论文部分内容阅读
为了克服粒子群优化算法容易陷入局部最优而发生早熟收敛的问题,提出一种基于进化停滞周期的局部变异粒子群优化算法.算法引入进化停滞周期和近期全局最优位置的概念,使粒子的飞行受近期全局最优位置影响,并在种群进化停滞时对随机选中的局部粒子执行变异操作,增加种群多样性,扩大搜索范围,提高求解质量.算法用种群进化停滞周期代替多样性度量,避免了多样性计算引起的高计算复杂度.对于几个常用基准函数的仿真结果验证了算法的合理性和有效性.
In order to overcome the premature convergence problem of Particle Swarm Optimization (PSO) algorithm that is easily trapped in local optima, a local variation PSO algorithm based on evolutionary stagnation period is proposed. The algorithm introduces the concept of evolutionary stagnation cycle and the recent global optimal location, The flight is affected by the recent global optimum location and performs mutation operations on randomly selected local particles during the stagnant population to increase the population diversity, expand the search range and improve the quality of the solution. The algorithm substitutes the population evolution stagnation period instead of the diversity measure to avoid The computational complexity caused by the diversity calculation is high.The simulation results of several commonly used benchmark functions verify the rationality and effectiveness of the algorithm.