关键词: 樽海鞘群算法, 高斯分布估计, 精英池, 函数优化

Abstract:

In order to address the shortcomings of the salp swarm algorithm (SSA) in solving complex optimization problems, such as reduced population diversity and easy to fall into local optimum, an improved SSA using elite pool strategy and Gaussian distribution estimation strategy (GDESSA) is proposed. Firstly, an elite pool strategy is proposed. When the leader position is updated at each time, an individual from the elite pool is randomly selected as a food source, which enhances the exploration ability of the leader and enriches the population diversity. Secondly, the follower formula is improved using a Gaussian distribution estimation strategy. By fitting the dominant population information, the evolutionary direction of the population is modified, and the algorithm's optimization ability is enhanced. The proposed algorithm is tested using the CEC2017 test suite and the performance of the improved algorithm is evaluated by statistical analysis, convergence analysis, stability analysis, Wilcoxon test, Friedman test, and Iman-Davenport test. The simulation results show that the improved strategy proposed can effectively improve the performance of the algorithm, and the proposed algorithm has faster convergence speed and better convergence accuracy compared with other algorithms.

Key words: salp swarm algorithm (SSA), Gaussian distribution estimation, elite pool, function optimization