A Method of Traffic Flow Prediction for Road Segments without Detectors Based on Spatial Structure of Local Network
-
摘要: 城市路网中存在大量尚未布设交通检测器的路段，其交通流数据难以获取，不利于开展精准路网管理，为此提出了利用局部路网空间结构特征预测无检测器路段交通流量的方法。基于有检测器路段的海量交通流数据，分析局部路网空间结构特征与路段交通流量之间的相关性；根据路网拓扑关系使用多元线性回归算法估计所有的有检测器交叉口交通流分配权重，并使用多元线性回归算法进一步挖掘局部路网空间结构特征对交通流分配权重的影响；结合空间特征影响度系数、无检测器路段所在的局部路网的空间结构特征及相邻路段的交通流，对无检测器路段进行交通流预测。实验结果表明，路段道路类型、相邻路段数量及相邻路段道路类型这3类局部路网空间结构特征与路段交通流量相关性显著，采用基于空间特征影响度系数对局部路网中只有单个相邻上游和具有多个相邻上游的无检测器路段进行预测，发现其平均误差分别在8%和22%左右。Abstract: Most links in an urban road network are not monitored by any traffic detector. Lack of traffic flow data has seriously hindered the performance of traffic management programs. In this regard, this paper proposes a traffic flow prediction method for road segments without a detector(RSWD)based on the spatial structure of the local road network. The correlation between the spatial structure of the local network and the traffic flow of the links is analyzed based on the big data of traffic flow. According to the topology of the local road network, multiple linear regression is used to estimate traffic flow assignment weights using data from links with detectors, and to analyze the impacts of the spatial structure of the local road network on traffic flow assignment weights. Then, a method for estimating the traffic flow of road segments without any detector is proposed by considering the spatial structure of the local network and traffic flow of adjacent links. The results show that a significant correlation is found among links of traffic flow and its functional class, and the number and functional class of its adjacent links. The average error of traffic flow prediction based on the proposed model is about 8% and 22% for the RSWD connected with one and several adjacent upstream links in the local road network, respectively.
-
图 2 上下游路段交通流关系示例
Figure 2. Cases of the traffic flow relationship between upstream and downstream roads
表 1 路段特征与流量的相关性分析
Table 1. Correlation analysis of road characteristics and traffic flow
路段道路类型 车道数 相邻路段数量 相邻路段道路类型 上游 下游 上游 下游 路段流量 相关系数 0.550** 0.440** -0.248** -0.150** 0.214** 0.200** 显著性(双尾） 0 0 0 0 0 0 个案数 4000 **-在0.01级别（双尾），相关性显著。 
下载: 导出CSV
表 2 预测绝对百分比误差统计
Table 2. Statistics of forecasted APE
% 路段 平均值 PR50 PR75 PR95 16176 8.96 7.49 11.05 19.57 170239 22.82 24.19 30.49 39.85
下载: 导出CSV
-
[1] ZHANG Yanru, ZHANG Yunlong. A comparative study of three multivariate short-term freeway traffic flow forecasting methods with missing data[J]. Journal of Intelligent Transporta tion Systems, 2016, 20(3): 205-218. doi: 10.1080/15472450.2016.1147813 [2] ZHANG Hong, WANG Xiaoming, CAO Jie, et al. A multivari ate short-term traffic flow forecasting method based on wavelet analysis and seasonal time series[J]. Applied Intelligence, 2018 (48): 3827-3838. doi: 10.1007/s10489-018-1181-7 [3] XU Liqiang, DU Xuedong, WANG Binguo. Short-term traffic flow prediction model of wavelet neural network based on mind evolutionary algorithm[J]. International Journal of Pattern Rec ognition and Artificial Intelligence, 2018, 32(12): 1850041. doi: 10.1142/S0218001418500416 [4] CHEN Qiuxia, SONG Ying, ZHAO Jianfeng. Short-term traffic flow prediction based on improved wavelet neural network[J/ OL]. (2020-04)[2020-10-25]. https://doi.org/10.1007/s00521- 020-04932-5. [5] 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.htmFENG Wei, CHEN Hong, ZHANG Zhaojin, et al. A forecast of short-term traffic flow based on GBRBM-DBN model[J]. Jour nal of Transport Information and Safety, 2018, 36(5): 99-108. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JTJS201805014.htm [6] RAZA A, ZHONG Ming. Hybrid artificial neural network and locally weighted regression models for lane-based short-term urban traffic flow forecasting[J]. Transportation Planning and Technology, 2018, 41(4): 1-17. [7] 李巧茹, 池维源, 陈亮, 等. 基于相空间重构和PSO-GPR的短时交通流预测[J]. 交通信息与安全, 2019, 37(2): 70-76. https://www.cnki.com.cn/Article/CJFDTOTAL-JTJS201902010.htmLI Qiaoru, CHI Weiyuan, CHEN Liang, et al. Short-term traf fic flow forecast basedon phase space reconstruction and PSO-GPR[J]. Journal of Transport Information and Safety, 2019, 37(2): 70-76. