《计算机应用研究》|Application Research of Computers

基于动态多策略差分进化模型的MOEA/D算法

MOEA/D based on dynamic multi-strategy differential evolution model

免费全文下载 (已被下载 次)  
获取PDF全文
作者 林震,侯杏娜,韦晓虎
机构 桂林电子科技大学 教学实践部,广西 桂林 541004
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2017)09-2624-05
DOI 10.3969/j.issn.1001-3695.2017.09.013
摘要 在基于分解技术的多目标进化算法的框架中,引入一种动态多策略差分进化模型。该模型在分析不同差分进化策略的特点基础上,选择了三种差分进化策略,并对每种策略分配一子种群。在进化过程中,依据每种策略对邻域更新的贡献度,动态地调整其子种群的大小。对比分析采用不同差分进化算法的性能,结果表明运用多个策略之间相互协同进化,有利于提高算法性能。将新算法同NSGA-Ⅱ与MOEA/D算法在LZ09系列基准函数上进行性能对比,实验结果显示该算法的收敛性和多样性均优于对比算法。将新应用于Ⅰ型梁多目标优化设计问题中,获得的Pareto前沿均匀,且解集域较宽广,对比分析表明了算法的工程实用性。
关键词 MOEA/D;多目标优化;多策略差分进化;动态子种群;I型梁设计
基金项目 国家自然科学基金资助项目(61261017)
桂林电子科技大学教育教学改革项目(JGB201431,JGB201530,ZJW43030)
本文URL http://www.arocmag.com/article/01-2017-09-013.html
英文标题 MOEA/D based on dynamic multi-strategy differential evolution model
作者英文名 Lin Zhen, Hou Xingna, Wei Xiaohu
机构英文名 Dept.ofExperientialPractice,GuilinUniversityofElectronicTechnology,GuilinGuangxi541004,China
英文摘要 In the framework of multi-objective evolutionary algorithm based on decomposition (MOEA/D), this paper introduced a dynamic multi-strategy differential evolution model (MOEA/D-DMDE). The model chose three differential evolution strategies and each sub-population was corresponding to a differential evolution strategy based on the analysis of the characteri-stics of different strategies. In order to improve the performance of the algorithm, it adjusted the size of sub-population dynamically on the basis of a differential evolution strategy contribution for updated of neighborhood.It adopted each strategy to participate in coordination during the evolution process. Via the comparative analysis of different schemes of differential strategy, MOEA/D-DMDE also performed well. Comparing with NSGA-Ⅱ and MOEA/D on the LZ09 benchmarks, the experimental results indicate that MOEA/D-DMDE has a better performance in terms of convergence and diversity. To validate its perfor-mance on constraint multi-objective optimization problems, the proposed MOEA/D-DMDE is applied for solving the Ⅰ-Beam. The uniformly distributed Pareto sets obtained by MOEA/D-DMDE show its practicability for engineering problems.
英文关键词 MOEA/D; multi-objective optimization; multi-strategy differential evolution; dynamic subpopulation; I-Beam design
参考文献 查看稿件参考文献
  [1] Zhang Qingfu, Li Hui. MOEA/D:a multi-objective evolutionary algorithm based on decomposition[J] . IEEE Trans on Evolutionary Computation, 2007, 11(6):712-731.
[2] Li Hui, Landa-Silva D. An adaptive evolutionary multi-objective approach based on simulated annealing[J] . Evolutionary Computation, 2011, 19(4):561-595.
[3] Moubayed N, Petrovski A, McCall J. A novel multi-objective particle swarm optimization based on decomposition[C] //Proc of International Conference on Parallel Problem Solving from Nature. 2010:1-10.
[4] Zapotecas-Martinez S, Coello C A C. A multi-objective particle swarm optimizer based on decomposition[C] // Proc of Genetic and Evolutionary Computation Conference. 2011:69-76.
[5] 张冬梅, 龚小胜, 戴光明, 等. 求解复杂多目标优化问题MOEA/D-GEP算法[J] . 华中科技大学学报:自然科学版, 2012, 40(4):33-36.
[6] Zhang Qingfu, Li Hui, Maringer D, et al. MOEA/D-DE with NBI-style Tchebycheff approach for portfolio management[C] // Proc of IEEE Congress on Evolutionary Computation. 2010:1-8.
[7] Ishibuchi H, Sakane Y, Tsukamoto N, et al. Adaptation of scalarizing functions in MOEA/D-DE:an adaptive scalarizing function-based multi-objective evolutionary algorithm[C] // Proc of International Conference on Evolutionary Multi-Criterion Optimization. 2009:438-452.
