-
摘要: 针对短时交通流变化的复杂性与非线性特点, 分析了分类回归树模型的建立, 包括模型的生长、分裂与剪枝, 研究了模型在高速路交通流短时预测中的应用, 并对美国波特兰州高速路网的真实交通流量数据进行分析建模。采用RMSE与MAPE误差分析法, 将试验结果与传统的交通流预测方法ARIMA模型与Kalman滤波预测模型进行比较。对比结果表明: 分类回归树预测模型的RMSE比ARIMA模型与Kalman滤波预测模型分别降低了42.1%、13.1%。Abstract: According to the complexity and nonlinearity characteristics of short-term traffic flow, the application of classification and regression tree model in freeway traffic volume prediction was investigated, and its including growing, splitting and pruning of the model was studied.The real traffic volume data of the freeways in Portland State of US was tested and verified.Afterwards, the experimental result of model was compared with the traditional ARIMA model and Kalman filtering model by using the error analysis methods of RMSE and MAPE.Comparison result indicates that the RMSEs of tree model are 42.1% and 13.1% lower than ARIMA model and Kalman filtering model, respectively.
-
表 1 三种模型的预测误差对比
Table 1. Prediction error comparison of 3 models
日期 RMSE MAPE CART模型 ARIMA模型 Kalman滤波模型 CART模型 ARIMA模型 Kalman滤波模型 5月29日 169.76 235.11 133.54 0.118 0.176 0.094 5月30日 273.16 381.20 266.98 0.167 0.307 0.151 5月31日 253.50 474.94 347.96 0.110 0.266 0.145 6月1日 229.86 458.04 278.51 0.111 0.271 0.131 6月2日 255.58 469.94 309.38 0.105 0.234 0.125 6月3日 195.67 427.81 262.34 0.083 0.215 0.103 6月4日 244.47 312.53 267.73 0.124 0.203 0.107 平均值 231.71 394.22 266.63 0.117 0.234 0.123 -
[1] VOORT M, DOUGHERTY M, WATSON S. Combining kohonen maps with ARIMA time series models to forecast traffic flow[J]. Transportation Research Part C: Emerging Technologies, 1996, 4(5): 307-318. doi: 10.1016/S0968-090X(97)82903-8 [2] WILLIAMS B M, HOEL L A. Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process: theoretical basis and empirical results[J]. Journal of Transportation Engineering, 2003, 129(6): 664-672. doi: 10.1061/(ASCE)0733-947X(2003)129:6(664) [3] XIE Yuan-chang, ZHANG Yun-long, YE Zhi-rui. Short-term traffic volume forecasting using Kalman filter with discrete wavelet decomposition[J]. Computer-Aided Civil and Infrastructure Engineering, 2007, 22(5): 326-334. doi: 10.1111/j.1467-8667.2007.00489.x [4] 陈相东, 张勇. 基于局部多项式拟合的交通流预测[J]. 计算机工程与应用, 2012, 48(19): 238-242. doi: 10.3778/j.issn.1002-8331.2012.19.054CHEN Xiang-dong, ZHANG Yong. Predication of traffic flow based on local polynomial fitting[J]. Computer Engineering and Applications, 2012, 48(19): 238-242. (in Chinese). doi: 10.3778/j.issn.1002-8331.2012.19.054 [5] ZHANG Yun-long, YE Zhi-rui. Short-term traffic flow forecasting using fuzzy logic system methods[J]. Journal of Intelligent Transportation Systems, 2008, 12(3): 102-112. doi: 10.1080/15472450802262281 [6] ZHENG Wei-zhong, LEE D H, SHI Qi-xin. Short-term freeway traffic flow prediction: Bayesian combined neural network approach[J]. Journal of Transportation Engineering, 2006, 132(2): 114-121. doi: 10.1061/(ASCE)0733-947X(2006)132:2(114) [7] MIN W, WYNTER L. Real-time road traffic prediction with spatio-temporal correlations[J]. Transportation Research Part C: Emerging Technologies, 2011, 19(4): 606-616. doi: 10.1016/j.trc.2010.10.002 [8] SUN Shi-liang, ZHANG Chang-shui, YU Guo-qiang. A Bayesian network approach to traffic flow forecasting[J]. IEEE Transactions on Intelligent Transportation Systems, 2006, 7(1): 124-132. doi: 10.1109/TITS.2006.869623 [9] VLAHOGIANNI E I, KARLAFTIS M G, GOLIAS J C. Spatio-temporal short-term urban traffic volume forecasting using genetically optimized modular networks[J]. Computer-Aided Civil and Infrastructure Engineering, 2007, 22(5): 317-325. doi: 10.1111/j.1467-8667.2007.00488.x [10] XIE Yuan-chang, ZHAO Kai-guang, SUN Ying, et al. Gaussian processes for short-term traffic volume forecasting[J]. Transportation Research Record, 2010(2165): 69-78. [11] XU Yan-yan, KONG Qing-jie, LIN Shu, et al. Urban traffic flow prediction based on road network model[C]//IEEE. The 9th IEEE International Conference on Networking, Sensing and Control. Beijing: IEEE, 2012: 334-339. [12] SMITH B L, WILLIAMS B M, OSWALD R K. Comparison of parametric and nonparametric models for traffic flow forecasting[J]. Transportation Research Part C: Emerging Technologies, 2002, 10(4): 303-321. doi: 10.1016/S0968-090X(02)00009-8 [13] 于滨, 邬珊华, 王明华, 等. K近邻短时交通流预测模型[J]. 交通运输工程学报, 2012, 12(2): 105-111. doi: 10.3969/j.issn.1671-1637.2012.02.017YU Bin, WU Shan-hua, WANG Ming-hua, et al. K-nearest neighbor model of short-term traffic flow forecast[J]. Journal of Traffic and Transportation Engineering, 2012, 12(2): 105-111. (in Chinese). doi: 10.3969/j.issn.1671-1637.2012.02.017 [14] DOUGHERTY M S, COBBETT M R. Short-term inter-urban traffic forecasts using neural networks[J]. International Journal of Forecasting, 1997, 13(1): 21-31. doi: 10.1016/S0169-2070(96)00697-8 [15] MANOEL C N, JEONG Y S, JEONG M K, et al. Online-SVR for short-term traffic flow prediction under typical and atypical traffic conditions[J]. Expert Systems with Applications, 2009, 36(3): 6164-6173. doi: 10.1016/j.eswa.2008.07.069 [16] 樊娜, 赵祥模, 戴明, 等. 短时交通流预测模型[J]. 交通运输工程学报, 2012, 12(4): 114-119. doi: 10.3969/j.issn.1671-1637.2012.04.015FAN Na, ZHAO Xiang-mo, DAI Ming, et al. Short-term traffic flow prediction model[J]. Journal of Traffic and Transportation Engineering, 2012, 12(4): 114-119. (in Chinese). doi: 10.3969/j.issn.1671-1637.2012.04.015 [17] 张立彬, 张其前, 胥芳, 等. 基于分类回归树(CART)方法的统计解析模型的应用与研究[J]. 浙江工业大学学报, 2002, 30(4): 315-318. doi: 10.3969/j.issn.1006-4303.2002.04.001ZHANG Li-bin, ZHANG Qi-qian, XU Fang, et al. Research and application of the statistical models based on CART[J]. Journal of Zhejiang University of Technology, 2002, 30(4): 315-318. (in Chinese). doi: 10.3969/j.issn.1006-4303.2002.04.001