摘要To improve the precision of short-term traffic flow prediction and to enhance the accuracy of programming as well as of traffic flow management, a novel short-term traffic flow prediction method based on similarity is proposed in this study. The similarity observed at a single point on the California expressway is examined, and the similarity on "the same day for four adjacent weeks" is higher than that on "four adjacent days." The wavelet neural network (WNN) is established on this basis; moreover, the traffic flow data regarding "the same day for four adjacent weeks" and regarding "the four adjacent days" are divided into two types. Then, more than 200 groups of data are used to train the WNN and to predict the traffic flow on the same day. Results indicate that the mean values of the mean relative estimation error (MRE), mean square percentage error (MSPE), and equalization coefficient (EC) as predicted by the first method are 8.55%, 1.32%, and 0.951 6 respectively; the corresponding mean values obtained with the second method are 13.80%, 3.71% and 0.916 8. The MRE and MSPE values generated with the first method are lower than those obtained with the second method; by contrast, the EC value of the first method is higher than that of the second method. This finding suggests that the prediction accuracy of the first method is higher than that of the second method. Accordingly, the effectiveness of the proposed method is verified.
Abstract：To improve the precision of short-term traffic flow prediction and to enhance the accuracy of programming as well as of traffic flow management, a novel short-term traffic flow prediction method based on similarity is proposed in this study. The similarity observed at a single point on the California expressway is examined, and the similarity on "the same day for four adjacent weeks" is higher than that on "four adjacent days." The wavelet neural network (WNN) is established on this basis; moreover, the traffic flow data regarding "the same day for four adjacent weeks" and regarding "the four adjacent days" are divided into two types. Then, more than 200 groups of data are used to train the WNN and to predict the traffic flow on the same day. Results indicate that the mean values of the mean relative estimation error (MRE), mean square percentage error (MSPE), and equalization coefficient (EC) as predicted by the first method are 8.55%, 1.32%, and 0.951 6 respectively; the corresponding mean values obtained with the second method are 13.80%, 3.71% and 0.916 8. The MRE and MSPE values generated with the first method are lower than those obtained with the second method; by contrast, the EC value of the first method is higher than that of the second method. This finding suggests that the prediction accuracy of the first method is higher than that of the second method. Accordingly, the effectiveness of the proposed method is verified.
基金资助:Supported by the National Natural Science Foundation of China (No.61273229)
通讯作者:
YANG Chun-xia,E-mail address:y.cx@163.com
E-mail: y.cx@163.com
引用本文:
杨春霞, 付睿, 符义琴. 基于相似性的短时交通流预测[J]. Journal of Highway and Transportation Research and Development, 2016, 10(1): 92-97.
YANG Chun-xia, FU Rui, FU Yi-qin. Prediction of Short-term Traffic Flow Based on Similarity. Journal of Highway and Transportation Research and Development, 2016, 10(1): 92-97.
[1] CHAN K Y, DILLON T S, SINGH J, et al. Neural-network-based Models for Short-term Traffic Flow Forecasting Using a Hybrid Exponential Smoothing and Levenberg-marquardt Algorithm[J]. IEEE Transactions on Intelligent Transportation Systems, 2012, 13(2):644-654.
[2] LU Hai-ting, ZHANG Ning, HUANG Wei, et al. Research Progress of Short Term Traffic Flow Prediction Methods[J]. Journal of Transportation Engineering and Information, 2009, 7(4):84-90. (in Chinese)
