A neural network algorithm for queue length estimation based on the concept of k-leader connected vehicles

Abstract

This paper presents a novel method to estimate queue length at signalised intersections using connected vehicle (CV) data. The proposed queue length estimation method does not depend on any conventional information such as arrival flow rate and parameters pertaining to traffic signal controllers. The model is applicable for real-time applications when there are sufficient training data available to train the estimation model. To this end, we propose the idea of ''k-leader CVs'' to be able to predict the queue which is propagated after the communication range of dedicated short-range communication (the communication platform used in CV system). The idea of k-leader CVs could reduce the risk of communication failure which is a serious concern in CV ecosystems. Furthermore, a linear regression model is applied to weigh the importance of input variables to be used in a neural network model. Vissim traffic simulator is employed to train and evaluate the effectiveness and robustness of the model under different travel demand conditions, a varying number of CVs (i.e. CVs' market penetration rate) as well as various traffic signal control scenarios. As it is expected, when the market penetration rate increases, the accuracy of the model enhances consequently. In a congested traffic condition (saturated flow), the proposed model is more accurate compared to the undersaturated condition with the same market penetration rates. Although the proposed method does not depend on information of the arrival pattern and traffic signal control parameters, the results of the queue length estimation are still comparable with the results of the methods that highly depend on such information. The proposed algorithm is also tested using large size data from a CV test bed (i.e. Australian Integrated Multimodal Ecosystem) currently underway in Melbourne, Australia. The simulation results show that the model can perform well irrespective of the intersection layouts, traffic signal plans and arrival patterns of vehicles. Based on the numerical results, 20% penetration rate of CVs is a critical threshold. For penetration rates below 20%, prediction algorithms fail to produce reliable outcomes.

Review of driving-behaviour simulation: VISSIM and artificial intelligence approach

“… Following the implementation of the (AFNN) algorithm, the average number of stops, average delay time, and average queue length dropped while the average fuel economy increased. [ 181 ] Evaluate the effectiveness and robustness of the model. Perceptron NN Estimating queue length using connected vehicle (CV) data.…”

Electromechanical coupling dynamic modeling and analysis of vertical electrodynamic shaker considering low frequency lateral vibration

“…The analytical calculation methods are also timeconsuming and it is difficult to quickly get the equivalent electromagnetic force of the moving coil under different motion conditions. In other fields, for the rapid calculation and estimation of physical quantities and parameters, scholars mostly apply multivariate nonlinear fitting, neural network and support vector machine method [22][23][24] based on orthogonal experimental design, which can be referred in this research.…”

Kalman Filtering Method for Real-Time Queue Length Estimation in a Connected Vehicle Environment

“…The shockwave models calculate queue length by capturing the queue formation and dissipation process based on the continuous traffic flow theory ( 16 , 17 ). However, existing queue length estimation methods are mainly based on data from fixed detectors ( 7 , 18 ) and probe vehicles ( 19 – 21 ). In particular, most of the research has focused on fixed detectors ( 12 , 15 , 18 , 22 , 23 ).…”

“…can be obtained in a CV environment ( 26 , 27 ). Some studies ( 20 , 28–31 ) have presented ways to improve the performance of queue length estimation with CV data. Table 1 summarizes the recent studies on queue length estimation in a CV environment.…”