自适应偏好半径划分区域的多目标进化方法

Multi-Objective Evolutionary Algorithm for Adaptive Preference Radius to Divide Region

偏好多目标进化算法是一类帮助决策者找到感兴趣的Pareto最优解的算法.目前,在以参考点位置作为偏好信息载体的偏好多目标进化算法中,不合适的参考点位置往往会严重影响算法的收敛性能,偏好区域的大小难以控制,在高维问题上效果较差.针对以上问题,通过计算基于种群的自适应偏好半径,利用自适应偏好半径构造一种新的偏好关系模型,通过对偏好区域进行划分,提出基于偏好区域划分的偏好多目标进化算法.将所提算法与4种常用的以参考点为偏好信息载体的多目标进化算法g-NSGA-II、r-NSGA-II、角度偏好算法、MOEA/D-PRE进行对比实验,结果表明,所提算法具有较好的收敛性能和分布性能,决策者可以控制偏好区域大小,在高维问题上也具有较好的收敛效果.

The preference-based multi-objective evolutionary algorithms are the sort of evolutionary algorithms to assist the decision maker （DM） in finding interesting Pareto optimal solutions. At present, the inappropriate locations of the reference points sometimes seriously impact the convergence performance of the algorithms when the locations of the reference points are used as the preference information during the optimization. Moreover, the size of the preferred region is difficult to control. And the comprehensive performance of the algorithms will degrade in dealing with many-objective problems. To address the above issues, in this paper, the self-adjustable preference-based radius is calculated to build a new preference relation model, and by dividing region of interest （ROI）, a preference-based multi-objective evolutionary algorithm based on the division of RoI is proposed. The proposed algorithm is compared with four reference point based multi-objective evolutionary algorithms （g-NSGA-II, r-NSGA-II, angle-based preference algorithm and MOEA/D-PRE）. The results show that the proposed algorithm has good convergence and diversity, and at meantime allows the DM control the size of the preferred region. In addition it has a good convergence in addressing the many-objective problems.