一种改进的人工生态系统优化算法

An improved artificial ecosystem optimization algorithm

人工生态系统优化算法是一种模拟生态系统中生物生产、消耗和分解的一种元启发式算法,具有简单、可调节参数少等优点,但容易早熟收敛或陷入局部最优。为了进一步提高人工生态系统优化算法的性能,本文提出一种改进的人工生态系统优化算法,记作IIAEO。通过模拟光的折射进行种群初始化,提高初始解的质量,将Lévy飞行和布朗运动相结合,更好地平衡探索和开采能力;同时,加入余弦算子和Cauchy算子,避免陷入局部最优。将IIAEO算法与其他四种算法在5个基准函数上进行对比实验,统计分析结果表明,该算法具有良好的性能,明显优于原始的人工生态系统优化算法。

Artificial Ecosystem based Optimization(AEO)is a kind of meta-heuristic algorithm that simulates the biological production,consumption and decomposition in the ecosystem.It has the advantages of simplicity and few adjustable parameters,but it is easy to converge prematurely and fall into local optimum.In order to further improve the performance of AEO,this paper proposes an improved AEO,denoted as IIAEO.Firstly,the population initialization is performed by simulating light refraction to improve the quality of the initial solution.Second,Lévy Flight and Brownian motion are combined to better balance between exploration and exploitation.At the same time,the cosine operator and Cauchy operator are added to avoid falling into local optimum.The comparison experiments among IIAEO algorithm and other four algorithms on five benchmark functions are condcuted.Statistical analysis results show that the proposed algorithm has good performance and is significantly better than the original AEO.