[3] LINGRAS P J, SHARMA S C, GOPALAKRISHNAN S. Short-term Traffic Volume Forecasts:Existing and Future Research[C]//Canadian Society for Civil Engineering-1999 Annual Conference. Montreal:Canadian Society for Civil Engineering, 1999:429-438. (in Chinese)
[4] YIN H G, WONG S C, XU J M, et al. Urban Traffic Flow Prediction Using a Fuzzy-neural Approach[J]. Transportation Research Part C:Emerging Technologies, 2002,10(2):85-98. (in Chinese)
[5] STATHOPOULOS A, KARLAFTIS M G. A Multivariate State Space Approach for Urban Traffic Flow Modeling and Prediction[J]. Transportation Research part C::Emerging Technologies, 2003, 11(2):121-135. (in Chinese)
[6] CLARK S. Traffic Prediction Using Multivariate Nonparametric Regression[J]. Journal of Transportation Engineering-ASCE, 2003,129(2):161-168.(in Chinese)
[7] SHEN Yong-zeng, YAN Ji-ru, WANG Wei. Short-time Traffic Flow Forecast Based on WNN Opitimised by CPSO[J], Computer Application and Software, 2014, 31(6):84-90. (in Chinese)
[8] YAO Chen, LUO Xia, FAN Shao-lun, et al. Short-term Traffic Flow Forecasting Based on Coupling of Rough Set and Neural Network[J]. Journal of Highway and Transportation Research and Development, 2010, 27(11):104-107. (in Chinese)
[9] YANG Shi-jian, HE Guo-guang. A Short-term Traffic Flow Forecasting Method Based on Combination of Fuzzy C-mean Clustering and Neural Network[J]. Systems Engineering, 2004, 22(8):83-86. (in Chinese)
[10] OU Xiao-ling, QIU Gang, ZHANG Yi, et al. Analysis of Similarity for Urban Traffic Volumes[J]. Central South Highway Engineering, 2003, 28(2):4-7. (in Chinese)
[11] WANG Jiao, LI Jun. Application of Minimax Probability Machine Regression in Short-term Traffic Flow Prediction[J]. Journal of Highway and Transportation Research and Development, 2014, 31(2):121-127. (in Chinese)
[12] SUN Zhan-quan, PAN Jing-shan, ZHANG Zan-jun, et al. Traffic Flow Forecast Based on Combining Principal Component Analysis with Support Vector Machine[J]. Journal of Highway and Transportation Research and Development, 2009, 26(5):127-131. (in Chinese)
[1]
周星宇, 李红梅, 郑伟皓, 唐智慧, 杨丽君. 基于交互式BP-UKF模型的短时交通流预测方法[J]. Journal of Highway and Transportation Research and Development, 2019, 13(2): 56-64.
[2]
李高盛, 彭玲, 李祥, 吴同. 基于LSTM的城市公交车站短时客流量预测研究[J]. Journal of Highway and Transportation Research and Development, 2019, 13(2): 65-72.
[3]
胡宝雨, 赵琥, 孙祥龙, 王弟鑫, 刘宁. 城市公交与农村客运同步换乘模型研究[J]. Journal of Highway and Transportation Research and Development, 2019, 13(2): 73-79.
[4]
郭建科, 邱煜焜, 白家圆, 王利. 基于城市公共交通可达性的医疗服务空间分异及均等化研究——以大连市为例[J]. Journal of Highway and Transportation Research and Development, 2019, 13(2): 80-89.
[5]
赵妮娜, 赵晓华, 林展州, 葛书芳. 主线分流互通立交指路标志版面形式研究[J]. Journal of Highway and Transportation Research and Development, 2019, 13(2): 90-102.
[6]
姜明, 陈艳艳, 冯移冬, 周瑞. 路侧示警桩设置关键指标研究[J]. Journal of Highway and Transportation Research and Development, 2019, 13(1): 79-87.
[7]
蔡静, 刘莹, 张明辉. 京津冀货物运输结构调整策略研究[J]. Journal of Highway and Transportation Research and Development, 2019, 13(1): 88-93.
[8]
常云涛, 王奕彤. 连续流交叉口信号配时优化模型[J]. Journal of Highway and Transportation Research and Development, 2018, 12(4): 66-74.
[9]
林丽, 冯辉, 朱泳旭. 基于Ring-Barrier相位的干线公交协调控制[J]. Journal of Highway and Transportation Research and Development, 2018, 12(4): 85-91.
[10]
胡祖平, 何建佳. 基于网络可靠性的街区开放适宜度研究[J]. Journal of Highway and Transportation Research and Development, 2018, 12(4): 51-58.
[11]
陈红, 马晓彤, 赵丹婷. 基于元胞自动机的破损路面车辆换道仿真研究[J]. Journal of Highway and Transportation Research and Development, 2018, 12(4): 75-84.
[12]
李新, 毛剑楠, 骆晨, 刘澜. 基于MFD的路网可扩展边界控制方法研究[J]. Journal of Highway and Transportation Research and Development, 2018, 12(4): 59-65.
[13]
郝丽, 胡大伟, 李晨. T-JIT环境下企业供应链中采购管理供应商选择和订单分配研究[J]. Journal of Highway and Transportation Research and Development, 2018, 12(3): 80-89.
[14]
姚佼, 徐洁琼, 倪屹聆. 城市干道多时段协调控制优化研究[J]. Journal of Highway and Transportation Research and Development, 2018, 12(3): 60-70.
[15]
潘兵宏, 余英杰, 武生权, 严考权. 基于UC-win/Road仿真的高速公路出口预告标志前置距离研究[J]. Journal of Highway and Transportation Research and Development, 2018, 12(3): 71-79.
2016, Vol. 10 
