摘要
提出一种基于演化历史信息的自变异协同量子行为粒子群优化算法(ESH-CQPSO).该算法采用二维空间分割树结构记录群体演化过程中的位置和适应值,借助群体之间的协同机制确保增强搜索能力,提高优化性能,防止过早收敛.通过空间分割机制可以获得一个快速的近似适应度函数.这个近似值可以提高ESH-CQPSO中的变异策略,使得相应的变异操作是一种无参数、多样性的自适应变异.对比其他传统算法,通过对标准测试函数的实验结果表明,ESH-CQPSO算法在处理多峰和单峰测试函数时具有更好的优化性能,收敛精度和收敛速度都得到了提高,证明该算法的有效性.
An improved cooperative QPSO algorithm with adaptive mutation based on entire search history （ESH- CQPSO） is proposed. The proposed algorithm employs a binary space partitioning tree structure to memorize the positions and the fitness values of the evaluated solution. The cooperation mechanism between the solutions can ensure enhanced search capabilities, improve the optimize performance and prevent premature convergence. Benefiting from the space partitio- ning scheme, a fast fitness function approximation using the archive is obtained. The approximation is used to improve the mutation strategy in ESH-CQPSO. The resultant mutation is adaptive and parameter-less. Compared with other traditional al- gorithms, the experiment results on standard testing functions show that the proposed algorithm is superior regarding the opti- mization of multimodal and unimodal functions, with enhancement in both convergence speed and precision, which demon- strate the effectiveness of the algorithm.
出处
《电子学报》
EI
CAS
CSCD
北大核心
2016年第12期2900-2907,共8页
Acta Electronica Sinica
基金
国家自然科学基金(No.61300149
No.61105128
No.61502203)
江苏省青蓝工程资助(No.2012-16)
江苏省自然科学基金(No.BK20131106)
江南大学自主科研重点计划(No.JUSRP51410B)
中国博士后科学基金(No.2014M560390)
关键词
量子行为粒子群优化
演化历史信息
自适应变异
二维空间分割
协同方式
quantum-behaved particle swarm optimization （ QPSO ）
entire search history
adaptive mutate
binary space partitioning
cooperative method
