SIMULATION

INTRODUCTION
Simulation can be defined as a technique that imitates the operation as it evolves over time. It is
basically a technique of conducting experiments on a model of a system. Simulation model usually
takes the form of a set of assumptions about the operation of the system, expressed as mathematical
or logical relations between the objects of interest in the system.
In order to study a system once it is defined, two alternatives are available: -
i) To study the actual system itself and the other
ii) To construct the model of the system and study the model
Generally, the study of the actual system has the disadvantages of being time consuming,
expensive and / or outright impossible (e.g., in a saw mill operation, it would be extremely time
consuming and costly to try every possibility of cutting logs to maximize profit Likewise it would
be impossible to study a proposed system without constructing some form of model.
Consequently, models most existing or proposed systems are constructed and the models are
analysed how the actual system will react to change. However, many realistic systems can't be
modeled for solution by the standard operation research methods. Therefore, some form of
simulation must be used to provide the solution. Simulation is a general method which can-be used
to solve problems in many areas of management such as
i) Inventory management
ii) Queuing problems
iii) Capital budgeting
iv) Project management
v) Profit planning (CVP analysis etc.)
DEFINITION OF TERMS IN SIMULATION
a) A System - a system can be defined as a collection of entities that act & interact towards the
accomplishment of some logical end.
b) State of a system- This is the collection of the variables necessary' to describe the status of the
system at any given time. Systems are usually classified as either discrete or continuous.
c) A discrete system is one which the state variable changes only as discrete or countable points
in time
d) A continuous system- is one in which the state variables change continuously over time
e) Dynamic simulation•-Representation a system as it evolves-overtime.
f) Static simulation model- Representation of a system at a particular point in time
g) Model –a model is a representation of the system and it usually takes the form of a set of
assumption about the operation of the system
There are several types of simulation model namely:
1. Static simulation model
2. Dynamic simulation models
3. Deterministic simulation-models
4. Stochastic simulation models
5. Discrete simulation models
6. Continuous simulation models
Static simulation model
This is a representation of a system at a particular point in time.
Dynamic simulation model
This is a representation of a system as it evolves over time.
Deterministic simulation model
This is a model that contains No random variables.
Stochastic simulation model
This model contains one or more random variables.
WHEN SIMULATION IS USED
i) When the assumptions made are unrealistic or unattainable.
ii) When the system takes too long to observe e.g., demographic / population issues (time
compression advantage)
iii) When, the cost and the danger of experimenting with the real-world situations is very high.
iv) Where there are difficulties in making observations e.g., space research and practice. Molecular
research.
Variables in a simulation model
A business model usually consists of linked series of equations and formulae arranged so that they
'behave' in a similar manner to the real system being investigated. The formulae and equations use
a number of factors or variables which can be classified into 4 groups.
(a) Input or exogenous variables
(b) Parameters
(c) Status variables
(d) Output or endogenous variables These are described below.
a) Input variables
These variables are of two types - controlled and non-controlled.
Controlled variables: These are the variables that can be controlled by management. Changing the
input values of the controlled values and noting the change in the output results is the prime activity
of simulation. For example, typical controlled variables in an inventory simulation might be the
re- order level and re-order quantity. These could be altered and the effect on the system outputs
noted. Non-controlled variables: These are Input variables which are not under management
control.
Typically, these are probabilistic or stochastic variables i.e., they vary but in some uncontrollable
probabilistic fashion.
For example, in a production simulation the number of breakdowns would be deemed to vary in
accordance with a probability distribution derived from records of past breakdown frequencies.' In
an inventory simulation demand and lead time would also be generally classified as non-
controlled, probabilistic variables
b) Parameters
These are also input variables which, for a given simulation have a constant value. Parameters are
factors which help to specify the relationships between other types of variables. For example, in a
production simulation a parameter (or constant) might be the time taken for routine maintenance,
in an inventory simulation a parameter might be the cost of a stock-out.
c) Status variables
In some types of simulation, the behavior of the system (rates, usages, speeds, demand and so on)
varies not only according to individual characteristics but also according to the general state of the
system at various times or seasons. As an example; in a simulation of supermarket demand and
checkout queuing, demand will be probabilistic and variable on any given day but the general level
of demand will be greatly influenced by the day of the week and the season of the year. Status
variables would be required to specify the day(s) and season(s) to be used in a simulation.
Note: On occasions status variables and parameters would both be termed just parameters although
strictly speaking there is a difference between the two concepts.
d) Output variables
These are the results of the simulation. They arise from the calculations and tests performed in the
model the input values of the controlled values. The values derived for probabilistic elements and
the specified parameters and status values. The output variables must be carefully chosen to reflect
the factors which are critical to the really system being simulated and they related to the objectives
of the really system. For example, output variables for an inventory simulation would typically
include:
• Cost of stock holding
• Number of stock outs
• Number of unsatisfied orders
• Number of replenishment orders
• Cost of the re-ordering and so on
Constructing a simulation model
Some broad guidelines for constructing a simulation model are given below. These will be useful
for dealing with examination questions but in this area especially, practice is vital.
Step 1: Identify the objective(s) of the simulation.
A detailed listing of the results expected from the simulation will help to clarify step 5 - the output
variables.
Step 2 Identify the input variables. Distinguish between controlled and non-controlled variables
Step 3 Where necessary determine the probability distribution for the non-controlled variables
Step 4 Identify any parameters and status variables.
Step 5 Identify the output variables.
Step 6 Determine the logic of the model
This is the heart of the simulation construction. The key questions are: how are the input variables
changed into output results? What formulae/decision rules are required? How will probabilistic
elements be dealt with? How should the results be presented?
Some examples of the variables that may be used in simulation are:
i) A set of prices and cost and the standard relationships could be used to simulate profits
