卡尔曼滤波短时交通流预测普通国省道适应性研究

申雷霄; 陆宇航; 郭建华

doi:10.3963/j.jssn.1674-4861.2021.05.015

卡尔曼滤波短时交通流预测普通国省道适应性研究

doi: 10.3963/j.jssn.1674-4861.2021.05.015

1.
江苏省徐州市公路管理处江苏徐州 221002
2.
东南大学智能运输系统研究中心南京 210018

基金项目:

国家自然科学基金项目 61573106

详细信息

作者简介:
申雷霄（1974—），硕士，高级工程师.研究方向：交通运输工程.E-mail：106163580@qq.com

通讯作者:
郭建华（1976—），博士，教授.研究方向：交通信息工程与控制.E-mail：seugjh@163.com

中图分类号: U491.1
计量
- 文章访问数: 708
- HTML全文浏览量: 286
- PDF下载量: 38
- 被引次数: 0
出版历程
- 收稿日期: 2021-04-13

Adaptability of Kalman Filter for Short-time Traffic Flow Forecasting on National and Provincial Highways

1.
Jiangsu Province Xuzhou Highway Administration Office, Xuzhou 221002, Jiangsu, China
2.
Intelligent Transportation System Research Center, Southeast University, Nanjing 210018, China

摘要

摘要:
短时交通流预测是提高普通国省道交通运行效率和安全的关键技术之一。普通国省道具有分布地域广、情况复杂的特点，要求短时交通流预测方法具有良好的适应性，然而，针对短时交通流预测算法适应性及其机制的系统性研究尚不多见。选取1种自适应卡尔曼滤波算法，系统分析其适应性和适应机制。获取江苏省徐州市普通国省道路网中8个交通调查站所采集的实际交通流数据开展实例分析，结果表明：在不同的交通流量水平下，所选算法均值预测的平均绝对百分比误差在10.98%~15.92%之间，区间预测的无效覆盖率在5.21%~6.15%之间，表明所选的自适应卡尔曼滤波算法在不同交通流水平下都具有良好的预测性能；对所选算法的参数进行分析发现，算法参数能够随交通流水平的变化而自动调整，具有良好的自适应机制；所选算法能够在预测初期实现有效的性能调整和收敛。
- 智能交通 /
- 普通国省道 /
- 自适应性 /
- 卡尔曼滤波 /
- 短时交通流预测
Abstract:
The forecast of short-term traffic flow is one of the significant technologies to improve safety of national and provincial highways. General national and provincial highways have the characteristics of wide distribution and complex conditions, which requires good adaptability of short-time traffic flow forecasting methods. However, there are few systematic studies on this adaptability and associated mechanism. Out of many forecasting algorithms of short-term traffic flow, the adaptive Kalman filter algorithm is selected to investigate adaptability and its adaptive mechanism. The empirical analysis is conducted using traffic flow data collected from 8 traffic survey stations of the national and provincial road network in Xuzhou, Jiangsu, China. Under different traffic flows, the average absolute percentage errors for mean prediction of the selected algorithm ranged from 10.98% to 15.92%. Furthermore, the invalid coverage of the interval generation ranged from 5.21% to 6.15% under different traffic levels. The results indicate the selected adaptive Kalman filter algorithm has good overall performance under different traffic levels. After analyzing the parameters of the selected algorithm, it can be found that the algorithm parameters can be adjusted automatically with the change of traffic flow level, presenting a good adaptive mechanism; in the early stage of prediction, the selected algorithm can achieve effective performance adjustment and convergence.
- intelligent transportation /
- national and provincial highways /
- adaptability /
- Kalman filter /
- short-term traffic flow forecasting

HTML全文

图 1 交通调查站分布

Figure 1. Distribution of traffic survey stations

下载: 全尺寸图片幻灯片

图 2 交通流预测图

Figure 2. Forecasting of traffic flows

下载: 全尺寸图片幻灯片

图 3 参数变化特征曲线

Figure 3. Characteristic curves of parameter change

下载: 全尺寸图片幻灯片

图 4 预测结果变化特征曲线

Figure 4. Characteristic changing curves of forecasting result

下载: 全尺寸图片幻灯片

表 1 检测地点说明

Table 1. Description of testsites

地点	车道数	平均流量/ (辆/15mm)	样本量	缺失量
丰县S254沙河	2	1 169	8 829	3
贾汪G206江庄	2	1 121	8 762	70
沛县G518鹿楼	2	1 014	8 825	7
邳州G310铁富	1	639	8 796	36
三环G311徐庄	2	1 543	8 832	0
睢宁G104官山	2	1 279	8 819	13
铜山G206三堡	3	1 264	8 832	0
新沂G205石涧	2	1 593	8 819	13

