基于差分进化的布谷鸟搜索算法

针对基本布谷鸟搜索算法局部搜索能力弱、寻优精度低等不足,提出了一种具有差分进化策略的改进布谷鸟搜索算法。该算法是在种群进入下一次迭代之前在其个体上增加两个带权的差来实现个体变异,再对其进行交叉、选择操作得到最优个体,使缺乏变异机制的布谷鸟搜索算法具有变异能力,从而提高布谷鸟搜索算法的多样性,避免种群个体陷入局部最优,增强算法全局寻优能力。对几种经典测试函数和1个典型应用实例进行测试,仿真实验结果表明,新算法具有更好的全局搜索能力,在收敛精度、收敛速度以及寻优成功率等性能上显著优于基本布谷鸟搜索算法。

Cuckoo search algorithm based on differential evolution

In order to solve the problems of Cuckoo Search (CS) algorithm including low optimizing accuracy and weak local search ability, an improved CS algorithm with differential evolution strategy was presented. The individual variation was completed in the algorithm before population with two weighted differences increased on its individuals entering the next iteration, then crossover operation and select operation were performed to obtain optimal individual, which making the CS algorithm lack of mutation mechanism have the variation mechanism, so as to increase the diversity of the CS algorithm, avoid individual species into local optimum and enhance the global optimization ability. The algorithm was put through several classical test functions and a typical application example. The simulation results show that the new algorithm has better global searching ability, and the convergence precision, convergence speed and optimization success rate are significantly better than those of the basic CS algorithm.