基于SARIMA-GA-Elman组合模型的短时交通流预测方法

兰州理工大学学报 ›› 2022, Vol. 48 ›› Issue (5): 107-113.

• 自动化技术与计算机技术 • 上一篇下一篇

基于SARIMA-GA-Elman组合模型的短时交通流预测方法

张玺君^*, 王晨辉

兰州理工大学计算机与通信学院, 甘肃兰州 730050

收稿日期:2021-04-23 出版日期:2022-10-28 发布日期:2022-11-21
通讯作者: 张玺君(1980-),男,甘肃临洮人,博士,副教授. Email:zhangxijun198079@sina.com
基金资助:
国家自然科学基金(61461027,61762059)

Research on short-term traffic flow forecasting method based on SARIMA-GA-Elman combined model

ZHANG Xi-jun, WANG Chen-hui

College of Computer and Communication, Lanzhou Univ. of Tech., Lanzhou 730050, China

Received:2021-04-23 Online:2022-10-28 Published:2022-11-21

摘要/Abstract

摘要： 针对单一模型无法深入挖掘交通流复杂的线性和非线性特征方面的局限性以及神经网络模型在训练时收敛速度缓慢等问题,提出了一种基于SARIMA-GA-Elman的组合预测模型.该组合模型有效地融合了季节性差分自回归滑动平均(seasonal autoregressive integrated moving average,SARIMA)模型良好的线性拟合能力和Elman递归神经网络强大的非线性映射能力;在预测过程中首先基于SARIMA滚动预测时间序列的线性分量,然后使用SARIMA模型的预测误差序列建立Elman-RNN构建非线性误差模型;此外在训练非线性误差模型的过程中使用经过二进制编码的遗传算法(genetic algorithm,GA)优化Elman-RNN,旨在提升Elman-RNN的训练效率,最后把两个模型的预测结果加权组合得到最终的预测值.实验结果表明,该组合模型在预测精度和鲁棒性方面相比单一模型都有较为明显的提升.

关键词: 智能交通, 交通流预测, 组合模型, 时间序列, SARIMA, Elman递归神经网络

Abstract: Aiming at the limitations of a single model that can not dig into the complex linear and nonlinear characteristics of traffic flow and the slow convergence of neural network models during training, a combined prediction model based on SARIMA-GA-Elman is proposed. The combined model effectively combines the excellent linear fitting ability of the seasonal autoregressive integrated moving average (SARIMA) model and the powerful nonlinear mapping ability of the Elman recurrent neural network. In the prediction process, the linear component of the time series is firstly predicted based on the SARIMA rolling, and then the prediction error sequence of the SARIMA model is used to establish the Elman-RNN to construct the nonlinear error model. In addition, in the process of training the nonlinear error model, the binary-coded genetic algorithm (GA) is used to optimize the Elman-RNN in order to improve the training efficiency of Elman-RNN. Finally the prediction results of the two models are weighted and combined to obtain the final prediction value. Experimental results show that the combined model has a significant improvement in prediction accuracy and robustness compared to a single model.

Key words: intelligent transportation, traffic flow forecast, combined model, time series, SARIMA, Elman-RNN

中图分类号:

U491.14

张玺君, 王晨辉. 基于SARIMA-GA-Elman组合模型的短时交通流预测方法[J]. 兰州理工大学学报, 2022, 48(5): 107-113.

ZHANG Xi-jun, WANG Chen-hui. Research on short-term traffic flow forecasting method based on SARIMA-GA-Elman combined model[J]. Journal of Lanzhou University of Technology, 2022, 48(5): 107-113.

