基于均方差值调节的多目标权重系数GA算法

Multi-Objective Weight Coefficient Genetic Algorithm Based on Averge Variance Value Adjustment

提出一种改进的权重系数调节算法求解多目标Pareto最优解问题.该算法采用均方差值自适应权重调节法对各目标函数权值进行有效调节,从而提高了GA所得最终种群在多目标最优意义下具有分散性.最后通过实验优化一组测试函数来评价该算法的性能,结果表明:该算法具有很强的寻优能力,相比于其它同类算法可以更好地解决多目标优化问题.

This paper proposes a improved weight coefficient adjustment algorithm to solve Multi- objective Pareto optimal solution problem, the algorithm uses the method of average variance value adapting weight coefficient to adjust the weight of every objective function, so that it enhances the dispersion of GA goal population in the sense of multi-objective optimization. Fin.ally a set of experiments has been implemented to evaluate the performance of this algorithm by optimizing a group of test function set. The results show that this algorithm has the powerful ability of searching optimal, and compared with other multi-objective optimization algorithms, the new algorithm can perform better in solving multi-objective optimization problems.