CN112419726B - Urban traffic signal control system based on traffic flow prediction - Google Patents
Urban traffic signal control system based on traffic flow prediction Download PDFInfo
- Publication number
- CN112419726B CN112419726B CN202011306672.7A CN202011306672A CN112419726B CN 112419726 B CN112419726 B CN 112419726B CN 202011306672 A CN202011306672 A CN 202011306672A CN 112419726 B CN112419726 B CN 112419726B
- Authority
- CN
- China
- Prior art keywords
- traffic
- traffic flow
- prediction
- time
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/07—Controlling traffic signals
- G08G1/08—Controlling traffic signals according to detected number or speed of vehicles
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses an urban traffic signal control system based on traffic flow prediction, which comprises: the data center is used for storing the neural network training of the data center and the prediction module and predicting the traffic data at the next time interval; the data center adds original real-time traffic data into historical traffic data before each time of real-time traffic data transmission, and then updates the real-time traffic data; the prediction module is used for predicting short-term traffic flow, for a multi-intersection road section, the road section to be predicted is i, if the current time is in a time interval k, the traffic flow of the next time interval is measured to be predicted, and the traffic flow in the past is predicted according to the known road section i and all the adjacent upstream or downstream road sections; and the optimization module is used for evaluating the congestion degree of the city according to the signal lamp timing scheme in the road and the prediction data output by the prediction module. The invention obtains the traffic jam condition of the next time period in advance to obtain the signal lamp timing scheme with minimum jam at the next time.
Description
Technical Field
The invention relates to the field of traffic signal control traffic flow prediction, in particular to an urban traffic signal control system based on traffic flow prediction.
Technical Field
Traffic signal control is an important component of an urban intelligent traffic system. Depending on the mode of operation, traffic signal controllers can be divided into two categories: a timing signal controller and an adaptive signal controller. The control effect of the adaptive signal controller is generally better because the period length and the split ratio of the former controller are fixed and can be adaptively adjusted in the latter controller. In recent years, artificial intelligence has provided a new approach to solving this problem. For example, some researchers have proposed Fuzzy theory for designing signal control schemes (X.Cheng and Z.Yang: Intelligent traffic control adaptive base on Fuzzy-genetic algorithm.2008Fifth International reference on Fuzzy Systems and KnowledDiscovery, Shandong, pp.221-225,2008.). The optimal signal control strategy may also be learned through reinforcement learning. Evolutionary algorithms such as genetic algorithm, particle swarm algorithm, etc. can also be used to solve the static timing optimization problem.
Although a variety of approaches have been developed, challenges remain in designing effective and efficient urban traffic signal control systems. First, in most studies, control of traffic signals was based solely on real-time traffic data, such as queue lengths detected by intersection sensors. Secondly, some studies are directed to signal control at a single intersection only, and lack consideration of the entire area. The result of this approach is therefore only a greedy solution and a single interaction for the current situation. To implement global solution, not only the current traffic conditions but also future traffic conditions are considered, and not only the single interaction but also the traffic conditions of the whole area are considered.
Traffic flow has characteristics of complexity, randomness, nonlinearity and the like. To date, a number of models and methods have been used to predict traffic flow. Early prediction methods mainly include self-regression models, moving average models (S.Hansun and M.B.Kristanda: Performance analysis of computational moving methods in form of information obtaining.2017 International Conference on Smart Cities, Automation & Intelligent Computing Systems (ICON-SONICS), Yogyakarta, pp.11-17,2017.), self-regression moving average models, etc., and as the research in this field goes deep, some more complicated and accurate prediction methods have appeared. Generally, traffic flow prediction models can be divided into three categories. One is a prediction model based on the traditional mathematical statistics technology, such as a time series model, a Kalman filtering model, a parameter Regression model (M.Z.Ali, N.S.K.Shabbir, M.S.A.Chowdhury, A.Ghosh and X.Liang: Regression Models of Critical Parameters influencing Peak greater computing and shaping.2018 IEEE Canadian Conference on electric & Computer Engineering (CCECE), Quebec City, QC, pp.1-4,2018.) and the like. Non-parametric regression methods and wavelet based methods have also been proposed for traffic flow prediction. Another class of predictive models is based on physical methods and simulations. In these models, dynamic systems have been developed to model and simulate the evolution of traffic flow in a road network. The third type of prediction model is based on modern computational intelligence methods, such as neural networks, fuzzy control and the like, and the prediction models do not strictly consider potential power systems or definite physical meanings, but pay more attention to the fitting effect of the actual traffic flow phenomenon.
