一种基于综合引导的偏好多目标优化算法-中南大学学报.PDFVIP

第 47 卷第 9 期 中南大学学报( 自然科学版) Vol.47 No.9 2016 年 9 月 Journal of Central South University (Science and Technology) Sep. 2016 DOI: 10.11817/j.issn.1672-7207.2016.09.022 一种基于综合引导的偏好多目标优化算法 戴永彬 (辽宁工业大学 软件学院，辽宁 锦州，121001) 摘要：针对多目标优化的偏好问题，提出一种综合引导的偏好多目标优化粒子群算法(IG−MOPSO) 。该算法的核 心思想是将多目标优化策略的参考点算法和参考区域算法结合在一起。在参考点移动的过程中，动态调整参考区 域面积。经过每一次的迭代计算，该算法可不断调整参考点从而获得更优的偏好解，同时借助参数 d 控制偏好的 范围。另外，采用 g−支配改进全局最优粒子的选取方法，提高搜索的有效性。研究结果表明：本文提出的算法是 可行、有效的。 关键词：多目标优化；偏好区域；粒子群；综合引导 中图分类号：TP301 文献标志码：A 文章编号：1672−7207(2016)09−3072−07 Preference multi-objective optimization algorithm with integrated guidance DAI Yongbin (School of Software, Liaoning University of Technology, Jinzhou 121001, China) Abstract: A preference multi-objective particle swarm optimization algorithm (IG−MOPSO) with integrated guidance for multi-objective optimization problem was proposed. The main ideas of the algorithm were to combine the notion of reference point with reference region. With the movement of reference points, the area of the reference regions was adjusted dynamically. The reference point was modified by the algorithm to refine the preferences through every iterative calculation, and the parameter d was set to control the reference range simultaneously. By means of g−dominance, the choosing method of best modes of particle swarm optimization was improved, and the effectiveness of the search was also enhanced. The results show that the presented algorithm has good feasibility and effectiveness. Key words: multi-objective optimization; preference region