Aplicación de PSO y GAs a la síntesis de agrupaciones lineales de antenas

Abstract

Genetic algorithms (GAs) and Particle Swarm Optimization (PSO) are commonly used to solve many optimization and synthesis problems. An important issue facing the user is the selection of their parameters, such as crossover and mutation strategies and rates in GAs, or the population size and boundary conditions in PSO. This paper shows an exhaustive process to obtain those parameters and demonstrates that PSO is more efficient than the real-valued GA when both are applied to linear array synthesis. PSO, with less computational burden and generally fewer lines of code than GAs, turns out to be a more efficent algorithm for the design problem analyzed.