Cooperative Coevolutionary Particle Swarms using Fuzzy Logic for Large Scale Optimization

A cooperative coevolutionary framework can improve the performance of optimization algorithms on large-scale problems. In this paper, we propose a new Cooperative Coevolutionary algorithm to improve our preliminary work, FuzzyPSO2. This new proposal, called CCFPSO, uses the random grouping technique that changes the size of the subcomponents in each generation. Unlike FuzzyPSO2, CCFPSO’s re-initialization of the variables, suggested by the fuzzy system, were performed on the particles with the worst fitness values. In addition, instead of updating the particles based on the global best particle, CCFPSO was updated considering the personal best particle and the neighborhood best particle. This proposal was tested on large-scale problems that resemble real-world problems (CEC2008, CEC2010), where the performance of CCFPSO was favorable in comparison with other state-of-the-art PSO versions, namely CCPSO2, SLPSO, and CSO. The experimental results indicate that using a Cooperative Coevolutionary PSO approach with a fuzzy logic system can improve results on high dimensionality problems (100 to 1000 variables).