Physical prior constraint time sequence diagram-based attention traffic signal control method and system

Abstract

The invention relates to the technical field of intelligent traffic systems, and provides an attention traffic signal control method and system based on a physical prior constraint time sequence diagram in order to solve the problems that in the prior art, risks cannot be recognized in advance, and direct quantification and constraint are lacked for core risks. The attention traffic signal control method based on the physical prior constraint time sequence diagram comprises the steps that the physical storage capacity of a road section is calculated, and the remaining storage space of a downstream road section is obtained in combination with the current vehicle number, namely overflow safety buffer; the overflow safety buffer is converted into overflow risk cost, and a constrained Markov decision process model with the passing efficiency as the return and the overflow risk as the cost is constructed; and solving the constrained Markov decision process model by using a pre-trained time sequence diagram attention network to obtain an optimal signal control action for balancing the traffic efficiency and the overflow risk. According to the method, the overflow risk can be proactively identified and actively avoided, so that cascade congestion caused by queue overflow can be actively avoided.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent transportation systems, and in particular to a traffic signal control method and system based on physical prior constraint time series graph attention. BACKGROUND

[0002] The statements in this section merely provide background information related to the present application and do not necessarily constitute prior art.

[0003] Under the condition of high-density vehicle operation, the city traffic system often triggers a chain reaction due to queue spillover at local intersections, eventually leading to large-scale gridlock, which seriously affects the traffic efficiency and system resilience of the road network. Traditional traffic signal control methods, such as fixed timing or local induction control, are difficult to intervene in the formation and propagation of congestion in a forward-looking manner due to their limited information sources and lagging reaction modes, especially in complex topological structures and densely populated short road networks in urban areas, which cannot effectively suppress the risk of cascading congestion.

[0004] In the prior art, deep reinforcement learning (Deep Reinforcement Learning) and graph neural network (Graph Neural Network, GNN) methods are combined to control adaptive traffic signals, which can effectively model the spatial dependence between intersections and improve the ability of multi-intersection coordinated control. However, the prior art still has the following problems: (1) In the time dimension, the model usually only relies on fixed-length historical data or short-term memory units, making it difficult to accurately capture the formation, propagation, and dissipation of congestion waves and other dynamic processes, resulting in the inability of the strategy to identify risks in advance when the road network approaches a critical state. (2) The optimization goal of the strategy is mainly around efficiency indicators such as travel delay and queue length, and there is a lack of direct quantification and constraints for the core risk of "avoiding queue spillover" at the network level, making the learned strategy tend to passively relieve congestion after it occurs, rather than actively controlling pressure before spillover. SUMMARY

[0005] To solve the above technical problems, the present application provides a traffic signal control method and system based on physical prior constraint time series graph attention, which can prospectively identify and actively avoid spillover risks, achieve adaptive trade-off between traffic efficiency and network safety, and thus actively avoid cascading congestion caused by queue spillover.

[0006] To achieve the above purpose, the present application adopts the following technical solutions: The first aspect of the present application provides a traffic signal control method based on physical prior constraint time series graph attention.

[0007] In one or more embodiments, a time-series graph attention-based traffic signal control method based on physical prior constraints is provided, comprising: Based on the traffic flow model based on inventory conservation and real-time traffic data, the physical storage capacity of the road segment is calculated. Then, combined with the current number of vehicles, the remaining storage space of the downstream road segment is obtained, which is the overflow safety buffer. Based on preset safety criteria, overflow safety buffer is transformed into overflow risk cost, and a constrained Markov decision process model is constructed with traffic efficiency as the reward and overflow risk as the cost; wherein, the state of the constrained Markov decision process model is the state information of the intersection node obtained based on the road network topology and real-time traffic data; the action is to select the next signal phase; By using a pre-trained temporal graph attention network to solve the constrained Markov decision process model, the optimal signal control action that balances traffic efficiency and spillover risk is obtained. During the training process, the temporal graph attention network adopts the Lagrange dual method optimization algorithm to adaptively adjust the penalty weights for spillover risk costs.

[0008] In one implementation, the status information of the intersection node is characterized by the intersection node status information, lane occupancy, queue length, average speed, signal phase, and overflow safety buffer.

[0009] As one implementation method, based on a preset safety criterion, the overflow safety buffer is transformed into an overflow risk cost as follows: ; in, It is a safety buffer threshold; It is a penalty curvature; for The cost of spillover risks at any given moment; It is a section of road exist A constant overflow safety buffer; For road segments; This indicates taking the maximum value.

