一种混合麻雀搜索算法
2021-04-13李敦桥
李敦桥



摘要:元启发式算法由于可产生多样的解决方案在科学及工业领域受到了广泛的应用,麻雀搜索算法(SSA)是一种相对新颖的基于群体的元启发式算法,已被证明具有较好的寻优求解性能。由于在某些情况下麻雀种群多样性不足,导致算法寻优精度低,易陷入局部最优,因此提出了一种混合麻雀搜索算法(HSSA),首先利用反向对立学习策略提高初始种群质量,其次混合了模拟退火算法的Metropolis准则,避免算法陷入局部最优。为了验证算法的性能,利用HSSA对多个单峰和多峰测试函数进行求解,实验结果表明,与WOA、SSA和IPSO相比,HSSA具有更快的收敛速度和更高的求解精度。
关键词:麻雀搜索算法;反向对立学习;Metropolis准则;混合算法;函数优化
Abstract: Meta-heuristic algorithm has been widely used in science and industry because it can produce a variety of solutions. The sparrow search algorithm (SSA) is a relatively new population-based meta-heuristic algorithm, which has been proved to have good performance in optimization. Due to the insufficient diversity of sparrow population in some cases, the optimization precision of the algorithm is low and it is easy to fall into the local optima. Therefore, the hybrid sparrow search algorithm (HSSA) is proposed, which firstly improves the initial population quality by using the Opposition-based learning strategy, and secondly the algorithm mixes the Metropolis criterion of simulated annealing algorithm to avoid the algorithm falling into local optimal. In order to verify the performance of the algorithm, HSSA was used to solve some unimodal and multimodal test functions. The experimental results show that compared with WOA, SSA and IPSO, the proposed HSSA has faster convergence rate and higher solution accuracy.
Key words: sparrow search algorithm; opposition-based learning; metropolis criterion; hybrid algorithm; function optimization
群智能优化算法已被广泛应用于现实生活中各种优化问题求解,通过模仿飞蛾、蜜蜂、狼和鸟类等自然界各种物理或生物行为构造出数学模型,利用多次迭代获取最佳解决方案[1-3]。麻雀搜索算法(Sparrow Search Algorithm, SSA)[4]是由沈波等在2020年提出的一種新型群智能优化算法,该算法通过模拟麻雀群体智慧、觅食和抗捕食行为来获取最优解,经实验证明,SSA在精度、收敛速度、稳定性和鲁棒性都具有较强的性能。但由于种群多样性不足,SSA算法在迭代过程中极易跳过最优解而陷入局部最优,导致全局搜索能力较差,No Free Lunch(NFL)定理[5]表明,没有任何一种算法可以在每个优化问题上都表现出色,因此,研究群智能优化算法的改进依旧具有很强的实际意义。
针对……
