<-上一篇/Previous Article 下一篇/Next Article->

[1]钱淑渠,张著洪.动态多目标免疫优化算法及性能测试研究[J].智能系统学报,2007,2(5):68-77.
　QIAN Shu-qu,ZHANG Zhu-hong.Dynamic multiobjective immune optimization algorithm 〖JZ〗and performance test[J].CAAI Transactions on Intelligent Systems,2007,2(5):68-77.

点击复制

动态多目标免疫优化算法及性能测试研究

PDF下载 HTML

《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷: 2 期数: 2007年第5期页码: 68-77 栏目: 学术论文—人工智能基础出版日期: 2007-10-25

Title:: Dynamic multiobjective immune optimization algorithm 〖JZ〗and performance test

文章编号:: 1673-4785(2007)05-0068-10

作者:: 钱淑渠^1，2，张著洪^1; 1. 贵州大学理学院，贵州贵阳550025;
2.贵州安顺学院数学系，贵州安顺561000

Author(s):: QIAN Shu-qu^1,2, ZHANG Zhu-hong¹; 1．College of Science, Guizhou University, Guizhou 550025， China;
2．Department of Mathematics, Anshun College， Anshun 561000， China

关键词:: 动态多目标优化; 时变 Pareto面; 环境跟踪; 自适应 ζ邻域; 免疫算法 

Keywords:: dynamic multiobjective optimization; timevarying Pareto front; en vironment tracking; adaptive neighborhood; immune algorithm.

分类号:: TP301.6

文献标志码:: A

摘要:: 基于生物免疫系统的自适应学习、免疫记忆、抗体多样性及动态平衡维持等功能, 提出一种动态多目标免疫优化算法处理动态多目标优化问题. 算法设计中, 依据自适应ζ邻域及抗体所处位置设计抗体的亲和力，基于Pareto控制的概念，利用分层选择确定参与进化的抗体，经由克隆扩张及自适应高斯变异,提高群体的平均亲和力，利用免疫记忆、动态维持和Average linkage聚类方法, 设计环境识别规则和记忆池，借助3种不同类型的动态多目标测试问题,通过与出众的动态环境优化算法比较, 数值实验表明所提出算法解决复杂动态多目标优化问题具有较大潜力.

Abstract:: A dynamic multiobjective immune optimization algorithm suitable for d ynamic multiobjective optimization problems is proposed based on the functions of adaptive learning, immune memory, antibody diversity and dynamic balance main tenance, etc. In the design of the algorithm, the scheme of antibody affinity w a s designed based on the locations of adaptiveneighborhood and antibody; ant i bodies participating in evolution were selected by Pareto dominance. In order to enhance the average affinity of the population, clonal proliferation and adapti ve Gaussian mutation were adopted to evolve excellent antibodies. Furthermore, t he average linkage method and several functions of immune memory and dynamic bal ance maintenance were used to design environmental recognition rules and the mem ory pool. The proposed algorithm was compared against several popular multiobj e ctive algorithms by means of three different kinds of dynamic multiobjective b e nchmark problems. Simulations show that the algorithm has great potential in s olving dynamic multiobjective optimization problems. 

参考文献/References:: ［1］BINGUL Z. Adaptive genetic algorithms applied to dynamic multiobjective pr oblems［J］. Applied Soft Computing，7(2007) 791-799.
［2］FARINA M, DEB K, AMATO P. Dynamic multiobjective optimization problems: te st case, approximations, and applications［J］. IEEE Transactions on Evolutionary Computation, 2004, 8(5): 425-442.
［3］ZITZLER E, LAUMANNS M, THIELE L. Speaii: improving the strength pareto evo lu tionary algorithm［A］. Evolutionary Methods for Design, Optimization and Contro l with Applications to Industrial Problems［C］. Athens, Greece, 2001.
［4］DEB K, AGRAWAL S, PRATAP A, et al. A fast elitist nondominated sorting gen et ic algorithm for multiobjective optimization: NSGAII［J］. IEEE Transactions o n Evolutionary Computation, 2002, 6(2): 182-197.
［5］JIN Y, BRANKE J. Evolutionary optimization in uncertain environmentsA sur vey［J］. IEEE Transactions on Evolutionary Computation, 2005, 9(3): 303-317.
［6］AMATO P, FARINA M. An alifeinspired evolutionary algorithm for dynamic mu ltiobjective optimization problems［A］. In WSC［C］.［S.l.］， 2003.
［7］HATZAKIS I, WALLACE D. Dynamic multiobjective optimization with evolutiona ry algorithm: a forwardlooking approach［A］. GECCO’06［C］ . Washington, USA, 2 006.
［8］DEB K, UDAYA B R N， KARTHIK S. Dynamic multiobjective optimiz ati on and decisionmaking using modified NSGAII: a case study on hydrothermal po we r scheduling biobjective optimization problems［R］. KanGAL Report, 2006.
［9］COELLO C A, CRUZ Cort N. Solving multiobjective optimization problems usin g an aritificial immune system［J］. Genetic Programming and Evolvable Machine, 20 05, 6 :163-190.
［10］SHANG R H, JIAO L C, GONG M G, et al. Clonal selection algorithm for dyn am ic multiobjective optimization［A］. CIS 2005［C］. Berlin: SpringerVerlag, 20 05.
［11］黄席越, 张著洪, 何传江，等. 现代智能算法理论及应用［M］. 北京: 科学出版社 , 2005.

备注/Memo

收稿日期：2006-12-05.
基金项目：国家自然科学基金资助项目(60565002).
作者简介：
钱淑渠, 男, 1978年生，硕士, 主要研究方向为智能算法. 
张著洪, 男, 1966年生，副教授, 工学博士, 主要研究方向为控制理论与计算智能. E-mail:sci.zhzhang@gzu.edu.cn.

更新日期/Last Update: 2009-05-08

动态多目标免疫优化算法及性能测试研究 PDF下载HTML

备注/Memo

动态多目标免疫优化算法及性能测试研究

PDF下载 HTML