[0010] As one implementation method, the calculation process for the overflow safety buffer is as follows: ; ; in, It is a section of road exist A constant overflow safety buffer; It is a section of road The effective length, It is the upper limit of the blocking density. It refers to the number of lanes; For road section exist Number of vehicles at any given time; It refers to storage capacity, i.e., the maximum number of vehicles that can be accommodated.

[0011] As one implementation method, Lagrange multipliers are introduced during the training of the temporal graph attention network. The constrained Markov decision process model described above is transformed into an unconstrained dual problem, with the corresponding Lagrangian function set as follows: : ; in, These are Lagrange multipliers, representing the dynamic price of risk; For policy network parameters; In strategy The following expectations; A discount factor for future returns; for The cost of spillover risks at any given moment; For traffic efficiency.

[0012] In one implementation, the time-series graph attention network comprises a multi-head graph attention network and a gated recurrent unit. The multi-head graph attention network is used to capture the attention weights between intersection nodes in the road network topology, and the gated recurrent unit is used to propagate states along the time axis and learn the temporal dynamics of congestion wave propagation. The multi-head graph attention network captures attention weights from intersection nodes... To the intersection node attention weights for: ; in, and It is node embedding. and It is a learnable parameter matrix. It is the coefficient of the time penalty term; It is a safety buffer threshold; for Transpose of; This represents an activation function with a leakage slope; It is the intersection node Relevant timestamps / update times; This represents a vector concatenation operation; It indicates that they are directly proportional.

[0013] As one implementation method, during the training of the temporal graph attention network, a proximal policy optimization algorithm is used to update the policy network parameters. Its alternative objective function also includes the advantage of return. and cost advantage : ; Using Lagrange multipliers The algorithm is updated using a subgradient ascent method, enabling it to dynamically adjust the penalty for risk. ; in It's the learning rate; when actual risk exceeds the budget, Increase the punishment; conversely, decrease it. Optimize the objective function for the PPO strategy; This indicates a batch of time steps sampled. Take the average; The probability ratio; The shear threshold of PPO; The updated Lagrange multipliers will be used for the next round of training / optimization; For the first Lagrange multipliers in the next iteration; In the current strategy Below, the price Expectations; Cost-based upper limit / risk budget; It is a data processing function used to limit numerical values ​​to a specified range; values ​​that exceed the range will be truncated to boundary values. It takes the minimum value; It takes the maximum value.

[0014] A second aspect of the present invention provides a timing graph-based attention traffic signal control system based on physical prior constraints.

[0015] In one or more embodiments, a physical prior constraint-based timing graph attention traffic signal control system includes: The overflow safety buffer calculation module is used to calculate the physical storage capacity of a road segment based on the traffic flow model based on inventory conservation and real-time traffic data, and then combine it with the current number of vehicles to obtain the remaining storage space of the downstream road segment, i.e. the overflow safety buffer. The decision process model construction module is used to transform overflow safety buffer into overflow risk cost based on preset safety criteria, and construct a constrained Markov decision process model with traffic efficiency as the reward and overflow risk as the cost; wherein, the state of the constrained Markov decision process model is the state information of the intersection node obtained based on the road network topology and real-time traffic data; the action is to select the next signal phase; An optimal signal control action determination module is configured to solve the constrained Markov decision process model by using the pre-trained time-series graph attention network to obtain the optimal signal control action balancing the traffic efficiency and the overflow risk; and in the training process of the time-series graph attention network, a Lagrange dual method optimization algorithm is used to adaptively adjust the penalty weight of the overflow risk cost.

[0016] A third aspect of the present application provides a computer-readable storage medium.

[0017] A computer-readable storage medium has a computer program stored thereon, and the program is executed by a processor to implement the steps in the physical-prior-constrained time-series graph attention traffic signal control method described above.

[0018] A fourth aspect of the present application provides an electronic device.

[0019] An electronic device includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor implements the steps in the physical-prior-constrained time-series graph attention traffic signal control method described above when executing the program.

