学校编码：10384
学号：X2012221013
硕 士 学 位 论 文
基于非支配排序的多目标优化算法改进研究
The improvement research on multi-objective
optimization algorithm based on
non-dominated sorting
颜曙林
指导教师：江敏
专业名称：工程硕士(计算机技术)
答辩日期：2016年5月
厦门大学博硕士论文摘要库
厦门大学学位论文原创性声明
本人呈交的学位论文是本人在导师指导下,独立完成的研究成果。
本人在论文写作中参考其他个人或集体已经发表的研究成果，均在文中
以适当方式明确标明，并符合法律规范和《厦门大学研究生学术活动规
范(试行)》。
另外，该学位论文为( )课题(组)的研究成果
，获得( )课题(组)经费或实验室的资助，在(
)实验室完成。(请在以上括号内填写课题或课题组负责人或
实验室名称，未有此项声明内容的，可以不作特别声明。)
声明人(签名)：
年 月 日
厦门大学博硕士论文摘要库
厦门大学学位论文著作权使用声明
本人同意厦门大学根据《中华人民共和国学位条例暂行实施办法
》等规定保留和使用此学位论文，并向主管部门或其指定机构送交学位
论文(包括纸质版和电子版)，允许学位论文进入厦门大学图书馆及其数
据库被查阅、借阅。本人同意厦门大学将学位论文加入全国博士、硕士
学位论文共建单位数据库进行检索，将学位论文的标题和摘要汇编出版
，采用影印、缩印或者其它方式合理复制学位论文。
本学位论文属于：
( )1.经厦门大学保密委员会审查核定的保密学位论文，于
年 月 日解密，解密后适用上述授权。
( )2.不保密，适用上述授权。
(请在以上相应括号内打“√”或填上相应内容。保密学位论文应
是已经厦门大学保密委员会审定过的学位论文，未经厦门大学保密委员
会审定的学位论文均为公开学位论文。此声明栏不填写的，默认为公开
学位论文，均适用上述授权。)
声明人(签名)：
年 月 日
厦门大学博硕士论文摘要库
摘 要
多目标优化问题（MOP）在许多科学研究和工程设计当中普遍存在，此类问题求解
十分复杂但又十分重要。尽管传统多目标优化算法已经有了长足的发展，但遗存的
问题依然很多，需要改进。
进化多目标优化算法将传统方法中的加权策略改为以种群为单位的进化策略，取得
了更理想的优化的效果，NSGA-II就是其中的佼佼者。在此次研究中本人在NSGA-II的基础上提出了一种基于随机交叉算子、变异算子的算法RCVO-NSGA-II（Random
Cross Variation Operator - nondominated sorting genetic algorithm II）用
于解多目标优化问题。RCVO-NSGA-II随机采用模拟二进制交叉或者单点交叉，即保
持了局部寻优的特性，又能够快速跳出局部最优解，有效地增强了全局搜索能力。
同时，为了既保留部分父代信息又兼顾解的多样性，RCVO-NSGA-II随机采用多项式
变异或者基因段变异。
此外，在多目标优化算法的最新研究成果NSGA-III的基础上，提出了基于分布估计
与随机交叉算子、变异算子的算法E-RCVO-NSGA-III（Estimation of
distribution -Random Cross Variation Operator - nondominated sorting
genetic algorithm III）。E-RCVO-NSGA-III一方面采用混合高斯模型的分布估计
策略生成额外的备选子代，增强了全局搜索能力，另一方面采用RCVO-NSGA-II的随
机交叉算子、随机变异算子来保持种群的多样性。在不同的评价标准下，与其它多
目标优化算法进行比较，实验结果证明了我们算法的有效性。
这项研究的意义在于，提出了两种高效的进化多目标优化算法，不仅提高了优化性
能，而且对进化多目标优化算法的进一步研究及其在工程领域的应用都有重要的意
义。
关键词：NSGA-II；NSGA-III；EDA；随机交叉算子；随机变异算子
厦门大学博硕士论文摘要库
Abstract
Multiobjective optimization problem is common existing in many scientific
researches and engineering design and the solution of this kind of problem is very
complicated and important. Although the development of the traditional
multi-objective optimization algorithm have made great progress, but a lot of problems
are need to be improved.
