基于惯性权值和自适应变异改进的麻雀搜索算法

Improved Sparrow Search Algorithm Based on Inertia Weight Value and Adaptive Mutation

摘要: 传统的麻雀搜索算法(SSA)在求解复杂优化问题的时候，可能出现陷入局部最优的情况。为改进SSA算法以提高算法的收敛速度与收敛精度，本文在已有研究的基础上提出了基于惯性权值和自适应变异改进的麻雀搜索算法(IASSA)。首先利用改进的Chebyshev混沌初始化种群来增加种群的多样性，提高麻雀个体的遍历性，以期望种群可以尽可能均匀分布搜索空间；其次，增加一种惯性权值来改善发现者的更新位置，以减小过早陷入局部最优的概率；最后，提出一种自适应的选择变异策略使得麻雀在陷入局部最优时能够跳出。通过对10个基准测试函数进行的仿真实验，结果表明，所提算法较原算法有着更好的收敛速度与收敛精度。

Abstract: The traditional sparrow search algorithm (SSA) may fall into local optimization when solving com-plex optimization problems. In order to improve the SSA algorithm to improve the convergence speed and accuracy of the algorithm, an improved sparrow search algorithm (IASSA) based on iner-tia weight value and adaptive mutation is proposed based on the existing research. Firstly, the im-proved Chebyshev chaos is used to initialize the population to increase the diversity of the popula-tion and improve the ergodicity of sparrow individuals, so as to expect the population to distribute the search space as evenly as possible; Secondly, an inertia weight value is added to improve the update position of the discoverer to reduce the probability of falling into the local optimum too ear-ly; Finally, an adaptive selection mutation strategy is proposed to make sparrows jump out when they fall into local optimization. The simulation results of 10 benchmark functions show that the proposed algorithm has better convergence speed and convergence accuracy than the original algo-rithm.