A memetic algorithm for multi-objective optimization problems with interval parameters
Dunwei Gong, Zhuang Miao, Jing Sun · 2016
Multi-objective optimization problems with interval parameters (IMOPs) are ubiquitous in real-world applications. The existing evolutionary algorithms for IMOPs (IMOEAs) require a large amount of function evaluations to generate an approximate Pareto front which is well converged and evenly distributed, and the generated front has uncertainties to a large extent. In this paper, a local search is embedded into an existing IMOEA, and a memetic algorithm for IMOPs is developed. The existing IMOEA is first employed to search the entire search space, and then the rate of changes of hypervolume is utilized to design an activation mechanism to specify when to conduct the local search. Finally, an initial population of the local search is created by taking the individuals with a large contribution to hypervolume and a small imprecision as the center, and the local search is implemented by taking the contribution to hypervolume as its fitness function. The proposed algorithm is applied to six benchmark IMOPs and an uncertain optimization problem of solar desalination, and compared with a typical IMOEA without the local search. The empirical results indicate the effectiveness of the proposed algorithm.