基于代理模型的差分进化约束优化

doi:10.11772/j.issn.1001-9081.2019091587

计算机应用 ›› 2020, Vol. 40 ›› Issue (4): 1091-1096.DOI: 10.11772/j.issn.1001-9081.2019091587

基于代理模型的差分进化约束优化

薛锋, 史旭华, 史非凡

宁波大学信息科学与工程学院, 浙江宁波 315211

收稿日期:2019-09-18 修回日期:2019-11-14 出版日期:2020-04-10 发布日期:2019-11-22
通讯作者: 薛锋
作者简介:薛锋(1995-),男,湖北荆州人,硕士研究生,主要研究方向:系统建模与优化、机器学习;史旭华(1967-),女,浙江宁波人,教授,博士,主要研究方向:系统建模与优化、机器人控制、机器学习;史非凡(1993-),男,辽宁沈阳人,硕士研究生,主要研究方向:系统建模与优化。
基金资助:
国家自然科学基金资助项目（61773225）。

Surrogate-based differential evolution constrained optimization

XUE Feng, SHI Xuhua, SHI Feifan

Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo Zhejiang 315211, China

Received:2019-09-18 Revised:2019-11-14 Online:2020-04-10 Published:2019-11-22
Supported by:
This work is partially supported by the National Natural Science Foundation of China(61773225).

摘要/Abstract

摘要： 针对耗时计算目标函数的约束优化问题，提出用代理模型来代替耗时计算目标函数的方法，并结合目标函数的信息对约束个体进行选择，从而提出基于代理模型的差分进化约束优化算法。首先，采用拉丁超立方采样方法建立初始种群，用耗时计算目标函数对初始种群进行评估，并以此为样本数据建立目标函数的神经网络代理模型。然后，用差分进化方法为种群中的每一个亲本产生后代，并对后代使用代理模型进行评估，采用可行性规则来比较后代与其亲本并更新种群，根据替换机制将种群中较劣的个体替换为备用存档中较优的个体。最后，当达到最大适应度评估次数时算法停止，给出最优解。该算法与对比算法在10个测试函数上运行的结果表明，该算法得出的结果更精确。将该算法应用于工字梁优化问题的结果表明，相较于优化前的算法，该算法的适应度评估次数减少了80%；相对于FROFI（Feasibility Rule with the incorporation of Objective Function Information）算法，该算法的适应度评估次数减少了36%。运用所提算法进行优化可以有效减少调用耗时计算目标函数的次数，提升优化效率，节约计算成本。

关键词: 代理模型, 差分进化, 约束进化优化, 可行性规则, 系统优化

Abstract: In order to solve the constrained optimization problem of objective function with time-consuming computation,a surrogate model was proposed to replace the objective function with time-consuming computation,the constraint individuals were selected based on the information of the objective function,and a surrogate-based differential evolution constrained optimization algorithm was proposed. Firstly,the Latin hypercube sampling method was used to establish the initial population,which was evaluated by the objective function with time-consuming calculation,and the neural network surrogate model of the objective function was established based on these sample data. Then,the differential evolution method was used to generate offsprings for each parent in the population,and the offspring individuals were evaluated by using the surrogate model. The feasibility rule was used to compare the offsprings with their parents and update the population,and the inferior individuals in the population were replaced with the better individuals in the alternate archive according to the replacement mechanism. Finally,the algorithm stopped when the maximum fitness evaluation number was reached,and the optimal solution was obtained. The results of this algorithm and comparison algorithms running on 10 test functions show that the results obtained by this algorithm are more accurate. The results of applying this algorithm to the I-beam optimization problem show that the number of fitness evaluations of this algorithm is reduced by 80% compared with that of the algorithm before optimization,and the number of fitness evaluations of this algorithm is reduced by 36% compared with that of FROFI (Feasibility Rule with the incorporation of Objective Function Information) algorithm. Using the proposed algorithm to realize the optimization can effectively reduce the number of calls for the objective function with time-consuming computation,improve optimization efficiency,and save computational cost.

Key words: surrogate model, differential evolution, constrained evolutionary optimization, feasibility rule, system optimization

中图分类号:

TP391

薛锋, 史旭华, 史非凡. 基于代理模型的差分进化约束优化[J]. 计算机应用, 2020, 40(4): 1091-1096.

XUE Feng, SHI Xuhua, SHI Feifan. Surrogate-based differential evolution constrained optimization[J]. Journal of Computer Applications, 2020, 40(4): 1091-1096.