参考文献

[1] MCCAULEY J W,PATEL P,CHEN M,et al.xAlON:A brief history of its emergence and evolution [J].Journal of the European Ceramic Society,2009,29(2):223-236.
[2] TAN H,WU Y,SHEN B,et al.Short-term traffic prediction based on dynamic tensor completion [J].IEEE Transactions on Intelligent Transportation Systems,2016,17(8):2123-2133.
[3] WAN J X,LI J,ZHANG S K.Prediction model for ship traffic flow considering periodic fluctuation factors [C]//Electronic and Automation Control Conference (IAEAC).Sanya:IEEE,2018:1506-1510.
[4] KECHAGIAS E P,GAYIALIS S P,KONSTANTAKOPOULOS G D,et al.Traffic flow forecasting for city logistics:A literature review and evaluation [J].International Journal of Decision Support Systems,2019,4(2):159-176.
[5] CHEN D,HU M,MA Y,et al.A network-based dynamic air traffic flow model for short-term en route traffic prediction [J].Journal of Advanced Transportation,2016,50(8):2174-2192.
[6] XIAO J H,XIAO Z,WANG D,et al.Short-term traffic volume prediction by ensemble learning in concept drifting environments [J].Knowledge-Based Systems,2019,164:213-225.
[7] JIA Y,WU J,BEN-AKIVA M,et al.Rainfall-integrated traffic speed prediction using deep learning method [J].IET Intelligent Transport Systems,2017,11(9):531-536.
[8] AQIB M,MEHMOOD R,ALZAHRANI A,et al.A deep learning model to predict vehicles occupancy on freeways for traffic management [J].International Journal of Computer Science and Network Security,2018,18:246-254.
[9] LIN L,LI Y,SADEK A.A k nearest neighbor based local linear wavelet neural network model for on-line short-term traffic volume prediction [J].Procedia-Social and Behavioral Sciences,2013,96:2066-2077.
[10] LIU Y,ZHANG K.Short-term traffic flow forecasting based on wavelet denoising and GA-Elman neural network [J].Technology & Economy in Areas of Communications,2015,17:80-85.
[11] YANG X F,ZHANG L W,XIE W.Forecasting model for urban traffic flow with BP neural network based on genetic Algorithm [C]//Chinese Control and Decision Conference (CCDC).Nanchang:IEEE,2019:4395-4399.
[12] HUANG D R,DENG Z P,ZHAO L,et al.A short-term traffic flow forecasting method based on Markov Chain and Grey Verhulst model [C]//Data Driven Control and Learning Systems (DDCLS).Chongqing:IEEE,2017:606-610.
[13] LI K L,ZHAI C J,XU J M.Short-term traffic flow prediction using a methodology based on ARIMA and RBF-ANN[C]//Chinese Automation Congress (CAC).Jinan:IEEE,2017:2804-2807.
[14] GAO H,ZHAO J Y,JIA L.Short-term traffic flow forecasting model of Elman neural network based on dissimilation particle swarm optimization [C]//International Conference on Networking,Sensing and Control.Sanya:IEEE,2008:1305-1309.
[15] SUN Y S,WANG L Z,WANG X H,et al.Reliability growth prediction method based on GA-Elman neural network [C]//International Conference on Reliability,Maintainability,and Safety (ICRMS).Shanghai:IEEE,2018:135-141.
[16] 张秋余,朱学明.基于GA-Elman神经网络的交通流短时预测方法 [J].兰州理工大学学报,2013,39(3):94-98.
[17] 谭满春,冯荦斌,徐建闽.基于ARIMA与人工神经网络组合模型的交通流预测 [J].中国公路学报,2007,20(4):118-121.

基于SARIMA-GA-Elman组合模型的短时交通流预测方法

Research on short-term traffic flow forecasting method based on SARIMA-GA-Elman combined model

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

本文评价

[1]	曹洁, 张敏, 张红, 陈作汉, 侯亮. 基于IFA优化RBF神经网络的短时交通流预测模型[J]. 兰州理工大学学报, 2022, 48(4): 99-104.
[2]	牛全福, 李月锋, 张曼, 傅建凯, 马亚娜. 基于Kalman滤波的ARIMA-NAR神经网络模型[J]. 兰州理工大学学报, 2022, 48(2): 131-135.