An evolutionary dynamic multi-objective optimization algorithm based on center-point prediction and sub-population autonomous guidance

Dynamic multi-objective optimization problems (DMOPs) provide a challenge in that objectives conflict each other and change over time. In this paper, a hybrid approach based on prediction and autonomous guidance is proposed, which responds the environmental changes by generating a new population. According to the position of historical population, a part of the population is generated by predicting roughly and quickly. In addition, another part of the population is generated by autonomous guidance. A sub-population from current population evolves several generations independently, which guides the current population into the promising area. Compared with other three algorithms on a series of benchmark problems, the proposed algorithm is competitive in convergence and diversity. Empirical results indicate its superiority in dealing with dynamic environments.