unit 1:Introduction to simulation

1. Simulation:

 Simulation is the imitation of the operation of a real world process or system over time.
 Simulation models help us to study the behavior of system as it evolves
 models keeps the set of assumption concerning the operation of the system
 Assumptions are expressed in terms of mathematical, logical and symbolic relationship
between the entities or object of interest of the system.
 Simulation modeling can be used both as an analysis tools to predict the performance of the
new system and also predict the effect of changes to existing system.
 simulation can be done by hand or computer its keeps the history of system
 Simulation produce the set of data is used to estimate the measures of performance of
system.

1.1 When Simulation is the Appropriate Tool:

 Study of and experimentation with the internal interactions of a complex system, or of a

subsystem within a complex system.
 Informational, organizational and environmental changes can be simulated and the model’s
behavior can be observer.
 The knowledge gained in designing a simulation model can be of great value
toward suggesting improvement in the system under investigation.
 By changing simulation inputs and observing the resulting outputs, valuable insight may be
obtained into which variables are most important and how variables interact.
 Simulation can be used as a pedagogical (teaching) device to reinforce analytic solution
methodologies.
 Can be used to experiment with new designs or policies prior to implementation, so as to
prepare for what may happen.
 Can be used to verify analytic solutions.
 By simulating different capabilities for a machine, requirements can be determined.
 Simulation models designed for training, allow learning without the cost and disruption
of on-the-job instructions.
 Animation shows a system in simulated operation so that the plan can be visualized.
 The modern system (factory, water fabrication plant, service organization, etc) is so
complex that the interactions can be treated only through simulation

1.2 When Simulation is Not Appropriate

 Simulation should not be used when the problem can be solved using common sense.
 Simulation should not be used if the problem can be solved analytically.
 Simulation should not be used if it is easier to perform direct experiments.
 Simulation should not be used, if the costs exceeds savings.
 Simulation should not be used if the resources or time are not available.
 No data is available, not even estimate simulation is not advised.
  If there is not enough time or the people are not available, simulation is not appropriate.
 If managers have unreasonable expectation say, too much soon – or the power of
simulation is over estimated, simulation may not be appropriate.
 If system behavior is too complex or cannot be defined, simulation is not appropriate

1.3Advantages of Simulation
1. New policies, operating procedures, decision rules, information flow, etc can be
explored without disrupting the ongoing operations of the real system.
2. New hardware designs, physical layouts, transportation systems can be tested
without committing resources for their acquisition.
3. Hypotheses about how or why certain phenomena occur can be tested for feasibility.
4. Time can be compressed or expanded allowing for a speedup or slowdown of the
phenomena under investigation.
5. Insight can be obtained about the interaction of variables.
6. Insight can be obtained about the importance of variables to the performance of the system.
7. Bottleneck analysis can be performed indication where work-in process, information materials
and so on are being excessively delayed.
8. A simulation study can help in understanding how the system operates rather than how
individuals think the system operates.
9. “what-if” questions can be answered. Useful in the design of new systems.

1.4Disadvantages of simulation
1. Model building requires special training. It is an art that is learned over time and through
experience.
2. If two models are constructed by two competent individuals, they may have similarities,
but it is highly unlikely that they will be the same.
3. Simulation results may be difficult to interpret. Since most simulation outputs are
essentially random variables (they are usually based on random inputs), it may be hard to
determine whether an observation is a result of system interrelationships or randomness.
4. Simulation modeling and analysis can be time consuming and expensive. Skimping on
resources for modeling and analysis may result in a simulation model or analysis that is not
sufficient for the task.
5. Simulation is used in some cases when an analytical solution is possible, or even preferable.
This might be particularly true in the simulation of some waiting lines where closed-form
queueing models are available.

1.5Applications of Simulation
 Manufacturing application
 Semiconductor manufacturing
 construction engineering
 military application
 Business process simulation
 Human system
1. Manufacturing Applications
 Analysis of electronics assembly operations
 Design and evaluation of a selective assembly station for high-precision scroll compressor
shells
 Comparison of dispatching rules for semiconductor manufacturing using large-facility
models
 Evaluation of cluster tool throughput for thin-film head production
 Determining optimal lot size for a semiconductor back-end factory
 Optimization of cycle time and utilization in semiconductor test manufacturing
 Analysis of storage and retrieval strategies in a warehouse
 Investigation of dynamics in a service-oriented supply chain
 Model for an Army chemical munitions disposal facility
2. Semiconductor Manufacturing
 Comparison of dispatching rules using large-facility models
 The corrupting influence of variability
 A new lot-release rule for wafer fabs
 Assessment of potential gains in productivity due to proactive retile management
 Comparison of a 200-mm and 300-mm X-ray lithography cell
 Capacity planning with time constraints between operations
 300-mm logistic system risk reduction
3. Construction Engineering
 Construction of a dam embankment
 Trenchless renewal of underground urban infrastructures
 Activity scheduling in a dynamic, multi project setting
 Investigation of the structural steel erection process
 Special-purpose template for utility tunnel construction
4. Military Application
 Modeling leadership effects and recruit type in an Army recruiting station
 Design and test of an intelligent controller for autonomous underwater vehicles
 Modeling military requirements for non war fighting operations
 Using adaptive agent in U.S Air Force pilot retention
5. Logistics, Transportation, and Distribution Applications
 Evaluating the potential benefits of a rail-traffic planning algorithm
 Evaluating strategies to improve railroad performance
 Parametric modeling in rail-capacity planning
 Analysis of passenger flows in an airport terminal
 Proactive flight-schedule evaluation
 Logistics issues in autonomous food production systems for extended-duration space
exploration
 Sizing industrial rail-car fleets
 Product distribution in the newspaper industry
 Design of a toll plaza
  Choosing between rental-car locations
 Quick-response replenishment
6. Business Process Simulation
 Impact of connection bank redesign on airport gate assignment
 Product development program planning
 Reconciliation of business and systems modeling
 Personnel forecasting and strategic workforce planning
7. Human Systems and Healthcare
 Modeling human performance in complex systems
 Studying the human element in air traffic control
 Modeling front office and patient care in ambulatory health care practices
 Evaluating hospital operations b/n the emergency department and a medical
 Estimating maximum capacity in an emergency room and reducing length of stay in that
room.
1.6 Systems and System Environment
System:
System is defined as a group of object that are joined together in some regular interaction or
interdependence toward the accomplishment of same.

System environment:
A system is often affected by changes occurring outside the system,Such changes are said to
occure in the system environment.

1.7 Components of a System

1) Entity: An entity is an object of interest in a system.
Ex: In the factory system, departments, orders, parts and products are the entities.
2) Attribute: An attribute denotes the property of an entity.
Ex: Quantities for each order, type of part, or number of machines in a department
are attributes of factory system.
3) Activity: Represent a time period of specified length
Ex: Manufacturing process of the department.
4) State of the System: The state of a system is defined as the collection of variables
necessary to describe a system at any time, relative to the objective of study.
5) Event: An event is defined as an instantaneous occurrence that may change the state of
the system.
Endogenous : IS used to descried activites and events occurring with in the
system
Exogenous: Is used to descried activites and events in the environment that
affect the system.
Examples of system and components
System Entities Attributes Activities Events State variables
Banking Customers Checking-account Making Arrival; No. of busy tellers; no. of
balance deposits departure customers waiting.
Rapid rail Riders Origination; Traveling Arrival at No. of riders waiting at each
destination station; arrival station; No. of riders in transit
at destination
Production Machines Speed; capacity; Welding; Breakdown Status of machines (busy, idle
breakdown rate stamping or down)
length
Inventory Warehouse Capacity Withdrawing Demand Levels of inventory;
backlogged demands

1.8 Discrete and Continuous Systems

Discrete System:
 Is one in which the state variable change only at a discrete
set of points in time.
 The bank is an example, since the state variable the
number of customer in the bank changes only when a
customer arrives or when the service provided a customer
is completed.

Continuous system:
 Is one in which the state variable change continuous over
time.
 head of water behind a dam, during and for some time
after a rain storm water flow into the lake behind the dam.
 1.9 Model of a system
 A model is defined as a representation of a system for the purpose of studying the system.
 It is necessary to consider only those aspects of the system that affect the problem under
investigation.
 These aspects are represented in a model, and by definition it is a simplification of the system.
Types of Models:
 Mathematical or physical model
 Static and dynamic model
 deterministic and stochastic model
 discrete and continuous model

1.Mathematical or physical model:

Mathematical model uses symbolic notation and equations to represents a system
2.Static model:
A static simulation models represent a system at a particular point in time it is also
called as monte carlo simulation.
3.dynamic model:
A dynamic simulation models represent system as the change over time. simulation of a
bank from 9 to 4 is an example
4.Deterministic model:
A simulation variable that contain no random variable, have a set of known input which
will result in a unique set of output.
5.Stochastic model:
A stochastic simulation model has one or more random variable as input. Random
input lead to random output.Since the output are random they can be consider only as
estimates of the true characteristics of a model.
6.Discrete System:
  Is one in which the state variable change only at a discrete set of points in time.
 The bank is an example, since the state variable the number of customer in the
bank changes only when a customer arrives or when the service provided a
customer is completed.

7.Continuous system:
 Is one in which the state variable change continuous over time.
 head of water behind a dam, during and for some time after a rain storm water
flow into the lake behind the dam.

