Hence, if you first run a 100 realization simulation, and then run a second simulation with Run the following Realization only checked (and, for example, Realization set to 14), the result of the second single realization simulation will be identical to the 14th realization of the first simulation. In this case, the random number sequence that is used is based on the Realization specified (and, if Latin Hypercube Sampling is used, the # Realizations). In fact, this is the default setting when you create a new GoldSim model.Īlternatively, you could choose to run a specific realization (other than the first) by checking Run the following Realization only and specifying a specific Realization. You can do this by setting the # Realizations to 1 in the Monte Carlo tab of the Simulation Settings dialog: One way is to simply run a single realization. But once you have built a probabilistic model (that includes, for example, multiple Stochastic elements and perhaps other elements that behave randomly such as time-shifted Time Series), what is the best way to do this? In general, the only way to properly test your model is to examine one realization at a time. However, while you are constructing and testing the logic of your model, viewing probabilistic results can make it difficult to test that your model logic is correct. After you have built your model and are trying to make probabilistic predictions, this is not a problem (and as illustrated in the last two Lessons, GoldSim provides a number of tools to help examine probabilistic results).
When you are building probabilistic models, the results can become quite complicated. Before we move on to other GoldSim topics, however, there is one final issue that needs to be discussed. We have now covered almost everything we need to in order for you to start to take advantage of GoldSim’s probabilistic simulation features. Lesson 11 - Running a Deterministic Simulation with Uncertain Inputs Understanding Random Numbers and Sampling
0 kommentar(er)
