一种基于小生境的自适应入侵野草优化算法

A Niche-based Adaptive Weed Invasion Optimization Algorithm

针对入侵野草优化(Invasive Weed Optimization,IWO)算法在迭代前期局部搜索能力不足和后期缺乏种群多样性的缺点,论文提出了一种基于小生境思想的自适应入侵野草优化(Niche-based Adaptive Invasive Weed Optimization,NAIWO)算法。小生境思想用来增加算法的种群多样性;自适应机制中引入周期算子和自适应算法,使野草个体的空间扩散的标准差不仅随迭代次数变化,而且可以根据周期算子的参数和个体的适应度值来动态变化。通过多个数学基准函数的寻优测试验证了所提出的NAIWO算法的有效性。

In view of the shortcomings of the local search ability of the Invasive weed optimization(IWO)algorithm in the early stage of iteration and the lack of population diversity in the later stage,a niche-based adaptive invasion weed optimization(NAIWO)algorithm is proposed. The niche is used to increase the population diversity of the algorithm. In the adaptive mechanism,periodic operator and adaptive algorithm are introduced to make the standard deviation of spatial diffusion of weeds vary not only with the number of iterations,but also according to the parameters of periodic operators and the fitness value of weed individuals. The optimization test of multiple mathematical benchmark functions verifies the effectiveness of the proposed NAIWO algorithm.