Please wait a minute...
J4  2010, Vol. 44 Issue (8): 1473-1478    DOI: 10.3785/j.issn.1008-973X.2010.08.007
自动化技术、计算机技术     
短时交通流智能混合预测技术
任沙浦1,沈国江2
1. 绍兴文理学院 计算机系,浙江 绍兴 312000; 2. 浙江大学 工业控制技术国家重点实验室,浙江 杭州 310027
Intelligent hybrid forecasting technique for short-term traffic flow
REN Sha-pu1, SHEN Guo-jiang2
1. Departement of Computer Science, Shaoxing University, Shaoxing 312000, China;
2. State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou 310027, China
 全文: PDF  HTML
摘要:

为了克服现有单项预测技术对不同交通流状况的局限性,提出一种新的短时交通流智能混合预测模型.该智能混合预测模型包括3个子模型:历史平均模型、人工神经网络模型和模糊综合模型.历史平均模型以历史数据为基础,利用一次指数平滑法良好的静态稳定特性,对交通流量进行预测.人工神经网络模型采用常见的由S函数神经元组成的15层前馈神经网络,由于人工神经网络具有强大的动态非线性映射能力,该模型对动态交通流量的预测具有较高的精度和满意度.根据上述2个单项模型的特点,为了充分利用它们对不同交通状况的适应性,进一步提高整体预测效果,采用模糊逻辑来综合这2个单项模型的输出,并把模糊综合模型的输出作为整个智能混合模型的最终交通流量预测值.实际应用结果表明,该混合模型的预测精度高于单项预测模型各自单独使用时的精度,发挥了2种模型各自的优势,是短时交通流预测的一种有效方法.

Abstract:

In order to transcend the limitation of exisiting single forecasting technique on different traffic condition, a novel intelligent hybrid (IH) forecasting model for shortterm traffic flow was presented. The IH model included three submodels that were history mean (HM) model, artificial neural network (ANN) model and fuzzy combination (FC) model. Based on the historical traffic data the HM model forecasted the traffic flow by the single exponential smoothing method which held the good static stabilization character. Otherwise, the ANN model was a 1.5layer feedforward neural network built by some common Sfuction neurons. By means of the strong dynamic nonlinear mapping ability of ANN, this submodel could estimate the dynamic traffic flow in a very precise and satisfactory sense. In order to take advantage of the useful information of the HM model and the ANN model to improve the forecasting effect further, the two individual models reflecting practical problems from different respects were combined by fuzzy logic. The FC model mixed the two individual forecast results and its output was regarded as the final forecasting of the traffic flow. Practical application results show that the IH model, which takes advantage of the unique strength of the HM model and the ANN model, can produce more precise forecasting than that of two individual models. Thus, the IH model can be an efficient forecasting method to the shortterm traffic flow.

出版日期: 2010-09-21
:  TP 393.04  
基金资助:

 国家“863”高技术研究发展计划资助项目(2007AA11Z216);国家自然科学基金资助项目(50708094);浙江省自然科学基金资助项目(Y1090208).

通讯作者: 沈国江,男,副研究员.     E-mail: gjshen@iipc.zju.edu.cn
作者简介: 任沙浦(1960-),男,浙江绍兴人,副教授,硕士.从事智能检测及控制应用开发.E-mail:renshapu@163.com
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  

引用本文:

任沙浦, 沈国江. 短时交通流智能混合预测技术[J]. J4, 2010, 44(8): 1473-1478.

LIN Sha-Pu, CHEN Guo-Jiang. Intelligent hybrid forecasting technique for short-term traffic flow. J4, 2010, 44(8): 1473-1478.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2010.08.007        http://www.zjujournals.com/eng/CN/Y2010/V44/I8/1473

[1] 韩超, 宋苏, 王成红. 基于ARIMA模型的短时交通流实时自适应预测系统[J]. 仿真学报,2004, 16(7):15301535.
HAN Chao, SONG Su,WANG Chenghong. A realtime shortterm traffic flow adaptive forecasting method based on ARIMA model [J]. Journal of System Simulation, 2004, 16(7):15301535.
[2] 四兵锋, 孙壮志,赵小梅. 基于随机用户平衡的混合交通网络流量分离模型[J]. 中国公路学报, 2006, 19(1): 9398.
SI Bingfeng, SUN Zhuangzhi, ZHAO Xiaomei. Mixed traffic network flowsplit model based on stochastic user equilibrium [J]. China Journal of Highway and Transport, 2006, 19(1): 9398.
[3] 熊烈强, 王富, 李杰. 路段交通流的动力学模型及其仿真[J]. 中国公路学报, 2006,19(2):9194.
XIONG Lieqiang, WANG Fu, LI Jie. Dynamical model of traffic flow on segment and its simulation [J]. China Journal of Highway and Transport, 2006,19(2):9194.
[4] 贺国光, 李宇,马寿峰. 基于数学模型的短时交通流预测方法探讨[J]. 系统工程理论与实践, 2000, 20(12): 5156.
HE Guoguang, LI Yu, MA Shoufeng. Discussion on shortterm traffic flow forecasting methods based on mathematical models [J]. Systems Engineering Theory and Practice, 2000, 20(12): 5156.
[5] 杨立才,贾磊,孔庆杰, 等. 粗正交小波网络及其在交通流预测中的应用[J]. 系统工程理论与实践,2005, 25(8):124129.
YANG Licai, JIA Lei, KONG Qingjie, et al. Rough orthogonal wavelet network and its applications to the traffic forecast [J]. Systems Engineering Theory and Practice, 2005, 25(8):124129.
[6] TAN Manchun. Study and implementation of a decision support system for urban transit planning [J]. Dynamics of Continuous Discrete and Impulsive Systems Series A, 2005, 13(1):17371742.
[7] YIN H B, Wong S C, XU J M, et al. Urban traffic flow prediction using a fuzzyneural approach [J]. Transportation Research Part C, 2002,10(2): 8598.
[8] CORINNE L. An urban traffic flow model integrating neural networks. Transportation Research Part C, 1997,5(5):287300.
[9] BATES J M, GRANGER C W J. The combination of forecasts [J]. Operational Research Quarterly, 1969, 20(1):451468.
[10] HORNIK K. Multilayer feedforward networks are universal approximators [J]. Neural Networks, 1989, 2(5):359366.
[11] HO F, IOANNOU P. Traffic flow modeling and control using artificial neural networks [J]. IEEE Control Systems Magazine, 1996, 16(5): 1627.
[12] 孔祥杰,沈国江,梁同海. 具有公交优先的路网交通流智能协调控制\
[J\]. 浙江大学学报:工学版, 2009, 43(6): 10261031.
KONG Xiangjie, SHEN Guojiang, LIANG Tonghai. Intelligent coordination control of traffic flow on road network with buspriority [J]. Journal of Zhejiang University: Engineering Science, 2009, 43(6): 10261031.

[1] 舒宇, 余锋, 汪乐宇. 基于预留带宽的光纤通道交换网硬实时通信[J]. J4, 2010, 44(9): 1698-1704.
[2] 赵备, 余锋, 胡璇, 等. 基于FPGA的光纤通道协议引擎的设计与实现[J]. J4, 2009, 43(09): 1604-1608.