1.10 Discrete event system simulation:

 The model of system in which state variable changes only at a discrete set of points in
times
 The simulation models are analyzed by numerical rather than by analytical methods.
 Analytical methods employ the deductive reasoning of mathematics to solve the model.
E.g.: Differential calculus can be used to determine the minimum cost policy for some
inventory models.
 Numerical methods use computational procedures and are ‘runs’, which is generated
based on the model assumptions and observations are collected to be analyzed and
to estimate the true system performance measures.
 Real-world simulation is so vast, whose runs are conducted with the help of computer.
Much insight can be obtained by simulation manually which is applicable for small
 systems.

1.11Steps in a simulation study:

1. Problem formulation
2. Setting of objectives and overall project plan
3. model conceptualization
4. data Collection
5. model translation
6. verified
7. validated
8. Experimental design
9. production runs and analysis
10. more runs
11. documentation and reporting
12. Implementation

1. Problem formulation:
 Every study should begin with a statement of the problem.
 If the statement is provided by the policy makers or those that have the problem, The
analyst must ensure that the problem being described is clearly understood
 If the problem statement is being developed by the analyst, it is important that the policy
makers understand and agree with the formulation.

2. Setting of objective and overall project plan:

 The objectives indicate the questions to be answered by simulation.
 At this point a determination should be made concerning whether simulation is the
appropriate methodology. Assuming that it is appropriate,
 the overall project plan should include the study in terms of
 A statement of the alternative systems
 A method for evaluating the effectiveness of these alternatives
 Plans for the study in terms of the number of people involved
 Cost of the study
 The number of days required to accomplish each phase of the work with the
anticipated results.

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 ability to have following:
 To abstract the essential features of a problem.
 To select and modify basic assumptions that characterizes the system.
 To enrich and elaborate the model until a useful approximation results.

4. Data Collection:
  There is a constant interplay between the construction of the model and the
collection of the needed input data.
 As complexity of the model changes the required data elements may also
change.
 Since data collection takes such a large portion of the total time required to
perform a simulation it is necessary to begin it as early as possible.
5. Model Translation:
 Since most real world system result in model that require a great deal of information
storage and computation, the model must be entered into a computer recognizable format.
 we use term program even though it is possible to accomplish the desired result in many
instances with little or no actual coding.

6.Varified:
 It pertains to the computer program and checking the performance.
 If the input parameters and logical structure and correctly represented, verification is
completed.

7.Validated:
 validation is the determination that a model is an accurate representation of the real
system.
 Is usually achieved through the calibration of the model an iterative process of comparing
the model to actual system behavior and using the discrepancy between the two and the
insights gained to improve the model.
 This process is repeated until model accuracy is judges acceptable.

8.Experimental Design:
 The alternatives that are to be simulated must be determined. For each system design,
decisions need to be made concerning

a. Length of the initialization period

b. Length of simulation runs
c. Number of replication to be made of each run

9.Production runs and analysis:

 They are used to estimate measures of performance for the system designs that are
being simulated.

10.More runs:

 Based on the analysis of runs that have been completed. The analyst determines if
additional runs are needed and what design those additional experiments should follow.
11.Documentation and reporting:
Two types of documentation. Program documentation and Process documentation
 Program documentation: Can be used again by the same or different
analysts to understand how the program operates
 Process documentation: This enable to review the final formulation and
alternatives, results of the experiments and the recommended solution to the
problem. The final report provides a vehicle of certification.

12.Implementation:

Success depends on the previous steps. If the model user has been thoroughly involved and
understands the nature of the model and its outputs, likelihood of a vigorous implementation is
enhanced.
1.12 Simulation of queuing systems
A Queuing system is described by its calling population, the nature of its arrivals, the service
mechanism, the system capacity, and queuing discipline.

Simulation is often used in the analysis of queuing models. In a simple typical queuing model,
shown in

 In the single-channel queue, the calling population is infinite; that is, if a unit leaves the
calling population and joins the waiting line or enters service, there is no change in the
arrival rate of other units that may need service.
 Arrivals for service occur one at a time in a random fashion; once they join the waiting
line, they are eventually served.
 The system capacity has no limit, meaning that any number of units can wait in line. Finally,
units are served in the order of their arrival (often called FIFO: first in, first out) by a single
server or channel.
 Arrivals and services are defined by the distributions of the time between arrivals and the
distribution of service times, respectively.
 The state of the system: the number of units in the system and the status of the server, busy or
idle.
 An event: a set of circumstances that cause an instantaneous change in the state of the system.
In a single-channel queueing system there are only two possible events that can affect
the state of the system.
 The simulation clock is used to track simulated time.
 The arrival event occurs when a unit enters the system. The flow diagram for the arrival event
is shown in

 The unit may find the server either idle or busy; therefore, either the unit begins service
immediately, or it enters the queue for the server. The unit follows the course of action shown
in fig 2.4.
 If the server is busy, the unit enters the queue. If the server is idle and the queue is empty,
the unit begins service. It is not possible for the server to be idle and the queue to be
nonempty.

 After the completion of a service the service may become idle or remain busy with the
next unit. The relationship of these two outcomes to the status of the queue is shown in fig
2.5. If the queue is not empty, another unit will enter the server and it will be busy
Problems:

Single channel queuing system problem formulas:

1. Time Customer wait in queue= Time service begin – Arrival Time

2. Time Service End= Service time + Time service begin
3. Time customer Spend In system= Time service end-Arrival Time
4. Idel Time of Server=Time service Begin(N)-Time Service end(N-1)

Standard Formulas:

1.Average waiting time(i.e customer wait)=total time customer wait in queue / Total number of
customer

2.Probability(Wait i.e customer wait)=Number of Customer who wait / Total number of

customer

3.Probability of idle server(idle time of server)=total idle time of server / total run time of
simulation

4.average service time=total service time/total number of customer

5.average times between arrivals=sum of all times between arrival/number of arrivals-1

6.Average waiting time those who wait in queue=total time customer wait in queue/total
number of customer who wait

7.Average time customer spend In the system=Total time customer spend in system/total
number of customer
 General Principles
1. Discrete-event simulation
• The basic building blocks of all discrete-event simulation models: entities and attributes, activities and
events.
• A system is modeled in terms of
o Its state at each point in time
o The entities that pass through the system and the entities that represent system resources
o The activities and events that cause system state to change.
• Discrete-event models are appropriate for those systems for which changes in system state occur
only at discrete points in time.
• This chapter deals exclusively with dynamic, stochastic systems (i.e., involving time and containing
random elements) which change in a discrete manner.

Concepts in Discrete-Event Simulation(components of discrete event

Simulation)

1. System: A collection of entities (e.g., people and machines) that together over time to accomplish one
or more goals.
2. Model: An abstract representation of a system, usually containing structural, logical, or mathematical
relationships which describe a system in terms of state, entities and their attributes, sets, processes,
events, activities, and delays.
3. System state: A collection of variables that contain all the information necessary to describe the system
at any time.
4. Entity: Any object or component in the system which requires explicit representation in the model (e.g., a
server, a customer, a machine).
5. Attributes: The properties of a given entity (e.g., the priority of a v customer, the routing of a job
through a job shop).
6. List: A collection of (permanently or temporarily) associated entities ordered in some logical fashion
(such as all customers currently in a waiting line, ordered by first come, first served, or by priority).
7. Event: An instantaneous occurrence that changes the state of a system as an arrival of a new customer).
8. Event notice: A record of an event to occur at the current or some future time, along with any
associated data necessary to execute the event; at a minimum, the record includes the event type and the
event time.
9. Event list: A list of event notices for future events, ordered by time of occurrence; also known as
 the future event list (FEL).

10. Activity: A duration of time of specified length (e.g., a service time or arrival time), which is
known when it begins (although it may be defined in terms of a statistical distribution).
11. Delay: A duration of time of unspecified indefinite length, which is not known until it ends (e.g., a
customer's delay in a last-in, first-out waiting line which, when it begins, depends on future arrivals).
12. Clock: A variable representing simulated time.

The Event-Scheduling/Time-Advance Algorithm

The mechanism for advancing simulation time and guaranteeing that all events occur
in correct chronological order is based on the future event list (FEL).
Future Event List (FEL)
o To contain all event notices for events that have been scheduled to occur at a future time.
o To be ordered by event time, meaning that the events are arranged chronologically; that
is, the event times satisfy.
o Scheduling a future event means that at the instant an activity begins, its duration is computed
or drawn as a sample from a statistical distribution and the end-activity event, together with
its event time, is placed on the future event list.
The sequence of actions which a simulator must perform to advance the clock system snapshot is called
the event- scheduling/time-advance algorithm.

The system snapshot at time t=0 and t=t1 (VIP VTU question)
ClK System State Future Event List

T (5,1,6) (3, t1)— Type 3 event to occur at timet1

(1, t2)— Type 1 event to occur at time t2
(1, t3)- Type 1 event to occur at time t3
(2, tn)— Type 2 event to occur at time tn

Event-scheduling/time-advance algorithm
Step 1. Remove the event notice for the imminent event
(event 3, time t\) from FEL
Step 2. Advance CLOCK to imminent event time
(i.e., advance CLOCK from r to t1).
 Step 3. Execute imminent event: update system state, change entity attributes, and set membership as needed.
Step 4. Generate future events (if necessary) and place their event notices on PEL ranked by event time.
(Example: Event 4 to occur at time t*, where t2 < t* < t3.)
Step 5. Update cumulative statistics and counters.

