Model 3b - Assignment of Stochastic Process Variables

Goals of this lesson

  • Getting more dynamics into the decision making at exclusive or inclusive gateways

  • Usage of stochastic process variables

How-to

The exclusive gateway in Model 3.a from lesson Exclusive Gateways is pretty static. During the simulation every process instance will use the same path, because the evaluation will always get the same result. Models with more dynamic (and realistic) path selection can be achieved by defining stochastic attributes. Stochastic attributes are variables, whose values change (similarly to the duration of activities) by a stochastic distribution.

3b model
Figure 1. Model 3b - Assignment of Stochastic Attributes / IYOPRO-Link

Creating Stochastic Attributes

To use a stochastic variable, we need to define it at the activity before the gateway:

  1. Make sure, you selected the Simulation option from the Property Set drop-down-box

  2. Click the first activity in the model

  3. Click the button right to the Stochastic Attribute Assignment property under Optional Simulation Properties

  4. The Process Attribute Editor shows up (see the picture below)

  5. Click the Add button to add a new stochastic attribute

  6. The Distribution Editor shows up. You will notice, that it is the same Distribution Editor that you already got to know by assigning durations of activities or inter-arrival times of start events.

  7. Now select the normal distribution with a mean value of 10 and a standard deviation of 3

  8. The variable will be given a name (something like "v1"). You can change this by double-clicking into the Name field. Rename it to X.

Assigning Conditions with Stochastic Attributes

We are now ready to go. Simply define the conditions (see lesson Assigning Gateway Conditions) like this:

  • Upper edge: Result=(X<7.0); which means that the variables value is below the mean minus the sigma (standard deviation, 10 - 3 = 7)

  • Middle edge: Result=(X>13.0); which means that the variables value is beyond the mean plus the sigma (standard deviation, 10 + 3 = 13)

  • Bottom edge: Put in on default by selecting Default Sequence Flow from the Element Type in the General Properties. This means the value is between the mean plus / minus the sigma (7 < X < 13).

Modell 3b Process Attribute
Figure 2. IYOPRO’S Simulation Process Attribute Editor

Report

See below for the run configuration, which we set up to receive the report statistics from below.

Please refer to the section Experiment Results for more information on the report specific data.

Run configuration

  • Stochastic Seed: 12345

  • Simulation start date: 1/1/2014 12:00:00 a.m.

  • Simulation stop time: 240

  • Simulation stop time unit: Hours

Report statistics

  • This report contains a beautiful pie chart, which almost resembles the stochastic correlations of the normal distribution, which are:

    • In 70% of cases the value is within the assigned interval (mean +/- the standard deviation)

    • in 15% of cases the value is below the assigned interval

    • in 15% of cases the value is above the assigned interval

    • You can verify this by extending the simulation’s run-time significantly

      • The percentages should converge to 70, 15 and 15

  • In the second table you can find the statistics in numbers, which also resemble the facts from above

model3b gateway
Figure 3. The report’s gateway details