Although various traffic flow prediction techniques have been developed and good prediction performance has been achieved, these studies are separated from the studies of traffic signal control. That is, existing research has focused on either traffic single optimization or traffic flow prediction, but little work has been done to combine these two techniques. To account for the effects of traffic signal control over a period of time, the predicted traffic conditions should also be considered
Disclosure of Invention
In order to solve the problems, the invention provides an urban traffic signal control system based on traffic flow prediction, which applies the traffic flow prediction to the urban road traffic control system
The invention is realized by at least one of the following technical schemes.
An urban traffic signal control system based on traffic flow prediction, comprising:
the data center is used for storing historical traffic data of urban roads, real-time monitored traffic data, neural network training of the prediction module and prediction of traffic data of the next time interval; the data center adds original real-time traffic data into historical traffic data before each time of transmission of the real-time traffic data, and updates the real-time traffic data;
the prediction module is used for neural network training and predicting traffic flow;
and the optimization module is used for evaluating the congestion degree of the city according to the signal lamp timing scheme in the road and the prediction data output by the prediction module.
Preferably, the prediction method of the prediction module comprises a BP neural network.
Preferably, for a multi-intersection road section, the road section to be predicted is i, and assuming that the current time is in the time interval k, the traffic flow with the amount to be predicted being the next time interval is marked as C i (k +1) predicting the traffic flow of the past p time intervals according to the known road section i and all the adjacent upstream or downstream road sections j, and recording the traffic flow as C i (k-2)、C i (k-1)、C i (k) And C j (k-2)、C j (k-1)、C j (k)。
Preferably, the BP neural network includes an input layer, a hidden layer and an output layer, the hidden layer is one or more layers of neuron nodes, connections between neuron nodes all correspond to a weight w, and two adjacent layers of neurons are fully connected.
Preferably, the BP network comprises two processes of forward propagation of signals and backward propagation of errors.
Preferably, during the forward propagation, the input signal acts on the output node through the hidden layer, and generates an output signal through nonlinear transformation; if the actual output does not accord with the expected output, the process of error back propagation is carried out;
the error back transmission is to back transmit the output error to the input layer by layer through the hidden layer, and distribute the error to all nodes of each layer, and the error signal obtained from each layer is used as the basis for adjusting the weight of each node, and the error is reduced along the gradient direction by adjusting the connection weight of the input node and the hidden node and the connection weight of the hidden node and the output node.
Preferably, the prediction data in the prediction module includes a road section ID, an adjacent signal light ID, a traffic direction and a cumulative number of vehicles driven in a time interval.
Preferably, the evaluation process of the optimization module is divided into two steps: firstly, traversing all signal lamp intersections in the traffic network, and calculating the total parking queuing number B of all traffic flows at the intersections under the current timing scheme x Then, a judgment B is performed x ＜B x-1 If the judgment result is true, executing a control optimization strategy on the signal lamp to obtain a new signal lamp timing scheme for reevaluation, and B during the first evaluation 0 0; otherwise, outputting the current signal lamp timing scheme.
Preferably, the signal lamp control optimization strategy comprises the following steps:
(3) traversing all signal lamp intersections in the traffic network, analyzing the parking queuing reasons of each traffic flow passing through the current intersection, and correspondingly marking the traffic flow causing the parking queuing reasons to be 1, 2 or 3 according to the fact that the vehicle throughput at the signal lamp intersections is limited by the minimum value of the upstream flow in the traffic flow driving direction, the traffic capacity of the signal lamp and the downstream residual capacity in the traffic flow driving direction.
(4) And if the traffic flow marked as 2 exists at the current intersection, reducing the duration of the green lights of the signal lights of all the traffic flows in the directions 1 and 3 by one unit time.
Preferably, step (1) is performed by using a cell transmission model-based traffic flow discrete time model.