Evolutionary multi-objective optimization algorithm change the traditional method
of weighted strategy to units of the population evolution strategy, which achieve a
ideal optimal results. NSGA-II is the leader. In this paper we propose an
algorithm-- RCVO-NSGA-IIRandom Cross Variation Operator - nondominated
sorting genetic algorithm II which based on randomized crossover operator and
mutation operator for solving multi-objective optimization problem.
RCVO-NSGA-II use Simulated Binary Crossover or Single Point Crossover by random. It not
only keep the characteristics of the local optimization,but also can quickly jump
out of local optimal solution, and to enhance the global search ability effectively.
Moreover, we proposes a multi-objective optimization algorithm called Estimation
of distribution-Random Cross Variation Operator - nondominated sorting genetic
algorithm III (E-RCVO-NSGA-III) based on the advance of NSGA-III algorithm. On
the one hand,the distribution estimation strategy of the Gaussian Mixture Model
was introduced to Generate additional alternative offspring enhancing the global
search ability of E-RCVO-NSGA-III.On the other hand , the RCVO-NSGA - II
Randomized Crossover Operator and Random Mutation Operator were
introduced to maintian the diversity of the population. Under the different
evaluation criteria, the results demonstrate thatour algorithm is effective
compared with other multi-objective optimization algorithms.
The significance of the study is that put forward two kinds of efficient evolutionary
multi-objective optimization algorithms.Not only improving the optimization
performance, but also promoting the further study of evolutionary multi-objective
optimization algorithm, and it also means a great deal to its actual application.
Keywords:
NSGA-IIIEDARandomizedCrossoverOperatorRandomMutationOperator
参考资料
[1] 刘彤. 解多目标优化问题的进化算法[硕士学位论文]. 西安：西安电子科技大学. 2010.
[2] M. Baltes, R. Schneider, C. Sturm, and M. Reuss., "Optimal experimental design for parameter estimation in unstructured growth models," Biotechnology Progress, 10, 480-488(1994).
[3] C.A. Coello and G.B. Lamont and D.A Van Veldhuizen, Evolutionary Algorithms for Solving Multi-Objective Problems, Springer, Norwell, MA: Kluwer, 2007.
[4] C. A. Coello. Comprehensive Survey of Evolutionary-Based Multiobjective Optimization Techniques, Knowledge and Information Systems. An International Journal, 1999, 269-308.
[5] ZadehL.A. Optimality and Nonscalar-Valued Performance Criteria. IEEE Transaction Automatic Control,1963, pp:59-60.
[6] Haimes, Lasdon L., and Wismer D. On a Bicriterion Formulation of the Problems of Integrated System Identification and System Optimization. IEEE Transaction System,Man, and Cybernetics,1971,1:296-297. [7] Tseng C.H., and T.WLu. Minimax Multiobjective Optimization in Structural Design. International Journal for Numerical Methods in Engineering, 1990, 30:1213-1228.
[8] Charnes A, Cooper and Ferguson W.W.R.O. Optimal Estimation of executive compensation by linear programming.Management Science, 1955,1:138-151.
[9] 李厚甫.基于博弈策略的多目标进化算法研究[硕士学位论文].湖南大学.2011. [10] 王红.带残损原材料二维优化下料问题的研究[硕士学位论文].山东大学.2006. [11] Schaffer JD. Multiple-objective optimization,with vector evaluated gentic algorithms[C].
Proceedings of International Conference on Genetic Algorithms and Their Applications.Pittsburgh,PA,1985:93-100.
[12] Fonceca CM,Fleming PJ.Genetic algorithm for multiobjectiveoptimization: Formulation,discussion and generation.In:Forrest S,ed Proc.of the 5th Int’l Conf, on Genetic Algorithms.San Mateo:Morgan Kauffman Publishers,1993.416-423.
