摘要
针对标准粒子群(SPSO)算法易收敛到局部最优的缺点,采用了一种改进的粒子速度更新公式,即在SPSO算法速度更新公式的基础上,加入一个平均极值项,使得各粒子能参考其它同伴的信息;此外在算法迭代过程中加入变异操作,适时初始化失活粒子的位置和速度来保持种群多样性.在输电网扩展规划中的应用结果表明,上述两个操作可以提高PSO算法的收敛精度,使算法最终寻找到全局最优解,从而证明了改进粒子群(IPSO)算法的有效性.
In view of the deficiency of Standard Particle Swarm Optimization （SPSO） algorithm, that is, easy convergence to the local optimum, an improved renewal equation of the particles＂ velocities is used, in which an average minimum on the renewal equation of SPSO is added so that each particle can refer to its companiong mes- sage. Furthermore, a mutation operation is added to the iterative process to initialize the positions and velocities of the unable particles in order to keep the diversity of particle swarm. The numerical simulation results of power transmission network expansion planning demonstrate that the above two operations can improve the convergence precision of SPSO algorithm and help it to find the global optimum, and therefore, the effectiveness of the Improved Particle Swarm （IPSO） algorithm is proved.
出处
《昆明理工大学学报（理工版）》
CAS
北大核心
2009年第1期82-86,共5页
Journal of Kunming University of Science and Technology(Natural Science Edition)
关键词
输电网规划
粒子群算法
变异操作
transmission network planning
particle swarm optimization algorithm
mutation operation