Compared with the prior art, the invention has the beneficial effects that: the traffic flow prediction research result is fully utilized, the traffic congestion condition at the next moment is mastered in advance, and the signal lamp timing scheme with the minimum congestion at the next moment is obtained, so that sufficient time is provided for design or other measures of signal lamp timing, the regulation and control are more accurate, and the traffic congestion alleviation degree is higher. On the basis of a specific signal lamp timing optimization scheme, the control system provided by the invention is not strictly limited, so that the most appropriate strategy can be selected according to the actual situation, for example, a small-sized urban road network can finely adjust the signal lamp timing in a traversal mode, and a large-sized urban road network can accelerate the optimization speed by using an evolutionary algorithm, and the like.
Drawings
Fig. 1 is a block diagram of an urban traffic signal control system based on traffic flow prediction according to the embodiment.
Detailed Description
The inventive system is further described below in conjunction with the appended drawings.
As shown in fig. 1, an urban traffic signal control system based on traffic flow prediction includes a data center, a prediction module and an optimization module.
Historical traffic data of the urban road and traffic data monitored in real time are stored in a data center separately and are used for neural network training of a prediction module and prediction of traffic data of the next time interval; the data center adds original real-time traffic data into historical traffic data before each time of real-time traffic data transmission, and then updates the real-time traffic data.
And the prediction module adopts a BP neural network for prediction. The prediction module performs short-term traffic flow prediction, for a multi-intersection road section, the road section to be predicted is i, and if the current time is in a time interval k, the traffic flow with the amount to be predicted being the next time interval is marked as C i (k +1) predicting the traffic flow of the past p time intervals according to the known road section i and all the adjacent upstream or downstream road sections j, and recording the traffic flow as C i (k-2)、C i (k-1)、C i (k) And C j (k-2)、C j (k-1)、C j (k)。
The prediction module reads historical traffic data from the data center during neural network training, and a good prediction model is trained by using a large amount of data. The time required for this process is long and therefore the frequency of updating the predictive model can be scheduled to be monthly or monthly. And transmitting the real-time traffic data collected on the road to a data center at intervals, and then inputting the real-time traffic data into a prediction model to obtain traffic prediction data of the next time interval, wherein the traffic prediction data comprises a road section ID, an adjacent signal lamp ID, a traffic flow direction and the accumulated number of vehicles driven in one time interval. The prediction data is output to an optimization module.
The BP neural network is a multi-layer feedforward network trained according to error back propagation, the algorithm is called BP algorithm, the basic idea is a gradient descent method, and the mean square error of the actual output value and the expected output value of the network is minimized by utilizing a gradient search technology. Structurally, the BP network has an input layer, a hidden layer and an output layer, and the hidden layer is one or more layers of neuron nodes. The external input is firstly transmitted to a first layer of neurons through connections, each connection corresponds to a weight w, and the w is obtained through training; the first layer neurons transmit their outputs to the second layer neurons, and so on. There is no communication between neurons in the same layer; the adjacent two layers of neurons are fully connected. The basic BP algorithm includes two processes, forward propagation of signals and back propagation of errors. During forward propagation, an input signal acts on an output node through a hidden layer, and an output signal is generated through nonlinear transformation; if the actual output does not match the expected output, the process proceeds to the back propagation of the error. The error back transmission is to back transmit the output error to the input layer by layer through the hidden layer, and distribute the error to all nodes of each layer, and the error signal obtained from each layer is used as the basis for adjusting the weight of each node. And the error is reduced along the gradient direction by adjusting the connection weight of the input node and the hidden node and the connection weight of the hidden node and the output node. After repeated learning and training, determining the network parameters (weight) corresponding to the minimum error, and immediately stopping training, wherein the trained neural network can automatically process the input information of similar samples and output the information which has the minimum error and is subjected to nonlinear transformation.
The optimization module firstly evaluates the congestion degree of the city according to the traffic flow prediction plan and traffic data of the signal lamp timing party in the road. The evaluation process is divided into two steps: firstly, traversing all signal lamp intersections in the traffic network, and calculating the accumulated parking queuing total number B of the traffic flow at all the intersections under the current timing scheme x . Then, a judgment B is performed x ＜B x-1 If the judgment result is true, executing a control optimization strategy on the signal lamp to obtain a new signal lamp timing scheme (B in the first evaluation) 0 0), re-evaluating; otherwise, outputting the current signal lamp timing scheme. The traffic flow data used in the method is prediction data output by the prediction module.
