Solving the Model

In this section, we are interested in the transient behavior of the model. We will solve the MMPP/Leaky Bucket Model using . Our interest is the state probabilities at different time points. This method produces an output file for each interval specified. To solve the model, click on the Analytical Model Solution button. Choose the Transient section and then Point Probabilities. The interface is shown in Figure .

Figure: The Point Probabilities Method.

In the next step we input the following parameters: Initial Probability, Time Intervals and Precision. These parameters are important to solve the model.

  Initial Probability - Equiprobable
  Time Intervals: n 0.1 10 10 
  Initial Time = 0.1
  Final Time = 10
  Number of points = 10 
  Precision = 1.0e-05

The Point Probabilities method generates files that will be used to calculate the measures of interest (e.g, probability mass function, expected value and so on). The names of the files generated are <name of model>.<TS>.<pp>.<final time interval>.

For example, suppose that we want to know the distribution of the number of the packets in the Leaky_Bucket buffer at time $t=10$. Then it is necessary to use the Measures of Interest Module ( of one or more state variables) and choose the appropriate file with the probabilities. This file is generated by the Point Probabilities Method. In this case, choose the file MMPP.TS.pp.1.0000000e+01 and choose the state variable Leaky_Bucket.buffer in the Choose Variables box. Click on the Evaluate button, and on the Plot button. We can obtain the of the number of the packets in the buffer (Fig ).

Figure: The Buffer size PMF