本文選題：粒子群　切入點：混沌粒子群　出處：《實驗室研究與探索》2016年10期 　論文類型：期刊論文

【摘要】：傳統(tǒng)的粒子群優(yōu)化(Particle Swarm Optimization,PSO)算法易陷入局部最優(yōu),因此引入了混沌優(yōu)化形成混沌粒子群(Chaotic Particle Swarm Optimization,CPSO)算法以減小粒子陷入局部最優(yōu)的可能,并在此基礎上結合了差異進化(Differential Evolution,DE)算法中的交叉操作得到改進粒子群優(yōu)化(Improved Particle Swarm Optimization,IPSO)算法以增加粒子的多樣性,從而增加獲得更優(yōu)解的可能。為驗證算法有效性,將PSO、CPSO和IPSO基于Matlab軟件分別對IEEE30節(jié)點測試系統(tǒng)進行電力系統(tǒng)無功優(yōu)化仿真。仿真結果表明,IPSO算法能找到質量更高的解,且收斂特性更好,體現(xiàn)了算法改進的優(yōu)越性。通過該仿真實驗,既可加強學生運用仿真軟件的能力,又可加深學生對無功優(yōu)化的理解和對智能算法的認識,從而有效提高教學質量。
[Abstract]:The traditional particle swarm optimization (PSO) algorithm is easy to fall into local optimum, so chaotic Particle Swarm optimization algorithm is introduced to reduce the possibility of particle falling into local optimization. On the basis of this, the improved Particle Swarm optimization (IPSOs) algorithm is obtained by combining the cross operation in the differential evolution evolution (DEE) algorithm to increase the diversity of particles and increase the possibility of obtaining a better solution. In order to verify the effectiveness of the algorithm, the improved particle swarm optimization (PSO) algorithm is proposed in this paper. The reactive power optimization simulation of IEEE30 node testing system based on Matlab software is carried out by PSO-CPSO and IPSO respectively. The simulation results show that the PSO-CPSO algorithm can find a higher quality solution and the convergence characteristic is better. The simulation experiment can not only strengthen the students' ability to use the simulation software, but also deepen the students' understanding of reactive power optimization and the understanding of the intelligent algorithm, so as to improve the teaching quality effectively.
【作者單位】： 重慶郵電大學自動化學院;重慶市教育科學研究院高等教育研究所;
【基金】：重慶市研究生教改項目(yig143061) 重慶郵電大學教育教學改革項目(XJG1522)
【分類號】：TP18
，

本文編號：1624514