下载: 导出CSV

表 2 性能指标结果

Table 2. Results of performance indices

地点	平均流量/(辆/15min)	MAE	MAPE/%	RMSE	KP/%	R_i
丰县S254沙河	1 175	175	15.83	220	5.21	0.88
贾汪G206江庄	1 197	147	13.03	187	5.55	0.65
沛县G518鹿楼	1 009	156	15.92	197	5.88	0.95
邳州G310铁富	631	101	14.86	127	5.71	0.93
三环G311徐庄	1 558	153	10.98	196	6.06	0.54
睢宁G104官山	1 283	176	14.63	222	5.56	0.72
铜山G206三堡	1 270	146	12.60	186	5.74	0.67
新沂G205石涧	1 569	160	11.03	204	6.15	0.55

下载: 导出CSV

参考文献(24)

[1]	杨兆升. 智能运输系统概论[M]. 北京: 人民交通出版社, 2003. YANG Zhaosheng. Introduction to intelligent transportation system[M]. Beijing: People's Communications Publishing House, 2003. (in Chinese)
[2]	陆海亭, 张宁, 黄卫, 等. 短时交通流预测方法研究进展[J]. 交通运输工稈与信息学报, 2009(4): 84-91. https://www.cnki.com.cn/Article/CJFDTOTAL-JTGC200904018.htm LU Haiting, ZHANG Ning, HUANG Wei, et al. Research progress of short-term traffic flow forecasting methods[J]. Journal of Traffic and Transportation Engineering and Information, 2009 (4): 84-91. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JTGC200904018.htm
[3]	GUO Jianhua, HUANG Wei, WILLIAMS B, Adaptive Kalman filter approach for stochastic short-term traffic flow rate prediction and uncertainty quantification[J]. Transportation Research Part C : Emerging Technologies, 2014(43) : 50-64. http://www.researchgate.net/profile/Jianhua_Guo5/publication/260680268_Adaptive_Kalman_filter_approach_for_stochastic_short-term_traffic_flow_rate_prediction_and_uncertainty_quantification/links/02e7e53c53751c68d4000000
[4]	刘静, 关伟. 交通流预测方法综述[J]. 公路交通科技, 2004, 21 (3)82-85. doi: 10.3969/j.issn.1002-0268.2004.03.022 LIU Jing, GUAN Wen. A summary of traffic flowforecasting methods[J]. Journal of Highway and Transportation Research and Development, 2004, 21(3) : 82-85(in Chinese) doi: 10.3969/j.issn.1002-0268.2004.03.022
[5]	郭良久, 工新渝, 章玉. 重要节假日期间重庆高速公路交通出行特征与预测分析[J]. 公路交通技术, 2020, 36 (3): 116-120. https://www.cnki.com.cn/Article/CJFDTOTAL-GLJT202003020.htm GUO Liangjiu, WANG Xinyu, ZHANG Yu, Characteristics and forecast analysis of Chongqing highway transportation during important holidays[J]. Technology of Highway and Transport, 2020, 36(3): 116-120. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-GLJT202003020.htm
[6]	高洪波, 张登银. 基于分形与三次指数平滑的交通流量预测模型[J]. 南京邮电大学学报(自然科学版), 2018, 38(6): 63-67. https://www.cnki.com.cn/Article/CJFDTOTAL-NJYD201806014.htm GAO Hongbo, ZHANG Dengyin. Traffic flow forecasting model based on fractal and cubic exponential smoothing[J]. Journal of Nanjing University of Posts and Telecommunications (Natural Science Edition), 2018, 38(6) : 63-67. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-NJYD201806014.htm
[7]	李桃迎, 工婷, 张羽琪. 考虑多特征的高速公路交通流预测模型[J]. 交通运输系统工稈与信息, 2021, 21(3): 101-111. https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT202103013.htm LI Taoying, WANG Ting, ZHANG Yuqi. Highway traffic flow prediction model considering multiple features[J]. Journal of Transportation Systems Engineering and Information Technology, 2021, 21(3): 101-111. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT202103013.htm
[8]	谢海红, 戴许昊, 齐远. 短时交通流预测的改进K近邻算法[J]. 交通运输工稈学报, 2014(3) : 87-94. https://www.cnki.com.cn/Article/CJFDTOTAL-JYGC201403015.htm XIE Haihong, DAI Xuhao, QI Yuan. Improved K-nearest neighbor algorithm for short-term traffic flow prediction[J]. Journal of Traffic and Transportation Engineering, 2014(3) : 87-94. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JYGC201403015.htm
[9]	MENG Meng, WANG Bobin, SHAO Chunfu, et al. A two-stage short-term traffic flow prediction method based on AVL and AKNN techniques[J]. Journal of Central South University, 2015, 22(2). http://edu.zndxzk.com.cn/down/2015/02_znen/47-p0779-e130955.pdf
[10]	WILLIAMS B, HOEL L. Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process: theoretical basis and empirical results[J]. ASCE Journal of Transportation Engineer ing, 2003, 129(6): 664-168 doi: 10.1061/(ASCE)0733-947X(2003)129:6(664)
[11]	GUO Jianhua, WILLIAMS B, SMITH B. Data collection time intervals for stochastic short-term traffic flow forecasting[J]. Transportation Research Record, 2007(2024) : 18-26. http://www.onacademic.com/detail/journal_1000039671558410_c65f.html