[0020] Compared with the prior art, the present application has the following beneficial effects: The present application introduces the overflow safety buffer and converts it into the overflow risk cost, and then builds a constrained Markov decision process model taking the traffic efficiency as the reward and the overflow risk as the cost. The optimal signal control action balancing the traffic efficiency and the overflow risk is determined by solving the constrained Markov decision process model by using the pre-trained time-series graph attention network. By combining the traffic engineering physical prior and the time-series graph attention network, the active avoidance control of the cascading congestion in the urban road network is realized, the technical problems that the traditional control method is difficult to suppress the queue overflow due to the lack of foresight and the existing learning method tends to "passive clearing" due to the single optimization goal are effectively solved, and finally the coordination of the traffic efficiency and the safety and stability of the urban complex road network is improved. BRIEF DESCRIPTION OF DRAWINGS

[0021] The drawings accompanying the specification of the present application form part of the present application and serve to further understand the present application, the illustrative embodiments of the present application and the description thereof serve to explain the present application and do not constitute an improper limitation of the present application.

[0022] Figure 1 is a physical-prior-constrained time-series graph attention traffic signal control method flowchart of an embodiment of the present application; Figure 2 is a physical-prior-constrained time-series graph attention traffic signal control system structure schematic diagram of an embodiment of the present application; Figure 3is a throughput comparison chart of the traffic signal control method based on the physical prior constraint timing diagram attention of the embodiment of the present application and a traditional algorithm; Figure 4 is a delay rate comparison chart of the traffic signal control method based on the physical prior constraint timing diagram attention of the embodiment of the present application and a traditional algorithm; Figure 5 is an average travel time comparison chart of the traffic signal control method based on the physical prior constraint timing diagram attention of the embodiment of the present application and a traditional algorithm; Figure 6 is an average queue length comparison chart of the traffic signal control method based on the physical prior constraint timing diagram attention of the embodiment of the present application and a traditional algorithm; Figure 7 is a schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] The present application will be further described below in conjunction with the accompanying drawings and embodiments.

[0024] It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the present application. Unless otherwise indicated, all technical and scientific terms used herein have the same meaning as would be commonly understood by one of ordinary skill in the art to which the present application belongs.

[0025] It should be noted that the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit exemplary embodiments according to the present application. As used herein, the singular form is intended to include the plural form unless the context clearly indicates otherwise, and it should also be understood that when the terms "comprise" and / or "include" are used in the specification, there is a presence of a feature, step, operation, device, component, and / or combinations thereof.

[0026] Term explanation: Queue Spillover: refers to the phenomenon that at an intersection, the queue length of waiting vehicles exceeds the physical storage capacity of the road segment, and the tail extends to the upstream intersection, thereby blocking the upstream traffic.

[0027] Gridlock: refers to the state in which the entire region traffic is paralyzed due to the interweaving of large-scale queue spillovers in the urban road network.

[0028] Graph Neural Network (GNN): a deep learning model that specifically processes graph structure data, learns the representation of nodes by passing and aggregating information between nodes, and is very suitable for modeling the mutual influence between intersections.

[0029] Constrained Markov Decision Process (CMDP): A mathematical framework for reinforcement learning that aims to maximize cumulative reward while satisfying one or more constraints on cumulative cost.

[0030] Figure 1 A schematic diagram of the timing graph attention-based traffic signal control method based on physical prior constraints, according to an embodiment of the present invention, is provided. Figure 1 The physical prior constraint time graph attention traffic signal control method of this embodiment may include the following steps S101 to S103.

[0031] The specific implementation process of steps S101 to S103 is as follows: Step S101: Calculate the physical storage capacity of the road segment based on the traffic flow model based on inventory conservation and real-time traffic data, and then combine it with the current number of vehicles to obtain the remaining storage space of the downstream road segment, i.e., the overflow safety buffer.

[0032] The Cell Transmission Model (CTM) is used to model traffic flow on road segments. The traffic flow model based on inventory conservation is as follows: Road segment exist Number of vehicles at any given time Depend on Number of vehicles and inflow at any given time and outflow The decision is made based on the downstream road segment's capacity to receive the outflow from the upstream segment, which in turn determines the inflow to the downstream segment. Strict constraints: ; ; The calculation process for the overflow safety buffer is as follows: ; ; in, It is a section of road exist A constant overflow safety buffer; It is a section of road The effective length, It is the upper limit of the blocking density. It refers to the number of lanes; For road section exist Number of vehicles at any given time; It refers to storage capacity, i.e., the maximum number of vehicles that can be accommodated.

[0033] Overflow safety buffer , i.e. the remaining storage space (receiving capacity) of the downstream road segment. Overflow safety buffer intuitively quantifies "how far away from overflow", when , the risk dramatically increases.

