【摘要】 布谷鸟搜索算法(CS)是一种简单有效的仿生学优化算法,但在处理高维复杂问题时不能快速收敛得到最优解,针对此问题,本文引入反向学习策略和逐维深度搜索策略改进基本的CS。在布谷鸟算法的搜索阶段,通过对Levy飞行后的解进行反向学习,从而有效提升最优解的搜索效率;另外,在每一代结束后,对当前的全局最优解进行逐维深度搜索,捕捉潜在最优解,弥补搜索步骤可能出现的问题。实验结果表明,本文对算法提出的改进,提高了算法的全局搜索能力,收敛速度以及收敛精度。更多还原

【Abstract】 Cuckoo search algorithm( CS) is a simple and effective bionic swarm optimization algorithm,however it cannot quickly converge to obtain the optimal solution when dealing with high dimensional complex problems.So in order to solve this problem,the reverse learning strategy and dimension-by-dimension depth search strategy were introduced to improve the basic CS. In the search phase of cuckoo algorithm,the efficiency of searching the optimal solution was effectively improved by opposition-based swarm strategy after Levy flight. In addition,at the end of each generation,the current global optimal solution was searched in depth and dimension to capture the potential optimal solution and make up for the problems that may arise in the search step. The research results show that the improved algorithm proposed in the text improves the global search ability,convergence speed and convergence accuracy of the algorithm.更多还原