Microsoft Office Tutorials and References
In Depth Information
2. The relative proportion of the type of service that is assigned to autos will remain
constant over time and it is applied to autos arriving as follows: 40% of autos
arrivals will request service type Engine/electrical Diagnosis ; 25% will request
Mechanical Diagnosis ; and 35% will request Oil Change .
3. We will assume that the portion of the parking lot that is allocated to the new
business is sufficiently large to handle any days demand without causing autos to
balk (arrive and then leave). By not restricting the capacity of the parking lot, we
reduce the complexity of the model, but we also eliminate the possibility of using
the model to answer various questions. For example, we may want to consider
how we would utilize a limited and costly lot capacity among the various services
Inez provides. A variable lot capacity is clearly a more sophisticated modeling
condition than we are currently considering.
4. Balancing the demand for service with the supply of service will be an important
issue for Inez to consider. Customer demand that is greatly in excess of service
supply can lead to customers spending inordinate amounts of time waiting and
subsequently the potential loss of customers. Conversely, if demand is far less
than supply, then the costs of operation can easily exceed the revenue generated
leading to low profits or losses.
As we consider these issues, we can construct more flexible and sophisticated
models, but at the cost of greater modeling complexity. The decision of how much
complexity is needed should be made in light of Inez’s goals for the simulation
analysis.
8.5.2 Building the Brain Worksheet
Exhibit 8.17, the Brain worksheet, shows the results of our discussion of the arrival
process. The Brain contains all the pertinent parameters and data to later supply
our Calculation and Data Collection worksheets. Note that the worksheet has 5
major categories of information: Arrival Data-Cumulative Probability Distribution ,
Selection of Arrival Order , Type of Service , Service Times Distributions , and Wor ke r
Assumptions . As in Exhibit 8.10, 8.17 contains a table of calculations based on
the cumulative Poisson distribution for the three customer categories: Corporate
Client, Police, and US Mail. The arrival period is divided into two distinct periods of
arrival—5:00–7:00 a.m. and 7:00–9:00 a.m. I have assumed Poisson average hourly
arrival rates in the two time periods of [2, 2], [2, 1], and [1, 1] for Corporate Clients,
Police, and US Mail, respectively. For example, cells B5 and C5 show the average
arrival rates for Corporate Clients in the 5:00–7:00 period, 2 per hour, and in the
7:00–9:00 period, 2 per hour. The values in the table for the range B7:G18 are the
corresponding cumulative Poisson probabilities for the various average arrival rates
for all types of clients and times periods. The cell comment for G9 provides the
detail for the formula used to determine the cumulative Poisson probability.
Search JabSto ::




Custom Search