[0034] Embodiments of the present application introduce the "overflow safety buffer" indicator derived from traffic physics theory, enabling the model to identify and respond to potential queue overflow risk earlier, achieving a shift from "passive response" to "active avoidance".

[0035] Step S102: According to a preset safety criterion, convert the overflow safety buffer into an overflow risk cost, and construct a constrained Markov decision process model with traffic efficiency as the reward and overflow risk as the cost; wherein the state of the constrained Markov decision process model is the state information of the intersection node obtained based on the road network topology and real-time traffic data; the action is to select the next signal phase.

[0036] To guide the control decision, a single-cycle safety criterion is proposed: for a given release phase, if the number of net inflow vehicles in the worst case exceeds the current safety buffer of the downstream road segment within its duration, the phase is considered to be at risk. The above safety criterion is converted into a continuous, differentiable convex cost function : ; wherein is a safety buffer threshold (for example, 15% of the storage capacity); is the penalty curvature; is the overflow risk cost at time ; is the overflow safety buffer of the road segment at time ; is the set of road segments; denotes taking the maximum value. This function applies a smooth and increasing penalty to the state "close to" overflow (i.e. ).

[0037] Formal definition of CMDP (i.e. constrained Markov decision process model). Express the adaptive signal control problem as a CMDP tuple , wherein: state : state information of the intersection node; action : select the next signal phase; transition : determined by the traffic simulation environment; reward : i.e. the passage efficiency, usually the negative of the cumulative delay or stress value at the intersection; cost : i.e. the risk cost of overflow ; discount : i.e. the discount factor of future return.

[0038] The urban traffic network is abstracted as a directed graph , where the nodes represent an intersection, and the directed edges represent a connected road segment in a driving direction. By deploying sensors (such as magnetometer coils, video detectors, etc.) at the intersections, the traffic state information of each road segment is obtained in real time.

[0039] The obtained state information not only includes traditional traffic variables, but also integrates physical prior quantities that serve as the core of the present invention. The state information of the intersection node is represented as: ; wherein, is the state information of the intersection node at time ; is the lane occupancy rate of the intersection node at time , is the queue length of the intersection node at time , is the average speed of the intersection node at time , is the signal phase of the intersection node at time , is the overflow safety buffer of the intersection node at time .

[0040] The optimization goal of the CMDP is to maximize the long-term cumulative return while meeting the condition that the long-term average risk cost is lower than the preset budget : ; wherein, is the expectation under policy ; is the passage efficiency at time ; is the discount factor of future return; is the set time period; is the policy The maximum value under the given conditions. This formalization transforms "proactive risk avoidance" from a vague concept into a mathematically defined and solvable optimization problem. Within a unified constrained reinforcement learning framework, collaborative optimization of traffic efficiency (reward) and network security (cost constraint) achieves an adaptive and interpretable trade-off between the two, rather than simply pursuing a single metric.

[0041] Step S103: Solve the constrained Markov decision process model using a pre-trained temporal graph attention network to obtain the optimal signal control action that balances traffic efficiency and spillover risk; wherein, during the training process, the temporal graph attention network adopts the Lagrange dual method optimization algorithm to adaptively adjust the penalty weights for spillover risk costs.

[0042] Lagrange multipliers are introduced during the training of the sequence graph attention network. The constrained Markov decision process model described above is transformed into an unconstrained dual problem, with the corresponding Lagrangian function set as follows: : ; in, The dynamic price of risk is learned automatically by the algorithm; For policy network parameters; In strategy The expectation below, that is, "according to the strategy" The expected value of the trajectory (state-action-reward-cost sequence) generated by interaction with the environment is simply calculated. In other words, it is to calculate the average effect after considering randomness. A discount factor for future returns; for The cost of spillover risks at any given moment; For traffic efficiency.

[0043] The temporal graph attention network consists of a multi-head graph attention network (GAT) and a gated recurrent unit (GRU). The GAT captures the attention weights between intersection nodes in the road network topology, while the GRU propagates states along the time axis and learns the temporal dynamics of congestion wave propagation. The GAT captures the attention weights between intersection nodes... To the intersection node attention weights for: ; in, and It is node embedding. and It is a learnable parameter matrix. It is the coefficient of the time penalty term (hyperparameter or learnable parameter), and the larger it is, the more "stale information is penalized"; It is a safety buffer threshold; for Transpose of; This represents an activation function with a leakage slope; It is the intersection node Relevant timestamps / update times; This represents a vector concatenation operation; It indicates that they are directly proportional.

