解约束优化问题的新PSO算法

对约束问题的处理通常采用罚函数法,而使用罚函数法的困难在于参数的选取。文中提出了一种解约束优化问题的新PSO算法(CLDPSO)。该方法基于平滑技术设计了一个平滑函数,此函数可以消除一些局部极小点,使算法CLDPSO能有效克服标准PSO算法易陷入局部最优的缺陷;另外,结合约束优化的约束条件给出的新开关选择算子,使算法在选择下一代时保持群体中不可行解的一定比例。这不但有效的增加了群体的多样性,而且避免了传统的过度惩罚,使群体向最优解更好、更快地逼近。数值试验表明该算法对约束优化问题求解是非常有效的。

A new PSO algorithm to solve the constrained optimization problems

Penalty function is often used to deal with the constrained optimization problems,however it is difficult to choose parameter property.A new PSO algorithm(CLDPSO) solving the constrained optimization problems is presented.First,in order to make CLDPSO overcome the defaults in which the simple PSO can easily plunge into the local optimal,a smooth function based on the smooth technology can eliminate all local optimal solutions.Second,a new switch selection operator based on the constrained conditions of constrained optimization problem is also given.Using the new selection operator,CLDPSO can keep a ratio of infeasible solutions in the swarm when selecting the next generation swarm.As a result,it can not only increase the diversity of swarm but also avoid the defects of over-penalization and make the swarm approach the optimal solutions.The numerical experiments show that the proposed algorithm is effectiveness in dealing with the constrained optimization problems.