基于模拟退火高斯扰动的蝙蝠优化算法

Bat algorithm based on simulated annealing and Gaussian perturbations

蝙蝠算法(bat algorithm,BA)是一类新型的搜索全局最优解的随机优化技术。为了提高BA算法的搜索效果,把模拟退火的思想引入到蝙蝠优化算法中,并对蝙蝠算法的某些个体进行高斯扰动,提出了一种基于模拟退火的高斯扰动蝙蝠优化算法(SAGBA)。分别将蝙蝠优化算法、模拟退火粒子群算法、SAGBA在20个典型的基准测试函数中进行仿真对比,结果表明SAGBA不仅增加了全局收敛性,而且在收敛速度和精度方面均优于其他两种算法。

Abstract： Bat algorithm is a new stochastic optimization technique for global optimization. This paper introduced both simula- ted annealing and Gaussian perturbations into the standard bat algorithm so as to enhance its search performance. As a result, it proposed a simulated annealing gaussian bat algorithm （SAGBA） for global optimization. It used BA, SAPSO and SAGBA to carry out numerical experiments for 20 test benchmarks. The simulation results show that the proposed SAGBA can indeed improve the global convergence. In addition, SAGBA is superior to the other two algorithms in terms of convergence and accu- racy.