Many-Objective Optimization of Antenna Arrays Using an Improved Multiple-Single-Objective Pareto Sampling Algorithm

Pareto-based multiobjective evolutionary algorithms are recognized as the standards for solving multiobjective antenna design problems. However, when the number of objectives exceeds three, these algorithms always exhibit deficiencies in searching the Pareto front. To eliminate these deficiencies, several algorithms, such as Hyper-volume Estimation (HypE) algorithm and Multiple-Single-Objective Pareto Sampling (MSOPS) algorithm, are introduced. In this letter, an improved MSOPS algorithm is proposed. The numerical results on many-objective optimal designs of a linear antenna array and a Yagi-Uda array have demonstrated that the proposed algorithm outperforms its ancestor, NSGA II, and HypE as well.