基于Log-Linear模型的Gauss-Cauchy自适应人工鱼群算法

针对基本人工鱼群算法在寻优过程中易在非全局极值点附近大量聚集,导致寻优精度降低、收敛速度过慢、人工鱼群多样性降低等问题,提出了一种基于Log-Linear模型的Gauss-Cauchy自适应人工鱼群算法。首先,在基本人工鱼群算法中引入Log-Linear模型来优化人工鱼的三个行为;其次,在算法中引入自适应调整人工鱼视野和步长的策略,随着算法的进行提高了人工鱼的搜索范围和寻优精度;再次,利用Gauss-Cauchy变异来提高人工鱼的多样性。仿真实验结果表明,该算法与其他改进算法相比,有效地提高了收敛速度和寻优精度,保持了人工鱼群的多样性。

A novel artificial fish swarm algorithm based on Log-Linear model and Gauss-Cauchy mutation

Aiming at some defects of the traditional artificial fish swarm algorithm (AFSA), such as low optimization precision and long running time, we propose a new adaptive artificial fish swarm algorithm based on Log-Linear model and Gauss-Cauchy mutation. Firstly, we use the Log-Linear model to improve the three typical behaviors of the artificial fish, which are foraging, clustering and rear-end collision. Secondly, we adopt a policy which can adaptively adjust vision and the step length of the artificial fish in the new algorithm. Thirdly, we leverage the Gauss-Cauchy mutation to keep individual diversity and to avoid falling into the local extremum. Simulation results show that compared with other algorithms, the proposed algorithm has a better convergence speed and stability.