摘要
为了避免微粒群优化算法在解决复杂优化问题时陷入局部最优,提高算法种群的多样性。将微粒群优化算法纳入文化算法框架,提出了一种新的基于文化算法框架的并行微粒群优化算法。在文化算法框架中,由微粒群组成的群体空间和信念空间各自独立并行演化,并相互影响,有效地提高了种群的多样性,降低了陷入局部极值的可能性。通过对不同测试函数的仿真实验表明,新提出的并行文化微粒群优化算法比标准微粒群优化算法更容易找到全局最优解,提高了微粒群优化算法的全局寻优能力。
In order to avoid being subject to falling into local optimum when particle swarm optimization algorithm solves some complicated problems,improve the diversity of the population.A new parallel particle swarm optimization algorithm based on cultural algorithm frame is proposed,which makes the particle swarm optimization bring into cultural algorithm frame.In the cultural algorithm frame,population space and belief space composed by particle swarm have their own parallel evolution process and affect with each other,improve the diversity of population and reduce the possibility of falling into local optima effectively.It is proven that the improved parallel particle swarm optimization based on cultural algorithm can be better to find the global optima on different benchmark optimization functions,and improve the global search capability.
出处
《计算机工程与应用》
CSCD
北大核心
2009年第35期44-46,79,共4页
Computer Engineering and Applications
基金
国家自然科学基金No.50539020
江西省自然科学基金No.2007GZS1056
江西教育厅科技项目(赣教技字[2007]339号)~~
关键词
微粒群优化算法
种群多样性
文化算法
Particle Swarm Optimization
diversity of population
cultural algorithm
