自适应粒子群神经网络交通流预测模型

许榕; 周东; 蒋士正; 陈启美

doi:10.7652/xjtuxb201510017

您当前的位置：

首页 >

文章列表页 >

自适应粒子群神经网络交通流预测模型

更新时间：2025-07-09

- 自适应粒子群神经网络交通流预测模型
- A Traffic Forecasting Model Using Adaptive Particle Swarm Optimization Trained Neural Network
- 西安交通大学学报 2015年49卷第10期页码：103-108
- 作者机构：
  
  南京大学电子科学与工程学院,南京,210023
- 作者简介：
- 基金信息：
  
  : 2015-02-20。作者简介: 许榕(1991—),男,硕士生;陈启美(通信作者),男,教授,博士生导师。基金项目: 国家自然科学基金资助项目(61105015);国家科技重大专项课题资助项目(2012ZX03005-004-003)
- DOI：10.7652/xjtuxb201510017
  中图分类号： TP183
- 网络首发：2015-10-10，
  
  纸质出版：2015
- 稿件说明：
移动端阅览
许榕, 周东, 蒋士正, 等. 自适应粒子群神经网络交通流预测模型[J]. 西安交通大学学报, 2015,49(10):103-108.

A Traffic Forecasting Model Using Adaptive Particle Swarm Optimization Trained Neural Network[J]. 2015, 49(10): 103-108.
许榕, 周东, 蒋士正, 等. 自适应粒子群神经网络交通流预测模型[J]. 西安交通大学学报, 2015,49(10):103-108. DOI： 10.7652/xjtuxb201510017.

A Traffic Forecasting Model Using Adaptive Particle Swarm Optimization Trained Neural Network[J]. 2015, 49(10): 103-108. DOI： 10.7652/xjtuxb201510017.

摘要

针对传统神经网络预测模型预测结果准确性低且存在大量无效迭代的问题

提出了自适应权重粒子群神经网络交通流预测(PSOA-NN)模型。首先根据待预测点的上下游观测点数和历史数据

随机初始化若干组模型参数并计算每组参数对应粒子的适应度; 然后采用改进的sigmoid函数替代原有模型中的固定惯性权重

并根据其中适应度变好的粒子更新粒子速度和位置

一直迭代到粒子适应度小于预设值为止; 最后将满足条件粒子对应的模型参数应用到神经网络模型

根据实时交通流数据预测出15 min后的数据。仿真结果表明

使用PSOA-NN模型

可使得在同等预测误差范围内收敛速度提升0.6～1.7倍。

Abstract

A novel traffic forecasting model using particle swarm optimized neural network with adaptive weights(PSOA-NN)is proposed to address the issue of low accuracy prediction of traditional neural network forecasting model with a lot of invalid iterations in prediction process. Several groups of model parameters are initialized casually according to the observing point numbers of up and down streams and historical data in a neighbourhood of the forecast location

and the particle fitness of corresponding parameters in each group is calculated. Then

an improved sigmoid function is used to replace the fixed inertia weights in original model

speeds and locations are updated for the particles with improved fitness

and the iteration continues until the fitnesses of particles are less than a preset value. Finally

the model parameters that satisfies particle requirement are applied to the neural network model

and the traffic data 15 min later is predicted according to real time traffic flow data. Simulation results show that the convergent speed of the PSOA-NN model increases by about 0.6 to 1.7 times within the identical deviation range.

关键词

Keywords

references

王进, 史其信. 短时交通流预测模型综述 [J]. 中国公共安全: 学术版, 2005, 1(6): 92-98.

WANG Jin, SHI Qixin. Short term traffic flow forecasting model review [J]. China Public Security: Academy Edition, 2005, 1(6): 92-98.

贺国光, 李宇, 马寿峰. 基于数学模型的短时交通流预测方法探讨 [J]. 系统工程理论与实践, 2000(12): 51-56.

HE Guoguang, LI Yu, MA Shoufeng. Discussion on short-term traffic flow forecasting methods based on mathematical models [J]. Systems Engineering: Theory Practice, 2000(12): 51-56.

许岩岩, 翟希, 孔庆杰, 等. 高速路交通流短时预测方法 [J]. 交通运输工程学报, 2013, 13(2): 114-119.

