Automatic construction of fuzzy controllers for evolutionary multiobjective optimization algorithms

We present techniques for designing fuzzy systems for controlling the behavior of multiobjective evolutionary algorithms. The aim of this work is to develop methods for improving the performance and understanding the behavior of multiobjective evolutionary algorithms. Because the output of a multiobjective optimization algorithm is a set rather than a single point, we present a search performance metric based on a set quality measure. According to this set quality measure, we demonstrate our techniques by developing fuzzy control strategies for a genetic algorithm based IC placement application