Virtual speed sensors based algorithm for expressway traffic state estimation

The accurate estimation of expressway traffic state can provide decision-making for both travelers and traffic managers. The speed is one of the most representative parameter of the traffic state. So the expressway speed spatial distribution can be taken as the expressway traffic state equivalent. In this paper, an algorithm based on virtual speed sensors (VSS) is presented to estimate the expressway traffic state (the speed spatial distribution). To gain the spatial distribution of expressway traffic state, virtual speed sensors are defined between adjacent traffic flow sensors. Then, the speed data extracted from traffic flow sensors in time series are mapped to space series to design virtual speed sensors. Then the speed of virtual speed sensors can be calculated with the weight matrix which is related with the speed of virtual speed sensors and the speed data extracted from traffic flow sensors and the speed data extracted from traffic flow sensors in time series. Finally, the expressway traffic state (the speed spatial distribution) can be gained. The acquisition of average travel speed of the expressway is taken for application of this traffic state estimation algorithm. One typical expressway in Beijing is adopted for the experiment analysis. The results prove that this traffic state estimation approach based on VSS is feasible and can achieve a high accuracy.

[1]  Fan Wang,et al.  Real-Time Freeway Traffic State Estimation Based on Cluster Analysis and Multiclass Support Vector Machine , 2009, 2009 International Workshop on Intelligent Systems and Applications.

[2]  Jianjun Wang,et al.  The Analysis of Traffic Flow State on Foggy Expressway Based on Fuzzy Clustering , 2009 .

[3]  R. Horowitz,et al.  Mixture Kalman filter based highway congestion mode and vehicle density estimator and its application , 2004, Proceedings of the 2004 American Control Conference.

[4]  Osama Tomeh,et al.  Urban Expressway Real-Time Traffic State Estimation and Travel Time Prediction within EFK Framework , 2008 .

[5]  Bin Ran,et al.  Particle filter based traffic state estimation using cell phone network data , 2006, 2006 IEEE Intelligent Transportation Systems Conference.

[6]  M. Papageorgiou,et al.  An adaptive freeway traffic state estimator and its real-data testing-part II: adaptive capabilities , 2005, Proceedings. 2005 IEEE Intelligent Transportation Systems, 2005..

[7]  Markos Papageorgiou,et al.  Real-time freeway traffic state estimation based on extended Kalman filter: a general approach , 2005 .

[8]  Hironori Suzuki,et al.  Unscented Kalman Filter-Based Real-Time Traffic State Estimation , 2007 .

[9]  Xi Chen,et al.  Urban Expressway Traffic State Estimation Based on FCM-Rough Set , 2010 .

[10]  L. Mihaylova,et al.  A particle filter for freeway traffic estimation , 2004, 2004 43rd IEEE Conference on Decision and Control (CDC) (IEEE Cat. No.04CH37601).

[11]  B De Schutter,et al.  Fuzzy models and observers for freeway traffic state tracking , 2010, Proceedings of the 2010 American Control Conference.

[12]  Haris N. Koutsopoulos,et al.  Nonlinear Kalman Filtering Algorithms for On-Line Calibration of Dynamic Traffic Assignment Models , 2006, IEEE Transactions on Intelligent Transportation Systems.

[13]  Hironori Suzuki,et al.  Application of Probe-Vehicle Data for Real-Time Traffic-State Estimation and Short-Term Travel-Time Prediction on a Freeway , 2003 .

[14]  Alexandre M. Bayen,et al.  Incorporation of Lagrangian measurements in freeway traffic state estimation , 2010 .

[15]  Markos Papageorgiou,et al.  Real-Time Freeway Traffic State Estimation Based on Extended Kalman Filter: A Case Study , 2007, Transp. Sci..