[13] Srinivas N,Deb K.Multiobjective optimization using non-dominated sorting in genetic algorithms. Evolutionary Computation,1994,2(3):221-248.
[14] Horn J,Nafpliotis N,Goldberg DE.A niched Pareto genetic algorithm for multiobjective optimization,In:Fogarty TC,ed.Proc. of the 1st IEEE Confress on Evolutionary
Computation.Piscataway:IEEE,1994. 82-87.
[15] Zitzler E,Thiele L. Multiobjective evolutionary algorithms: a comparative case study and the strength Pareto approach. IEEE Trans. on Evolutionary Computation, 1999,3(4):257-271.
[16] Corne D W, Knowles J D,Oates M J. The Pareto Envelope-Based Selection Algorithm for Multi-objective optimization//Proceedings of the Parallel Problem Solving from Nature VI Conference,2000:839-848.
[17] Corne DW, Jerram NR,Knowles JD,Oates MJ,PESA-Ⅱ: Region-Based selection in evolutionary multi-objective optimization,In: Spector L, Goodman ED, Wu A, Langdon WB, Voigt HM, Gen M,eds. Proc. of the Genetic and Evolutionary Computation Conf, GECCO 2001. San Francisco: Morgan Kaufmann
Publishers,2001.283-290.
[18] Erichson M,Mayer A, Horn J. The niched Pareto genetic algorithm 2 applied to the design of groundwater remediation system. In: Zitzler E, Deb K, Thiele L,Coello Coello CA, Come D,eds.Proc, of the 1st Int’l Cond. On Evolutionary Multi-Criterion Optimization, EMO 2001.Berlin: Springer-Verlag,2001.681-695.
[19] Coello Coello C A,Pulido G T. A micro-genetic algorithm for multiobjective optimization. In: Proceedings of the Genetic and Evolutionary Computation Conference, San Francisco, 2001:274-282.
[20] Zitzler E,Laumanns M, Thiele L. SPEA2: Improving the strength Pareto evolutionary algorithm. In:Giannakoglou K, Tsahalis DT,Periaux J, Papailiou KD, Fogarty T, eds. Evolutionary Methods for Design, Optimization and Control with Applications to Industrial Problems.Berlin:Springer-Verlag, 2002. 95-100. [21] K. Deb, A. Pratap, S. Agarwal, T. Meyarivan. A fast and elitist multiobjective genetic algorithm: NSGA-II,
IEEE Transactions on Evolutionary Computation, Vol.6, No.2, 182-197, 2002.
[22] 时丽娜.进化多目标优化算法及其应用研究[硕士学位论文].广西师范大学.2010.
[23] Dorigo M,Maniezzo V,Clolorni A. The ant system:optimization by acolony of cooperating agents. IEEE Transaction on Systems,Man and Cybernetics, Part B, 1996,26(1):29-41.
[24] Garcia-Martinez C,Cordon O,Herrera F. A taxonomy and an empirical analysis of multiple objective ant colony optimization algorithms for the bi-criteria TSP. European Journal of Operational
Research,2007,180(1):116-148.
[25] Angus D, Woodward C. Multiple objective ant colony optimization. Swarm Intelligence, 2009,3(1):69-85. [26] Lopez-Ibanez M, Stutzle T. Automatic configuration of multi-objective ant colony optimization algorithms. IRIDIA Technical Report Series, TR/IRIDIA/2011-003,2011.
[27] Kennedy J, Eberhart R C. Particle swarm optimization. In:proceedings of IEEE International Conference on Neural Networks, Piscataway, 1995:1942-1948.
[28] Moore J, Chapman R. Application of particle swarm to multiobjective optimization. Technical report, Department of Computer Science and Software Engineering, Auburn University,1999.
[29] Coello C A, Pulido G T,Lechuga M S. Handing multiple objectives with particle swarm optimization. IEEE Transactions on Evolutionary Computation,2004,8(3):256-279.
