计算机科学 ›› 2024, Vol. 51 ›› Issue (11A): 231000079-11.doi: 10.11896/jsjkx.231000079

• 智能计算 • 上一篇    下一篇

目标个数不规则变化的动态多目标优化算法

栗三一, 刘爽   

  1. 郑州轻工业大学 郑州 450000
  • 出版日期:2024-11-16 发布日期:2024-11-13
  • 通讯作者: 栗三一(wslisanyi@163.com)
  • 基金资助:
    国家自然科学基金(62203402,62103378);河南省科技攻关项目(202102310284,32102321034)

Dynamic Multi-Objective Optimization Algorithm with Irregularly Varying Number of Objectives

LI Sanyi, LIU Shuang   

  1. Zhengzhou University of Light Industry,Zhengzhou 450000,China
  • Online:2024-11-16 Published:2024-11-13
  • About author:LI Sanyi,born in 1988,Ph.D,lecturer.His main research interests include multi-objective optimization,process automation in process industry,neural network modeling and fault diagnosis of power system equipment.
  • Supported by:
    National Natural Science Foundation of China(62203402,62103378) and Science and Technology Project of Henan Province(202102310284,232102321034).

摘要: 文中提出了一种基于混合策略的初始种群预测算法(A Hybrid Strategy Based Initial Population Rrediction Algorithm,HIPPA)来解决目标个数随时间不规则变化的动态多目标优化问题。HIPPA依据目标个数判断环境是否发生变化,根据不同的目标个数划分环境类型。在种群初始化阶段,初始种群由3种机制产生。首先,利用历史种群信息训练改进的神经网络算法,生成一部分初始种群。其次,改进的精英策略利用历史种群信息生成一部分初始种群。最后,使用改进的随机策略生成一部分种群,以保持种群的多样性。本文使用基准实验F1-F5验证所提算法的有效性,并将结果与其他动态优化算法对比。实验结果表明,HIPPA可以更加有效地解决目标个数随时间不规则变化的动态多目标优化问题。

关键词: 动态多目标优化, 神经网络, 预测, 目标个数不规则变化

Abstract: tIn this paper,a hybrid strategy based initial population prediction algorithm(HIPPA) is proposed to solve the dynamic multi-objective optimization problem where the number of objectives varies irregularly with time.HIPPA determines whether the environment has changed according to the number of objectives,and divides the environment type according to the different number of objectives.In the population initialization stage,the initial population is generated by three mechanisms.First,an improved neural network algorithm is trained using historical population information to generate a part of the initial population.Second,the improved elite strategy uses historical population information to generate a portion of the initial population.Finally,an improved random strategy is used to generate a portion of the population to maintain the diversity of the population.In this paper,the effectiveness of the proposed algorithm is verified by reference experiment F1-F5,and the results are compared with other dynamic optimization algorithms.Experimental results show that HIPPA can more effectively solve the dynamic multi-objective optimization problem where the number of objectives varies irregularly with time.

Key words: Dynamic multi-objective optimization, Neural network, Prediction, The number of objectives varies irregularly

中图分类号: 

  • TP301
[1]CHEN J H,CHENG C W.Multi-objective evolutionary optimization of dynamic service facility location problems[J/OL].https://doi.org/10.1109/SECON.2011.5752961.
[2]DEB K,BHASKARA RAO U,KARTHIK S.Dynamic multi-objective optimization and decision-making using modified NSGA-II:A case study on hydro-thermal power scheduling[J/OL].https://doi.org/10.1007/978-3-540-70928-2_60.
[3]HUTZSCHENREUTER A K,BOSMAN P A N,POUTRÉ H L.Evolutionary Multiobjective Optimization for Dynamic Hospital Resource Management[J/OL].https://doi.org/10.1007/978-3-642-01020-0_27.
[4]OU J W,ZHENG J H,RUAN G,et al.A pareto-based evolutionary algorithm using decomposition and truncation for dynamic multi-objective optimization[J].Applied Soft Computing,2019,85:105673.
[5]LIU M,ZHENG J H,WANG J N,et al.An Adaptive Diversity Introduction Method for Dynamic Evolutionary Multiobjective Optimization[J/OL].https://doi.org/10.1109/CEC.2014.6900364.
[6]GOH C K,TAN K C.A competitive-cooperative coevolutionaryparadigm for dynamic multiobjective optimization[J].IEEE Transactions on Evolutionary Computation,2009,13(1):103-127.
[7]LI J X,LIU R C,WANG R N.A change type-based self-adaptive response strategy for dynamicmulti-objective optimization[J].Knowledge-Based Systems,2022,243:108447.
[8]WANG C F,YEN G G,ZOU F.A novel predictive methodbased on key points for dynamic multi-objective optimization[J].Expert Systems with Applications,2022,190:116127.
[9]WANG Y,LI K C,WANG G G.Combining Key-Points-Based Transfer Learning and Hybrid Prediction Strategies for Dynamic Multi-Objective Optimization[J].Mathematics,2022,10(12):2117.
[10]OU J W,LI M G,XING L N,et al.Individual-based self-lear-ning prediction method for dynamic multi-objective optimization[J].Information Sciences,2022,613:401-418.
[11]YAN L,QI W L,LIANG J,et al.Inter-individual correlation and Dimension Based Dual Learning for Dynamic Multi-objective Optimization[J/OL].https://doi.org/10.1109/TEVC.2023.3235196.
[12]KAMALI S R,BANIROSTAM T,MOTAMENI H,et al.An immune inspired multi-agent system for dynamic multi-objective optimization[J].Knowledge-Based Systems,2023,262:110242.
[13]XU X X,TAN Y Y,ZHENG W,et al.Memory-Enhanced Dynamic Multi-Objective Evolutionary Algorithm Based on Lp Decomposition[J].Applied Sciences,2018,8(9):1673.
[14]YANG Y,LIAO Q F,WANG J,et al.Application of multi-objective particle swarm optimization based on short-term memory and K-means clustering in multi-modal multi-objective optimization[J].Engineering Applications of Artificial Intelligence,2022,112:104866.
[15]KARABADJI N E I,BELDJOUDI S,SERIDI H,et al.Improving memory-based user collaborative filtering with evolutionary multi-objective optimization[J].Expert Systems with Applications,2018,98:153-165.
[16]ZHUO J L,CHAKRABARTI C.An efficient dynamic taskscheduling algorithm for battery powered DVS systems[C]//ASP-DAC '05.2005:846-849.
[17]CHEN R Z,LI K,YAO X.Dynamic Multi-Objectives Optimization with a Changing Number of Objectives[J].IEEE Transactions on Evolutionary Computation,2018,22:157-171.
[18]ISMAYILOV G,TOPCUOGLU H R.Neural network basedmulti-objective evolutionary algorithm for dynamic workflow scheduling in cloud computing[J].Future Generation Computer Systems,2020,102:307-322.
[19]JIANG Y,ZHENG Y P,ZHANG X,et al.Motor AbnormalSound Diagnosis Based on Improved BP Neural Network[J].Journal of Chongqing University of Technology,2020,34(1):242-246,262.
[20]ZENG G Q,CHEN J,LI L M,et al.An improved multi-objective population-based extremal optimization algorithm with polynomial mutation[J].Information Sciences,2016,330:49-73.
[21]DEB K,THIELE L,LAUMANNS M,et al.Scalable test pro-blems for evolutionary multiobjective optimization[J].Evolutio-nary Multiobjective Optimization,2005:105-145.
[22]ALLMENDINGER R,JASZKIEWICZ A,LIEFOOGHE A,et al.What if we increase the number of objectives?Theoretical and empirical implications for many-objective combinatorial optimization[J].Computers & Operations Research,2022,145:105857.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!