New system snapshot at time t1

OCK System Future Event List

T1 (5,1,5) (1, t2)— Type 1 event to occur at time t1

(4, t*)— Type 4 event to occur at time t*
(1, t3)— Type 1 event to occur at time t3
(2, tn)— Type 2 event to occur at time tn

2.Manual Simulation Using Event Scheduling

In an event-scheduling simulation, a simulation table is used to record the successive system snapshots
as time advances.
Let us consider the example of a grocery shop which has only one checkout counter. (Single-Channel Queue)

The system consists of those customers in the waiting line plus the one (if any) checking out. The model has
the following components:
System state (LQ (t), LS (t)), where LQ (t) is the number of customers in the waiting line, and LS (t) is
the number being served (0 or 1) at time t.
Entities: The server and customers are not explicitly modeled, except in terms of the state variables above.
Events
Arrival(A)
Departure(D)
Stopping event (E), scheduled to occur at time 60.

Event notices
(A, t). Representing an arrival event to occur at future time t

(D, t), representing a customer departure at future time t

(E, 60), representing the simulation-stop event at future time 60
Activities
Interarrival time, Service time,
Delay Customer time spent in waiting line.
In this model, the FEL will always contain either two or three event notices.

Flow Chart for execution of arrival and departure event using time advance /Event scheduling
algorithm (vtu Question)
 Question Bank

1. When the simulation is appropriate tool & when it is not.

2. Advantages & disadvantages of simulation.
3. Components of systems & model and it types.
4. Steps in simulation study.
5. Examples (single server channel queue refer 2015, 2014, 2013 question paper, & class problem.
6. Examples Able & Bakes call center problem (two channel server problem)
7. Explain the terms used in discrete event simulation with an example(Ex. Able & Baker)
8. Explain the event scheduling algorithm by generating system snapshots at clock =t and clock=t1.
9. Explain the event scheduling algorithm with an example (single-channel-queue – execution of arrival event &
execution of departure event).
 UNIT 4: QUEUEING MODELS

4.1 Characteristics of Queueing System

 The key element’s of queuing system are the “customer and servers”.
 Term Customer: Can refer to people, trucks, mechanics, airplanes or anything
that arrives at a facility and requires services.
 Term Server: Refer to receptionists, repairperson, medical personal, retrieval
machines that provides the requested services.
4.1.1 Calling Population
 The population of potential customers referred to as the “calling population”.
 The calling population may be assumed to be finite or infinite.
 The calling population is finite and consists
 In system with a large population of potential customers, the calling population is
usually assumed to be infinite.
 The main difference between finite and infinite population models is how the arrival
rate is defined.
 In an infinite population model, arrival rate is not affected by the number of
customer who have left the calling population and joined the queueing.
4.1.2 System Capacity
 In many queueing system , there is a limit to the number of customers that may be
in the waiting line or system.
 An arriving customer who finds the system full does not enter but returns
immediately to the calling population.
4.1.3 Arrival Process
 The arrival process for “Infinite population” models is usually characterized in
terms of interarrival time of successive customers.
 Arrivals may occur at scheduled times or at random times.
 When random times , the interarrival times are usually characterized by a
probability distribution.
 Customer may arrive one at a time or in batches, the batches may be of constant
size or random size.
 The second important class of arrivals is scheduled arrivals such as scheduled
airline flight arrivals to an input.
 Third situation occurs when one at customer is assumed to always be present in the
queue. So that the server is never idle because of a lack of customer.
 For finite population model, the arrivals process is characterized in a completely
different fashion.
 Define customer as pending when that customer is outside the queueing system and
a member of the calling population
4.1.4 Queue Behavior and Queue Discipline
 It refers to the actions of customers while in a queue waiting for the service to begin.
 In some situations, there is a possibility that incoming customers will balk(leave
when they see that the line is too long) , renege(leave after being in the line when
they see that the line is moving slowly) , or jockey( move from one line to another
if they think they have chosen a slow line).
 Queue discipline refers to the logical ordering of the customers in a queue and
determines which customer will be chosen for service when a server becomes free.
 Common queue disciplines include FIFO, LIFO, service in random order(SIRO),
shortest processing time first( SPT) and service according to priority (PR).

4.1.5 Service Times and Service Mechanism

 The service times of successive arrivals are denoted by s1, s2, sn.. They may be
constant or of random duration.
 When {s1,s2,sn} is usually characterized as a sequence of independent and
identically distributed random variables.
 The exponential, weibull, gamma, lognormal and truncated normal distribution
have all been used successively as models of service times in different situations.
 A queueing system consists of a number of service centers and inter connecting
queues. Each service center consists of some number of servers c, working in
parallel.
 That is upon getting to the head of the line of customer takes the first available
server.
 Parallel Service mechanisms are either single server or multiple server(1<c<∞) are
unlimited servers(c=∞).
 A self service facility is usually characterized as having an unlimited number of
servers.
4.2 Queueing Notation(Kendal’s Notation)
 Kendal’s proposal a notational s/m for parallel server s/m which has been widely adopted.
 An a bridge version of this convention is based on format A|B|C|N|K
 These letters represent the following s/m characteristics:

A-Represents the InterArrival Time distribution

B-Represents the service time distribution
C-Represents the number of parallel servers
N-Represents the s/m capacity
K-Represents the size of the calling populations

Common symbols for A & B include M(exponential or Markov), D(constant or

deterministic), Ek (Erlang of order k), PH (phase-type), H(hyperexponential), G(arbitrary or
general), & GI(general independent).
 For eg, M|M|1|∞|∞ indicates a single server s/m that has unlimited queue capacity & an
infinite population of potential arrivals
 The interarrival tmes & service times are exponentially distributed when N & K are
infinite, they may be dropped from the notation.
 For eg, , M|M|1|∞|∞ is often short ended to M|M|1. The tire-curing s/m can be initially
represented by G|G|1|5|5.
  Additional notation used for parallel server queueing s/m are as follows:

4.3 Long-run Measures of performance of queueing systems

 The primary long run measures of performance of queueing system are the long run time
average number of customer in s/m(L) & queue(LQ)
 The long run average time spent in s/m(w) & in the queue(wQ) per customer
 Server utilization or population of time that a server is busy (p).

4.3.1 Time average Number in s/m (L):

 Consider a queueing s/m over a period of time T & let L(t) denote the number of
customer I the s/m at time t.
 Let Ti denote the total time during[0,T] in which the s/m contained exactly I customers.
4.3.2 Average Time spent in s/m per customer (w):
 Average s/m time is given as:

 For stable s/m N-> ∞

With probability 1, where w is called the long-run average s/m time.

 Considering the equation 1 & 2 are written as,

4.3.3 Server utilization:
 Server utilization is defined as the population of time server is busy
 Server utilization is denoted by ƥ is defined over a specified time interval[01]
 Long run server utilization is denoted by p

Ƥ -> P as T -> ∞

 Server utilization in G|G|C|∞|∞ queues

 Consider a queuing s/m with c identical servers in parallel
 If arriving customer finds more than one server idle the customer choose a server
without favoring any particular server.
 The average number of busy servers say Ls is given by,

Ls = λ / μ 0<= Ls <= C
 The long run average server utilization is defined by

 The utilization P can be interpreted as the proportion of time an arbitrary server is busy in
the long run
 4.4 STEADY-STATE BEHAVIOUR OF INFINITE-
POPULATION MARKOVIAN MODLES
 For the infinite population models, the arrivals are assumed to follow a poisson process
with rate λ arrivals per time unit
 The interarrival times are assumed to be exponentially distributed with mean 1/λ
 Service times may be exponentially distributed(M) or arbitrary(G)
 The queue discipline will be FIFO because of the exponential distributed assumptions on
the arrival process, these model are called “MARKOVIAN MODEL”.
 The steady-state parameter L, the time average number of customers in the s/m can be
computed as
∞

𝐿 = ∑ 𝑛𝑃𝑛
𝑛=0

Where Pn are the steady state probability of finding n customers in the s/m
 Other steady state parameters can be computed readily from little equation to whole
system & to queue alone
w = L/λ
wQ = w – (1/μ)
LQ = λwQ
Where λ is the arrival rate & μ is the service rate per server

4.4.1 SINGLE-SERVER QUEUE WITH POISSON ARRIVALS & UNLIMITED

CAPACITY: M|G|1
 Suppose that service times have mean 1/μ & variance σ² & that there is one server
 If P = λ / μ <1, then the M|G|1 queue has a steady state probability distribution with
steady state characteristics
 The quantity P = λ / μ is the server utilization or lon run proportion of time the server
is busy
 Steady state parameters of the M|G|1 are:
4.4 2 MULTISERVER QUEUE: M|M|C|∞|∞

 Suppose that there are c channels operating in parallel

 Each of these channels has an independent & identical exponential service time
distribution with mean 1/μ
 The arrival process is poisson with rate λ. Arrival will join a single queue & enter the first
available service channel
  For the M|M|C queue to have statistical equilibrium the offered load must satisfy λ/μ <c
in which case λ/ (cμ) = P the server utilization.

WHEN THE NUMBER OF SERVERS IS INFINITE (M|c|∞|∞ )

 There are at least three situations in which it is appropriate to treat the number of server
as infinite
1. When each customer is its own server in other words in a self service s/m
2. When service capacity far exceeds service demand as in a so called ample server
s/m
3. When wee want to know how many servers are required so that customer will
rarely be delayed.
4.5 STEADY STATE BEHAVIOR OF FINITE POPULATION
MODELS (M|M|C|K|K)

 In many practical problems, the assumption of an infinite calling population leads

to invalid results because the calling population is, in fact small.

 When the calling population is small, the presence of one or more customers in
the system have a strong effect on the distribution of future arrivals and the use of
an infinite population model can be misleading.

