多子群的共生非均匀高斯变异樽海鞘群算法

针对樽海鞘群算法求解精度不高和收敛速度慢等缺点, 提出一种多子群的共生非均匀高斯变异樽海鞘群算法. 根据不同适应度值将樽海鞘链群分为三个子种群, 各个子种群分别进行领导者位置更新、追随者共生策略和链尾者非均匀高斯变异等操作. 使用统计分析、收敛速度分析、Wilcoxon检验、经典基准函数和CEC 2014函数的标准差来评估改进樽海鞘群算法的效率. 结果表明, 改进算法具有更好的寻优精度和收敛速度. 尤其在求解高维和多峰测试函数上, 改进算法拥有更好性能.

Multi-subpopulation Based Symbiosis and Non-uniform Gaussian Mutation Salp Swarm Algorithm

In order to solve the problem that the standard salp swarm algorithm has a small convergent rate and low result precision in the evolutionary process, an improved algorithm called multi-subpopulation based symbiosis and non-uniform Gaussian mutation salp swarm algorithm (MSNSSA) is proposed in this paper. According to the different fitness values, the salp chain population is divided into three sub-populations, which perform the operations of leader position update, follower symbiosis strategy and chain tail non-uniform Gaussian mutation, respectively. The efficiency of the MSNSSA is evaluated using statistical analysis, convergence rate analysis, Wilcoxon＇s test, standard deviations on classical benchmark functions and modern CEC 2014 functions. The results show that the MSNSSA has better optimization accuracy and convergence rate. Especially, in solving the high-dimension and multimodal function optimization problem, the improved algorithm has better performance.