[1]李荣龙,罗杰. 一种改进的粒子群优化算法[J].计算机技术与发展,2015,25(07):57-71.
　LI Rong-long,LUO Jie. An Improved Particle Swarm Optimization Algorithm[J].,2015,25(07):57-71.
点击复制

 一种改进的粒子群优化算法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
25
期数:
2015年07期
页码:
57-71
栏目:
智能、算法、系统工程
出版日期:
2015-07-10

文章信息/Info

Title:
 An Improved Particle Swarm Optimization Algorithm
文章编号:
1673-629X（2015)07-0067-05
作者:
 李荣龙; 罗杰
 南京邮电大学 自动化学院
Author(s):
 LI Rong-long; LUO Jie
关键词:
 ; 粒子群优化; 全局最优解; 早熟收敛; 拉伸操作; 自适应拉伸因子
Keywords:
 ; particle swarm optimization; global optimal solution; premature convergence; stretching operation; adaptive stretch factor
分类号:
TP301
文献标志码:
A
摘要:
 近年来，粒子群优化算法已被广泛地用于解决各类优化问题。粒子群优化算法具有概念简单和收敛速度较快等优点。但是当用粒子群算法处理高维复杂问题时，往往会遇到陷入局部最优值，迭代后期收敛速度慢，解的精度低等缺点。针对粒子群优化算法容易收敛到局部最小值的缺点，文中提出了一种改进的粒子群优化算法。当粒子陷入较差的搜索区域时，以一定的概率对被困粒子实行拉伸操作，将粒子从较差区域向目前搜索到的较好区域拉伸，使被困粒子跳出较差区域，向较好的区域搜索，这样就可以合理分配搜索资源。这种改进算法一定程度上减少了粒子搜索到局部最优解的概率，使得粒子具有更大的搜索到全局最优解的可能性，并且可能搜索到精度更高的解。针对基准测试函数，对改进的粒子群算法和标准粒子群算法进行对比实验，结果表明该改进粒子群算法在大部分基准测试函数上取得了比较好的效果。
Abstract:
 In recent years,PSO algorithm has been widely used to solve various optimization problems. The advantages of PSO are with a simple concept and a higher convergence speed. But when dealing with high-dimensional complex optimization problems with particle swarm optimization,it often runs into a local optimum and the solution has a low accuracy. An improved particle swarm optimization al-gorithm is proposed in order to solve the defect of falling into local optimum easily. When the particles trapped into a bad search area,a stretching operation will be implemented with a certain probability. The trapped particles will be stretched out the bad search areas and search in the better areas. In this way,the resources of searching can be allocated more reasonably. This improved PSO algorithm reduces the probability of searching for a local optimal solution,and with a higher probability to get the global optimal solution or a solution with a higher accuracy. A comprehensive experimental study is conducted on a set of benchmark functions. Compared with the standard PSO algorithm,the improved PSO algorithm performs more competitively in the majority of the benchmark functions.

相似文献/References:

[1]崔海青 刘希玉.基于粒子群算法的RBF网络参数优化算法[J].计算机技术与发展,2009,(12):117.
　CUI Hai-qing,LIU Xi-yu.Parameter Optimization Algorithm of RBF Neural Network Based on PSO Algorithm[J].,2009,(07):117.
[2]陆克中 吴璞 王汝传.基于粒子群优化算法的非线性系统模型参数估计[J].计算机技术与发展,2008,(06):57.
　LU Ke-zhong,WU Pu,WANG Ru-chuan.A Method of Parameter Estimation in a Nonlinear System Model Based on Particle Swarm Optimization[J].,2008,(07):57.
[3]赵传信 张雪东 季一木[].改进的粒子群算法在VRP中的应用[J].计算机技术与发展,2008,(06):240.
　ZHAO Chuan-xin,ZHANG Xue-dong,JI Yi-mu.Application of Improved Particle Swarm Optimization in VRP[J].,2008,(07):240.
[4]陆克中 方康年.PSO算法在非线性回归模型参数估计中的应用[J].计算机技术与发展,2008,(12):134.
　LU Ke-zhong,FANG Kang-nian.Application of PSO Algorithm in Parameter Estimation of Nonlinear Regression Models[J].,2008,(07):134.
[5]苏守宝 汪继文 方杰.粒子群优化技术的研究与应用进展[J].计算机技术与发展,2007,(05):249.
　SU Shou-bao,WANG Ji-wen,et al.Overview Applications and Research on Particle Swarm Optimization Algorithm[J].,2007,(07):249.
[6]陆克中 张秋华 孙兰娟.一种改进的粒子群优化算法及其仿真[J].计算机技术与发展,2007,(11):88.
　LU Ke-zhong,ZHANG Qiu-hua,SUN Lan-juan.An Improved Particle Swarm Optimization and Simulation[J].,2007,(07):88.
[7]方峻 唐普英 任诚.一种基于加权有向拓扑的改进粒子群算法[J].计算机技术与发展,2006,(08):62.
　FANG Jun,TANG Pu-ying,REN Cheng.A Modified Particle Swarm Optimization Based on Directional Weighting Topology[J].,2006,(07):62.
[8]张璐 张国良 张维平 敬斌.基于粒子群三次样条优化的局部路径规划方法[J].计算机技术与发展,2012,(11):145.
　ZHANG Lu,ZHANG Guo-liang,ZHANG Wei-ping,et al.Local Path Planning Algorithm Based on Particle Swarm Optimization of Cubic Splines[J].,2012,(07):145.
[9]张奇 黄卫东.构建基于PSO—BP网络的电信客户信用度评估模型[J].计算机技术与发展,2012,(12):146.
　ZHANG Qi,HUANG Wei-dong.Construction of Credit Evaluation Model for Telecommunication Clients Based on PSO-BP Neural Network[J].,2012,(07):146.
[10]宋发兴,高留洋,刘东升,等.基于粒子群优化的BP神经网络图像复原方法[J].计算机技术与发展,2014,24(06):149.
　SONG Fa-xing,GAO Liu-yang,LIU Dong-sheng,et al.A Method of Image Restoration Based on Particle Swarm Optimization for BP Neural Network[J].,2014,24(07):149.
[11]谭文安[][],查安民[],陈森博[]. 优化粒子群的云计算任务调度算法[J].计算机技术与发展,2016,26(07):6.
　TAN Wen-an[]],ZHA An-min[],CHEN Sen-bo[]. Task Scheduling Algorithm of Cloud Computing Based on Particle Swarm Optimization [J].,2016,26(07):6.
[12]查安民[],谭文安[][]. 融合粒子群与蚁群的云计算任务调度算法[J].计算机技术与发展,2016,26(08):24.
　ZHA An-min[],TAN Wen-an[][]. A Task Scheduling Algorithm of Cloud Computing Merging Particle Swarm Optimization and Ant Colony Optimization[J].,2016,26(07):24.
[13]邓文杰. 基于聚粒子群算法的神经网络权值优化方法[J].计算机技术与发展,2017,27(10):16.
　DENG Wen-jie. A Neural Network Weights Optimization Method Based on Clustering Particle Swarm Optimization[J].,2017,27(07):16.

更新日期/Last Update: 2015-09-06