Evolutionary multi-objective optimization using expected improvement and generalized DEA

Evolutionary optimization methods, for example genetic algorithms have been applied for solving multi-objective optimization problems, and have been observed to be useful for generating Pareto optimal solutions. In order to improve the convergence and the diversity in the search, this paper suggests a recombination method using the expected improvement (EI) and generalized data envelopment analysis (GDEA) in real-coded multi-objective genetic algorithms. In addition, the effectiveness of the proposed method will be investigated through several numerical examples in comparison with the conventional methods.