Lesson 3 - Steps in A Simulation Study
Lesson 3 - Steps in A Simulation Study
1. Define the Problem: Start by clearly stating what problem you're trying to solve.
If someone else gives you the problem, make sure you understand it. If you're
figuring it out yourself, make sure others agree with your understanding.
2. Set Goals and Make a Plan: Figure out what you want to learn from the
simulation. Plan out how you'll do it, including what different options you'll
consider, how you'll measure success, and how long it will take.
3. Build the Model: Making a model is like making a simplified version of the real
problem. It's both an art and a science. You start simple and add detail as
needed. It's also important to involve others who will use the model.
4. Collect Data: As you build your model, you'll need information to make it
accurate. You have to determine what type of data to collect. Start gathering
data early, and make sure it matches what you need to know. Data is fitted to
theoretical distributions. For example, the arrival rate of a specific part to the
manufacturing plant may follow a normal distribution curve. The collection of
these distributions is known as an Input Model.
5. Translate the model: Models can get complicated, so you need to make them
computer-friendly. This step involves putting your model into a format that a
computer can understand. You might need to do some programming.
6. Verified: This step ensures that the computer program used for the simulation
model is working correctly. It involves checking if the program accurately
represents the model's input parameters and logical structure. Sometimes,
debugging is needed to fix any issues.
9. Production Runs and Analysis: This phase runs simulations and analyses the
results to estimate system performance measures. Special software like
AutoStat, OptQuest, and SimRunner can help with this analysis.
10. More Runs: Based on the analysis of completed runs, the analyst decides if
additional simulations are needed and plans their design.
12. Implementation: The success of this phase depends on the effectiveness of the
previous steps. It involves putting the simulation model into action, and
effective communication with the model user is crucial for successful
implementation.