This preview has intentionally blurred sections. Sign up to view the full version.View Full Document
Unformatted text preview: Simulation with Process Model In Chapter 21, we learned how to build simulation models of many different situations. In this chapter, we will explain how the powerful, user-friendly simulation package Process Model can be used to simulate queuing systems. 22.1 Simulating an M / M /1 Queuing System After installing Process Model from the book’s CD-ROM, you can start Process Model by selecting Start Programs Process Model 4. You will see the screen shown in Figure 1, where some key icons have been labeled. It is simple to simulate an M / M /1 queuing system having l 10 arrivals/hour and m 15 customers/hour. See file MM1.igx. Assume that these are calls for directory assistance. Step 1 Click on one of the arrival icons (a person or a phone) and drag the icon to the blank part of the screen (called the Layout portion). We have chosen to use the phone icon. Your screen should look like Figure 2. Step 2 Select the Process rectangle and drag it right over the arrival icon. Click on it and drag it to the right. You will now have a double-arrowed connection between the arrival icon and the Process rectangle. The double-arrowed icon indicates the arrival of entities into the system. Later we will tell Process Model that interarrival times are exponential with mean 6 minutes. After Taking Calls is typed within the Process rectangle, the Lay- out window looks as shown in Figure 3. Step 3 Choose one of the server icons to represent a telephone operator (say, the person with the computer) and drag this icon to the Layout window above the Take Calls Process rectangle. Then type the word “operator” to indicate a phone operator. Next, click on the Connector Line tool in the Toolbox and place the cursor over the operator. We then click once and drag a connection down to the Take Calls activity. This indicates that the oper- ator can take calls. The Layout window should now look as shown in Figure 4. Step 4 Next, tell Process Model to make interarrival times exponential. Process Model works off the mean interarrival time or service time, not the arrival or service rates. Process Model supports many distributions, including the triangular, normal, and Erlang random variables. For now, we will use the exponential distribution. Since the average time between arrivals is 6 minutes, we will model the interarrival times as E(6). (E stands for exponential.) To enter the interarrival time distribution, click on the double arrow con- necting Call to Take Calls and fill in the dialog box as shown in Figure 5. Entering Peri- odic and E(6) ensures that interarrival times will be generated over and over as indepen- dent exponential random variables with mean 6. MM1.igx 1192 C H A P T E R 2 2 Simulation with Process Model Step 5 We now need to tell Process Model that service times are exponential with mean 4. To do this, click on the Take Calls Process rectangle and fill in the dialog box as shown in Figure 6....
View Full Document
- Fall '10
- Exponential distribution, Cycle Time, process model, tire station