摘要
针对粒子群算法在解决复杂多目标问题时存在过早收敛和多样性不足的问题,提出多角色多策略多目标粒子群优化算法(MOPSO_RS).该算法根据粒子的角色划分指标,给不同性能的粒子赋予不同角色;提出多策略的学习参数调整方法和多策略的全局最优粒子选取方法,帮助种群执行各种搜索策略.不同的学习参数使各角色粒子获得不同的搜索策略,以调整粒子的探索和开发能力.不同的全局最优粒子使各角色粒子搜索不同区域,提高种群的搜索效率.为了避免算法陷入局部最优,引入带有高斯函数的变异算子,使粒子根据其角色朝向不同的全局最优粒子变异,提高算法的求解精度.实验结果表明,对比其他改进多目标算法,MOPSO_RS具有良好的收敛性和多样性,并验证了所提策略的有效性.
A multi-objective particle swarm optimization algorithm with multi-role and multi-strategy(MOPSO_RS)was proposed,in view of the immature convergence and poor diversity of particle swarm optimization in solving complex multi-objective problems.According to index-based role,the particles with different performances were assigned for different roles.A multi-strategy parameter adjustment method and global optimal particle selection method were proposed to help the population carry out various search mechanisms.Different learning parameters enabled particles with different performances to obtain different search strategies so as to adjust the exploration and exploitation capabilities of the particles.Different global optimal particles made particles search different regions to improve the search efficiency of the population.To avoid the algorithm from falling into the local optimal,a mutation operator with Gaussian function was introduced to make particles mutate toward different global optimal particles and increase accuracy of the algorithm.The experiment results indicate that MOPSO_RS has better convergence and diversity than other improved multi-objective optimization algorithms,and verifies the effectiveness of the proposed strategy.
作者
王万良
金雅文
陈嘉诚
李国庆
胡明志
董建杭
WANG Wan-liang;JIN Ya-wen;CHEN Jia-cheng;LI Guo-qing;HU Ming-zhi;DONG Jian-hang(College of Computer Science and Technology,Zhejiang University of Technology,Hangzhou 310023,China)
出处
《浙江大学学报（工学版）》
EI
CAS
CSCD
北大核心
2022年第3期531-541,共11页
Journal of Zhejiang University：Engineering Science
基金
国家自然科学基金资助项目(61873240).
关键词
多角色
多目标优化
粒子群优化算法
多策略
收敛性
多样性
multi-role
multi-objective optimization
particle swarm optimization algorithm
multi-strategy
convergence
diversity
