New operators for multi-objective clonal selection algorithms
Lucas S. Batista, Jaime Arturo Ramírez, Frederico Gadelha Guimarães · COMPEL The International Journal for Computation and Mathematics in Electrical and Electronic Engineering · 2009
Purpose The purpose of this paper is to present a new multi-objective clonal selection algorithm (MCSA) for the solution of electromagnetic optimization problems. Design/methodology/approach The method performs the somatic hypermutation step using different probability distributions, balancing the local search in the algorithm. Furthermore, it includes a receptor editing operator that implicitly realizes a dynamic search over the landscape. Findings In order to illustrate the efficiency of MCSA, its performance is compared with the nondominated sorting genetic algorithm II (NSGA-II) in some analytical problems and in the well-known TEAM benchmark Problem 22. Three performance evaluation techniques are used in the comparison, and the effect of each operator of the MCSA in its accomplishment is estimated. Research limitations/implications In the analytical problems, the MCSA enhanced both the extension and uniformity in its solutions, providing better Pareto-optimal sets than the NSGA-II. In the Problem 22, the MCSA also outperformed the NSGA-II. The MCSA was not dominated by the NSGA-II in the three variables case and clearly presented a better convergence speed in the eight variables problem. Practical implications This paper could be useful for researchers who deal with multi-objective optimization problems involving high-computational cost. Originality/value The new operators incorporated in the MCSA improved both the extension, uniformity and the convergence speed of the solutions, in terms of the number of function evaluations, representing a robust tool for real-world optimization problems.