[30] Kirkpatrick S, Gelatt Jr C D, Vecchi M P. Optimization by simulated annealing[J], Science,220(1983),671-680.
[31] Cai W S, Shao X G. A fast annealing evolutionary algorithm for global optimization. J Comput Chem, 2002, 23(4): 427-435.
[32] Coello Coello C A, Cruz-Cortes N. An approach to solve multiobjective optimization problems based on an aritificial Immune System. In: proceedings of 1st International Conference on Artificial Immune Systems, Canterbury, 2002:212-221.
[33] Gong M G, Jiao L C,Du H F, et al. Multiobjective immune algorithm with nondominated neighbor-based selection. Evolutionary Computation,2008, 16(2):225-255.
[34] Yang D D, Jiao L C, Gong M G. Adaptive multi-objective optimization based on nondominated solutions. Computational Intelligence, 2009,25(2):84-108.
[35] 焦李成,尚荣华,马文萍等.多目标优化免疫算法、理论和应用.北京:科学出版社,2010.
[36] Khare V, Yao X, Deb K. Performance scaling of multi-objective evolutionary algorithms. In: Fonseca CM, Fleming PJ, Zitzler E, Deb K, Thiele L, eds. Proc. of the 2nd Int’1 Conf. on Evolutionary Multi-Criterion Optimization, EMO 2003. Berlin: Springer-Verlag, 2003. 376-390.
[37] Deb K, Saxena DK. On finding Pareto-optimal solutions through dimensionality reduction for certain large-dimensional mult-objective optimization problems. Technical Report, 2005011. Kalyanmoy Deb and Dhish Kumar Saxena, Indian Institute of Technology Kanpur, 2005.
[38] Saxena DK, Deb K. Non-Linear dimensionality reduction procedure for certain large-dimensional multi-objective optimization problems: Employing correntropy and a novel maximum variance unfolding. In: Coello Coello CA, Aguirre AH, Zitzler E, eds. Proc. of the 4th Int’1 Conf. on Evolutionary Mlti-Criterion
Optimization, EMO 2007. Berlin: Springer-Verlag, 2007. 772-787.
[39] Deb K, Jain H. An Evolutionary Many-Objective Optimization Algorithm Using Reference-Point-Based Nondominated Sorting Approach. IEEE Transactions on evolutionary compution, VOL. 18, NO. 4, AUGUST 2014:577-622.
[40] Yuhui. Wang, Xiaohui Lei. Performance Comparison of Three Multi-objective Optimization Algorithms on Calibration of Hydrological Model. In: 2010 Sixth International Conference on Natural Computation (ICNC 2010),2010:2798-2803.
[41] Araujo, D.R.B., Daniel A. R. A Performance Comparison of Multi-objective Optimization Evolutionary Algorithms for All-Optical Networks Design, Computational Intelligence in Multicriteria Decision-Making (MDCM), 2011 IEEE Symposium on,April 2011,89-96.
[42] K. Deb, A. Pratap, S. Agarwal, T. Meyarivan. A fast and elitist multiobjective genetic algorithm: NSGA-II,
IEEE Transactions on Evolutionary Computation, Vol.6, No.2, 182-197, 2002.
[43] Zitzler E,Thiele L. Multiobjective evolutionary algorithms: a comparative case study and the strength Pareto approach. IEEE Trans. on Evolutionary Computation, 1999,3(4):257-271.
[44] N. Srinivas and Kalyanmoy Deb, Multiobjective Optimization Using Nondominated Sorting in Genetic Algorithms, Evolutionary Computation 2 (1994), no. 3, 221 – 248.
[45] P. Murugana, S. Kannana, S. Baskarb, NSGA-II algorithm for multi-objective generation expansion planning problem, Electric Power Systems Research 79 (2009) 622–628.
[46] Kalyanmoy Deb and R. B. Agarwal. Simulated Binary Crossover for Continuous Search Space.Complex Systems, 9:115-148, April 1995.
