t Re c o rd Dis p o s e

Lines To ta l WIP c o m p l e te d c a ll s In c o m i n g Ca l l s
0
Model 6: An Inventory Model System

Consider a manufacturing firm who wants to minimize the inventory to reduce the
manufacturing cost. But they also want to achieve a good service level by meeting
demands of most of their loyal customers. The demand rate for the firm is calculated
by using the past historical data which is equal to the Gamma (0.697, 0.529). They
produce three different products and their respective demands are given with the
empirical distribution i.e. DISC (0.959, 1, 0.9972, 2, 1, 3). The manufacturing firm can
receive inventory from 8 AM till 5 PM. Develop a simulation model to compute lost
orders and inventory levels. The initial value for inventory is 20, reorder point is 10,
and order amount is 15. Simulation run length is 365 days with warm-up period equal
to 30 days.

Variables Resources Queues Replicate DStats

Demand Machine Scan queue 365 Lost orders
Demand met Demand met/(Demand met + Lost orders + 1)
Inventory level Inventory level
Lost orders
Reorder point
Order amount ( ( (TNOW - AINT(TNOW) ) * 24 ) >= 8 ) && ( ( (TNOW - AINT(TNOW) ) * 24 ) <= 17)

Queue Scan Seize Delay Release Assign

Assign Branch
Scan queue Order amount * (NORM(0.003, 0.001))
Demand met Machine Machine Inventory level
If
Inventory level
Else
Inventory level <= Reorder point && NR(Machine) == 0 && NQ(Scan queue) == 0
Create Assign Branch

Gamma (0.697, 0.529)

Demand If
Else Dispose
Inventory level >= demand

Assign

Lost orders