[8] Ishibuchi H, Sakane Y, Tsukamoto N, et al. Simultaneous use of different scalarizing functions in MOEA/D-DE[C] // Proc of Genetic and Evolutionary Computation Conference. 2010:519-526.
[9] Tan Yanyan, Jiao Yongchang, Li Hong, et al. MOEA/D+uniform design:a new version of MOEA/D for optimization problems with many objectives[J] . Computer & Operations Research, 2013, 40(6):1648-1660.
[10] Ma Xiaoliang, Qi Yutao, Li Lingling, et al. MOEA/D with uniform decomposition measurement for many-objective problems[J] . Soft Computing, 2014, 18(12):2541-2564.
[11] Gu Fangqing, Liu Hailin. A novel weight design in multi-objective evolutionary algorithm[C] // Proc of International Conference on Computational Intelligence and Security. 2010:137-141.
[12] Qi Yutao, Ma Xiaoliang, Liu Fang, et al. MOEA/D with adaptive weight adjustment[J] . Evolutionary Computation, 2014, 22(2):231-264.
[13] Li Hui, Zhang Qingfu. Multi-objective optimization problems with complicated Pareto sets, MOEA/D and NSGA-Ⅱ[J] . IEEE Trans on Evolutionary Computation, 2009, 13(2):284-302.
[14] 周爱民, 张青富, 张桂戌. 一种基于混合高斯模型的多目标进化算法[J] . 软件学报, 2014, 25(5):913-928.
[15] Chen C M, Chen Yingping, Zhang Qingfu. Enhancing MOEA/D with guided mutation and priority update for multi-objective optimization[C] // Proc of IEEE Congress on Evolutionary Computation. 2009:209-216.
[16] Huang Waibin, Li Hui. On the differential evolution schemes in MOEA/D[C] //Proc of the 6th International Conference on Natural Computation. 2010:2788-2792.
[17] Li Hui, Landa-Silva D. An adaptive evolutionary multi-objective approach based on simulated annealing[J] . Evolutionary Computation, 2011, 19(4):561-595.
[18] 毕晓君, 肖婧. 基于自适应差分进化的多目标进化算法[J] . 计算机集成制造系统, 2011, 17(12):2660-2665.
[19] Miettinen K. Nonlinear multi-objective optimization[C] //Proc of International Series in Operations Research & Management Science. 1999.
[20] Das I, Dennis J E. Normal-boundary intersection:a new method for ge-nerating the Pareto surface in conlinear multicriteria optimization problems[J] . SIAM Journal on Optimization, 1998, 8(3):631-657.
[21] Messac A, Ismail-Yahaya, Mattson C A. The normalized constraint method for generating the Pareto frontier[J] . Structural and Multidisciplinary Optimization, 2003, 25(2):86-98.
[22] Zhang Jingqiao, Sanderson A C. JADE:adaptive differential evolution with optional external archive[J] . IEEE Trans on Evolutionary Computation, 2009, 13(5):945-958.
[23] Zitzler E, Thiele L. Multi-objective evolutionary algorithms:a comparative case study and the strength Pareto approach[J] . IEEE Trans on Evolutionary Computation, 1999, 3(4):257-271.
[24] Bosman T, Thierens D. The balance between proximity and diversity in multi-objective evolutionary algorithms[J] . IEEE Trans on Evolutionary Computation, 2003, 7(2):174-188.
[25] Deb K, Pratap A, Agarwal S, et al. A fast and elitist multi-objective genetic algorithm:NSGA-Ⅱ[J] . IEEE Trans on Evolutionary Computation, 2002, 6(2):182-197.
[26] Zou Feng, Wang Lei, Hei Xinhong, et al. Multi-objective optimization using teaching-learning-based optimization algorithm[J] . Engineering Applications of Artificial Intelligence, 2013, 26(4):1291-1300.
[27] Deb D K, Agrawal R B. Simulated binary crossover for continuous search space[J] . Complex Systems, 1995, 9(2):115-148.
收稿日期 2016/6/28
修回日期 2016/8/22
页码 2624-2628
中图分类号 TP18;TP301.6
文献标志码 A