唐圣期,,
李胜,
何怡刚
合肥工业大学电气与自动化工程学院 合肥 230009
基金项目:国家自然科学基金(51577046, 61673153)，国防科技计划项目(C1120110004, 9140A27020211DZ5102)，教育部科学技术研究重大项目(313018)，安徽省科技计划重点项目(1301022036)
详细信息
作者简介:殷礼胜：男，1974年生，博士，副教授，研究方向为复杂系统建模；非线性时间序列预测；交通流预测等
唐圣期：男，1995年生，硕士生，研究方向为交通流预测、智能控制系统
李胜：男，1993年生，硕士生，研究方向为交通流预测、复杂系统建模
何怡刚：男，1966年生，博士，教授，研究方向为通讯信道建模与检测、复杂电磁分析与建模等
通讯作者:唐圣期 tsq951024@163.com
中图分类号:TP391, U491.1计量
文章访问数:1660
HTML全文浏览量:769
PDF下载量:75
被引次数:0
出版历程
收稿日期:2018-11-22
修回日期:2019-03-29
网络出版日期:2019-04-03
刊出日期:2019-09-10
Traffic Flow Prediction Based on Hybrid Model of Auto-Regressive Integrated Moving Average and Genetic Particle Swarm Optimization Wavelet Neural Network
Lisheng YIN,Shengqi TANG,,
Sheng LI,
Yigang HE
School of Electrical Engineering and Automation, Hefei University of Technology, Hefei 230009, China
Funds:The National Natural Science Foundation of China (51577046, 61673153), The National Defense Advanced Research Project (C1120110004, 9140A27020211DZ5102), The Key Grant Project of Chinese Ministry of Education (313018), Anhui Provincial Science and Technology Foundation of China (1301022036)
摘要
摘要:针对短时交通流数据的非线性和随机性特点，为提高它的预测精度和收敛速度，该文从模型构建和算法两方面提出一种整合移动平均自回归(ARIMA)模型和遗传粒子群算法优化小波神经网络(GPSOWNN)相结合的预测模型和算法。在模型构建方面，将ARIMA模型预测值和灰色关联系数大于0.6的相关性强的前3个时刻的历史数据作为小波神经网络(WNN)的输入，在兼顾历史数据的平稳和非平稳的情况下，进行了模型结构简化。在算法方面，通过遗传粒子群算法对小波神经网络的参数初始值进行最优选取，可使其结果在不易陷入局部最优的条件下加快网络训练收敛速度。实验结果表明，在预测精度方面，该方法的模型明显优于整合移动平均自回归模型和遗传粒子群算法优化小波神经网络，在收敛速度方面，用遗传粒子群算法优化模型明显优于仅用遗传算法优化模型。
关键词:短时交通流预测/
灰色关联分析法/
整合移动平均自回归/
遗传粒子群优化小波神经网络
Abstract:In view of the nonlinear and stochastic characteristics of short-term traffic flow data, this article proposes a prediction model and algorithm based on hybrid Auto-Regressive Integrated Moving Average (ARIMA) and Genetic Particle Swarm Optimization Wavelet Neural Network (GPSOWNN) in order to improve its prediction accuracy and rate of convergence. In terms of model construction, the ARIMA model prediction value and the historical data of the first three moments with strong correlation with gray correlation coefficient greater than 0.6 are used as input of the Wavelet Neural Network(WNN), and the structure of the model is simplified considering both the stationary and non-stationary historical data. In terms of algorithm, by using the genetic particle swarm optimization algorithm to select optimally the initial values of the wavelet neural network, the results can speed up the convergence of network training under the condition that it is not easy to fall into local optimum. The experimental results show that the proposed model is superior to hybrid ARIMA and GPSOWNN in terms of prediction accuracy, the genetic particle swarm optimization algorithm is superior to the genetic algorithm optimization model in terms of convergence speed.
Key words:Short-term traffic flow prediction/
Grey relational analysis/
Auto-Regressive Integrated Moving Average (ARIMA)/
Genetic Particle Swarm Optimization Wavelet Neural Network (GPSOWNN)
PDF全文下载地址:
https://jeit.ac.cn/article/exportPdf?id=684f76ad-959c-41b1-9480-7798dfbfeda4