[47] Deb K, Goyal M. A combined genetic adaptive search (GeneAS) for engineering design[J]. Computer Science and Informatics, 1996,26(4): 30-45.
[48] C. A. C. Coello and M. R. Sierra. A Coevolutionary Multi-objective Evolutionary Algorithm. Proc of the 2003 Congress on Evolutionary Computation, Australia: IEEE Press, 2003, 482-489.
[49] Schaffer JD.Multiple objective optimization with vector evaluated genetic algorithms. In:Grefenstette JJ, ed. Proc. of the Int’I Conf. on Genetic Algorithms and Their Applications. Hillsdale:L. Erlbaum Associates,Inc ,1985.93-100.
[50] Zitzler E, Deb K, Thiele L. Comparison of multiobjective evolutionary algorithms: empirical results. Evolutionary Computation, 2000,8(2):173-195. [doi: 10.1162/106365600568202].
[51] Deb K, Thiele L, Laumanns M, Zitzler E. Scalable multiobjective optimization test problems. In: Fogel DB, ed. Proc. of the IEEE Congress on Evolutionary Computation (CEC 2002). Piscataway: IEEE Service Center, 2002. 825-830. [doi: 10.1109/CEC.2002. 1007032].
[52] 韩荣荣. 基于遗传算法的BP神经网络在多目标药物优化分析中的应用[D]. 山西医科大学, 2011. [53] The Mathworks Inc. MATLAB R2014b Help [CP/CD]. 2014.
[54] Gong MG, Jiao LC, Du HF, Bo LF. Multi-objective immune algorithm with nondominatedneighbor-based selection. Evolutionary Computation 2008, 16(2):225-255.
[55] de Castro L,TimmisJ. Artificial immune systems: a new computational intelligence approach. Springer-Verlag, London, 2002, ISBN 978-1852335946.
[56] 康姝. 基于NNIA的多目标时间表调度问题研究[D]. 西安电子科技大学, 2014.
[57] 公茂果,焦李成,杨咚咚,马文萍. 进化多目标优化算法研究. 软件学报 ISSN 1000-9825, CODEN RUXUEW. Journal of Software,Vol.20, No.2, February 2009, PP.271-289.
[58] Coello coello CA. Recent trends in evolutionary mult-objective optimization. In:Abraham A, Jain LC, Goldberg R, eds. Evolution Multi-Object Optimization: Theoretical Advances and Applications.
Berlin:Springer-Verlag,2005.7-32.
[59] Zhang QF, Li H. MOEA/D: A multiobjective evolutionary algorithm based on decomposition. IEEE Trans. on Evolutionary Computation, 2007,11(6):712 731. [doi: 10.1109/TEVC.2007.892759].
[60] Deb K,Jain S. Running performance metrics for evolutionary multi-objective optimization. Technical Report, No.2002004,Kanpur:Indian Institute of Technology Kanpur,2002.
[61] Schott, JR. Fault tolerant design using single and multicriteria genetic algorithm optimization [MS. Thesis]. Cambridge: Massachusetts Institute of Technology,1995.
[62] 胡 旺, Gary G. YEN, 张鑫. 基于 Pareto 熵的多目标粒子群优化算法. 软件学报ISSN 1000-9825, CODEN RUXUEW. Journal of Software,2014,25(5):1025-1050.
[63] McGill R, Tukey JW, Larsen WA. Variations of boxplots. The American Statistician, 1978,32(1):12-16. [64] 谭艳艳. 几种改进的分解类多目标进化算法及其应用[D]. 西安电子科技大学, 2013.
[65] I. Das and J. Dennis, “Normal-boundary intersection: A new method for generating the Pareto surface in nonlinear multicriteria optimization problems,” SIAM J. Optimization, vol. 8, no. 3, pp. 631–657, 1998. [66] D. Hadka and P. Reed, “Borg: An auto-adaptive many-objective evolutionary computing framework,” Evol. Comput., vol. 21, no. 2,pp. 231–259, 2013.
