LAUSR

Abstract Evolutionary algorithms are optimization methods commonly used to solve engineering and business optimization problems. The parameters in evolutionary algorithm must be perfectly tuned in a way that the optimization algorithm solves the optimization problems efficiently and effectively. Several parameter tuning approaches with a single performance metric have been proposed in the literature. However, simultaneous consideration of multiple performance metrics could provide the optimal setting for the parameters in the evolutionary algorithm. In this research, a new hybrid parameter tuning approach is proposed to simultaneously optimize the performance metrics of the evolutionary optimization algorithm while it is used in solving an optimization problem. The proposed hybrid approach provides the optimal value of parameters of the evolutionary optimization algorithm. The proposed approach is the first parameter tuning approach in the evolutionary optimization algorithm which simultaneously optimizes all performance metrics of the evolutionary optimization algorithm. To do this, a full factorial design of experiment is used to find the significant parameters of the evolutionary optimization algorithm, as well as an approximate equation for each performance metric. The individual and composite desirability function approaches are then proposed to provide the optimal setting for the parameters of the evolutionary optimization algorithm. For the first time, we use the desirability function approach to find an optimal level for the parameters in the evolutionary optimization algorithm. To show the real application of the proposed parameter tuning approach, we consider two multi-objective evolutionary algorithms, i.e., a multi-objective particle swarm optimization algorithm (MOPSO) and a fast non-dominated sorting genetic algorithm (NSGA-III) and solve a single machine scheduling problem. We demonstrate the applicability and efficiency of the proposed hybrid approach in providing the optimal values of all parameters of the evolutionary optimization algorithms to optimize their performance in solving an optimization problem.