Dynamic Multi-Objective Evolutionary Algorithm Based on New Model

This paper presents an new approach in which the rank and density of the individual are firstly defined and then the ideal variance of rank and density variance of population are clearly given. The ideal variance of rank is a measure of the quality of solutions, and the density variance is a measure of the uniformity of the distribution of solutions. Using these two measures as two objective functions, the multi-objective optimization problems is finally converted into a two objective optimization problem. For the transformed problem, a novel dynamic multiobjective evolutionary algorithm based on new model is proposed. In designing the algorithm, the uniform distribution index function is integrated into the mutation operator to adaptively adjust the search. As a result, the solutions will gradually move to the entire Pareto front and their distribution will gradually become uniform. The proposed approach is validated by using five benchmark functions taken from the standard literature on evolutionary multi-objective optimization. Results indicate the approach that is highly competitive and it can be considered a viable alternative to solve multi-objective optimization problems.