文章分析了M A S建模方法学提出的动因,指出了M A S建模中的关键问题;阐述了基于A gen t的建模方法学分析阶段的过程及其不足,研究了对系统子目标进行表述、求解的规范化工具——G/A矩阵及其求解方法;并在此基础上提出了一种新的M A S...文章分析了M A S建模方法学提出的动因,指出了M A S建模中的关键问题;阐述了基于A gen t的建模方法学分析阶段的过程及其不足,研究了对系统子目标进行表述、求解的规范化工具——G/A矩阵及其求解方法;并在此基础上提出了一种新的M A S中个体A gen t的识别方法,最后通过实例说明该方法简单易行。展开更多
The uniform and extension distribution of the optimal solution are very important criterion for the quality evaluation of the multi-objective programming problem. A genetic algorithm based on agent and individual dens...The uniform and extension distribution of the optimal solution are very important criterion for the quality evaluation of the multi-objective programming problem. A genetic algorithm based on agent and individual density is used to solve the multi-objective optimization problem. In the selection process, each agent is selected according to the individual density distance in its neighborhood, and the crossover operator adopts the simulated binary crossover method. The self-learning behavior only applies to the individuals with the highest energy in current population. A few classical multi-objective function optimization examples were used tested and two evaluation indexes U-measure and S-measure are used to test the performance of the algorithm. The experimental results show that the algorithm can obtain uniformity and widespread distribution Pareto solutions.展开更多
文摘文章分析了M A S建模方法学提出的动因,指出了M A S建模中的关键问题;阐述了基于A gen t的建模方法学分析阶段的过程及其不足,研究了对系统子目标进行表述、求解的规范化工具——G/A矩阵及其求解方法;并在此基础上提出了一种新的M A S中个体A gen t的识别方法,最后通过实例说明该方法简单易行。
文摘The uniform and extension distribution of the optimal solution are very important criterion for the quality evaluation of the multi-objective programming problem. A genetic algorithm based on agent and individual density is used to solve the multi-objective optimization problem. In the selection process, each agent is selected according to the individual density distance in its neighborhood, and the crossover operator adopts the simulated binary crossover method. The self-learning behavior only applies to the individuals with the highest energy in current population. A few classical multi-objective function optimization examples were used tested and two evaluation indexes U-measure and S-measure are used to test the performance of the algorithm. The experimental results show that the algorithm can obtain uniformity and widespread distribution Pareto solutions.
