SIMULATION
A. Introductory Concepts
• Simulation is the attempt to duplicate the features, appearance and characteristics
of a real system. Often, it involves the building of a mathematical model that comes
as close as possible to representing the reality of the system. The idea is to imitate a
real-world situation mathematically, then to study its properties and operating
characteristics, and finally to draw conclusions and make action decisions based on
the results of the simulation.
• The problems tackled by simulation may range from very simple to extremely
complex. Although very small simulations may be conducted by hand, effective use
of this technique requires some automated means of calculation with the aid of
computer software.
• While simulation is one of the older Management Science techniques, it was not until
the introduction of computers that it became a practical means of solving large-scale
problems.
• Simulation can handle queuing problems in which arrivals are not Poisson
distributed, service time are not exponentially distributed or constant, or the FIFO
priority system is inappropriate.
Advantages of Simulation
- It is relatively straightforward and flexible;
- It can be used to analyze large and complex real world situations that cannot be
solved by conventional Management Science models.
- Simulation allows for the inclusion of real world complications that most
Management Science models require exponential or Poisson distributions. Some
models require normality and standard deviations, the simulation does not.
- “Time compression” is possible with simulation.
- Simulation allows “what-if” types of questions;
- Simulations do not interfere with the real world system. With simulation,
experiments are done with the model, now on the system itself; and
- Simulation allows us to study interactive effect of individual components or
variables in order to determine which ones are important.
Disadvantages of Simulation
- Good simulation models can be very expensive;
- Simulation may not generate optimal solutions to problems as like Linear
Programming;
- Each simulation model is unique. Its solutions and inferences are not usually
transferable to other problems or situations.
Top 10 List of Simulation NO-NOs
- Performing a simulation without a clear definition of the objectives;
- Believing that the model itself can compensate for poor data collection;
- Lacking an understanding of statistical processes;
- Failing to do order profiling;
- Ignoring the effects of randomness;
- Incorporating randomness inappropriately;
- Failing to consider down time;
- Making illogical assumptions;
- Failing to question the results;
- Failing to recognize that simulation is a study tool
The Simulation Process
1. Define the problem.
2. Identify and introduce important variables.
3. Construct the simulation model.
4. Specify the values of the variables to be tested
5. Conduct simulation.
6. Examine the results.
7. Select the best course of action.
B. Monte Carlo Simulation
• When a system contains elements that exhibit chance in their behavior, the Monte
Carlo method of simulation may be applied. The basis of Monte Carlo simulation is
experimentation on the chance (or probabilistic) elements of the problem through
random sampling
Monte Carlo Steps.
1. Set up a probability distribution.
2. Build cumulative probability distribution for each of the variables.
3. Establish an interval of random numbers for each variable.
4. Generate random numbers.
5. Simulate a series of trials.