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JTJS201902010.htm [8] ERMAGUN A, LEVINSON D. Spatiotemporal short-term traf fic forecasting using the network weight matrix and systematic detrending[J]. Transportation Research Part C: Emerging Tech nologies, 2019, 104: 38-52. doi: 10.1016/j.trc.2019.04.014 [9] 张赫, 杨兆升, 李贻武. 无检测器交叉口交通流量预测方法综合研究[J]. 公路交通科技, 2002, 19(1): 91-95. https://www.cnki.com.cn/Article/CJFDTOTAL-GLJK200201024.htmZHANG He, YANG Zhaosheng, LI Yiwu. Study on forecast of traffic volume at non-detector intersections[J]. Journal of High way and Transportation Research and Development, 2002, 19 (1): 91-95. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-GLJK200201024.htm [10] ZHANG Jian, LI Hua. Traffic forecasting at non-detector roads based on city road network[C]. International Asia Conference on Industrial Engineering and Management Innovation(IE MI2012), Changsha: IEEE, 2012. [11] ZHANG He, WANG Wei GU Huaizhong. Application of clus ter analysis and stepwise regression in predicting the traffic volume of lanes[J]. Journal of Southeast University(English Edition), 2005, 21(3): 359-362. http://en.cnki.com.cn/Article_en/CJFDTOTAL-DNDY200503022.htm [12] 柯凤琴. 一种改进的GM(1, 1)模型在交通量预测中的应用[J]. 承德石油高等专科学校学报, 2010, 12(1): 44-47. https://www.cnki.com.cn/Article/CJFDTOTAL-CDSY201001016.htmKE Fengqin. Research of RRGM(1, 1)model and its applica tion[J]. Journal of Chengde Petroleum College, 2010, 12(1): 44-47. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-CDSY201001016.htm [13] 陈新全, 侯志祥, 吴义虎, 等. 无检测器交叉口交通流量预测的灰色神经网络模型[J]. 系统仿真学报, 2004, 16(12): 2655-2656. doi: 10.3969/j.issn.1004-731X.2004.12.007CHEN Xinquan, HOU Zhixiang, WU Yihu, et al. A gray neu ral network model for traffic flow prediction at non-detector in tersections[J]. Journa of System Simulation, 2004, 16(12): 2655-2656. (in Chinese) doi: 10.3969/j.issn.1004-731X.2004.12.007 [14] 王志建. 基于遗传回归分析的无检测器交叉口流量预测研究[D]. 长春: 吉林大学, 2008.WANG Zhijian. Research on prediction of traffic volume at non-detector intersections based on genetic algorithm and step wise regression analysis[D]. Changchun: Jilin University, 2008. (in Chinese) [15] 郭沂鑫. 城市交叉口短时交通流预测模型与算法研究[D]. 兰州: 兰州交通大学, 2014.GUO Yixin. Study on forecasting model and algorithm for ur ban intersections short-term traffic flow[D]. Lanzhou: Lanzhou Jiaotong University, 2014. (in Chinese). [16] 张明辉. 基于FCM的无检测器交叉口短时交通流量预测[J]. 计算机技术与发展, 2017, 27(4): 39-41+45. https://www.cnki.com.cn/Article/CJFDTOTAL-WJFZ201704009.htmZHANG Minghui. Short-term traffic flow prediction of non-de tector intersections based on FCM[J]. Computer Technology And Development, 2017, 27(4): 39-41, 45. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-WJFZ201704009.htm [17] 李欣, 罗庆, 孟德友. 基于时空权重相关性的交通流大数据预测方法[J]. 北京大学学报(自然科学版), 2017, 53(4): 775-782. https://www.cnki.com.cn/Article/CJFDTOTAL-BJDZ201704019.htmLI Xin, LUO Qing, MENG Deyou. Traffic flow-big data fore casting method based on spatial-temporal weight correla tion[J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2017, 53(4): 775-782. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-BJDZ201704019.htm [18] 陆百川, 李玉莲, 舒芹. 基于时空相关性和遗传小波神经网络的路网短时交通流预测[J]. 重庆理工大学学报(自然科学), 2020, 34(5): 32-41. https://www.cnki.com.cn/Article/CJFDTOTAL-CGGL202005004.htmLU Baichuan, LI Yulian, SHU Qin. Short-term traffic flow fore casting of road network based on spatiotemporal correlation and genetic wavelet neural network[J]. Journal of Chongqing University of Technology(Natural Science), 2020, 34(5): 32-41. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-CGGL202005004.htm [19] 丁青艳, 孙占全, 潘景山, 等. 一种无检测器路段交通流数据的测量方法及装置: CN201210508941.7[P]. 2014-06-11.DING Qingyan, AUN Zhanquan, PAN Jingshan, et al. A method and device for measuring traffic flow data of road section without detector: CN201210508941.7[P]. 2014-06-11. (in Chinese) [20] 王方, 李华, 杜金玲. 无检测器道路交通流数据质量检测方法[J]. 计算机工程, 2014, 40(3): 218-223. https://www.cnki.com.cn/Article/CJFDTOTAL-JSJC201403047.htmWANG Fang, LI Hua, DU Jinling. Quality detection method for non-detector road traffic flow data[J]. Computer Engineer ing, 2014, 40(3): 218-223. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JSJC201403047.htm -
点击查看大图
图(4) / 表(2)
计量
- 文章访问数: 466
- HTML全文浏览量: 251
- PDF下载量: 15
- 被引次数: 0