 Consider a finite calling population model with k customers. The time between
the end of one service visit and the next call for service for each member of the
population is assumed to be exponentially distributed with mean 1/ λ time units.

 Service times are also exponentially distributed, with mean 1/ µ time units. There
are c parallel servers and system capacity is so that all arrivals remain for service.
Such a system is shown in figure.
The effective arrival rate λe has several valid interpretations:
Λe = long-run effective arrival rate of customers to queue
= long-run effective arrival rate of customers entering service
= long-run rate at which customers exit from service
= long-run rate at which customers enter the calling population
=long-run rate at which customers exit from the calling population.
4.6 NETWORKS OF QUEUE
 Many systems are naturally modeled as networks of single queues in which
customer departing from one queue may be routed to another
 The following results assume a stable system with infinite calling population and
no limit on system capacity.
1) Provided that no customers are created or destroyed in the queue,then the
departure rate out of a queue is the same as the arrival rate into the queue over the
long run.
2) If customers arrive to queue i at rate λi and a fraction 0≤pij≤ 1 of them are routed
to queue j upon departure, then the arrival rate from queue i to queue j is λipij is
over long run
3) The overall arrival rate into queue j,λi is the sum of the arrival rate from all
source.If customers arrive from outside the network at rate ai then

4) If queue j has ci<∞ parallel servers, each working at rate µ ,then the long run
utilization of each server is

& Pj<1 is required for queue to be stable

5) If, for each queue j ,arrivals from outside the network form a poisson process
with rate a and if there are ci identical services delivering exponentially
distributed service times with mean 1/µ then in steady state queue j behaves like
a M|M|C; queue with arrival rate
 UNIT 5:Random number generation And Variation Generation

RANDOM-NUMBER GENERATION Random numbers are a necessary basic ingredient in the

simulation of almost all discrete systems. Most computer languages have a subroutine, object, or function
that will generate a random number. Similarly simulation languages generate random numbers that are
used to generate event times and other random variables.

5.1 Properties of Random Numbers A sequence of random numbers, R1, R2... must have two
important statistical properties, uniformity and independence. Each random number Ri, is an independent
sample drawn from a continuous uniform distribution between zero and 1.
That is, the pdf is given by

The density function is shown below:

Some consequences of the uniformity and independence properties are the following:
1. If the interval (0, 1) is divided into n classes, or subintervals of equal length, the expected number of
observations m each interval ii N/n where A' is the total number of observations.
2. The probability of observing a value in a particular interval is of the previous values drawn.

5.2 Generation of Pseudo-Random Numbers

Pseudo means false, so false random numbers are being generated. The goal of any generation scheme, is
to produce a sequence of numbers between zero and 1 which simulates, or initiates, the ideal properties of
uniform distribution and independence as closely as possible. When generating pseudo-random numbers,
certain problems or errors can occur. These errors, or departures from ideal randomness, are all related to
the properties stated previously. Some examples include the following

1) The generated numbers may not be uniformly distributed.

2) The generated numbers may be discrete -valued instead continuous valued

3) The mean of the generated numbers may be too high or too low.

4) The variance of the generated numbers may be too high or low

5) There may be dependence.

The following are examples:

a) Autocorrelation between numbers.

b) Numbers successively higher or lower than adjacent numbers.

c) Several numbers above the mean followed by several numbers below the mean.

Usually, random numbers are generated by a digital computer as part of the simulation. Numerous
methods can be used to generate the values. In selecting among these methods, or routines, there are a
number of important considerations.
1. The routine should be fast. The total cost can be managed by selecting a computationally efficient
method of random-number generation.
2. The routine should be portable to different computers, and ideally to different programming languages
.This is desirable so that the simulation program produces the same results wherever it is executed.
3. The routine should have a sufficiently long cycle. The cycle length, or period, represents the length of
the random-number sequence before previous numbers begin to repeat themselves in an earlier order.
Thus, if 10,000 events are to be generated, the period should be many times that long.
A special case cycling is degenerating. A routine degenerates when the same random numbers appear
repeatedly. Such an occurrence is certainly unacceptable. This can happen rapidly with some methods.
4. The random numbers should be replicable. Given the starting point (or conditions), it should be
possible to generate the same set of random numbers, completely independent of the system that is being
simulated. This is helpful for debugging purpose and is a means of facilitating comparisons between
systems.
5. Most important, and as indicated previously, the generated random numbers should closely
approximate the ideal statistical properties of uniformity and independences

5.3 Techniques for Generating Random Numbers

5.3.1 The linear congruential method

It widely used technique, initially proposed by Lehmer [1951], produces a sequence of integers, X1,
X2,... between zero and m — 1 according to the following recursive relationship:
Xi+1 = (aXi + c) mod m, i = 0, 1, 2.... (7.1)

The initial value X0 is called the seed, a is called the constant multiplier, c is the increment, and m is the
modulus.
If c ≠ 0 in Equation (7.1), the form is called the mixed congruential method. When c = 0, the form is
known as the multiplicative congruential method.

The selection of the values for a, c, m and X0 drastically affects the statistical properties and the cycle
length. An example will illustrate how this technique operates.
EXAMPLE 1 Use the linear congruential method to generate a sequence of random numbers with X0 =
27, a= 17, c = 43, and m = 100.

Here, the integer values generated will all be between zero and 99 because of the value of the modulus.
These random integers should appear to be uniformly distributed the integers zero to 99.
Random numbers between zero and 1 can be generated by
Ri =Xi/m, i= 1,2,…… (7.2)

The sequence of Xi and subsequent Ri values is computed as follows:

X0 = 27
X1 = (17*27 + 43) mod 100 = 502 mod 100 = 2 R1=2/100=0. 02
X2 = (17*2 + 43) mod 100 = 77 mod 100 = 77 R2=77 /100=0. 77
X3 = (17*77+ 43) mod 100 = 1352 mod 100 = 52 R3=52 /100=0. 52
Second, to help achieve maximum density, and to avoid cycling (i.e., recurrence of the same sequence of
generated numbers) in practical applications, the generator should have the largest possible period.
Maximal period can be achieved by the proper choice of a, c, m, and X0.

The max period (P) is:

 For m a power of 2, say m = 2b, and c ¹≠0, the longest possible period is P = m = 2b, which is
achieved provided that c is relatively prime to m (that is, the greatest common factor of c and m is 1),
and a = 1 + 4k, where k is an integer.
 For m a power of 2, say m = 2b, and c = 0, the longest possible period is P = m / 4 = 2b-2, which
is achieved provided that the seed X0 is odd and the multiplier, a, is given by a = 3 + 8k or a = 5 + 8k,
for some k = 0, 1,...
 For m a prime number and c = 0, the longest possible period is P = m - 1, which is achieved
provided that the multiplier, a, has the property that the smallest integer k such that ak - 1 is divisible
by m is
k = m – 1.
Multiplicative Congruential Method:

Basic Relationship:

Xi+1 = a Xi (mod m), where a ≥ 0 and m ≥ 0 … (7.3)

Most natural choice for m is one that equals to the capacity of a computer word. m = 2b (binary
machine), where b is the number of bits in the computer word.

m = 10d (decimal machine), where d is the number of digits in the computer word.

EXAMPLE 1: Let m = 102 = 100, a = 19, c = 0, and X0 = 63, and generate a sequence c random
integers using Equation

Xi+1 = (aXi + c) mod m, i = 0, 1, 2....

X0 = 63 X1 = (19)(63) mod 100 = 1197 mod 100 = 97

X2 = (19) (97) mod 100 = 1843 mod 100 = 43

X3 = (19) (43) mod 100 = 817 mod 100 = 17 . . . .

When m is a power of 10, say m = 10b, the modulo operation is accomplished by saving the b rightmost
(decimal) digits.

5.3.2 Combined Linear Congruential Generators

As computing power has increased, the complexity of the systems that we are able to simulate has also
increased. One fruitful approach is to combine two or more multiplicative congruential generators in such a way
that the combined generator has good statistical properties and a longer period. The following result from
L'Ecuyer [1988] suggests how this can be done: If Wi,1, Wi,2 ,... , Wi,k are any independent, discrete-valued random
variables (not necessarily identically distributed), but one of them, say Wi,1, is uniformly distributed on the integers
0 to mi — 2, then
 is uniformly distributed on the integers 0 to mi — 2. To see how this result can be used to form combined
generators, let Xi,1, Xi,2,..., X i,k be the i th output from k different multiplicative congruential generators, where the
j th generator has prime modulus mj, and the multiplier aj is chosen so that the period is mj — 1. Then the j'th
generator is producing integers Xi,j that are approximately uniformly distributed on 1 to mj - 1, and Wi,j = X i,j — 1 is
approximately uniformly distributed on 0 to mj - 2. L'Ecuyer [1988] therefore suggests combined generators of the
form

5.4 Tests for Random Numbers

1. Frequency test. Uses the Kolmogorov-Smirnov or the chi-square test to compare the distribution
of the set of numbers generated to a uniform distribution.
2. Autocorrelation test. Tests the correlation between numbers and compares the sample
correlation to the expected correlation of zero.
5.4.1 Frequency Tests
A basic test that should always be performed to validate a new generator is the test of
uniformity. Two different methods of testing are available.
1. Kolmogorov-Smirnov(KS test) and
2. Chi-square test.
• Both of these tests measure the degree of agreement between the distribution of a sample of
generated random numbers and the theoretical uniform distribution.
• Both tests are on the null hypothesis of no significant difference between the sample distribution
and the theoretical distribution.
1. The Kolmogorov-Smirnov test. This test compares the continuous cdf, F(X), of the uniform
distribution to the empirical cdf, SN(x), of the sample of N observations. By definition,

F(x) = x, 0 ≤ x ≤ 1

If the sample from the random-number generator is R1 R2, ,..., RN, then the empirical cdf, SN(x), is
defined by

The Kolmogorov-Smirnov test is based on the largest absolute deviation between F(x) and SN(X) over the
range of the random variable. That is. it is based on the statistic D = max |F(x) -SN(x)| For testing
against a uniform cdf, the test procedure follows these steps:

Step 1: Rank the data from smallest to largest. Let R (i) denote the i th smallest observation, so that

R(1) ≤ R(2) ≤ … ≤ R(N)

Step 2: Compute
Step 3: Compute D = max (D+, D-).

