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

基于多策略排序变异的多目标差分进化算法

Multi-objective differential evolution algorithm with multi-strategy and ranking-based mutation

免费全文下载 (已被下载 次)  
获取PDF全文
作者 艾兵,董明刚,敬超
机构 桂林理工大学 信息科学与工程学院,广西 桂林 541004
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2018)07-1950-05
DOI 10.3969/j.issn.1001-3695.2018.07.006
摘要 针对多目标差分进化算法求解多目标优化问题时收敛慢和均匀性欠佳等不足,提出了一种基于多策略排序变异的多目标差分进化算法。该算法利用基于排序变异算子来快速接近真实的Pareto最优解,同时引入多策略差分进化算子以保持种群的多样性;通过自适应策略动态调整控制参数以提高算法的鲁棒性,并且从理论证明的角度分析了所提算法的收敛性。仿真实验结果表明,该算法相对于近期相关文献中的改进算法具有更好的收敛性与多样性,从而表明了所提算法的有效性。
关键词 多目标优化;多策略差分进化;排序变异算子;自适应参数调整
基金项目 国家自然科学基金资助项目(61563012,61203109)
广西自然科学基金资助项目(2014GXNSFAA118371,2015GXNSFBA139260)
广西研究生教育创新计划资助项目(YCSZ2015165)
本文URL http://www.arocmag.com/article/01-2018-07-006.html
英文标题 Multi-objective differential evolution algorithm with multi-strategy and ranking-based mutation
作者英文名 Ai Bing, Dong Minggang, Jing Chao
机构英文名 SchoolofInformationScience&Engineering,GuilinUniversityofTechnology,GuilinGuangxi541004,China
英文摘要 Focused on slow convergence and poor uniformity of multi-objective differential evolution algorithm in solving multi-objective optimization problems, this paper put forward a multi-objective differential evolution algorithm with multi-strategy and ranking-based mutation. This algorithm took full advantage of ranking-based mutation operator to approximate the true Pareto optimal solutions quickly, and introduced the multi-strategy differential evolution operator to maintain the diversity of population. It adjusted the control parameters dynamically through the adaptive parameter adjustment to enhance the robustness. This paper analyzed the convergence of the proposed algorithm from the point of view of theoretical proof. Simulation results indicate that, compared with some recently proposed improved algorithms, the proposed algorithm has better convergence and diversity, which demonstrates the effectiveness of the proposed algorithm.
英文关键词 multi-objective optimization; multi-strategy differential evolution; ranking-based mutation operator; adaptive parameter adjustment
参考文献 查看稿件参考文献
  [1] 胡旺, Yen G G, 张鑫. 基于Pareto熵的多目标粒子群优化算法[J] . 软件学报, 2014, 25(5):1025-1050.
[2] 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.
[3] 王万良, 范丽霞, 徐新黎, 等. 多目标差分进化算法求解柔性作业车间批量调度问题[J] . 计算机集成制造系统, 2013, 19(10):2481-2492.
[4] Gholaminezhad I, Jamali A. A multi-objective differential evolution approach based on ε-elimination uniform-diversity for mechanism design[J] . Structural & Multidisciplinary Optimization, 2015, 52(5):861-877.
[5] Venske S M, Gonalves R A, Delgado M R. ADEMO/D:multi-objective optimization by an adaptive differential evolution algorithm[J] . Neurocomputing, 2014, 127(3):65-77.
[6] Rakshit P, Konar A. Extending multi-objective differential evolution for optimization in presence of noise[J] . Information Sciences, 2015, 305(6):56-76.
[7] Wang Yong, Cai Zixing. Combining multi-objective optimization with differential evolution to solve constrained optimization problems[J] . IEEE Trans on Evolutionary Computation, 2012, 16(1):117-134.
[8] Singh H, Srivastava L. Recurrent multi-objective differential evolution approach for reactive power management[J] . IET Generation, Transmission & Distribution, 2016, 10(1):192-204.
[9] Kotinis M. Improving a multi-objective differential evolution optimizer using fuzzy adaptation and K-mediods clustering[J] . Soft Computing, 2014, 18(4):757-771.
[10] Chen Xu, Du Wenli, Qian Feng. Multi-objective differential evolution with ranking-based mutation operator and its application in chemical process optimization[J] . Chemometrics & Intelligent Laboratory Systems, 2014, 136(8):85-96.
[11] 朱大林, 詹腾, 张屹, 等. 多策略差分进化的元胞多目标粒子群算法[J] . 电子学报, 2014, 42(9):1831-1838.
[12] 王亚辉, 吴金妹, 贾晨辉. 基于动态种群多策略差分进化模型的多目标进化算法[J] . 电子学报, 2016, 44(6):1472-1480.
[13] Wang Jiahai, Liao Jianjun, Zhou Ying, et al. Differential evolution enhanced with multi-objective sorting-based mutation operators[J] . IEEE Trans on Cybernetics, 2014, 44(12):2792-2805.
[14] 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.
[15] Cui Laizhong, Li Genghui, Lin Qiuzhen, et al. Adaptive differential evolution algorithm with novel mutation strategies in multiple subpopulations[J] . Computers & Operations Research, 2015, 67(3):155-173.
[16] 贺毅朝, 王熙照, 刘坤起, 等. 差分演化的收敛性分析与算法改进[J] . 软件学报, 2010, 21(5):875-885.
[17] 谢承旺, 丁立新. 多目标进化算法中多样性策略的研究[J] . 计算机科学, 2010, 37(2):175-179.
[18] Zou Hailin. An adaptive mutated multi-objective particle swarm optimization with an entropy-based density assessment scheme[J] . Journal of Information & Computational Science, 2013, 10(4):1065-1074.
[19] 施展, 陈庆伟. 基于QPSO和拥挤距离排序的多目标量子粒子群优化算法[J] . 控制与决策, 2011, 26(4):540-547.
[20] Coello C A C, Pulido G T, Lechuga M S. Handling multiple objectives with particle swarm optimization[J] . IEEE Trans on Evolutionary Computation, 2004, 8(3):256-279.
[21] Zitzler E, Thiele L, Laumanns M, et al. Performance assessment of multi-objective optimizers:an analysis and review[J] . IEEE Trans on Evolutionary Computation, 2003, 7(2):117-132.
收稿日期 2017/3/14
修回日期 2017/4/27
页码 1950-1954
中图分类号 TP301.6
文献标志码 A