The specific process of the signal lamp control optimization strategy is as follows:
(1) and traversing all signal lamp intersections in the traffic network, and judging the parking queuing reason of each traffic flow passing through the current intersection. According to the traffic flow discrete time model based on the cellular transmission model, the vehicle throughput at the signal light intersection is limited by the minimum value of the upstream flow in the traffic flow driving direction, the signal light traffic capacity and the downstream residual capacity in the traffic flow driving direction, and the vehicle marking the reason causing the parking queue is correspondingly marked as 1, 2 or 3.
The cellular transmission model is a macroscopic traffic flow model, and utilizes the concept of cellular automata to research network traffic flow. It discretizes the road segment space into small grids and the time into time steps to simulate the formation and dissipation of queues.
(2) If the traffic flow marked as 2 exists at the current intersection, the green duration of the signal lights of all other traffic flows in the directions 1 and 3 is reduced by one unit time, for example, the green duration is shortened by 5 seconds, and then the green duration of the cut-off traffic lights is averagely distributed to the signal lights of the traffic flows in the directions 2.
A simplified urban traffic network is used as a system experimental environment to test the performance of the traffic control system of the invention on relieving traffic congestion. The urban traffic network is formed by connecting 25 intersections and 132 roads. A contrast experiment is based on a self-adaptive signal lamp control optimization strategy, and the accumulated parking queue number B of the traffic flow at all intersections is respectively calculated under the conditions of prediction and non-prediction x The reason for this is that if the traffic data does not pass through the prediction module, the real-time traffic data is input into the optimization module after a period of time, and the optimized signal lamp timing scheme can only be used in the next time interval, which means that the optimization is delayed. The following table gives the number of parking lines with forecasts reduced relative to no forecast control system for different traffic settings for 30 consecutive days, where the base traffic is the sum of the traffic during peak hours (7: 00-9: 00, 17: 00-20: 00) for all segments of the day and λ is the ratio of the base traffic scaling. The values in the table are always positive, i.e. congestion levels are relieved at different traffic settings, which proves that the inventive system is effective.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such changes, modifications, substitutions, combinations, and simplifications are intended to be included in the scope of the present invention.
Claims (1)
1. An urban traffic signal control system based on traffic flow prediction, comprising:
the data center is used for storing historical traffic data of urban roads, real-time monitored traffic data, neural network training of the prediction module and prediction of traffic data of the next time interval; the data center adds original real-time traffic data into historical traffic data before the real-time traffic data are transmitted every time, and updates the real-time traffic data;
the prediction module is used for neural network training and predicting traffic flow;
the optimization module is used for evaluating the congestion degree of the city according to a signal lamp timing scheme in the road and prediction data output by the prediction module;
the prediction module predicts by adopting a BP neural network, prediction data in the prediction module comprises a road section ID, an adjacent signal lamp ID, a traffic flow direction and an accumulated number of vehicles driving in a time interval, for a multi-intersection road section, a road section to be predicted is i, and if the current time is in a time interval k, the traffic flow of the next time interval to be predicted is marked as C i (k +1) predicting the traffic flow of the past p time intervals according to the known road section i and all the adjacent upstream or downstream road sections j, and recording the traffic flow as C i (k-2)、C i (k-1)、C i (k) And C j (k-2)、C j (k-1)、C j (k)；
