New evolutionary algorithm for dynamic multiobjective optimization problems

In this paper, a new evolutionary algorithm for dynamic multi-objective optimization problems(DMOPs) is proposed. first, the time period is divided into several equal subperiods. In each subperiod, the DMOPs is approximated by a static multi-objective optimization problem(SMOP). Second, for each SMOP, the static rank variance and the static density variance of the population are defined. By using the two static variance of the population, each SMOP is transformed into a static bi-objective optimization problem. Third, a new evolutionary algorithm is proposed based on a new mutation operator which can automatically check out the environment variation. The simulation results indicate the proposed algorithm is effective.