Step 4: Determine the critical value, Dα, from Table A.8 for the specified significance level α and the
given sample size N.

Step 5:

We conclude that no difference has been detected between the true distribution of {R1, R2,... RN} and the
uniform distribution.

EXAMPLE 6: Suppose that the five numbers 0.44, 0.81, 0.14, 0.05, 0.93 were generated, and it is
desired to perform a test for uniformity using the Kolmogorov-Smirnov test with a level of significance α
of 0.05.

Step 1: Rank the data from smallest to largest. 0.05, 0.14, 0.44, 0.81, 0.93

Step 2: Compute D+ and D-

Step3: Compute D = max (D+, D-)

. D=max (0.26, 0.21) = 0.26

Step 4: Determine the critical value, Dα, from Table A.8 for the specified significance level α and the
given sample size N. Here α=0.05, N=5 then value of Dα = 0.565

Step 5: Since the computed value, 0.26 is less than the tabulated critical value, 0.565,

the hypothesis of no difference between the distribution of the generated numbers and the uniform
distribution is not rejected.

compare F(x) with Sn(X)

2. The chi-square test.
The chi-square test uses the sample statistic

Where, Oi is observed number in the i th class

Ei is expected number in the i th class,

N – No. of observation
n – No. of classes

Note: sampling distribution of approximately the chi square has n-1 degrees of freedom

Example 7: Use the chi-square test with α = 0.05 to test whether the data shown below are uniformly
distributed. The test uses n = 10 intervals of equal length, namely [0, 0.1), [0.1, 0.2)... [0.9, 1.0).
(REFER TABLE A.6)
5.4.2 Tests for Auto-correlation

The tests for auto-correlation are concerned with the dependence between numbers in a sequence. The list
of the 30 numbers appears to have the effect that every 5th number has a very large value. If this is a
regular pattern, we can't really say the sequence is random.

The test computes the auto-correlation between every m numbers (m is also known as the lag) starting
ρ
with the ith number. Thus the autocorrelation im between the following numbers would be of interest.
EXAMPLE : Test whether the 3rd, 8th, 13th, and so on, numbers in the sequence at the beginning of this
section are auto correlated. (Use a = 0.05.) Here, i = 3 (beginning with the third number), m = 5 (every
five numbers), N = 30 (30 numbers in the sequence), and M = 4 (largest integer such that 3 + (M +1)5 <
30).

Solution:
2.Random Variate Generation TECHNIQUES:
• INVERSE TRANSFORMATION TECHNIQUE
• ACCEPTANCE-REJECTION TECHNIQUE

All these techniques assume that a source of uniform (0,1) random numbers is available R1,R2….. where
each R1 has probability density function and cumulative distribution function.
Note: The random variable may be either discrete or continuous.

2.1 Inverse Transform Technique The inverse transform technique can be used to sample
from exponential, the uniform, the Weibull and the triangle distributions.

2.1.1 Exponential Distribution The exponential distribution, has probability density function (pdf)
given by

and cumulative distribution function (cdf) given by

The parameter λ can be interpreted as the mean number of occurrences per time unit. For example, if interarrival
times X1, X2, X3 . . . had an exponential distribution with rate, and then could be interpreted as the mean number of
arrivals per time unit, or the arrival rate. For any i,

E(Xi)= 1/λ

And so 1/λ is mean inter arrival time. The goal here is to develop a procedure for generating values X1, X2,
X3 . . . which have an exponential distribution.

The inverse transform technique can be utilized, at least in principle, for any distribution. But it is most
useful when the cdf. F(x), is of such simple form that its inverse, F-1, can be easily computed.

A step-by-step procedure for the inverse transform technique illustrated by me exponential

distribution, is as follows:

Step 1: Compute the cdf of the desired random variable X. For the exponential distribution, the cdf is

F(x) = 1-e-λ x , x≥0.

Step 2: Set F(X) = R on the range of X. For the exponential distribution, it becomes

1 – e-λ X = R on the range x ≥ 0.

Since X is a random variable (with the exponential distribution in this case), so 1-e-λx is also a random
variable, here called R. As will be shown later, R has a uniform distribution over the interval (0,1).,

Step 3: Solve the equation F(X) = R for X in terms of R. For the exponential distribution, the solution
proceeds as follows:
Equation (5.1) is called a random-variate generator for the exponential distribution. In general, Equation
(5.1) is written as X=F-1(R). Generating a sequence of values is accomplished through steps 4.

Step 4: Generate (as needed) uniform random numbers R1, R2, R3,... and compute the desired random
variates by

Xi = F-1 (Ri)

For the exponential case, F-1 (R) = (-1/λ)ln(1- R) by Equation (5.1),

so that Xi = -1/λ ln ( 1 – Ri) …( 5.2 ) for i = 1,2,3,.... One simplification that is usually employed in
Equation (5.2) is to replace 1 – Ri by Ri to yield Xi = -1/λ ln Ri …( 5.3 ) which is justified since both Ri
and 1- Ri are uniformly distributed on (0,1).

Example: consider the random number As fellows, where λ=1

Solution:

Using equation compute Xi

Uniform Distribution :
Consider a random variable X that is uniformly distributed on the interval [a, b]. A reasonable guess
for generating X is given by
X = a + (b - a)R ……….5.5

[Recall that R is always a random number on (0,1).

The pdf of X is given by
f (x) = 1/ ( b-a ), a ≤ x ≤ b
0, otherwise
The derivation of Equation (5..5) follows steps 1 through 3 of Section 5.1.1:

Step 1. The cdf is given by

F(x) = 0, x < a
( x – a ) / ( b –a ), a ≤ x ≤ b
1, x > b

Step 2. Set F(X) = (X - a)/(b -a) = R

Step 3. Solving for X in terms of R yields

X = a + (b — a)R,
which agrees with Equation (5.5).
Weibull Distribution:
The weibull distribution was introduce for test the time to failure of the machine or electronic
components. The location of the parameters V is set to 0.

where α>0 and β>0 are the scale and shape of parameters.
Steps for Weibull distribution are as follows:

step 1: The cdf is given by

step2 :set f(x)=R

step 3:Solving for X in terms of R yields.

Empirical continuous distribution:

Respampling of data from the sample data in systamtic manner is called empirical continuos
distribution.
Step1:Arrange data for smallest to largest order of interval
x(i-1)<x<X(i) i=0,1,2,3….n
Step2:Compute probability 1/n
Step3:Compute cumulative probability i.e i/n where n is interval
step4:calculate a slope i.e
without frequency ai=x(i)-x(i-1)/(1/n)
with frequency ai= x(i)-x(i-1)/(c(i)-c(i-1) where c(i) is cumulative probability
2.1 Acceptance-Rejection technique

 Useful particularly when inverse cdf does not exist in closed form
 Illustration: To generate random variants, X ~ U(1/4, 1)
 Procedures:

Step 1: Generate a random number R ~ U [0, 1]

Step 2a: If R ≥ ¼, accept X=R.
Step 2b: If R < ¼, reject R, return to Step 1
 R does not have the desired distribution, but R conditioned (R’) on the event {R ³ ¼} does.
 Efficiency: Depends heavily on the ability to minimize the number of rejections.

2.1.1 Poisson Distribution A Poisson random variable, N, with mean a > 0 has pmf

 N can be interpreted as number of arrivals from a Poisson arrival process during one unit of time
• Then time between the arrivals in the process are exponentially distributed with rate α.
• Thus there is a relationship between the (discrete) Poisson distribution and the (continuous)
exponential distribution, namely
The procedure for generating a Poisson random variate, N, is given by the following steps:

Step 1: Set n = 0, and P = 1

Step 2: Generate a random number Rn+1 and let P = P. Rn+1

Step 3: If P < e-α, then accept N = n. Otherwise, reject current n,

increase n by one, and return to step 2

Example: Generate three Poisson variants with mean a =0.2 for the given Random number

0.4357,0.4146,0.8353,0.9952,0.8004

Solution:

Step 1.Set n = 0, P = 1.

tep 2.R1 = 0.4357, P = 1 • R1 = 0.4357.

Step 3. Since P = 0.4357 < e-b = 0.8187, accept N = 0. Repeat Above procedure

Gamma distribution:

Is to check the random variants are accepted or rejected based on

dependent sample data.

