Basic Framework for Discrete Event Simulation

Written by: Ajeng Alfia F.T.

Discrete event simulation is a kind of simulation that uses mathematical modelling of a physical system to present changes in such a period of time. This type of simulation is usually performed to presents queue systems, inventory managements, etc. Follow this simple guide as the basic framework for Discrete Event Simulation Projects:

  1. Set the objective

The key to a successful simulation project is to start with a clear goal. Goal should highlight the issues for which problem the project desire to answer. Discrete Event Simulation can be used for multiple purposes such as diagnosing process issues, sizing inventories, sizing manpower, supporting decision making process for facilities development investments, etc. Besides the goal, other important things that should be considered before building simulations are:

  1. Boundaries of the system to be studied
  2. Project timeline
  3. Key Performance Indicator of the project
  4. Project timeline
  5. Identify and Collect data

Accurate and timely data is crucial in building a simulation project, it is to ensure that the model built matches the reality of the system. In this step, the researcher must analyze the actual system and check what information is relevant to construct the model. The data requirements are commonly driven by the process map, process objective, and model inputs/outputs.

When the researchers have identified which data is necessary, they need to determine where the data should be collected. Common manual method to collect data is by performing time studies, work sampling, etc. The goal of data collection process is to obtain the largest possible amount of data. Therefore, an accurate simulation can possibly be made.

  1. Build the model

It is necessary to build a model considering the logical and procedures to make sure that the model is representing the actual system. There are several software that can be used to make a simulation such as Flexsim, Arena, etc.

  1. Model Verification and validation

Model verification and validation is important. Without those 2 steps, simulation results can be compromised. Verification is ensuring that the actual system is defined accurately in conceptual model. One method that can be used for model verification is to compare the model to activity cycle diagram of actual system. Almost similar to verification, validation is a process to ensure that a model made is representing the actual system. The validation process varies depending upon the type of model that is built. It is common to do a validation based on historical data. Researchers usually compare some parameter of the model to historical data

  1. Perform simulation and Analyze the result

When model verification and validation is done, it means that the model is ready to use. Researchers can start the simulation and collect the results. The simulation should be rum as many as it is necessary to get a reliable result.  It is possible to make a little change in order to see how the system reacts to those changes. When all possibilities tested, researchers need to analyze the results and turn them into information that is valuable for decision making process. Through the analysis, it can be concluded which alternative should be done in order to reach the goal (objective).

  1. Make the final documentation

As a final step, documentation should be prepared. Containing all information from the simulation, the document is important to explain how the simulation is made and explain the conclusion of the project.