The BP neural network comprises an input layer, a hidden layer and an output layer, wherein the hidden layer is one or more layers of neuron nodes, the connections between the neuron nodes correspond to a weight w, and two adjacent layers of neurons are in full connection; the BP neural network comprises two processes of forward propagation of signals and backward propagation of errors; during forward propagation, an input signal acts on an output node through a hidden layer, and an output signal is generated through nonlinear transformation; if the actual output does not accord with the expected output, the process of error back propagation is carried out;
the error reverse transmission is to reversely transmit the output error to the input layer by layer through the hidden layer, and distribute the error to all nodes of each layer, and take the error signal obtained from each layer as the basis for adjusting the weight of each node, and make the error descend along the gradient direction by adjusting the connection weight of the input node and the hidden node and the connection weight of the hidden node and the output node;
the evaluation process of the optimization module comprises two steps: firstly, traversing all signal lamp intersections in the traffic network, and calculating the total parking queuing number B of all traffic flows at the intersections under the current timing scheme x Then, judgment B is performed x ＜B x-1 If the judgment result is true, executing a control optimization strategy on the signal lamp to obtain a new signal lamp timing scheme for reevaluation, and B during the first evaluation 0 0; otherwise, outputting the current signal lamp timing scheme;
the signal lamp control optimization strategy comprises the following steps:
(1) traversing all signal lamp intersections in a traffic network, analyzing the parking queuing reasons of each traffic flow passing through the current intersection, analyzing by adopting a cell transmission model-based traffic flow discrete time model, and correspondingly marking the traffic flow of the reasons causing the parking queuing as 1, 2 or 3 according to the fact that the vehicle throughput at the signal lamp intersections is limited by the minimum value of the upstream flow in the traffic flow driving direction, the traffic light traffic capacity and the downstream residual capacity in the traffic flow driving direction;
(2) if the current intersection has the traffic flow marked as 2, the duration of the green light of the signal lights of all the traffic flows in the directions 1 and 3 is reduced by one unit time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011306672.7A CN112419726B (en) | 2020-11-20 | 2020-11-20 | Urban traffic signal control system based on traffic flow prediction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011306672.7A CN112419726B (en) | 2020-11-20 | 2020-11-20 | Urban traffic signal control system based on traffic flow prediction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112419726A CN112419726A (en) | 2021-02-26 |
| CN112419726B true CN112419726B (en) | 2022-09-20 |
Family
ID=74773912
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011306672.7A Active CN112419726B (en) | 2020-11-20 | 2020-11-20 | Urban traffic signal control system based on traffic flow prediction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112419726B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113099408A (en) * | 2021-03-15 | 2021-07-09 | 西安交通大学 | Simulation-based data mechanism dual-drive sensor node deployment method and system |
| GB2605130B (en) * | 2021-03-17 | 2023-08-16 | Xan Labs Int Ltd | Method and system of predictive traffic flow and of traffic light control |
| CN113240902B (en) * | 2021-03-25 | 2022-06-07 | 同济大学 | Signal control road network path flow estimation method based on sampled vehicle trajectory data |
| CN113299069B (en) * | 2021-05-28 | 2022-05-13 | 广东工业大学华立学院 | Self-adaptive traffic signal control method based on historical error back propagation |
| CN113256472B (en) * | 2021-07-12 | 2021-11-26 | 深圳市永达电子信息股份有限公司 | Intelligent traffic control method and system and brain-like computer readable storage medium |
| CN113781784B (en) * | 2021-11-09 | 2022-02-11 | 深圳市奥新科技有限公司 | Intelligent traffic light and control method thereof |
| CN114023074B (en) * | 2022-01-10 | 2022-04-15 | 佛山市达衍数据科技有限公司 | Traffic jam prediction method, device and medium based on multiple signal sources |
| CN114333361B (en) * | 2022-02-22 | 2022-06-28 | 南京慧尔视智能科技有限公司 | Signal lamp timing method and device |
| CN114708746A (en) * | 2022-04-01 | 2022-07-05 | 河北金锁安防工程股份有限公司 | Traffic signal prompting method and system for smart city |
| CN114677844B (en) * | 2022-04-29 | 2022-11-22 | 立昂技术股份有限公司 | Intelligent traffic resource allocation service system and method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101901547A (en) * | 2010-07-21 | 2010-12-01 | 浙江工业大学 | Adaptive control method for variable lane |
| KR20140028801A (en) * | 2012-08-30 | 2014-03-10 | 경희대학교 산학협력단 | Prediction of urban congestion using its based data |