[0044] GAT's attention weight In the calculation, a negative bias term based on the downstream safety buffer is explicitly introduced; the above formula ensures that when neighboring nodes... downstream buffer When it is nearing exhaustion, it is passed to the node. The information weight will increase significantly, forcing the model to "pay attention" to potential sources of risk.

[0045] During the training of the temporal graph attention network, the proximal policy optimization algorithm is used to update the policy network parameters. Its alternative objective function also includes the advantage of return. and cost advantage : ; Using Lagrange multipliers The algorithm is updated using a subgradient ascent method, enabling it to dynamically adjust the penalty for risk. ; in It's the learning rate; when actual risk exceeds the budget, Increase the punishment; conversely, decrease it. Optimize the objective function for the PPO strategy; This indicates a batch of time steps sampled. Take the average; The probability ratio; The shear threshold of PPO; The updated Lagrange multipliers will be used for the next round of training / optimization; For the first Lagrange multipliers in the next iteration; In the current strategy Below, the price Expectations; Cost-based upper limit / risk budget; It is a data processing function used to limit numerical values ​​to a specified range; values ​​that exceed the range will be truncated to boundary values. is taking the minimum value; is taking the maximum value.

[0046] The embodiment of the present application integrates the risk indicator into the attention mechanism and action screening layer of the graph neural network, strengthens the sensitivity of the model to the critical state of the network from two aspects of feature representation and decision space, and improves the robustness of the strategy.

[0047] At the strategy execution level, the embodiment of the present application adds a final action filtering layer. For any candidate phase proposed by the strategy network, the system will be tested according to the safety criterion. If the phase is determined to have a high overflow risk in the current state, it will be excluded from the candidate action set, ensuring that the final executed decision always meets the most basic physical safety boundary.

[0048] Through the implementation of the above steps, the embodiment of the present application is based on the deep integration of traffic flow physical priori and time series graph attention network, and through the collaborative optimization of traffic efficiency and overflow risk in the constraint reinforcement learning framework, the propagation of queue overflow and cascading congestion in the urban road network is effectively suppressed, realizing the forward-looking and stable traffic signal control, and providing strong support for improving the resilience and intelligent level of modern urban transportation system.

[0049] The embodiment of the present application combines the physical theory of traffic engineering and deep reinforcement learning technology, uses the interpretable physical quantity of “overflow safety buffer” to guide and constrain the decision-making process of the artificial intelligence model, thereby improving the traffic efficiency and operation stability of the traffic network. This method not only reduces the average driving delay, but also significantly reduces the probability of gridlock. In addition, the embodiment of the present application also has good scalability and adaptability, and can continuously optimize the model through continuous training on new traffic data to adapt to the long-term changes of urban development and traffic patterns.

[0050] The embodiment adopts an algorithm based on the cellular transmission model to quantify the risk of the road network, and provides a forward-looking physical priori for the strategy by calculating the “overflow safety buffer”; a time series graph attention network (PC-STGAT) model customized for the traffic network is adopted, which captures the spatial coupling between intersections through the graph attention mechanism and learns the time dynamics of congestion propagation through the gated recurrent unit. Based on the proximal policy optimization (PPO-Lagrangian) algorithm of Lagrange duality, the reward signal representing the traffic efficiency and the cost signal representing the congestion risk are jointly optimized, and the “efficiency” and “risk avoidance” are adaptively balanced by dynamically adjusting the Lagrange multiplier. Through the deep coupling of physical priori, spatio-temporal representation learning and constraint optimization, the performance, robustness and safety of traffic signal control in high saturation and high uncertainty scenarios are significantly improved.

[0051] The embodiment aims to realize the "active avoidance" type control of cascading congestion in urban road network by combining traffic engineering physical priori and time series graph attention network, and to improve the sensitivity and adaptability of the control strategy to the critical state of the network by using deep reinforcement learning algorithm to learn the traffic dynamic evolution law under high density and high uncertainty in the simulation environment. The urban traffic network presents significant space-time coupling characteristics under high load, and the congestion evolution is a highly nonlinear dynamic process. Deep learning model, especially spatio-temporal graph neural network, can flexibly model the complex topological dependence and dynamic evolution relationship. The method effectively solves the technical problems that the traditional control method is difficult to suppress queue overflow due to lack of foresight, and the existing learning method tends to "passive obstacle removal" due to single optimization goal, and finally realizes the coordinated improvement of traffic efficiency and safety and stability of complex urban road network.