参考文献

[1] MEZURA-MONTES E,COELLO C A C. Constraint-handling in nature-inspired numerical optimization:past,present and future[J]. Swarm and Evolutionary Computation,2011,1(4):173-194.
[2] WU G,PEDRYCZ W,SUGANTHAN P N,et al. Using variable reduction strategy to accelerate evolutionary optimization[J]. Applied Soft Computing,2017,61:283-293.
[3] MEZURA-MONTES E,COELLO C A C. A simple multimembered evolution strategy to solve constrained optimization problems[J]. IEEE Transactions on Evolutionary Computation,2005,9(1):1-17.
[4] WANG Y,CAI Z,GUO G,et al. Multiobjective optimization and hybrid evolutionary algorithm to solve constrained optimization problems[J]. IEEE Transactions on Systems Man and Cybernetics, Part B(Cybernetics),2007,37(3):560-575.
[5] 李智勇, 黄滔, 陈少淼, 等. 约束优化进化算法综述[J]. 软件学报,2017,28(6):1529-1546.(LI Z Y,HUANG T,CHEN S M, et al. Overview of constrained optimization evolutionary algorithms[J]. Journal of Software,2017,28(6):1529-1546.)
[6] GONG W,CAI Z,LIANG D. Adaptive ranking mutation operator based differential evolution for constrained optimization[J]. IEEE Transactions on Cybernetics,2015,45(4):716-727.
[7] SAHA A,DATTA R,DEB K. Hybrid gradient projection based genetic algorithms for constrained optimization[C]//Proceedings of the 2010 IEEE Congress on Evolutionary Computation. Piscataway:IEEE,2010:1-8.
[8] RUNARSSON T P,YAO X. Stochastic ranking for constrained evolutionary optimization[J]. IEEE Transactions on Evolutionary Computation,2000,4(3):284-294.
[9] TAKAHAMA T,SAKAI S. Constrained optimization by the ε constrained differential evolution with gradient-based mutation and feasible elites[C]//Proceedings of the 2006 IEEE International Conference on Evolutionary Computation. Piscataway:IEEE,2006:1-8.
[10] MALLIPEDDI R,SUGANTHAN P N. Ensemble of constraint handling techniques[J]. IEEE Transactions on Evolutionary Computation,2010,14(4):561-579.
[11] 于明渊. 基于自适应代理模型的粒子群算法在天线优化中的应用[D]. 郑州:郑州大学,2018,11-19. (YU M Y. Application of particle swarm optimization algorithm based on adaptive surrogate model in antenna optimization[D]. Zhengzhou:Zhengzhou University,2018,11-19.)
[12] STORN R,PRICE K. Differential evolution-a simple and efficient heuristic for global optimization over continuous spaces[J]. Journal of Global Optimization,1997,11(4):341-359.
[13] WANG Y,WANG B,LI H X,et al. Incorporating objective function information into the feasibility rule for constrained evolutionary optimization[J]. IEEE Transactions on Cybernetics,2016,46(12):2938-2952.
[14] 崔承刚, 杨晓飞. 基于内部罚函数的进化算法求解约束优化问题[J]. 软件学报,2015,26(7):1688-1699. (CUI C G,YANG X F. Interior penalty rule based evolutionary algorithm for constrained optimization[J]. Journal of Software,2015,26(7):1688-1699.)
[15] WANG G G. Adaptive response surface method using inherited Latin hypercube design points[J]. Journal of Mechanical Design, 2003,125(2):210-220.

基于代理模型的差分进化约束优化

Surrogate-based differential evolution constrained optimization

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	张祥飞, 鲁宇明, 张平生. 基于协同进化的约束多目标优化算法[J]. 计算机应用, 2021, 41(7): 2012-2018.
[2]	蔡瑞光, 张德生, 肖燕婷. 参数独立的加权局部均值伪近邻分类算法[J]. 计算机应用, 2021, 41(6): 1694-1700.
[3]	贾鹤鸣, 姜子超, 李瑶, 孙康健. 基于改进斑点鬣狗优化算法的同步优化特征选择[J]. 计算机应用, 2021, 41(5): 1290-1298.
[4]	赵志学, 李夏苗, 周鲜成. 考虑拥堵区域的多车型绿色车辆路径问题优化[J]. 计算机应用, 2020, 40(3): 883-890.
[5]	冯帅栋, 陈立家, 刘名果. 基于随机结构的无乘法无限冲激响应数字滤波器设计方法[J]. 计算机应用, 2018, 38(9): 2621-2625.
[6]	张鑫, 邹德旋, 沈鑫. 含交叉项的混合二范数粒子群优化算法[J]. 计算机应用, 2018, 38(8): 2148-2156.
[7]	刘宝, 董明刚, 敬超. 改进的排序变异多目标差分进化算法[J]. 计算机应用, 2018, 38(8): 2157-2163.
[8]	袁亦川, 杨洲, 罗廷兴, 秦进. 求解动态优化问题的多种群竞争差分进化算法[J]. 计算机应用, 2018, 38(5): 1254-1260.
[9]	李龙澍, 翁晴晴. 基于反向学习的自适应差分进化算法[J]. 计算机应用, 2018, 38(2): 399-404.
[10]	张强, 邹德旋, 耿娜, 沈鑫. 基于多变异策略的自适应差分进化算法[J]. 计算机应用, 2018, 38(10): 2812-2821.
[11]	张斌, 李延晖, 郭昊. 基于反向学习的跨种群差分进化算法[J]. 计算机应用, 2017, 37(4): 1093-1099.
[12]	刘曦, 张潇璐, 张学杰. 异构云系统中基于智能优化算法的多维资源公平分配[J]. 计算机应用, 2016, 36(8): 2128-2133.
[13]	关志艳, 冯秀芳. 差分进化融合混合虚拟力的有向传感器网络覆盖算法[J]. 计算机应用, 2016, 36(12): 3244-3250.
[14]	刘洁, 何胜学, 张皓东. 城市轨道交通车站序列瓶颈系统优化分析[J]. 计算机应用, 2016, 36(1): 271-274.
[15]	汪慎文, 张文生, 秦进, 谢承旺, 郭肇禄. 朴素差分进化算法[J]. 计算机应用, 2015, 35(5): 1333-1335.