K. Zielinski and R. Laur (Germany)
Differential Evolution, Adaptive Parameter Setting
Optimal settings for control parameters of the Differential Evolution algorithm depend on the considered optimiza tion problem and may also change during an optimization run. In this work an approach is suggested that adaptively controls the parameters F and CR that influence the muta tion and recombination processes in Differential Evolution. By application of Design of Experiments methods signifi cant differences in performance due to different parameter settings can be detected during an optimization run. Ad ditionally, interaction effects of the parameters are discov ered. By changing the parameter settings on the basis of these results, feedback from the current state of the opti mization run is taken into account. The method is tested using a constrained single-objective optimization problem. A comparison with another study using the same problem with tuned fixed parameter values shows promising results.
Important Links:
Go Back