[12]	韩超, 宋苏, 工成红. 基于ARIMA模型的短时交通流实时自适应预测[J]. 系统仿真学报, 2004, 16(7) : 1530-1532, 1535. doi: 10.3969/j.issn.1004-731X.2004.07.042 HAN Chao, SONG Su, WANG Chenghong. Real-time adaptive prediction of short-term traffic flow based on ARIMA model[J]. Journal of System Simulation, 2004, 16(7) : 1530-1532 + 1535. (in Chinese) doi: 10.3969/j.issn.1004-731X.2004.07.042
[13]	刘钊, 杜威, 闫冬梅, 等. 基于K近邻算法和支持向量回归组合的短时交通流预测[J]. 公路交通科技, 2017, 34(5): 122-128+158. https://www.cnki.com.cn/Article/CJFDTOTAL-GLJK201705017.htm LIU Zhao, DU Wei, YAN Dongmei, et al. Short-term traffic flow prediction based on the combination of K-nearest neighbor algorithm and support vector regression[J]. Journal of Highway and Transportation Research and Development, 2017, 34(5): 122-128+158. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-GLJK201705017.htm
[14]	冯微, 陈红, 张兆津, 等. 基于GBRBM-DBN模型的短时交通流预测方法[J]. 交通信息与安全, 2018, 36(5) : 99-108. https://www.cnki.com.cn/Article/CJFDTOTAL-JTJS201805014.htm FENG Wei, CHEN Hong, ZHANG Zhaojin, et al. Short-term traffic flow prediction method based on GBRBM-DBN model[J]. Journal of Transport Information and Safety, 2018, 36 (5): 99-108. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JTJS201805014.htm
[15]	梅朵, 郑黎黎, 冷强奎, 等. 基于时空GPSO-SVM的短时交通流预测[J]. 交通信息与安全, 2017, 35(2): 68-74+120. https://www.cnki.com.cn/Article/CJFDTOTAL-JTJS201702010.htm MEI Duo, ZHENG Lili, LENG Qiangkui, et al. Short-term traffic flow prediction based on time-space GPSO-SVM[J]. Journal of Transport Information and Safety, 2017, 35(2) : 68-74+120. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JTJS201702010.htm
[16]	ENGLER E, Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation[J]. Econometrica. 1982, 50(4): 987-1008. http://www.researchgate.net/publication/238655506_autoregressive_conditional_heteroskedasticity_with_estimates_of_the_variance_of_united_kingdom_inflation
[17]	BOLLERSLEV T. Generalized autoregressive conditional heteroskedasticity[J]. Journal of Business & Economic Statistics, 1986, 14(2): 139-151. http://econpapers.repec.org/scripts/redir.pf?u=http%3A%2F%2Fwww.eeri.eu%2Fdocuments%2Fwp%2FEERI_RP_1986_01.pdf;h=repec:eei:rpaper:eeri_rp_1986_01
[18]	GUO Jianhua, HUANG Wei, WILLIAMS B. Integrated heteroscedasticity test for vehicular traffic condition series[J]. ASCE Journal of Transportation Engineering, 2012, 138 (9): 1161-1170.
[19]	GUO Jianhua, WILLIAMS B. Real-time short-term traffic speed level forecasting and uncertainty quantification using layered Kalman filters[J]. Transportation Research Record, 2010 (2175): 28-37. http://trb.metapress.com/content/r2m4886862234u35/fulltext.pdf?page=1
[20]	王晓全, 邵春福, 尹超英, 等. 基于ARIMA-GARCH-M模型的短时交通流预测方法[J]. 北京交通大学学报, 2018, 42 (4): 79-84. https://www.cnki.com.cn/Article/CJFDTOTAL-BFJT201804011.htm WANG Xiaoquan, SHAO Chunfu, YIN Chaoying, et al. Short-term traffic flow prediction method based on ARIMA-GARCH-M model[J]. Journal of Beijing Jiaotong University, 2018, 42(4): 79-84. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-BFJT201804011.htm
[21]	凌墨,吴桢,郭建华.考虑交通流不确定性的单交叉口信号配时方法[J]. 南通大学学报(自然科学版),2020,19(1): 33-41. LING Mo,WU Zhen,GUO Jianhua. Signal timing method for Single intersection considering the uncertainty of traffic flow[J]. Journal of Nantong University(Natural Science Edition),2020,19(1):33-41.(in Chinese)
[22]	GUO Jianhua,LIU Zhao,HUANG Wei,et al. Short-term traffic flow prediction using fuzzy information granulation approach under different time intervals[J]. IET of Intelligent Transportation System,2018,12(2):143-150. http://ieeexplore.ieee.org/iel7/4149681/8277378/08277420.pdf
[23]	ZHANG Yanru,HAGHANI A,SUN R,A stochastic volatility modeling approach to account for uncertainties in travel time reliability forecasting[J]. Transportation Research Record,2014 (2442):62-70. http://assets.conferencespot.org/fileserver/file/65367/filename/14-1066.pdf
[24]	TSEKERIST,STATHOPOULOSR,Short-term prediction of urban traffic variability:stochastic volatility modeling approach[J]. ASCE Journal of Transportation Engineering,2010, 136(7):606-613.