| KR101821494B1 (en) * | 2016-08-10 | 2018-01-24 | 중앙대학교 산학협력단 | Adaptive traffic signal control method and apparatus |
| CN111243299A (en) * | 2020-01-20 | 2020-06-05 | 浙江工业大学 | Single cross port signal control method based on 3 DQN-PSER algorithm |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8825350B1 (en) * | 2011-11-22 | 2014-09-02 | Kurt B. Robinson | Systems and methods involving features of adaptive and/or autonomous traffic control |
| CN103927890B (en) * | 2014-04-29 | 2016-01-13 | 北京建筑大学 | A kind of Trunk Road Coordination signal control method based on dynamic O-D Matrix Estimation |
| CN103927891B (en) * | 2014-04-29 | 2015-11-25 | 北京建筑大学 | A kind of based on two Bayesian crossings dynamic steering ratio two-staged prediction method |
| CN106355885A (en) * | 2016-11-24 | 2017-01-25 | 深圳市永达电子信息股份有限公司 | Traffic signal dynamic control method and system based on big data analysis platform |
| CN108922204B (en) * | 2018-05-10 | 2021-07-20 | 华南理工大学 | Cell transmission model improvement method considering intersection signal control |
| CN108877253B (en) * | 2018-07-27 | 2020-09-08 | 济南市市政工程设计研究院（集团）有限责任公司 | Internet of things-based bus lane resource dynamic sharing method and system |
| CN110047278B (en) * | 2019-03-30 | 2021-06-08 | 北京交通大学 | Adaptive traffic signal control system and method based on deep reinforcement learning |
-
2020
- 2020-11-20 CN CN202011306672.7A patent/CN112419726B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101901547A (en) * | 2010-07-21 | 2010-12-01 | 浙江工业大学 | Adaptive control method for variable lane |
| KR20140028801A (en) * | 2012-08-30 | 2014-03-10 | 경희대학교 산학협력단 | Prediction of urban congestion using its based data |
| KR101821494B1 (en) * | 2016-08-10 | 2018-01-24 | 중앙대학교 산학협력단 | Adaptive traffic signal control method and apparatus |
| CN111243299A (en) * | 2020-01-20 | 2020-06-05 | 浙江工业大学 | Single cross port signal control method based on 3 DQN-PSER algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112419726A (en) | 2021-02-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112419726B (en) | Urban traffic signal control system based on traffic flow prediction | |
| Araghi et al. | A review on computational intelligence methods for controlling traffic signal timing | |
| CN112216124B (en) | Traffic signal control method based on deep reinforcement learning | |
| CN112365724B (en) | Continuous intersection signal cooperative control method based on deep reinforcement learning | |
| Heung et al. | Coordinated road-junction traffic control by dynamic programming | |
| CN106971566B (en) | Self-adaptive control method based on genetic algorithm | |
| CN110570672B (en) | Regional traffic signal lamp control method based on graph neural network | |
| CN114360266B (en) | Intersection reinforcement learning signal control method for sensing detection state of internet connected vehicle | |
| Nagare et al. | Traffic flow control using neural network | |
| Jiang et al. | An urban traffic signal control system based on traffic flow prediction | |
| Dai et al. | Neural network based online traffic signal controller design with reinforcement training | |
| CN112863179B (en) | Intersection signal lamp control method based on neural network model predictive control | |
| Kong et al. | Urban arterial traffic two-direction green wave intelligent coordination control technique and its application | |
| Chen et al. | Dynamic traffic light optimization and Control System using model-predictive control method | |
| Lin et al. | Scheduling eight-phase urban traffic light problems via ensemble meta-heuristics and Q-learning based local search | |
| CN114694382B (en) | Dynamic one-way traffic control system based on Internet of vehicles environment | |
| Kao et al. | A self-organizing map-based adaptive traffic light control system with reinforcement learning | |
| Srinivasan et al. | Computational intelligence-based congestion prediction for a dynamic urban street network | |
| Balaji et al. | Multi-agent system based urban traffic management | |
| De Oliveira et al. | Optimization of traffic lights timing based on multiple neural networks | |
| CN114120670A (en) | Method and system for traffic signal control | |
| CN110021168B (en) | Grading decision method for realizing real-time intelligent traffic management under Internet of vehicles | |
| Cheng et al. | The adaptive road routing recommendation for traffic congestion avoidance in smart city | |
| Reza et al. | Artificial Intelligence-Based Protocol for Macroscopic Traffic Simulation Model Development | |
| Joo et al. | Reinforcement learning for traffic signal timing optimization |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |