Novel Prediction Strategies for Dynamic Multiobjective Optimization

被引:105
作者
Zhang, Qingyang [1 ]
Yang, Shengxiang [2 ,3 ]
Jiang, Shouyong [4 ]
Wang, Ronggui [5 ]
Li, Xiaoli [6 ]
机构
[1] Jiangsu Normal Univ, Sch Comp Sci & Technol, Xuzhou, Jiangsu, Peoples R China
[2] De Montfort Univ, Sch Comp Sci & Informat, Leicester LE1 9BH, Leics, England
[3] Southern Univ Sci & Technol, Dept Comp Sci & Engn, Shenzhen 518055, Peoples R China
[4] Univ Lincoln, Sch Comp Sci, Lincoln LN6 7TS, England
[5] Hefei Univ Technol, Sch Comp & Informat, Hefei 230009, Peoples R China
[6] Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
基金
中国国家自然科学基金; 英国工程与自然科学研究理事会;
关键词
Heuristic algorithms; Sociology; Statistics; Prediction algorithms; Optimization; Optical fibers; Convergence; Dynamic multiobjective optimization; nondominated sorting; prediction-based reaction; probability distribution; ALGORITHM; ENVIRONMENTS; MODEL;
D O I
10.1109/TEVC.2019.2922834
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper proposes a new prediction-based dynamic multiobjective optimization (PBDMO) method, which combines a new prediction-based reaction mechanism and a popular regularity model-based multiobjective estimation of distribution algorithm (RM-MEDA) for solving dynamic multiobjective optimization problems. Whenever a change is detected, PBDMO reacts effectively to it by generating three subpopulations based on different strategies. The first subpopulation is created by moving nondominated individuals using a simple linear prediction model with different step sizes. The second subpopulation consists of some individuals generated by a novel sampling strategy to improve population convergence as well as distribution. The third subpopulation comprises some individuals generated using a shrinking strategy based on the probability distribution of variables. These subpopulations are tailored to form a population for the new environment. The experimental results carried out on a variety of bi- and three-objective benchmark functions demonstrate that the proposed technique has competitive performance compared with some state-of-the-art algorithms.
引用
收藏
页码:260 / 274
页数:15
相关论文
共 49 条
[1]  
Abello MB, 2011, IEEE C EVOL COMPUTAT, P1711
[2]  
[Anonymous], [No title captured]
[3]  
[Anonymous], 1995, CELL IMMUNOL
[4]   A dynamic multi-objective evolutionary algorithm using a change severity-based adaptive population management strategy [J].
Azzouz, Radhia ;
Bechikh, Slim ;
Ben Said, Lamjed .
SOFT COMPUTING, 2017, 21 (04) :885-906
[5]  
Branke J, 2000, EVOLUTIONARY DESIGN AND MANUFACTURE, P299
[6]   Global memory schemes for dynamic optimization [J].
Bravo, Yesnier ;
Luque, Gabriel ;
Alba, Enrique .
NATURAL COMPUTING, 2016, 15 (02) :319-333
[7]  
Bui L. T., 2010, IEEE Cong Evolut Comp, P1, DOI DOI 10.1109/CEC.2010.5586343
[8]   Optimization in dynamic environments: a survey on problems, methods and measures [J].
Cruz, Carlos ;
Gonzalez, Juan R. ;
Pelta, David A. .
SOFT COMPUTING, 2011, 15 (07) :1427-1448
[9]   Dynamic multiobjective optimization problems: Test cases, approximations, and applications [J].
Farina, M ;
Deb, K ;
Amato, P .
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION, 2004, 8 (05) :425-442
[10]   Dynamic Adjustment of Hidden Node Parameters for Extreme Learning Machine [J].
Feng, Guorui ;
Lan, Yuan ;
Zhang, Xinpeng ;
Qian, Zhenxing .
IEEE TRANSACTIONS ON CYBERNETICS, 2015, 45 (02) :279-288