Chapter 8 – Simulation

Simulation is the method of studying the effects of changes in the real system through models. A model is manipulated to know the end result. The method is more appropriate to situations where the size and/or complexity of the problem makes the use of other techniques difficult or impossible.

Use of simulation :

The simulation can be used in Air traffic control queuing, air craft maintenance, assembly line scheduling, inventory order designing, rail freight carriers, facility layout etc.

In a simulation model

The system’s elements are represented by arithmetic, analog or logical processes that can be executed, to predict the dynamic properties of the real system. In this model, the time can be increased by fixed time increments (say on hourly, daily, weekly basis) or variable time increments. At each point of time, the system is scanned to determine if any event has happened. Then the events are simulated and time is advanced. Time is advanced by one unit, even when the events do not occur.

Why use simulation? :

Some situations do not lend themselves to precise mathematical treatment. Others may be difficult, time-consuming, or expensive to analyze. In these situations, simulation may approximate real-world results; yet, require less time, effort, and/or money than other approaches.

How to Conduct a Simulation

The steps required to produce a useful simulation are presented below.

1. Defining the problem (i.e. define objectives and variables)
2. Construct the simulation model (specify the variables, parameters, decision rule)
3. Specify the values of parameters and variables.
4. Run the simulation (determine the starting conditions and run length)
5. Evaluate the result and propose new experiment. (determine statistical tests and compare withother information).

Advantages:

Simulation is useful where the experiments on real system

• would disrupt ongoing activities
• Wouldbe too costly to undertake
• require many observations over an extended period of time
• do not permitexact replication of events and
• do not permit control over key variables.

It is preferable when a mathematical model

• is not available to handle the problem
• is too complex
• is beyond the capability of available personnel
• is not robust enough to provide information on all factors.

Disadvantages :

• It is time consuming
• It requires computer experience and expertise on the part of the user
• There are very few principles to guide the user in making decisions on what to include in the modeland the length and no. of simulation runs. The user has to use his intuitive judgment.