A logarithmic mutation operator to solve constrained optimization problems
暂无分享,去创建一个
We propose a method based on improving the exploration of the search space to solve constrained optimization problems. This exploration is performed with a mutation operator, whose distribution function is logarithmic. A BLX-0.5 crossover is also used. These operators are associated to a rudimentary constraint handling method implemented by a dedicated ranking selection such that feasible individuals are more likely selected than unfeasible ones.
[1] Zbigniew Michalewicz,et al. Evolutionary Algorithms, Homomorphous Mappings, and Constrained Parameter Optimization , 1999, Evolutionary Computation.
[2] Zbigniew Michalewicz,et al. Genetic AlgorithmsNumerical Optimizationand Constraints , 1995, ICGA.
[3] Larry J. Eshelman,et al. Proceedings of the 6th International Conference on Genetic Algorithms , 1995 .
[4] Zbigniew Michalewicz,et al. Evolutionary Algorithms for Constrained Parameter Optimization Problems , 1996, Evolutionary Computation.