[0052] In the simulation test, the application not only improves the average traffic efficiency, but also significantly reduces the probability of grid lock and the congestion recovery time, and shows superior network level stability and flexibility.

[0053] As shown in Figure 2 The physical priori constraint time series graph attention traffic signal control system provided by the embodiment of the application can be implemented in a software manner, and the physical priori constraint time series graph attention traffic signal control system includes the following software modules: an overflow safety buffer calculation module 201, a decision process model construction module 202, and an optimal signal control action determination module 203.

[0054] The functions of each software module in the physical priori constraint time series graph attention traffic signal control system are introduced as follows: The overflow safety buffer calculation module 201 is used to calculate the physical storage capacity of a road section according to a traffic flow model based on inventory conservation and real-time traffic data, and then obtain the remaining storage space of the downstream road section, i.e. the overflow safety buffer, in combination with the current number of vehicles. The decision process model construction module 202 is used to convert the overflow safety buffer into an overflow risk cost according to a preset safety criterion, and construct a constraint Markov decision process model with traffic efficiency as the reward and the overflow risk as the cost. The state of the constraint Markov decision process model is the state information of the intersection node obtained based on the road network topology structure and real-time traffic data, and the action is to select the next signal phase. The optimal signal control action determination module 203 is used to solve the constraint Markov decision process model by using a pre-trained time series graph attention network to obtain the optimal signal control action that balances the traffic efficiency and the overflow risk. In the training process of the time series graph attention network, the Lagrange dual method optimization algorithm is used to adaptively adjust the penalty weight of the overflow risk cost.

[0055] It should be noted that each module in the traffic signal control system based on the physical prior constraint timing diagram attention of the embodiment of the application corresponds to each step in the traffic signal control method based on the physical prior constraint timing diagram attention in the above-mentioned embodiment, and the specific implementation process is the same, which will not be repeated here.

[0056] Through experimental comparative analysis, Figures 3-6 The comparative results of the traffic signal control method based on the physical prior constraint timing diagram attention of the embodiment of the application and the traditional algorithms CoLight, MAPG, IPPO and MaxPressure in terms of throughput, delay rate, average travel time and average queue length are given respectively.

[0057] Among them, in the field of traffic control, CoLight is a multi-agent traffic signal control model based on reinforcement learning and graph attention network, which models traffic signal control as a Markov game, each intersection is controlled by an agent, and the action (such as phase switching) is selected by observing the local traffic state (such as lane vehicle number and phase), and the goal is to minimize the average queue length.

[0058] MAPG, Multi-Agent Policy Gradient, is an extension of reinforcement learning in multi-agent systems, which directly optimizes random policy parameters to maximize expected returns through gradient ascent. The core idea is to evaluate the joint policy using global reward signals and calculate the gradient for each agent to update its own policy.

[0059] IPPO, Independent PPO, is a completely decentralized algorithm, which uses the single-agent algorithm PPO to train each agent.

[0060] MaxPressure algorithm is an intelligent traffic signal control method based on pressure difference, which uses the data backlog degree of each node in the dynamic perception network as the core driving force of traffic scheduling, and prioritizes the service of the upstream and downstream link pair with the largest pressure, so as to realize the rapid relief of global congestion.

[0061] According to Figures 3-6 In the high-throughput environment of 3900 vehicles / hour, the traffic signal control method based on the physical prior constraint timing diagram attention of the embodiment of the application achieves excellent results, the throughput is higher than other comparative algorithms, the average travel time, delay rate and queue length are significantly lower than the traditional algorithms CoLight, MAPG, IPPO and MaxPressure.

[0062] The structure of the electronic device of the embodiment of the present application is described in detail as follows, Figure 7 The schematic diagram of the component structure of the electronic device provided by the embodiment of the present application can be understood as, Figure 7 Only the exemplary structure of the electronic device is shown, not all the structures, and the shown part or all of the structures can be implemented as needed.

