结合特征扰动与分配策略的集成辅助多目标优化算法

doi:10.19678/j.issn.1000-3428.0061885

摘要/Abstract

摘要： 代理模型利用近似预测代替算法对多目标优化问题的真实评价，大幅减少了算法寻优所需的真实适应度评估次数。为提高代理模型在求解高维问题时的准确性并降低计算开销，提出一种基于特征扰动与分配策略的集成辅助多目标优化算法。将径向基函数网络代理模型与支持向量机回归代理模型作为集成过程中的基模型，降低算法在高维问题上的计算开销。结合特征扰动与基于记忆的影响因子分配策略构建集成代理模型，提高集成准确性。使用集成预测值与不确定信息加权辅助管理集成代理模型，平衡全局搜索与局部探索，增强算法在目标空间中的寻优能力。实验结果表明，该算法在ZDT1~ZDT3和ZDT6测试问题上所得解集的分布性与收敛性相比经典算法更好，并且当决策变量维数增加时，使用集成代理模型相比于Kriging代理模型约减少了90%的适应度评估次数，同时可获得更准确的预测结果。

关键词: 集成代理模型, 多目标优化, 特征扰动, 历史记忆, 不确定信息

Abstract: A surrogate model can use its approximate prediction to replace the real evaluation of an algorithm when applied to the multi-objective optimization problem, which greatly reduces the number of real fitness evaluations required by the multi-objective optimization algorithm for determining the optimal optimization algorithm.To improve the accuracy of the surrogate model under high-dimensional problems and reduce its computational overhead, this study proposes an ensemble-assisted multi-objective optimization algorithm based on feature perturbation and allocation strategy.First, the algorithm uses a Radial Basis Function Network(RBFN) and a Support Vector Regression(SVR) surrogate model as the basis model during the integration, which reduces the computational cost of the algorithm on high-dimensional problems.Second, the algorithm combines feature disturbance and memory-based influence factor allocation strategies to construct an integrated surrogate model and improve the accuracy of the integration.Finally, the algorithm uses the integrated prediction value and the weighted uncertainty information to assist in the management of the integrated surrogate model, balance the global search and local exploration, and enhance the optimization capability of the algorithm within the target space.The experimental results show that the distribution and convergence of the solution set obtained by this algorithm on the ZDT1~ZDT3 and ZDT6 test problems are better than those of a classical algorithm.In addition, when the number of dimensions of the decision variables increases, the ensemble surrogate model used by the algorithm reduces the number of fitness evaluations by approximately 90% in comparison with the Kriging surrogate model, and at the same time can obtain more accurate prediction results.

Key words: ensemble surrogate model, multi-objective optimization, feature disturbance, historical memory, uncertain information

中图分类号:

TP18

刘子怡, 王宇嘉, 孙福禄, 贾欣, 聂方鑫. 结合特征扰动与分配策略的集成辅助多目标优化算法[J]. 计算机工程, 2022, 48(6): 115-123.

LIU Ziyi, WANG Yujia, SUN Fulu, JIA Xin, NIE Fangxin. Ensemble-Assisted Multi-Objective Optimization Algorithm Combining Feature Perturbation and Allocation Strategy[J]. Computer Engineering, 2022, 48(6): 115-123.

