不同映射的混沌免疫进化算法性能分析

Performance Analysis of Chaos Immune Evolutionary Algorithm with Different Maps

针对目前混沌免疫进化算法采用的混沌映射类型单一,并存在对混沌映射影响算法性能大小和机制缺乏深入研究等问题,分析和探讨基于不同混沌映射混沌免疫进化算法的性能。对几个典型测试函数的比较结果表明,Logistic-CIEA和Cubic-CIEA的性能易出现大波动,Kent-CIEA则具有相对稳定的收敛速度,表现出较强的鲁棒性。由此证明,混沌映射作为产生局部搜索轨迹的迭代函数,其混沌特性对算法性能影响较大。

Considering single type of chaotic map and not deeply study of effect size and mechanism of chaotic map on the algorithm performance at present, this paper analyzes and dicusses performance of Chaos Immune Evolutionary Algorithm（CIEA） based on different chaotic maps. Four benchmark functions are employed to test performances of the three chaos immune evolutionary algorithms. Comparison results demonstrate that the performances of Logistic-CIEA and Cubic-CIEA are easy to cause large fluctuation. However, Kent-CIEA has relatively steady convergence rate and shows strong robustness. It proves that the performance of chaos immune evolutionary algorithm is deeply affected by the characteristic of chaotic map, which is applied to generate the local search trajectory.