[67] Tsung-Che Chiang and Wei-Huai Hsu, A knowledge-based evolutionary algorithm for the multiobjective
vehicle routing problem with time windows, Computers & Operations Research, vol. 45, pp. 25 - 37, 2014. [68] Tsung-Che Chiang, Enhancing rule-based scheduling in wafer fabrication facilities by evolutionary algorithms: Review and opportunity, Computers & Industrial Engineering, vol. 64, no. 1, pp. 524 - 535, 2013. [69] Special Session on Evolutionary Multiobjective Optimization and Games, in IEEE Conference on Computational Intelligence and Games (CIG 2015), August 31 - September 2, 2015.
[70] Larranaga P, Lozano J A. Estimation of distribution algorithms: A new tool for evolutionary computation[M].Boston: Kluwer Press, 2002.
[71] 王圣尧, 王凌, 方晨,等. 分布估计算法研究进展[J]. 控制与决策, 2012,27(7):961-966.
[72] Zhang QF, Li H. MOEA/D: a multi-objective evolutionary algorithm based on decomposition. IEEE Transactions on Evolutionary Computation 2007, 11(6):712-731.
[73] Q. Zhang, W. Liu and H. Li. The performance of a new version of MOEA/D on CEC09 unconstrained MOP test instances. IEEE Congress on Evolutionary Computation (CEC'09), Piscataway, NJ: IEEE Press, 2009, 203-208.
[74] S. Pal, S. Das, A. Basak, and P. N. Suganthan, "Synthesis of difference patterns for monopulse antennas with optimal combination of array-size and number of subarrays --- a multi-objective optimization approach," Progress In Electromagnetics Research B, Vol. 21, 257-280, 2010.
[75] Antony Waldocka, David Corne, Multiple Objective Optimisation applied to Route Planning, SEAS DTC Fifth Conference Proceedings, 2010.
[76] Zhang Jiandong et al, The Research on Multiple-impulse Correction Submunition Multi-objective Optimization Based on MOEA/D , Journal of Projectiles, Rockets, Missiles and Guidance, 2010-02. [77] R. De. Carvalho, et al., An efficient algorithm for multiobjective optimization problems based on mathematical decomposition and evolutionary computation, XVIII SIMPóSIO DE ENGENHARIA DE PRODUÇÃO Gestão de projetos e Engenharia de produção, Bauru, SP, Brasil, 08 a 10 de novembro de 2010.
[78] K. Miettinen. Nonlinear Multiobjective Optimization[M]. Norwell, MA: Kluwer, 1999,178-230.
[79] I. Das and J. E. Dennis. Normal-bounday intersection: A new method for generating Pareto optimal points in multicriteria optimization problems[J]. SIAM J.Optim., 1998, 8(3): 631-657.
[80] A. Messac, A. Ismail-Yahaya and C. Mattson. The normalized normal constraint method for generating the Pareto frontier[J]. Struct Multidisc. Optim, 2003,25:86-98.
[81] Q. Zhang. (2012, Mar.). MOEA/D Homepage [Online]. Available: http://dces.essex.ac.uk/staff/zhang/webofmoead.htm
[82] D. V. Veldhuizen and G. B. Lamont, “Multiobjective evolutionary algorithm research: A history and analysis,” Dept. Electr. Comput. Eng.,Air Force Instit. Technol., Dayton, OH, USA, Tech. Rep. TR-98-03,1998.
[83] 刘文娟. 基于分解的多目标量子差分进化算法研究[D]. 山西财经大学, 2015.
[84] Coello Coello CA, Van Veldhuizen DA,Lamont GB. Evolutionary Algorithms for Solving Multi-Objective Problems, Second Edition, New York: Springer-Verlag,2007.
[85] Kalyanmoy Deb, Lothar Thiele, Marco Laumanns, Eckart Zitzler. Scalable Test Problems for Evolutionary Multiobjective Optimization, Evolutionary Multiobjective Optimization[M].London: Springer
London,2005:105-145.
