Rockwell Automation Arena OptQuest Users Guide - Manual (Page 49)

5 • O PTIMIZATION T IPS AND S UGGESTIONS
45
•
•
•
• •
5
• T
ips and Sug
gest
io
ns
OptQuest makes finding a feasible solution its highest priority. Once it has found a feasible
solution, then it concentrates on finding better solutions. For further details on feasibility,
see “Constraints” on page 22.
Number of replications and simulations
When OptQuest runs an optimization, it uses an Arena simulation to evaluate each set of
control values. The quality of the optimization results therefore depends on the number of
simulations and the number of replications per simulation.
For a set period of time, the number of replications per simulation is inversely related to
the number of simulations; as you increase one, the other decreases. Using the option to
vary the number of replications can help increase the number of simulations.
The more simulations OptQuest can run, the more sets of values it can evaluate, and the
more likely it is to find a solution close to the optimal solution.
Simulation accuracy
There are two factors that affect simulation accuracy:
„
Number of replications
„
Noisiness of the objective
N UMBER OF REPLICATIONS PER SIMULATION
For sufficient accuracy, you must set the number of replications to the minimum number
necessary to obtain a reliable estimate of the statistic being optimized. The minimum
number is typically found with empirical testing.
O BJECTIVE NOISINESS
Noisiness can also affect the accuracy of your OptQuest results.