Otimizador de Enxame da Ratazana Implementado na Identificação de um Sistema MIMO

Allan Christian Krainski Ferrari; Gideon Villar Leandro; Leandro dos Santos Coelho; Carlos A. Gouvea da Silva; Douglas Antonio Firmino Pelacini; Cristiano Osinski

doi:10.20906/sbai.v1i1.2734

Allan Christian Krainski Ferrari Centro Universitário UNIFACEAR, Araucária, Paraná
Gideon Villar Leandro Departamento de Engenharia Elétrica, Universidade Federal do Paraná, Curitiba, Paraná
Leandro dos Santos Coelho Departamento de Engenharia Elétrica, Pontifícia Universidade Católica do Paraná, Curitiba, Paraná
Carlos A. Gouvea da Silva Centro Universitário UNIFACEAR, Araucária, Paraná
Douglas Antonio Firmino Pelacini Departamento de Engenharia Elétrica, Universidade Federal do Paraná, Curitiba, Paraná
Cristiano Osinski Departamento de Engenharia Elétrica, Universidade Federal do Paraná, Curitiba, Paraná

DOI: https://doi.org/10.20906/sbai.v1i1.2734

Keywords: Rats, metaheuristics, identification, MIMO system, hypothesis test

Abstract

This article implements a new metaheuristic called the rat swarm optimizer (RSO) in the process of identification of a real multivariable system. The ability to solve global optimization problems of this algorithm was analyzed for a sequence of 100 runs. In simulation, the values of the multiple correlation coefficient and the mean square error were obtained, which were used to analise the quality of the identification process. The performance RSO was compared with other metaheuristics such as the gray wolf optimizer (GWO), whale optimization algorithm (WOA), particle swarm optimization (PSO) and differential evolution (DE). The results show that RSO can be an alternative method to be used effectively in processes of identification of real multivariable systems.