Particle Swarm Optimization Versus Genetic Algorithms for Phased Array Synthesis

TLDR

Particle swarm optimization is a high‑performance, easy‑to‑implement optimizer similar to genetic algorithms but with less computational overhead. The study implements a particle swarm optimizer and compares it to a genetic algorithm for synthesizing phased arrays with far‑field sidelobe notches using amplitude‑only, phase‑only, and complex tapering. The authors applied both algorithms to phased array synthesis problems, evaluating their performance across different tapering schemes. The results show that PSO performs better in some scenarios while GA performs better in others, indicating different traversal of the hyperspace, and that PSO’s simpler implementation offers strong potential for widespread use in electromagnetic optimization.

Abstract

Particle swarm optimization is a recently invented high-performance optimizer that is very easy to understand and implement. It is similar in some ways to genetic algorithms or evolutionary algorithms, but requires less computational bookkeeping and generally only a few lines of code. In this paper, a particle swarm optimizer is implemented and compared to a genetic algorithm for phased array synthesis of a far-field sidelobe notch, using amplitude-only, phase-only, and complex tapering. The results show that some optimization scenarios are better suited to one method versus the other (i.e., particle swarm optimization performs better in some cases while genetic algorithms perform better in others), which implies that the two methods traverse the problem hyperspace differently. The particle swarm optimizer shares the ability of the genetic algorithm to handle arbitrary nonlinear cost functions, but with a much simpler implementation it clearly demonstrates good possibilities for widespread use in electromagnetic optimization.