原文传递
A Multisource Data Approach for Estimating Vehicle Queue Length at Metered On-Ramps
| 题名： | A Multisource Data Approach for Estimating Vehicle Queue Length at Metered On-Ramps |
| 正文语种： | eng |
| 作者： | Luo, Xiaoling;Ma, Xiaobo;Munden, Matthew;Wu, Yao-Jan;Jiang, Yangsheng |
| 作者单位： | Chongqing Jiaotong Univ Chongqing Key Lab Traff & Transportat Chongqing 400041 Peoples R China|Southwest Jiaotong Univ Sch Transportat & Logist 111 Second Ring Rd North Chengdu 610031 Sichuan Peoples R China;Univ Arizona Dept Civil & Architectural Engn & Mech 1209 E 2nd St Tucson AZ 85721 USA;Arizona Dept Transportat Aeronaut Grp 1801 W Jefferson St MD 426M Phoenix AZ 85007 USA;Univ Arizona Dept Civil & Architectural Engn & Mech 1209 E 2nd St Tucson AZ 85721 USA;Southwest Jiaotong Univ Sch Transportat & Logist 111 Second Ring Rd North Chengdu 610031 Sichuan Peoples R China |
| 关键词： | Queue length;Ramp metering;Resilient back-propagation neural network;Freeway operation |
| 摘要： | Queue length information is a critical input for ramp metering management. Based on accurate and reliable queue length, the inflow rate can be optimized to maximize the benefit of ramp metering. This paper proposes a queue length estimation method for metered on-ramps. In the proposed method, multiple data sources including INRIX data, controller event-based data, and loop detector data are used. The proposed method is based on the resilient back-propagation neural network model. In addition, the proposed method is enhanced by two techniques. The first technique is implementing the decision tree to determine whether or not the queue length is larger than zero and the second technique is checking whether or not the queue length reaches the ramp queue capacity by using the loop occupancy rate data. Three ramps along the SR-51 freeway in Phoenix, Arizona, were selected to evaluate the proposed method. The proposed method is compared with the Kalman filter (KF)-based method that has been proposed in previous research. The results show that the average improvements over the KF-based method are 46.82% and 63.08% for the estimated mean absolute error and root-mean-square error, respectively. |
| 出版年： | 2022 |
| 期刊名称： | Journal of Transportation Engineering |
| 卷： | 148 |
| 期： | 2 |
| 页码： | 04021117.1-04021117.9 |
相关文献
- Impact of On-Ramp Traffic Flow Arrival Profile on Queue Length at Metered On-Ramps
- Vehicle Speed and Acceleration Profile Study for Metered On-Ramps in California
- Optimization of Consecutive On-Ramp Control for Urban Freeways: An Application of the Store-and-Forward Approach
- Cycle-Based Estimation on Lane-Level Queue Length at Isolated Signalized Intersection Using License Plate Recognition Data
- Shockwave-based queue estimation approach for undersaturated and oversaturated signalized intersections using multi-source detection data
- Probe Vehicle Lane Identification for Queue Length Estimation at Intersections
检索历史
应用推荐