XU Yanyan, ZHAi Xi, KONG Qingjie, et al. Short-term prediction method of freeway traffic flow [J]. Journal of Traffic and Transportation Engineering, 2013, 13(2): 114-119.

The Transportation Research Boards. Highway capacity manual [M]. Washington, DC, USA: National Research Council, 2000: 26-27

HASEGAWA M, WU G, MIZUNI M. Applications of nonlinear prediction methods to the internet traffic [C]∥The 2001 IEEE International Symposium on Circuits and Systems. Piscataway, NJ, USA: IEEE, 2001: 169-172.

林军, 倪宏, 孙鹏, 等. 一种采用神经网络PID控制的自适应资源分配方法 [J]. 西安交通大学学报, 2013, 47(4): 112-117, 136.

LIN Jun, NI Hong, SUN Peng, et al. Adaptive resource allocation based on neural network PID control [J]. Journal of Xi'an Jiaotong University, 2013, 47(4): 112-117, 136.

高瑞鹏, 尚春阳, 江航. 遗传算法结合小波神经网络的列车车轮扁疤故障检测方法 [J]. 西安交通大学学报, 2013, 47(9): 88-91, 111.

GAO Ruipeng, SHANG Chunyang, JIANG Hang. A fault detection strategy for wheel flat scars with wavelet neural network and genetic algorithm [J]. Journal of Xi'an Jiaotong University, 2013, 47(9): 88-91, 111.

VENAYAGAMOORTHY G K. Online design of an echo state network based wide area monitor for a multimachine power system [J]. Neural Networks, 2007, 20(3): 404-413.

赵建华, 张陵, 孙清. 利用粒子群算法的传感器优化布置及结构损伤识别研究 [J]. 西安交通大学学报, 2015, 49(1): 79-85.

ZHAO Jianhua, ZHANG Ling, SUN Qing. Optimal placement of sensors for structural damage identification using improved particle swarm optimization [J]. Journal of Xi'an Jiaotong University, 2015, 49(1): 79-85.

ZHU Y, ZHANG G, QIU J. Network traffic prediction based on particle swarm BP neural network [J]. Journal of Networks, 2013, 8(11): 2685-2691.

ZHANG H, ZHAO G, CHEN L, et al. Short-term prediction of wind power based on an improved PSO neural network [J]. TELKOMNIKA Indonesian Journal of Electrical Engineering, 2014, 12(7): 4973-4980.

ZHANG K, LIANG L, HUANG Y. A network traffic prediction model based on quantum inspired PSO and neural network [C]∥2013 Sixth International Symposium on Computational Intelligence and Design. Piscataway, NJ, USA: IEEE, 2013: 219-222.

ZHAO J, JIA L, CHEN Y, et al. Urban traffic flow forecasting model of double RBF neural network based on PSO [C]∥Sixth International Conference on Intelligent Systems Design and Applications, 2006. Piscataway, NJ, USA: IEEE, 2006: 892-896.

LI S, WANG L, LIU B. Prediction of short-term traffic flow based on PSO-optimized chaotic BP neural network [C]∥2013 International Conference on Computer Sciences and Applications. Piscataway, NJ, USA: IEEE, 2013: 292-295.

李松, 刘力军, 解永乐. 遗传算法优化BP神经网络的短时交通流混沌预测 [J]. 控制与决策, 2011, 26(10): 1581-1585.

LI Song, LIU Lijun, XIE Yongle. Chaotic prediction for short-term traffic flow of optimized BP neural network based on genetic algorithm [J]. Control and Decision, 2011, 26(10): 1581-1585.

California Department of Transportation. Caltrans PeMS[EB/OL]. [2014-02-18]. http: ∥pems.dot.ca.gov/?dnode=searchcontent=cnt_searchview=e.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

利用粒子群优化的人脸特征提取识别算法

结合分割逼近和粒子群法的燃气轮机叶片轮廓度误差计算

采用矩谐分析和支持向量机的地磁导航基准图构建方法

云计算环境下的大规模图状数据处理任务调度算法

电动车动力总成噪声品质粒子群-向量机预测模型