scholarly journals Development of a Neural Network Based Q Learning Algorithm for Traffic Signal Control

2011 ◽  
Vol 2-3 ◽  
pp. 91-95
Author(s):  
Li Bi Fu ◽  
Kil To Chong
Keyword(s):  
Neural Network ◽  
Memory Load ◽  
Learning Algorithm ◽  
Control Area ◽  
Traffic Signal ◽  
Signal Control ◽  
Traffic Signal Control ◽  
Q Learning ◽  
Traffic Efficiency ◽  
Continuous State

As one kind of reinforcement learning method, Q learning algorithm has already been proved to achieve many significant results in traffic signal control area. However, when the state of Markov Decision Process is very big or continuous, the computation load and the memory load will become very big and can not be solved then. Therefore, this paper proposed a neural network based Q learning algorithm to solve this problem known as “Curse of Dimensionality”. This new method realized generalization of conventional Q learnig algorithm in huge and continuous state space as neural network is a very effective value function approximator. Experiment has been implemented upon an isolated intersection and simulation results show that the proposed method can improve the traffic efficiency significantly than the conventional Q learning algorithm.

scholarly journals Adaptive traffic signal control based on bio-neural network

2017 ◽  
Vol 109 ◽  
pp. 1182-1187 ◽  
Author(s):  
Guilherme B. Castro ◽  
André R. Hirakawa ◽  
José S.C. Martini
Keyword(s):  
Neural Network ◽  
Traffic Signal ◽  
Signal Control ◽  
Traffic Signal Control ◽  
Adaptive Traffic Signal Control

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

2019 ◽  
Vol 27 (4) ◽  
pp. 341-354 ◽  
Author(s):  
Azadeh Emami ◽  
Majid Sarvi ◽  
Saeed Asadi Bagloee
Keyword(s):  
Neural Network ◽  
Queue Length ◽  
Travel Demand ◽  
Penetration Rate ◽  
Estimation Method ◽  
Traffic Signal ◽  
Signal Control ◽  
Traffic Signal Control ◽  
Market Penetration ◽  
Length Estimation

AbstractThis 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.

scholarly journals Hybrid Radial Basis Function Neural Networks for Urban Traffic Signal Control

2020 ◽  
Vol 8 (4) ◽  
Author(s):  
Burcu Caglar Gencosman ◽  
Keyword(s):  
Neural Network ◽  
Control System ◽  
Radial Basis Function ◽  
Real World ◽  
Basis Function ◽  
Traffic Signal ◽  
Signal Control ◽  
Traffic Signal Control ◽  
Classification Methods ◽  
Radial Basis

In this study, a real-world isolated signalized intersection with a fixed-time signal control system is considered. The signal timing plans are arranged regardless of the traffic density, and these plans cause delays in vehicle queues. To increase the efficiency of the intersection, an adaptive traffic signal control system is proposed to manage the intersection. To find the appropriate adaptive green times for each lane, simulations are performed by traffic simulation software using vehicle arrivals and other information about vehicle movements gathered from the real-world intersection. Then, a hybrid radial basis function neural network is developed to forecast the adaptive green times, which is trained and tested with historical arrivals and simulation results. The performance of the proposed network is compared with well-known data mining classification methods, such as support vector regression, k-nearest neighbors, decision tree, random forest, and multilayer perceptron methods, by different evaluation parameters. The comparison results provide that the developed radial basis function neural network outperforms other classification methods and can be successfully used for forecasting adaptive green times as an alternative to complex unsupervised classification methods.

Sign in / Sign up

Export Citation Format

Share Document