[0063] The electronic device provided by the embodiment of the present application comprises at least one processor 701, a memory 702, a user interface 703 and at least one network interface 704. The various components in the physical prior constraint timing diagram attention traffic signal control system are coupled together through a bus system 705. It can be understood that the bus system 705 is used to realize the connection communication between the components. The bus system 705 includes not only a data bus, but also a power bus, a control bus and a status signal bus. However, for the purpose of clear illustration, all the buses are marked as the bus system 705 in Figure 7 .

[0064] The user interface 703 can include a display, a keyboard, a mouse, a trackball, a click wheel, a key, a button, a touchpad or a touch screen, etc.

[0065] It can be understood that the memory 702 can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. The memory 702 in the embodiment of the present application can store data to support the operation of the terminal. Examples of the data include any computer programs for operating on the terminal, such as an operating system and an application program. The operating system contains various system programs, such as a framework layer, a core library layer, a driver layer, etc., for realizing various basic services and processing hardware-based tasks. The application program can contain various application programs.

[0066] In some embodiments, the physical prior constraint timing diagram attention traffic signal control system provided by the embodiments of the present application can be implemented in a combination of software and hardware. For example, the physical prior constraint timing diagram attention traffic signal control system provided by the embodiments of the present application can be a processor in the form of a hardware decoding processor programmed to perform the physical prior constraint timing diagram attention traffic signal control method provided by the embodiments of the present application. For example, the processor in the form of a hardware decoding processor can be implemented by one or more application specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field programmable gate arrays (FPGAs), or other electronic elements.

[0067] For example, the processor 701 can be an integrated circuit chip with a processing capability of signals, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., where the general-purpose processor can be a microprocessor or any conventional processor.

[0068] For example, the processor 701 can be an integrated circuit chip with a processing capability of signals, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., where the general-purpose processor can be a microprocessor or any conventional processor.

[0069] The memory 702 in the embodiments of the present application is used to store various types of data to support the operation of the physical prior constraint timing diagram attention traffic signal control system, or to store programs for executing the physical prior constraint timing diagram attention traffic signal control method provided by the embodiments of the present application. Figure 1program code of the method. Examples of such data include any executable code such as an executable instruction for operating on a physical-prior-constraint based timing diagram attention traffic signal control system, a program implementing the physical-prior-constraint based timing diagram attention traffic signal control method of embodiments of the present application can be included in the executable instruction.

[0070] In particular, the processes described above with reference to the flow charts can be implemented as computer software programs in accordance with embodiments of the present application. For example, embodiments of the present application include a computer program product which includes a computer program tangibly embodied on a computer readable medium, the computer program including instructions for execution by a processor to perform the various functions defined in the apparatus of the present application. Figure 1 program code of the method. In such embodiments, the computer program can be downloaded and installed from a network via the communication section, and / or installed from a removable medium. When the computer program is executed by the central processing unit, various functions defined in the apparatus of the present application are performed.

[0071] The present application is described with reference to the flow charts and / or block diagrams of the methods, apparatus (system) and computer program products of embodiments of the present application. It is understood that each flow and / or block in the flow charts and / or block diagrams, and combinations of flows and / or blocks in the flow charts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flow charts and / or block diagrams block or blocks. Figure 1 one or more flows and / or blocks Figure 1 an apparatus to perform the functions specified in the flow chart

[0072] The above merely provides the preferred embodiments of the present application and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall fall within the scope of the present application.

Claims

1. A traffic signal control method based on physical prior constraints and time-series graph attention, characterized in that, include: Based on the traffic flow model based on inventory conservation and real-time traffic data, the physical storage capacity of the road segment is calculated. Then, combined with the current number of vehicles, the remaining storage space of the downstream road segment is obtained, which is the overflow safety buffer. Based on preset safety criteria, overflow safety buffer is transformed into overflow risk cost, and a constrained Markov decision process model is constructed with traffic efficiency as the reward and overflow risk as the cost; wherein, the state of the constrained Markov decision process model is the state information of the intersection node obtained based on the road network topology and real-time traffic data; the action is to select the next signal phase; By using a pre-trained temporal graph attention network to solve the constrained Markov decision process model, the optimal signal control action that balances traffic efficiency and spillover risk is obtained. During the training process, the temporal graph attention network adopts the Lagrange dual method optimization algorithm to adaptively adjust the penalty weights for spillover risk costs.

2. The traffic signal control method based on physical prior constraints and time-series graph attention as described in claim 1, characterized in that, The status information of the intersection node is characterized by the intersection node status information, lane occupancy, queue length, average speed, signal phase, and overflow safety buffer.

