A Novel PSO-DE Co-evolutionary Algorithm Based on Decomposition Framework

Comparing with single-population optimization, co-evolution has more benefits in tackling multi-objective optimization problems, as different evolutionary algorithms can work collaboratively. This paper presents a new co-evolution algorithm which employs three populations and integrates particle swarm optimization (PSO) and differential evolution (DE) into the framework of decomposition, named MODEPSO. The main contribution is that the elite solutions got by PSO and archive evolution are considered as evolutionary candidates which will be further evolved by DE operation, so PSO and DE operators can work collaboratively. Experimental results indicate that MODEPSO has better performance than the compared algorithms.