Steps 1: Refer the steps which given in problems.

 unit 6: INPUT MODELING
6. INPUT MODELING
• Input data provide the driving force for a simulation model. In the simulation of a queuing
system, typical input data are the distributions of time between arrivals and service times.
• For the simulation of a reliability system, the distribution of time-to=failure of a
component is an example of input data.
There are four steps in the development of a useful model of input data:

• Collect data from the real system of interest. This often requires a substantial time and
resource commitment. Unfortunately, in some situations it is not possible to collect data
• Identify a probability distribution to represent the input process. When data are
available, this step typically begins by developing a frequency distribution, or histogram,
of the data.
• Choose parameters that determine a specific instance of the distribution family.
When data are available, these parameters may be estimated from the data.
• Evaluate the chosen distribution and the associated parameters for good-of- fit.
Goodness-of-fit may be evaluated informally via graphical methods, or formally via
statistical tests. The chisquare and the Kolmo-gorov-Smirnov tests are standard
goodness-of-fit tests. If not satisfied that the chosen distribution is a good approximation
of the data, then the analyst returns to the second step, chooses a different family of
distributions, and repeats the procedure. If several iterations of this procedure fail to yield
a fit between an assumed distributional form and the collected data

6.1 Data Collection

• Data collection is one of the biggest tasks in solving real problem. It is one of the most
important and difficult problems in simulation. And even if when data are available, they
have rarely been recorded in a form that is directly useful for simulation input modeling.

1
 The following suggestions may enhance and facilitate data collection, although they are not
all – inclusive.
1. A useful expenditure of time is in planning. This could begin by a practice or
pre observing session. Try to collect data while pre-observing.
2. Try to analyze the data as they are being collected. Determine if any data being
collected are useless to the simulation. There is no need to collect superfluous
data.
3. Try to combine homogeneous data sets. Check data for homogeneity in
successive time periods and during the same time period on successive days.
4. Be aware of the possibility of data censoring, in which a quantity of interest is
not observed in its entirety. This problem most often occurs when the analyst is
interested in the time required to complete some process (for example, produce
a part, treat a patient, or have a component fail), but the process begins prior to,
or finishes after the completion of, the observation period.
5. To determine whether there is a relationship between two variables, build a
scatter diagram.
6. Consider the possibility that a sequence of observations which appear to be
independent may possess autocorrelation. Autocorrelation may exist in
successive time periods or for successive customers.
7. Keep in mind the difference between input data and output or performance
data, and be sure to collect input data. Input data typically represent the
uncertain quantities that are largely beyond the control of the system and will
not be altered by changes made to improve the system.

6.2 Identifying the Distribution with Data.

• In this section we discuss methods for selecting families of input distributions when data
are available.
6.2.1 Histogram

• A frequency distribution or histogram is useful in identifying the shape of a distribution.

A histogram is constructed as follows:
1. Divide the range of the data into intervals (intervals are usually of equal width;
2
 however, unequal widths however, unequal width may be used if the heights of the
frequencies are adjusted).
2. Label the horizontal axis to conform to the intervals selected.
3. Determine the frequency of occurrences within each interval.
4. Label the vertical axis so that the total occurrences can be plotted for each interval.
5. Plot the frequencies on the vertical axis.

• If the intervals are too wide, the histogram will be coarse, or blocky, and its shape and
other details will not show well. If the intervals are too narrow, the histogram will be
ragged and will not smooth the data.
• The histogram for continuous data corresponds to the probability density function of a
theoretical distribution.

Example 6.2 : The number of vehicles arriving at the northwest corner of an intersection in a 5
min period between 7 A.M. and 7:05 A.M. was monitored for five workdays over a 20-week
period. Table shows the resulting data. The first entry in the table indicates that there were 12:5
min periods during which zero vehicles arrived, 10 periods during which one vehicles arrived,
and so on,

Table 6:1 Number of Arrivals in a 5 Minute period

3
 Fig 6.2 Histogram of number of arrivals per period.

6.2.2 Selecting the Family of Distributions

• Additionally, the shapes of these distributions were displayed. The purpose of preparing
histogram is to infer a known pdf or pmf. A family of distributions is selected on the
basis of what might arise in the context being investigated along with the shape of the
histogram.

• Thus, if interarrival-time data have been collected, and the histogram has a shape similar
to the pdf in Figure 5.9.the assumption of an exponential distribution would be warranted.

• Similarly, if measurements of weights of pallets of freight are being made, and the
histogram appears symmetric about the mean with a shape like that shown in Fig 5.12,
the assumption of a normal distribution would be warranted.

• The exponential, normal, and Poisson distributions are frequently encountered and are
not difficult to analyze from a computational standpoint. Although more difficult to
analyze, the gamma and Weibull distributions provide array of shapes, and should not be
overlooked when modeling an underlying probabilistic process. Perhaps an exponential
4
 distribution was assumed, but it was found not to fit the data. The next step would be to
examine where the lack of fit occurred.

• If the lack of fit was in one of the tails of the distribution, perhaps a gamma or Weibull
distribution would more adequately fit the data.

• Literally hundreds of probability distributions have been created, many with some
specific physical process in mind. One aid to selecting distributions is to use the physical
basis of the distributions as a guide. Here are some examples:

6.2.3 Quantile-Quantile Plots

• Further, our perception of the fit depends on widths of the histogram intervals. But even
if the intervals are well chosen, grouping of data into cells makes it difficult to compare a
histogram to a continues probability density function

• If X is a random variable with cdf F, then the q-quintile of X is that y such that F(y) =
P(X < y) = q, for 0 < q < 1. When F has an invererse, we write y = F-1(q).

• Now let {Xi, i = 1, 2,...,n} be a sample of data from X. Order the observations from
the smallest to the largest, and denote these as {yj, j =1,2 ,,,n}, where y1 < y2 < ….. <
yn- Let j denote the ranking or order number. Therefore, j = 1 for the smallest and j = n
for the largest. The q-q plot is based on the fact that y1 is an estimate of the (j — 1/2)/n
quantile of X other words,

• Now suppose that we have chosen a distribution with cdf F as a possible representation of
the distribution of X. If F is a member of an appropriate family of distributions, then a

plot of yj versus F-1((j —1/2)/n) will be approximately a straight line.

5
6.3 Parameter Estimation

• After a family of distributions has been selected, the next step is to estimate the
parameters of the distribution. Estimators for many useful distributions are described in
this section. In addition, many software packages—some of them integrated into
simulation languages—are now available to compute these estimates.

6.3.1 Preliminary Statistics: Sample Mean and Sample Variance

• In a number of instances the sample mean, or the sample mean and sample variance, are
used to estimate of the parameters of hypothesized distribution;

• If the observations in a sample of size n are X1, X2,..., Xn, the sample mean ( X) is
defined by

and the sample variance, s2 is defined by

If the data are discrete and grouped in frequency distribution, Equation (9.1) and (.2) can
be modified to provide for much greater computational efficiency, The sample mean can be
computed by

6
And the sample variance by

where k is the number of distinct values of X and fj is the observed frequency of the value Xj, of
X.

6.3.2 Suggested Estimators

• Numerical estimates of the distribution parameters are needed to reduce the family of
distributions to a specific distribution and to test the resulting hypothesis.
• These estimators are the maximum-likelihood estimators based on the raw data. (If the
data are in class intervals, these estimators must be modified.)
• The triangular distribution is usually employed when no data are available, with the
parameters obtained from educated guesses for the minimum, most likely, and maximum
possible value's; the uniform distribution may also be used in this way if only minimum
and maximum values are available.

7
6.4 Goodness-of-Fit Tests

• These two tests are applied in this section to hypotheses about distributional forms of
input data. Goodness-of-fit tests provide help full guidance for evaluating the suitability
of a potential input model.
• However, since there is no single correct distribution in a real application, you should not
be a slave to the verdict of such tests.
• It is especially important to understand the effect of sample size. If very little data are
available, then a goodness-of-fit test is unlikely to reject any candidate distribution; but if
a lot of data are available, then a goodness-of-fit test will likely reject all candidate
distribution.

6.4.1 Chi-Square Test

• One procedure for testing the hypothesis that a random sample of size n of the random
variable X follows a specific distributional form is the chi-square goodness-offit test.
• This test formalizes the intuitive idea of comparing the histogram of the data to the shape
of the candidate density or mass function, The test is valid for large sample sizes, for both
discrete and continuous distribution assumptions, When parameters are estimated by
maximum likelihood.

• where 0, is the observed frequency in the ith class interval and Ei, is the expected
frequency in that class interval. The expected frequency for each class interval is computed
as Ei=npi, where pf is the theoretical, hypothesized probability associated with the ith class
interval.
• It can be shown thatX02 approximately follows the chi-square distribution with k-s-1
degrees of freedom, where s represents the number of parameters of the hypothesized
distribution estimated by sample statistics. The hypotheses are :
8
 H0: the random variable, X, conforms to the distributional assumption with the
parameter(s) given by the parameter estimate(s)

H1 : the random variable X does not conform

• If the distribution being tested is discrete, each value of the random variable should be a
class interval, unless it is necessary to combine adjacent class intervals to meet the
minimum expected cell-frequency requirement. For the discrete case, if combining
adjacent cells is not required,

Pi = P(XI) = P(X Xi)

Otherwise, pi, is determined by summing the probabilities of appropriate adjacent cells.

• If the distribution being tested is continuous, the class intervals are given by [ai-1,ai),
, where ai-1 and ai, are the endpoints of the ith class interval. For the continuous case
with assumed pdf f(x), or assumed cdf F(x), pi, can be computed By

Pi= ai-1 ai f(x) dx= F(ai) – F(ai -1 )

6.4.2 Chi-Square Test with Equal Probabilities

• If a continuous distributional assumption is being tested, class intervals that are equal in
probability rather than equal in width of interval should be used.
• Unfortunately, there is as yet no method for deter mining the; probability associated with
each interval that maximize the; power of a test o f a given size.