http://www.ecice06.com/CN/Y2022/V48/I6/115

图/表 8

20220625174849

20220625174853

20220625174857

20220625174900

20220625174904

20220625174908

20220625174912

20220625174915

参考文献

[1] FLEMING P J, PURSHOUSE R C, LYGOE R J.Many objective optimization:an engineering design perspective[C]//Proceedings of International Conference on Evolutionary Multi-Criterion Optimization.Berlin, Germany:Springer, 2005:14-32.
[2] MIN A T W, ONG Y S, GUPTA A, et al.Multiproblem surrogates:transfer evolutionary multiobjective optimization of computationally expensive problems[J].IEEE Transactions on Evolutionary Computation, 2019, 23(1):15-28.
[3] CHENG R, RODEMANN T, FISCHER M, et al.Evolutionary many-objective optimization of hybrid electric vehicle control:from general optimization to preference articulation[J].IEEE Transactions on Emerging Topics in Computational Intelligence, 2017, 1(2):97-111.
[4] WANG H D, HE S, YAO X.Nadir point estimation for many-objective optimization problems based on emphasized critical regions[J].Soft Computing, 2017, 21(9):2283-2295.
[5] CHUGH T, SINDHYA K, MIETTINEN K, et al.Surrogate-assisted evolutionary multiobjective shape optimization of an air intake ventilation system[C]//Proceedings of IEEE Congress on Evolutionary Computation.Washington D.C., USA:IEEE Press, 2017:1541-1548.
[6] JIN Y C, WANG H D, CHUGH T, et al.Data-driven evolutionary optimization:an overview and case studies[J].IEEE Transactions on Evolutionary Computation, 2019, 23(3):442-458.
[7] CHUGH T, JIN Y C, MIETTINEN K, et al.A surrogate-assisted reference vector guided evolutionary algorithm for computationally expensive many-objective optimization[J].IEEE Transactions on Evolutionary Computation, 2018, 22(1):129-142.
[8] SUN C L, JIN Y C, ZENG J C, et al.A two-layer surrogate-assisted particle swarm optimization algorithm[J].Soft Computing, 2015, 19(6):1461-1475.
[9] CLARKE S M, GRIEBSCH J H, SIMPSON T W.Analysis of support vector regression for approximation of complex engineering analyses[J].Journal of Mechanical Design, 2005, 127(6):1077-1087.
[10] LUO J P, GUPTA A, ONG Y S, et al.Evolutionary optimization of expensive multiobjective problems with co-sub-Pareto front Gaussian process surrogates[J].IEEE Transactions on Cybernetics, 2019, 49(5):1708-1721.
[11] GASPAR-CUNHA A, VIEIRA A.A multi-objective evolutionary algorithm using neural networks to approximate fitness evaluations[J].International Journal of Computing System Signals, 2005, 6(1):18-36.
[12] LI F, CAI X W, GAO L, et al.A surrogate-assisted multiswarm optimization algorithm for high-dimensional computationally expensive problems[J].IEEE Transactions on Cybernetics, 2021, 51(3):1390-1402.
[13] LIU B, ZHANG Q F, GIELEN G G E.A Gaussian process surrogate model assisted evolutionary algorithm for medium scale expensive optimization problems[J].IEEE Transactions on Evolutionary Computation, 2013, 18(2):180-192.
[14] TIAN J, TAN Y, ZENG J C, et al.Multiobjective infill criterion driven Gaussian process-assisted particle swarm optimization of high-dimensional expensive problems[J].IEEE Transactions on Evolutionary Computation, 2019, 23(3):459-472.
[15] GOEL T, HAFTKA R T, SHYY W, et al.Ensemble of surrogates[J].Structural and Multidisciplinary Optimization, 2007, 33(3):199-216.
[16] TANG Y F, CHEN J Q, WEI J H.A surrogate-based particle swarm optimization algorithm for solving optimization problems with expensive black box functions[J].Engineering Optimization, 2013, 45(5):557-576.
[17] WANG H D, JIN Y C, DOHERTY J.Committee-based active learning for surrogate-assisted particle swarm optimization of expensive problems[J].IEEE Transactions on Cybernetics, 2017, 47(9):2664-2677.
[18] HABIB A, SINGH H K, CHUGH T, et al.A multiple surrogate assisted decomposition-based evolutionary algorithm for expensive multi/many-objective optimization[J].IEEE Transactions on Evolutionary Computation, 2019, 23(6):1000-1014.
[19] ROSALES-PÉREZ A, COELLO C A C, GONZALEZ J A, et al.A hybrid surrogate-based approach for evolutionary multi-objective optimization[C]//Proceedings of IEEE Congress on Evolutionary Computation.Washington D.C., USA:IEEE Press, 2013:2548-2555.
[20] 魏锋涛, 卢凤仪.融合核函数在改进径向基代理模型中的应用[J].计算机工程与应用, 2019, 55(7):58-65. WEI F T, LU F Y.Application of hybrid kernel function in improved radial basis function metamodel[J].Computer Engineering and Applications, 2019, 55(7):58-65.(in Chinese)
[21] EBERHART R, KENNEDY J.A new optimizer using particle swarm theory[C]//Proceedings of the 6th International Symposium on Micro Machine and Human Science.Washington D.C., USA:IEEE Press, 1995:39-43.
[22] BROWN G, WYATT J, TINO P.Managing diversity in regression ensembles[J].Journal of Machine Learning Research, 2005, 6:1621-1650.
[23] 王旭仁, 马慧珍, 冯安然, 等.基于信息增益与主成分分析的网络入侵检测方法[J].计算机工程, 2019, 45(6):175-180. WANG X R, MA H Z, FENG A R, et al.Network intrusion detection method based on information gain and principal components analysis[J].Computer Engineering, 2019, 45(6):175-180.(in Chinese)
[24] NEBRO A J, DURILLO J J, GARCIA-NIETO J, et al.SMPSO:a new PSO-based metaheuristic for multi-objective optimization[C]//Proceedings of IEEE Symposium on Computational Intelligence in Multi-Criteria Decision-Making.Washington D.C., USA:IEEE Press, 2009:66-73.
[25] DEB K, PRATAP A, AGARWAL S, et al.A fast and elitist multiobjective genetic algorithm:NSGAII[J].IEEE Transactions on Evolutionary Computation, 2002, 6(2):182-197.
[26] ZHANG Q F, LI H.MOEA/D:a multiobjective evolutionary algorithm based on decomposition[J].IEEE Transactions on Evolutionary Computation, 2007, 11(6):712-731.
[27] EMMERICH M T M, GIANNAKOGLOU K C, NAUJOKS B.Single-and multiobjective evolutionary optimization assisted by Gaussian random field metamodels[J].IEEE Transactions on Evolutionary Computation, 2006, 10(4):421-439.

选择文件类型/文献管理软件名称

选择包含的内容