Compensation method in genetic algorithm for multi-objective optimization

被引：0

作者：

Yuan Hua ^{[1
]}

Chen Guo-qing ^{[1
]}

机构：

[1] Tsinghua Univ, Sch Econ & Management, Beijing 100084, Peoples R China

来源：

PROCEEDINGS OF 2005 CHINESE CONTROL AND DECISION CONFERENCE, VOLS 1 AND 2 | 2005年

关键词：

multi-objective optimization; pareto-solutions; genetic algorithm; rank-based evaluation; compensation process;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Genetic algorithm (GA) in solving complex multi-objective optimization problems does not take sufficiently the effect of mathematical objective functions properties to chromosome evolution into consideration. Which makes fast convergence empower the objective function to affect much the fitness of chromosomes in evolution process. To such affection a compensation method is presented to renew the rank-based fitness evaluation GA. An example is showed and some interesting empirical results are obtained: more rational individuals survive and the set of pareto-solutions is enlarged.

引用

页码：943 / 946

页数：4

共 7 条

[1] [Anonymous], 1989, GENETIC ALGORITHM SE
[2] DHINGRA AK, 1992, IEEE T RELIABILITY, V41
[3] GEN M, 2000, GENETIC ALGORITHMS E, P224
[4] Approximating the Nondominated Front Using the Pareto Archived Evolution Strategy
Knowles, Joshua D.
Corne, David W.
[J]. EVOLUTIONARY COMPUTATION, 2000, 8 (02) : 149 - 172
[5] Srinivas N., 1994, EVOLUTIONARY COMPUTA, V2, P221, DOI [10.1162/evco.1994.2.3.221, DOI 10.1162/EVCO.1994.2.3.221]
[6] Van Veldhuizen DA, 2000, EVOL COMPUT, V8, P125, DOI 10.1162/106365600568158
[7] Multiobjective evolutionary algorithms: A comparative case study and the Strength Pareto approach
Zitzler, E
Thiele, L
[J]. IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION, 1999, 3 (04) : 257 - 271

← 1 →