3. The traffic signal control method based on physical prior constraints and time-series graph attention as described in claim 1, characterized in that, Based on the preset safety criteria, the cost of converting the overflow safety buffer into an overflow risk is as follows: ； in, It is a safety buffer threshold; It is a penalty curvature; for The cost of spillover risks at any given moment; It is a section of road exist A constant overflow safety buffer; For road segments; This indicates taking the maximum value.

4. The traffic signal control method based on physical prior constraints and time-series graph attention as described in claim 1, characterized in that, The calculation process for the overflow safety buffer is as follows: ； ； in, It is a section of road exist A constant overflow safety buffer; It is a section of road The effective length, It is the upper limit of the blocking density. It refers to the number of lanes; For road section exist Number of vehicles at any given time; It refers to storage capacity, i.e., the maximum number of vehicles that can be accommodated.

5. The traffic signal control method based on physical prior constraints and time-series graph attention as described in claim 1, characterized in that, Lagrange multipliers are introduced during the training of the sequence graph attention network. The constrained Markov decision process model described above is transformed into an unconstrained dual problem, with the corresponding Lagrangian function set as follows: : ； in, These are Lagrange multipliers, representing the dynamic price of risk; For policy network parameters; In strategy The following expectations; A discount factor for future returns; for The cost of spillover risks at any given moment; For traffic efficiency.

6. The traffic signal control method based on physical prior constraints and time-series graph attention as described in claim 1, characterized in that, The time-series graph attention network comprises a multi-head graph attention network and a gated recurrent unit. The multi-head graph attention network captures the attention weights between intersection nodes in the road network topology, while the gated recurrent unit propagates states along the time axis and learns the temporal dynamics of congestion wave propagation. The multi-head graph attention network captures attention weights from intersection nodes... To the intersection node attention weights for: ； in, and It is node embedding. and It is a learnable parameter matrix. It is the coefficient of the time penalty term; It is a safety buffer threshold; for Transpose of; This represents an activation function with a leakage slope; It is the intersection node Relevant timestamps / update times; This represents a vector concatenation operation; It indicates that they are directly proportional.

7. The traffic signal control method based on physical prior constraints and time-series graph attention as described in claim 1, characterized in that, During the training of the temporal graph attention network, the proximal policy optimization algorithm is used to update the policy network parameters. Its alternative objective function also includes the advantage of return. and cost advantage : ； Using Lagrange multipliers The algorithm is updated using a subgradient ascent method, enabling it to dynamically adjust the penalty for risk. ； in It is the learning rate; When actual risks exceed the budget Increase the punishment; conversely, decrease it. Optimize the objective function for the PPO strategy; This indicates a batch of time steps sampled. Take the average; The probability ratio; The shear threshold of PPO; The updated Lagrange multipliers will be used for the next round of training / optimization; For the first Lagrange multipliers in the next iteration; In the current strategy Below, the price Expectations; Cost-based upper limit / risk budget; It is a data processing function used to limit numerical values ​​to a specified range; values ​​that exceed the range will be truncated to boundary values. It takes the minimum value; It takes the maximum value.

8. A traffic signal control system based on physical prior constraints and time-series graph attention, characterized in that, The method for traffic signal control based on physical prior constraints and time-series graph attention, as described in any one of claims 1-7, includes: The overflow safety buffer calculation module is used to calculate the physical storage capacity of a road segment based on the traffic flow model based on inventory conservation and real-time traffic data, and then combine it with the current number of vehicles to obtain the remaining storage space of the downstream road segment, i.e. the overflow safety buffer. The decision process model construction module is used to transform overflow safety buffer into overflow risk cost based on preset safety criteria, and construct a constrained Markov decision process model with traffic efficiency as the reward and overflow risk as the cost; wherein, the state of the constrained Markov decision process model is the state information of the intersection node obtained based on the road network topology and real-time traffic data; the action is to select the next signal phase; The optimal signal control action determination module is used to solve the constrained Markov decision process model using a pre-trained temporal graph attention network to obtain the optimal signal control action that balances traffic efficiency and spillover risk. During the training process, the temporal graph attention network adopts the Lagrange dual method optimization algorithm to adaptively adjust the penalty weights for spillover risk costs.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps in the physical prior constraint timing graph attention traffic signal control method as described in any one of claims 1-7.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps in the physical prior constraint timing graph attention traffic signal control method as described in any one of claims 1-7.

Images