Ei = n p i 5

• Substituting for p i yields n/k 5

• and solving for k yields k n/5

9
6.4.3 Kolmogorov - Smirnov Goodness-of-Fit Test

• The chi-square goodness-of-fit test can accommodate the estimation of parameters from
the data with a resultant decrease in the degrees of freedom (one for J each parameter
estimated). The chi-square test requires that the data be placed in class intervals, and in
the case of continues distributional assumption, this grouping is arbitrary.

• Also, the distribution of the chi-square test statistic is known only approximately, and the
power of the test is sometimes rather low. As a result of these considerations, goodness-
of-fit tests, other than the chi-square, are desired.

• The Kolmogorov-Smirnov test is particularly useful when sample sizes are small and
when no parameters have been estimated from the data.

• ( Kolmogoro-Smirnov Test for Exponential Distribution)

Ho : the interarrival times are exponentially distributed

H1: the interarrival times are not exponentially distributed

• The data were collected over the interval 0 to T = 100 min. It can be shown that if the
underlying distribution of interarrival times { T1, T2, … } is exponential, the arrival
times are uniformly distributed on the interval (0,T).

10
 • The arrival times T1, T1+T2, T1+T2+T3,…..,T1+…..+T50 are obtained by
adding interarrival times.
• On a (0,1) interval, the points will be [T1/T, (T1+T2)/T,…..,(T1+….+T50)/T].

6.5 Selecting Input Models without Data

Unfortunately. it is often necessary in practice to develop a simulation model

for demonstration purposes or a preliminary study—before any i data are available.) In this
case the modeler must be resourceful in choosing input models and must carefully check
the sensitivity of results to the models.

Engineering data : Often a product or process has performance ratings pro vided by the
manufacturer.
Expert option : Talk to people who are experienced with the procesws or similar
processes. Often they can provide optimistic, pessimistic and most likely
times.
Physical or conventional limitations : Most real processes have physical limit on
performance. Because of company policies, there may be upper limits on
how long a process may take. Do not ignore obvious limits or bound: that
narrow the range of the input process.
The nature of the process It can be used to justify a particular choice even when no data
are available.
6.6 Multivariate and Time-Series Input Models
The random variables presented were considered to be independent of any other variables
within the context of the problem. However, variables may be related, and if the variables
appear in a simulation model as inputs, the relationship should be determined and taken into
consideration.

11
6.7 Time series input model:
If X1,X2..Xn is a sequence of identically distributed,but dependent and convarianc stationary
random variables,then there are a number of times series model that can be used to represent the
process. The two models that have the characteristics that the autocorrelatrion take the form.

for h=1,2,..n that the log-h autocorrelation decreases geometrically as the lag increases.
AR(1) Model:
consider the time series model

for t=2,3,..n where ε2, ε3 are the independent and identically distributed with men 0 and variance
σ2 ε and -1< ϕ<1. If the initial value x1 is chosen appropriately,then x1,x2..are all normal
distributed with mean u and variance

EAR(1) Model:
Consider the time series model

for t=2,3,..n where ε2, ε3 are the independent and identically distributed with mean and 0<
ϕ<1. If the initial value x1 is chosen appropriately, then x1,x2.. are all exponentially distributed
with mean and variance

12
13
 OUTPUT ANALYSIS FOR A SINGLE MODEL
Estimate system performance via simulation
• If q is the system performance, the precision of the estimator can be measured by:
1. The standard error of .
2. The width of a confidence interval (CI) for q.
• Purpose of statistical analysis:
1. To estimate the standard error or CI .
2. To figure out the number of observations required to achieve desired error/CI.
• Potential issues to overcome:
1. Autocorrelation, e.g. inventory cost for subsequent weeks lack statistical
independence.
2. Initial conditions, e.g. inventory on hand and # of backorders at time 0 would
most likely influence the performance of week 1.

7.1 Type of Simulations

• Terminating verses non-terminating simulations

• Terminating simulation:
1. Runs for some duration of time TE, where E is a specified event that stops
the simulation.
2. Starts at time 0 under well-specified initial conditions.
3. Ends at the stopping time TE.
4. Bank example: Opens at 8:30 am (time 0) with no customers present and 8
of the 11 teller working (initial conditions), and closes at 4:30 pm (Time TE
= 480 minutes).
5. The simulation analyst chooses to consider it a terminating system
because the object of interest is one day‘s operation.

7.2 Stochastic Nature of Output Data

• Model output consist of one or more random variables (r. v.) because the model is an
input-output transformation and the input variables are r.v.‘s.

• M/G/1 queuing example:

1. Poisson arrival rate = 0.1 per minute;
service time ~ N(m = 9.5, s =1.75).

2. System performance: long-run mean queue length, LQ(t).

3. Suppose we run a single simulation for a total of 5,000 minutes
• Divide the time interval [0, 5000) into 5 equal subintervals of 1000 minutes.
Average number of customers in queue from time (j-1)1000 to j(1000) is Yj .

• M/G/1 queueing example (cont.):

• Batched average queue length for 3 independent replications:

Batching Interval Replication

(minutes) Batch, j 1, Y1j 2, Y2j 3, Y3j
[0, 1000) 1 3.61 2.91 7.67
[1000, 2000) 2 3.21 9.00 19.53
[2000, 3000) 3 2.18 16.15 20.36
[3000, 4000) 4 6.92 24.53 8.11
[4000, 5000) 5 2.82 25.19 12.62
[0, 5000) 3.75 15.56 13.66

• Inherent variability in stochastic simulation both within a single replication and

across different replications.
• The average across 3 replications, can be regarded as independent observations,
but averages within a replication, Y11, …, Y15, are not.

7.3 Measures of performance

• Consider the estimation of a performance parameter, q (or f), of a simulated system.

1. Discrete time data: [Y1, Y2, …, Yn], with ordinary mean: q

2. Continuous-time data: {Y(t), 0  t  TE} with time-weighted mean: f

7.3.1 Point Estimator

• Point estimation for discrete time data[Y1, Y2, …, Yn] is defined by.
The point estimator:
ˆ 1 n
 =  Yi
n i=1

• Where ˆ is a sample mean based on sample of size n The pointer estimator ˆ is said to be
unbiased for  if its expected value is , that is if: Is biased

E(ˆ) = 
• Point estimation for continuous-time
data. The point estimator:
ˆ 1 TE
 = T 0 Y (t)dt
E
 ◼ An unbiased or low-bias estimator is desired.

• Usually, system performance measures can be put into the common framework of q or f:
the proportion of days on which sales are lost through an out-of-stock situation, let:

1, if out of stock on day i

Y (t) = 
0, otherwise

• Performance measure that does not fit: quantile or percentile:

• Estimating quantiles: the inverse of the problem of estimating a proportion or

probability. Pr{Y  } = p
• Consider a histogram of the observed values Y:

• Find such that 100p% of the histogram is to the left of (smaller than) .

7.3.2 Confidence-Interval Estimation

To understand confidence intervals fully, it is important to distinguish between measures of
error, and measures of risk, e.g., confidence interval versus prediction interval.
Suppose the model is the normal distribution with mean q, variance s2 (both unknown).

 Let Yi be the average cycle time for parts produced on the ith replication of the
simulation (its mathematical expectation is q).
 Average cycle time will vary from day to day, but over the long-run the average
of the averages will be close to q.
S 2 = 1  (Y − Y ) 2
R
 Sample variance across R replications:
i
. ..
R −1 i=1
7.3.3 Confidence-Interval Estimation
◼ Confidence Interval (CI):
 A measure of error.

 Where Yi. are normally distributed.

S
Y..  t / 2,R−1
R
  We cannot know for certain how far is from q but CI attempts to bound that
error.
 A CI, such as 95%, tells us how much we can trust the interval to actually bound
the error between and q .
 The more replications we make, the less error there is in (converging to 0 as R
goes to infinity).

7.3.4 Confidence-Interval Estimation

◼ Prediction Interval (PI):

 A measure of risk.
 A good guess for the average cycle time on a particular day is our estimator but it
is unlikely to be exactly right.
 PI is designed to be wide enough to contain the actual average cycle time on any
particular day with high probability.
 Normal-theory prediction interval:
1
Y..  t / 2,R−1S 1+
R

 The length of PI will not go to 0 as R increases because we can never simulate

away risk.
 PI‘s limit is:   z / 2
 UNIT 8: Verification and validation modeling

 One of the most important and difficult tasks facing a model developer is the
Verification and validation of the simulation model.

 It is the job of the model developer to work closely with the end users
Throughout the period (development and validation to reduce this skepticism
And to increase the credibility.

The goal of the validation process is twofold:

1: To produce a model that represents true system behavior closely enough for the
model to be used as a substitute for the actual system for the purpose of experimenting
with system.

2: To increase an acceptable, level the credibility of the model ,so that the model will be
used by managers and other decision makers. |

The verification and validation process consists of the following components:-

1:Verification is concerned with building the model right. It is utilized in comparison of
the conceptual model to the computer representation that implements that conception.
It asks the questions: Is the model implemented correctly in the computer? Are the
input parameters and logical structure of the model correctly represented?

