摘要
针对蛇算法求解精度不高和收敛速度慢等缺点,提出一种基于精英反向学习策略和正余弦算法优化的蛇算法(ESSO)首先在初始化种群时,引入精英反向学习策略生成初始种群,以增加初始个体的多样性;在战斗模式下,引入正余弦算法对蛇个体的位置进行更新,使其有效地避免陷入局部最优,并引入自适应权重,平衡全局和局部搜索能力;最后基于12个基准函数进行测试以评估改进算法的效率。结果表明,改进算法与其它6种算法相比,具有更好的全局搜索能力和稳定性,同时,寻优精度和收敛速度也相较原算法有所增强。
A Snake Optimizer(ESSO)based on elite reverse learning strategy and sine-cosine algorithm optimi⁃zation is proposed to solve the problems of low solution accuracy and slow convergence speed of Snake Optimizer.First,when initializing the population,the elite reverse learing strategy is introduced to generate the initial population,in order to increase the diversity of the initial individuals;In the combat mode,the sine and cosine algorithm is intro⁃duced into the position update formula of male and female individuals,which effectively avoids fallinginto local opti⁃mum,and introduces adaptive weights to balance global andlocal search capabilities;Finally,performance tests are performed based on 12 benchmark functions toevaluate the efficiency of theimproved algorithm.The results show that compared with the other six algorithms,the improved algorithmhas better global search ability and solution robustness.At the same time,the optimization accuracy andconvergence speed of the algorithm are also better than the previous Snake Optimizer.
作者
储飞
王加阳
田福林
CHU Fei;WANG Jia-yang;TIAN Fu-lin(School of Computer Science,Central South University,Changsha 410006,Hunan,China)
出处
《计算机仿真》
2024年第6期455-461,共7页
Computer Simulation
基金
国家自然科学基金(61772031)。
关键词
蛇优化
反向学习
正余弦算法
Snake Optimizer
Reverse learning
Sine and cosine algorithm
