用于约束多目标优化问题的双群体差分进化算法

A Differential Evolution Based on Double Populations for Constrained Multi-Objective Optimization Problem

首先给出一种改进的差分进化算法,然后提出一种基于双群体搜索机制的求解约束多目标优化问题的差分进化算法.该算法同时使用两个群体,其中一个用于保存搜索过程中找到的可行解,另一个用于记录在搜索过程中得到的部分具有某些优良特性的不可行解,避免了构造罚函数和直接删除不可行解.此外,文中算法、NSGA-Ⅱ和SPEA的时间复杂度的比较表明,NSGA-Ⅱ最优,文中算法与SPEA相当.对经典测试函数的仿真结果表明,与NSGA-Ⅱ相比较,文中算法在均匀性及逼近性方面均具有一定的优势.

An improved differential evolution approach is given first, and a new algorithm based on double populations for Constrained Multi-objective Optimization Problem （CMOP） is presented. In the proposed algorithm, two populations are adopted, one is for the feasible solutions found during the evolution, and the other is for infeasible solutions with better performance which are allowed to participate in the evolution with the advantage of avoiding difficulties such as constructing penalty function and deleting infeasible solutions directly. In addition, the time complexity of the proposed algorithm, NSGA-Ⅱ and SPEA are compared, which show the best is NSGA-Ⅱ , followed by SPEA and the proposed algorithm simultaneously. The experiments on benchmarks indicate that the proposed algorithm is superior to NSGA-Ⅱ in the measure of GD and SP.