2: Validation is concerned with building the right model. It is utilized to determine that
a model is an accurate representation of the real system. It is usually achieved
through the calibration of the model

Dept of CSE,CEC Page 1

7.1 Model Building, Verification, and Validation
The first step in model building consists of observing the real system and the interactions
among its various components and collecting data on its behavior. Operators, technicians , repair
and maintenance personnel, engineers, supervisors, and managers under certain aspects of the system
which may be unfamiliar to others. As model development proceeds, new questions may arise, and the
model developers will return, to this step of learning true system structure and behavior.
The second step in model building is the construction of a conceptual model – a collection of
assumptions on the components and the structure of the system, plus hypotheses on the values of
model input parameters, illustrated by the following figure.
The third step is the translation of the operational model into a computer recognizable form- the
computerized model

Dept of CSE,CEC Page 2

7.2 Verification of Simulation Models
 The purpose of model verification is to assure that the conceptual model is reflected
accurately in the computerized representation.
 The conceptual model quite often involves some degree of abstraction about system operations,
or some amount of simplification of actual operations.

Many common-sense suggestions can be given for use in the verification process:-

 Have the computerized representation checked by someone other than its developer.
 Make a flow diagram which includes each logically possible action a system can take when
an event occurs, and follow the model logic for each a for each action for each event type.
 Closely examine the model output for reasonableness under a variety of settings of Input
parameters.
 Have the computerized representation print the input parameters at the end of the
Simulation to be sure that these parameter values have not been changed inadvertently.
 Make the computerized representation of self-documenting as possible.
 If the computerized representation is animated, verify that what is seen in the
animation imitates the actual system.
 The interactive run controller (IRC) or debugger is an essential component of Successful
simulation model building. Even the best of simulation analysts makes mistakes or commits
logical errors when building a model.
The IRC assists in finding and correcting those errors in the follow ways:
(a) The simulation can be monitored as it progresses.
(b) Attention can be focused on a particular line of logic or multiple lines of logic
that constitute a procedure or a particular entity.
(c) Values of selected model components can be observed. When the simulation has
paused, the current value or status of variables, attributes, queues, resources,
counters, etc., can be observed

(d) The simulation can be temporarily suspended, or paused, not only to view
information but also to reassign values or redirect entities.

 Graphical interfaces are recommended for accomplishing verification & validation

Dept of CSE,CEC Page 3
7.3 Calibration and Validation of Models (As an aid in the validation process or
Naylor finger approches):
 Verification and validation although are conceptually distinct, usually are conducted
Simultaneously by the modeler.
 Validation is the overall process of comparing the model and its behavior to the real
System and its behavior.
 Calibration is the iterative process of comparing the model to the real system,
making adjustments to the model, comparing again and so on.
 The following figure 7.2 shows the relationship of the model calibration to the overall
validation process.
 The comparison of the model to reality is carried out by variety of test Test are subjective
and objective.
 Subjective test usually involve people, who are knowledgeable about one
or more aspects of the system, making judgments about the model and its output.
 Objective tests always require data on the system's behavior plus the
corresponding data produced by the model.

Dept of CSE,CEC Page 4

As an aid in the validation process, Naylor finger:
1. Build a model that has high face validity.
2. Validate model assumption.
3. Compare the model input-output transformation to cooresponding input-output
transformation for the real system.
7.3.1 FACE VALIDITY
 The first goal of the simulation modeler is to construct a model that appears reasonable
on its face to model users and others who are knowledgeable about the real system
being simulated.
 The users of a model should be involved in model construction from its
conceptualization to its implementation to ensure that a high degree of realism is built
into the model through reasonable assumptions regarding system structure, and
reliable data.
 Another advantage of user involvement is the increase in the models perceived
validity or credibility without which manager will not be willing to trust simulation
results as the basis for decision making.
 Sensitivity analysis can also be used to check model's face validity.
 The model user is asked if the model behaves in the expected way when one or more
input variables is changed.
 Based on experience and observations on the real system the model user and model
builder would probably have some notion at least of the direction of change in model
output when an input variable is increased or decreased.
 The model builder must attempt to choose the most critical input variables for
testing if it is too expensive or time consuming to: vary all input variables

7.3.2 Validation of Model Assumptions

 Model assumptions fall into two general classes: structural assumptions and
data assumptions.
 Structural assumptions involve questions of how the system operates and usually involve
simplification and abstractions of reality.

Dept of CSE,CEC Page 5

  For example, consider the customer queuing and service facility in a bank. Customers may
form one line, or there may be an individual line for each teller. If there are many lines,
customers may be served strictly on a first-come, first-served basis, or some customers may
change lines if one is moving faster.
 The number of tellers may be fixed or variable. These structural assumptions should be
verified by actual observation during appropriate time periods together with discussions
with managers and tellers regarding bank policies and actual implementation of these
policies.
 Data assumptions should be based on the collection of reliable data and correct statistical
analysis of the data.data were collected on:

1. Inter arrival times of customers during several 2-hour periods of peak loading
("rush-hour" traffic)
2. Inter arrival times during a slack period
3. Service times for commercial accounts
4. Service times for personal accounts

 Validation is not an either/or proposition—no model is ever totally representative of

the system under study. In addition, each revision of the model, as in the Figure above
involves some cost, time, and effort.
 The procedure for analyzing input data consist of three steps:-
1: Identifying the appropriate probability distribution.
2: Estimating the parameters of the hypothesized distribution .
3: Validating the assumed statistical model by goodness – of – fit test such as the chi
square test, KS test and by graphical methods

10.3.3 Validating Input-Output Transformation

 In this phase of validation process the model is viewed as input –output transformation.
 That is, the model accepts the values of input parameters and transforms these inputs into
output measure of performance. It is this correspondence that is being validated.
 Instead of validating the model input-output transformation by predicting the future ,the
modeler may use past historical data which has been served for validation purposes that

Dept of CSE,CEC Page 6

 is, if one set has been used to develop calibrate the model, its recommended that a
separate data test be used as final validation test.
 Thus accurate “ prediction of the past” may replace prediction of the future for purpose of
validating the future.
 A necessary condition for input-output transformation is that some version of the system
under study exists so that the system data under at least one set of input condition can be
collected to compare to model prediction.
 If the system is in planning stage and no system operating data can be collected, complete
input-output validation is not possible.
 Validation increases modeler’s confidence that the model of existing system is accurate.
 Changes in the computerized representation of the system, ranging from relatively minor
to relatively major include :

1: Minor changes of single numerical parameters such as speed of the machine, arrival
rate of the customer etc.
2: Minor changes of the form of a statistical distribution such as distribution of service
time or a time to failure of a machine.
3: Major changes in the logical structure of a subsystem such as change in queue
discipline for waiting-line model, or a change in the scheduling rule for a job shop
model.
4: Major changes involving a different design for the new system such as computerized
inventory control system replacing a non computerized system .

 If the change to the computerized representation of the system is minor such as in items one
or two these change can be carefully verified and output from new model can be accepted
with considerable confidence.

7.3.4: Input-Output Validation: Using Historical Input Data

 When using artificially generated data as input data the modeler expects the model produce
event patterns that are compatible with, but not identical to, the event patterns that
occurred in the real system during the period of data collection.
 Thus, in the bank model, artificial input data {X\n, X2n, n = 1,2, , .} for inter arrival and service

Dept of CSE,CEC Page 7

 times were generated and replicates of the output data Y2 were compared to what was observed
in the real system
 An alternative to generating input data is to use the actual historical record, {An, Sn, n =
1,2,...}, to drive simulation model and then to compare model output to system data.
 To implement this technique for the bank model, the data Ai, A2,..., S1 S2 would have to be
entered into the model into arrays, or stored on a file to be read as the need arose.
 To conduct a validation test using historical input data, it is important that all input data
(An, Sn,...) and all the system response data, such as average delay(Z2), be collected during
the same time period.
 Otherwise, comparison of model responses to system responses, such as the comparison of
average delay in the model (Y2) to that in the system (Z2), could be misleading.
 responses (Y2 and 22) depend on the inputs (An and Sn) as well as on the structure of the
system, or model.
 Implementation of this technique could be difficult for a large system because of the need for
simultaneous data collection of all input variables and those response variables of primary
interest.
7.3.5: Input-Output Validation: Using a Turing Test

 In addition to statistical tests, or when no statistical test is readily applicable persons

knowledgeable about system behavior can be used to compare model output to system
output.
 For example, suppose that five reports of system performance over five different days are
prepared, and simulation output are used to produce five "fake" reports. The 10 reports
should all be in exactly in the same format and should contain information of the type that
manager and engineer have previously seen on the system.
 The ten reports are randomly shuffled and given to the engineers, who is asked to decide
which report are fake and which are real.
 If engineer identifies substantial number of fake reports the model builder questions the engineer
and uses the information gained to improve the model.
 If the engineer cannot distinguish between fake and real reports with any consistency, the
modeler will conclude that this test provides no evidence of model inadequacy .

Dept of CSE,CEC Page 8

  This type of validation test is called as TURING TEST.

8.4 Optimization via simulation:

 Optimization via simulation to refer to the problem of maximizing or minimizing the expected
performance of a discrete event, stochastic system that is represented by a computer
simulation model.
 Optimization usually deals with problems with certainty, but in stochastic discrete-event
simulation the result of any simulation run is a random variable
 let x1,x2,..xm be the m controllable design variable and Y(x1,x2,..xm)be the observed
simulation output performance on one run:
 To optimize Y(x1,x2,..xm) with respect to x1,x2,..xm is to maximize or minimize the
mathematical expectation of performance. E[Y(x1,x2,..xm)]

Dept of CSE,CEC Page 9

OutPut analysis of steady state simulation(unit 7 vvimp 10m):

1.Initialization Bias.

2.Error Estimation

3.Replication mathods.

4.Sample size.

5.Batch means.

Dept of CSE,CEC Page 10

Dept of CSE,CEC Page 11
.

Dept of CSE,CEC Page 12

Dept of CSE,CEC Page 13