ii) The components of a queuing system such as the arrival rates and the service rates could be
used to simulate a queuing system to generate such data as the waiting time, the length of a queue
and the problems of a system being busy.
iii) In inventory management, variables such as demand and the lead time can be used in simulation
to generate such cost data as the holding cost, shortage cost, ordering cost
MONTE CARLO SIMULATION
This is a form of simulation that deals with the allocation of random numbers. When a system
contains elements that exhibit chance in their behavior, the method of Monte Carlo sampling /
simulation may be applied.
The basis of this method is experimentation on chance or probabilistic elements through sampling,
Steps in Monte Carlo Simulation
1. Set up probability distribution for the relevant random variables
2. Build up cumulative probability distributing for each of the variables in step 1.
3. Establish the intervals of the random numbers for each variable and allocate the random number
ranges,
4. Obtain the random numbers -random numbers can be obtained from:
a) Random number tables
b) Calculators
c) Computers
5 Run the simulation trials
THE ROLE OF COMPUTERS IN SIMULATION
1. It generates the random number
2. It simulates thousands of trials extremely fast, accurately and reliably. A computer can also
stock large mass of data.
3. The computer simulates several combinations of the decision variables e.g., the re-order quantity
and the re-order level in the inventory management or the service channel and the service time in
queuing model in a matter of seconds.
4. It provides the management with printed reports which are very useful for decision making.
RANDOM NUMBER AND THEIR ALLOCATION
1. For uniform random number table, each unit has an equal chance of occurring at any point in
the table i.e., a uniform distribution.
2. For uniform random number table, each unit has an equal chance of occurring at any point in
the table i.e., a uniform distribution.
3. Each number is allocated once and only once.
4. The number allocated to a value of the random number is directly proportional to the problem
of that value. i.e.
a) Single decimal probability distribution is allocated 10 digits i.e., from 0-9 or from 1 -0
b) Two decimal probability distribution are allocated 100 digits i.e., from 00-99 or 01 -00
c) Three decimal probability distribution are located 1000 digits i.e., from 000-999 or 001 - 000
etc.
Advantages of simulation
1. Simulation is well suited to problems which are difficult or impossible to solve analytically
i.e., where main assumptions are unrealistic e.g., inventory management, queuing problems and
capital budgeting.
2. Simulation allows the analyst or the decision maker to experiment with the system behavior in
a controlled environment instead of the real life setting which can be very costly or has inherent
risks
3. It enables a decision maker to compress time in order to evaluate the long-term effects of various
alternatives.
4. Simulation can serve as a mode of training decision makers by enabling them to observe the
behavior of a system under different circumstances without experimenting with the actual system
e.g., military and business training/ gaming.
5. Simulation has the order of being relatively free from complicated mathematics thus very easy
to understand for the operating personnel and for the non-technical managers.
6. Simulation models are comparatively flexible and can easily be modified to accommodate the
changing environment e.g., a company manager can try several policy options in a matter of minute
7. Simulation allows us to study the interactive effects of the individual components or variables
to determine which ones are important.
8. Recent advancements in the software make some simulation models to be very easy to develop.
Disadvantages of simulation
1. Simulation is not precise i.e.; it's not an approximation process and it does not necessarily yield
an optimal answer but merely provides a set of system responses to the different operating
conditions. In many cases, lacking precession is difficult to measure. However, as the number of
simulation trials increases precision, increases provided that in the problem distribution the
relevant variables do not change.
2. A good simulation model may be expensive in terms of design personnel (consultants,
computing facilities software etc.)
3. Simulation model is unique i.e.; its solutions and inferences are not easily transferred to the
other problems thus further increasing the cost of simulation.
4. Simulation can take time in terms of data collection and the designing of the model and this
could delay the decision making which is costly in the long run.
5. In a number of situations it's not possible to quantify all the variables that affect the behavior of
a system.
OTHER TYPES OF SIMULATION MODELS
Simulation models are often broken into three categories. The first, the Monte Carlo method just
discussed, uses the concept probability distribution and random numbers to evaluate system
responses to various policies. The two other categories are called operational gaming and system
simulation. Although in theory the three models are distinctly different, the growth - of
computerized simulation has tended to create a common basis in procedures and blur these
differences.
a) Operational gaming
Operational gaming refers to simulation involving two or more competing players. The best
examples are military games and business games. Both all participants to match their management
arid decision-making skills in hypothetical situations of conflict
Military games are used world-wide to train a nation's top military officers, to test offensive and
defensive strategies, and to examine the effectiveness of equipment and armies.
Business games, first developed by the firm Booz, Allen and Hamilton in the 1950s, are popular
with both executives and business students. They provide an opportunity to test out business skills
and decision-making ability in competitive environment. The person or team that performs best in
the simulated environment is rewarded by knowing that his or' her company has been most
successful in earning the largest profit, grabbing a high market share, or perhaps increasing the
firm's trading value on the stock exchange.
b) Systems Simulation
Systems simulation is similar to business gaming in that it allows users to test various managerial
policies and decisions to evaluate their effect on the operating environment. The variation of
simulation models the dynamics of large systems. Such systems include corporate operations, the
national economy, a hospital, or a city government system.
In a corporate operating system, sales, production levels, marketing policies, investments, union
contracts, .utility rates, financing, and other factors are ail related in a series of mathematical'
equations that are examined by simulation. In a simulation of an urban government, systems
simulation may be employed to evaluate the impact of tax increase, capital expenditures for roads
and buildings, housing availability, new garbage routs. in- migration and out-migration, locations
of new schools or senior citizens centers, birth and death rates and many more vital issues.
Simulation of economic systems, often called econometric models are used by government
agencies, bankers, 'and large organizations to predict inflation rates, domestic and foreign money
supplies, and unemployment levels.
ILLUSTRATION 1
XYZ Ltd is considering launching a new product which will require an investment of Shs. 5000.
The product has a life of 1years. There are uncertain variables namely; selling price unity variable
cost and demand as shown in probability distribution below:

