Methods for Multi-Type Sensor Allocations Along a Freeway Corridor

Existing layouts of sensors on freeways usually have room for improvement. The optimal allocation of multi-type sensors could increase the accuracy and coverage of data acquisition for traffic control and management. This paper aims to explore the appropriate method to solve the multi-type sensor allocation problem on freeways. Two types of sensors, the micro-loop sensor and the microwave sensor, are considered in this study. Three sensor allocation methods, the Integer Programming-Genetic Algorithm (IP-GA) method, the cluster method, and the two-stage method, are proposed to identify the optimal sensor locations. To investigate the performances of our proposed methods, a case study of sensor allocations on Ning-Hang freeway in Jiangsu province, China was conducted. The analysis results demonstrated that the IP-GA method has the best performance among the three proposed algorithms in view of the Mean Absolute Relative Errors (MAREs) of link travel time. Besides, this study also found that optimizing the composition of sensors has a far greater impact on data accuracy than just increasing the number of sensors. Within a specific range, data accuracy increases along with the number of sensors. Under the cases of the total number being constant, the greater the proportion of high accuracy sensors, the more accurate of the estimated traffic information.

[1]  Qing Ou,et al.  Fusing Heterogeneous Traffic Data: Parsimonious Approaches using Data-Data Consistency , 2011 .

[2]  M. Ganesh Kumar,et al.  Mobile Century Using GPS Mobile Phones as Traffic Sensors : A Field Experiment , 2008 .

[3]  Jay L. Devore,et al.  Probability and statistics for engineering and the sciences , 1982 .

[4]  Praveen Edara,et al.  Optimizing Freeway Traffic Sensor Locations by Clustering Global-Positioning-System-Derived Speed Patterns , 2010, IEEE Transactions on Intelligent Transportation Systems.

[5]  Rosaldo J. F. Rossetti,et al.  Using GPS-based AVL data to calculate and predict traffic network performance metrics: A systematic review , 2016, 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC).

[6]  Xuegang Ban,et al.  Sequential Modeling Framework for Optimal Sensor Placement for Multiple Intelligent Transportation System Applications , 2011 .

[7]  Guo Xiuchen.  Research on Application of Detective Technique for Dynamic Traffic Data of Expressway , 2008 .

[8]  Byungkyu Brian Park,et al.  Determining optimal sensor locations in freeway using genetic algorithm-based optimization , 2011, Eng. Appl. Artif. Intell..

[9]  Ruimin Li,et al.  Evaluation of speed-based travel time estimation models , 2006 .

[10]  Praveen Edara,et al.  Optimal Placement of Point Detectors on Virginia’s Freeways: Case Studies ofNorthern Virginia and Richmond , 2008 .

[11]  Hyoshin Park,et al.  Optimal number and location of Bluetooth sensors considering stochastic travel time prediction , 2015 .

[12]  Alexandre M. Bayen,et al.  Optimal Sensor Placement for Freeway Travel Time Estimation , 2009 .

[13]  Adam Danczyk,et al.  A mixed-integer linear program for optimizing sensor locations along freeway corridors , 2011 .

[14]  Peter T. Martin,et al.  DETECTOR TECHNOLOGY EVALUATION , 2003 .

[15]  Ning Zhu,et al.  Travel time estimation oriented freeway sensor placement problem considering sensor failure , 2017, J. Intell. Transp. Syst..

[16]  Marc Teboulle,et al.  Grouping Multidimensional Data - Recent Advances in Clustering , 2006 .

[17]  Ashkan Sharafsaleh.  Commercially-off-the-Shelf (COTS) and Emerging Technologies Sensor Testing and Evaluation , 2006 .

[18]  Kaan Ozbay,et al.  Clustering-Based Methodology for Determining Optimal Roadway Configuration of Detectors for Travel Time Estimation , 2007 .

[19]  Xuan Di,et al.  A probabilistic optimization model for allocating freeway sensors , 2016 .

[20]  Pushkin Kachroo,et al.  Observability and Sensor Placement Problem on Highway Segments: A Traffic Dynamics-Based Approach , 2016, IEEE Transactions on Intelligent Transportation Systems.

[21]  Chris Bachmann,et al.  A comparative assessment of multi-sensor data fusion techniques for freeway traffic speed estimation using microsimulation modeling , 2013 .

[22]  R. M. Betts,et al.  3M microloop field evaluation report: Appendices. Final research report , 1999 .

[23]  Henry X. Liu,et al.  Optimal Sensor Locations for Freeway Bottleneck Identification , 2009, Comput. Aided Civ. Infrastructure Eng..

[24]  Carlos A. Coello Coello,et al.  Constraint-handling techniques used with evolutionary algorithms , 2019, GECCO.

[25]  Michael Hunter,et al.  Practical Procedure to Collect Arterial Travel Time Data Using GPS-Instrumented Test Vehicles , 2006 .

[26]  Der-Horng Lee,et al.  Probe Vehicle Population and Sample Size for Arterial Speed Estimation , 2002 .

[27]  Mark E Hallenbeck,et al.  A Guide to Documenting VISSIM-Based Microscopic Traffic Simulation Models , 2007 .

[28]  Bin Ran,et al.  Sample Size Reduction Method Based on Data Fusion for Freeways with Fixed Detectors , 2015 .

[29]  Eric Horvitz,et al.  Predicting Travel Time Reliability using Mobile Phone GPS Data , 2017 .