Microsoft Office Tutorials and References
In Depth Information
Exhibit 8.17 Brain worksheet for model parameters and assumptions
The order of customer arrival is also important in our model, and each customer
arrives as a group in a period; that is, a caravan of Police autos might arrive at
Autohaus in the 5:00–7:00 time period. The Selection of Arrival Order table pro-
vides the six possible combinations of arrival orders for the three clients, and is the
result of some subjective opinion by Wolfgang. For example, there is a 40% chance
that the precise order of arrival in a period will be Corporate Client first, Police
second, and USMail third. As you can see, the CorporateClient is very likely to
be the first to arrive in the morning, with a 60% (40+20%) chance of being first
overall. Order will be important when Inez begins to examine which of the vari-
ous clients does not receive service should a day’s demand be greater than service
supply.
The table entitled Type of Service provides the mix or service types for the
arrivals. Notice it is deterministic: a fixed or non-probabilistic value. Thus, it is not
necessary to resolve uncertainty for this model factor. If 20 autos arrive in a period
of time, 8 (20 0.4) will be assigned to Engine/electrical Diagnosis ,5(20 0.25) to
Mechanical Diagnosis , and 7 (20 0.35) to Oil Change . If Inez anticipated a great
deal of variation in the short term service types, then it might be wise to deter-
mine a distribution for the service types that can be sampled, as we did for arrival
order. Service could also be seasonal, with certain types of service, for example
engine/electrical diagnosis, occurring more frequently in a particular season. Our
model handles service type quite simply and, certainly, more sophisticated models
could be constructed.
Search JabSto ::




Custom Search