Using the following random numbers

806,043,632,140,360,589,161,573,996,497,726,953, 050,118,664886,924,077,008,401,658,401
Carry out 25 trial numbers
SOLUTION
1. Step one
Assign the random number ranges
i)

ii)
ILLUSTRATION 2
XYZ has a policy of ordering stock when level falls to 15 units the quantity ordered from the
supply is always 20 units. The stock at beginning of 1st week is 20 units. The stock holding costs
are sh. 10 per week / unit. The cost of placing one order = 25. The stock out cost are Sh100 per
unit. The usage (demand) and lead time (time taken by supply to deliver stock) is uncertain as
shown below.
NB: Ordering is done the following week upon discovery of the shortages.
Required;
Use the following random numbers
68 52 50 90 59 08 72 44 95 85 81 93 28 89 15 60 03
Use 14 trial numbers to find the cost

SOLUTION
ASSIGNMENT 1
1. ABC Ltd. recently acquired a threshing machine with a useful life of 15 years. Over the
useful life, the machine is likely to have periodic failures and breakdowns. Past data for
similar machines indicate a probability distribution of failures as follows:
Number of failures 0 1 2 3
Probability 0.80 0.15 0.04 0.01
Required:
(i) Using the random numbers provided below, simulate the number of failures that will
occur over the useful life of the machine.
Random numbers: 70,88,37,12,45,99,54,71,64,93,67,80,55,34,22
(ii) Determine the average annual failure rate.
2. Manukato Ltd. produces a designer perfume called “Hint of Elegance.” Production of the
perfume involves the use of two ingredients, X1 and X2 represented by the production
function given below:

Currently, the company is operating at a level where the daily usage of X1 and X2 is set at
250 units and 360 units respectively.
The price of the designer perfume and the cost of ingredients X1 and X2 are random
variables. The data below relate to the three random variables.
 Required:
(i) Calculate the daily expected profit of the company.
(ii) Simulate the company’s profit for 10 days using the following random numbers:
58, 71, 96, 30, 24, 18, 46, 23, 34, 27, 85, 13, 99, 24, 44, 49, 18, 09, 79, 49, 74, 16,
32, 23, 02, 56, 88, 87, 59, 41, 06
3. Nairobi Manufacturers Ltd. produces component X on machine Y at a rate of 4,000 units
per month. Machine Z uses component X at the rate of 1,000 units per month, the remainder
being put into stock. It costs Shs. 2,000 to set up machine Y while the stock holding cost
is estimated at Shs. 2.50 per unit per annum plus a 20% opportunity cost of capital per
annum. Each component costs Shs. 25 to produce.
Required:
(i) Compute the optimal batch size that should be produced using machine Y.
(ii) Assume that the actual set-up cost of machine Y is Shs. 1,000 instead of Shs. 2,000.
Calculate the cost of prediction error.