基于改进混沌优化的多目标遗传算法

Multi-objective genetic algorithm based on improved chaotic optimization

针对多目标遗传算法存在的缺陷,提出了基于改进混沌优化的多目标遗传算法.引入基于改进Tent映射的自适应变尺度混沌优化方法细化搜索空间和高效寻优,结合非支配排序的群体分级机制和精英保留等多目标优化策略,保持种群多样性的同时保证了进化向Pareto最优解集的方向进行.多目标测试函数的数值仿真和电力系统无功优化的算例分析表明了该算法的有效性和可行性.

For the problems of multi-objective genetic algorithms（MGA）, chaotic optimization multi-objective optimization genetic algorithm（CMGA） is proposed. Adaptive mutative scale chaotic optimization algorithm based on improved chaotic map is used for search space refinement and efficient optimization. Multi-objective optimization strategies such as non- dominated sorting mechanisms and elitist preserve are used to maintain population diversity while ensuring the evolution direction of Pareto global optimal solution set. Multi-objective test functions simulation and numerical example of reactive power optimization show the effectiveness and feasibility of the proposed algorithm.