采用异构搜索的多子群协同进化粒子群算法  

Multi-swarm cooperative particle swarm algorithm with heterogeneous search strategy

作　　者：林国汉[1,2] 章兢[2] 刘朝华[3] 

机构地区：[1]湖南工程学院电气信息学院,湖南湘潭411101 [2]湖南大学电气与信息工程学院,长沙410082 [3]湖南科技大学信息与电气工程学院,湖南湘潭411021

出　　处：《计算机应用研究》2016年第3期677-681,共5页Application Research of Computers

基　　金：国家自然科学基金资助项目(61174140);中国博士后基金资助项目(2013M540628);湖南省自然科学基金资助项目(14JJ3107)

摘　　要：针对传统的单种群粒子群优化算法易陷入局部最优、搜索精度低的问题,提出一种异构多子群粒子群算法。算法由自适应子群、精英子群和若干普通子群构成,精英子群由普通子群和自适应子群中的优秀个体组成,每个子群采用不同策略进行进化,根据种群的早熟收敛程度和粒子的适应度值自适应地调整惯性权重;自适应子群根据普通子群的适应度值和速度自适应调整飞行方向,采用免疫克隆选择算子对精英子群进行精细搜索,普通子群、自适应子群与精英子群之间通过迁移操作实现信息的充分交流。针对典型的Benchmark函数优化问题测试,仿真结果表明所提算法能较好地保持粒子多样性,收敛精度高且全局搜索能力强,具有良好的优化性能。Conventional particle swarm optimization is easily trapped in local optima and has the problem of low search accuracy. This paper proposed a multi-swarm particle swarm optimization with heterogeneous search. The proposed algorithm consisted of one adaptive sub-swarm,one elite sub-swarm and several ordinary sub-swarm,particles in elite sub-swarm were outstanding individuals migrated from adaptive sub-swarm and ordinary sub-swarm. Each sub-swarm evolved with heterogeneous strategies. It changed the inertia weight adaptively according to the degree of population premature convergence. It adjusted the flight direction of the particles in adaptive sub-swarm according to fitness value and speed of ordinary sub-swarm. It employed the immune clonal selection operator for optimizing the elite sub-swarm while employed the migration scheme for the information exchange between elite sub-swarm and others sub-swarm. Experiments on four benchmark function show that the proposed method can maintain the diversity of particles with strong global search capability,and converge with high precision and with better optimization performance.

关 键 词：粒子群优化 异构搜索 多子群 协同进化 多样性 克隆选择 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]