Rockwell Automation Arena OptQuest Users Guide - Manual (Page 5)

1
1
1 •
W
elc
ome
Welcome to OptQuest for Arena
What is OptQuest for Arena?
OptQuest enhances the analysis capabilities of Arena by allowing you to search for
optimal solutions within your simulation models. Many simulation models are embedded
in the broader context of a decision problem, where the ultimate goal is to determine the
best values for a set of controls. For example, you might be interested in having a model
help you select a staffing configuration that optimizes some performance objective. One
of the limitations of simulation models in general is that they basically act as “black
boxes”—they can only evaluate the model for the controls that you’ve specified. Thus, to
use a simulation model for evaluating the performance of a process, you must first select
the specific staffing levels and then run a simulation to forecast the performance of that
particular configuration.
Without an appropriate tool, finding an optimal solution for a simulation model generally
requires that you search in a heuristic or ad hoc fashion. This usually involves running a
simulation for an initial set of decision variables, analyzing the results, changing one or
more variables, re-running the simulation, and repeating this process until a satisfactory
solution is obtained. This process can be very tedious and time consuming even for small
problems, and it is often not clear how to adjust the controls from one simulation to the
next.
OptQuest overcomes this limitation by automatically searching for optimal solutions
within Arena simulation models. You describe your optimization problem in OptQuest,
then let it search for the values of controls that maximize or minimize a predefined
objective. Additionally, OptQuest is designed to find solutions that satisfy a wide variety
of constraints that you may define. Best of all, you don’t need to learn about the details of
optimization algorithms to use it.
What does OptQuest do to my Arena model?
OptQuest automates, or controls, Arena to set variable values, start and continue simula-
tion runs, and retrieve simulation results. The interface between the two programs is
implemented using the Arena COM object model, which is also available to Arena users
through VBA, Visual Basic
® , and other development tools.
When OptQuest is launched, it checks the Arena model and loads information from the
model, including the defined controls and responses, into its own database. The user then
proceeds to define the optimization problem using OptQuest’s explorer interface.
When an optimization runs, OptQuest starts the simulation by issuing a start-over
command. It then changes the values of the control variables and resource capacities to
those identified by OptQuest for the simulation scenario. Next, OptQuest instructs Arena
to perform the first replication.