自适应变尺度混沌免疫优化算法及其应用

An adaptive chaos immune optimization algorithm with mutative scale and its application

结合混沌优化算法与免疫算法的特点,提出了一种采用折叠次数无限的自映射x=sin(2/x)产生混沌变量的自适应变尺度混沌免疫优化算法.该算法通过自适应变尺度方法不断调整优化变量的搜索空间,同时采用最大循环次数作为控制指标,既保证了寻优的准确性,又保证了算法的快速性.应用该算法对3个测试函数进行优化计算得到了比较满意的结果.将此算法应用于移动AdHoc网络入侵检测时的仿真实验结果表明,自适应变尺度混沌免疫优化算法能有效地减少对训练样本的依赖,同时减少噪音数据对入侵检测系统性能的影响,适用于移动自组网络对于入侵检测系统高检测率、高抗噪能力和低计算延迟的要求.

By combing the chaos optimization method and the immune algorithm, we propose an adaptive chaos immune optimization algorithm（AMSCIOA） with mutative scale, using one-dimensional iterative chaotic self mapping x = sin（2/x） with infinite collapses within the finite region [-1, 1]. In the optimization process, to ensure the high speed and precision some measures are taken, including： 1） the ranges of optimized variables are reduced continuously by the adaptive mutative scale method, and the searching precision is enhanced accordingly; 2） the maximal number of repetitions is regarded as a controlled index. The simulation results for three testing functions validate the high speed and precision of the AMSCIOA with mutative scale. The simulation of the intrusion detection system for detecting the intrusions to mobile Ad Hoc networks show that this algorithm lowers the dependence of training samples, reduces the noise influence on the performance, provides a high detection rate, and produces a small time-delay caused by computation.