Intersection dynamic signal control method, electronic device, storage medium and program product

Abstract

This application provides a method, electronic device, storage medium, and program product for dynamic signal control at intersections, relating to the field of intelligent transportation technology. The method includes: acquiring a phase set, a lane index set, and current queuing information, acceleration information set, and headway information for each lane corresponding to the intersection in a road network; determining the target phase to be controlled at the intersection based on the current queuing information, phase set, and lane index set; adjusting the current queuing information of each lane corresponding to the target phase based on the lane's acceleration information set to obtain target queuing information; and controlling the signal at the intersection based on the target phase, the headway information of all lanes corresponding to the target phase, and the target queuing information. This application makes traffic signal control more accurate, reducing road congestion and improving intersection traffic efficiency.

Description

Technical Field

[0001] This application relates to the field of intelligent transportation technology, and in particular to a method for dynamic signal control at intersections, electronic equipment, storage medium, and program products. Background Technology

[0002] With the acceleration of urbanization, the continuous expansion of urban areas has led to increasingly serious traffic congestion problems. As a core part of the urban transportation system, traffic signal control's main task is to intelligently regulate intersection traffic lights, optimize road resource allocation, improve traffic efficiency, and ensure smooth travel for citizens.

[0003] Existing traffic signal control technologies have undergone several stages of development. Early fixed-time-cycle control, which presets signal light change cycles based on historical traffic flow data, is simple to operate but lacks flexibility and struggles to cope with real-time traffic changes. Critical-road green wave control strategies coordinate the green light times of main road traffic lights to form "green wave bands," reducing the frequency of vehicle stops and starts. Inductive control technology uses detection equipment to monitor traffic flow at intersections in real time and dynamically adjusts the signal light phase accordingly. The maximum pressure rule calculates the difference in vehicle traffic entering and exiting lanes at intersections and prioritizes allocating green lights to directions with higher pressure.

[0004] However, existing traffic signal control methods still suffer from poor control performance when faced with complex and ever-changing traffic environments. Summary of the Invention

[0005] The intersection dynamic signal control method, electronic device, storage medium, and program product provided in this application are intended to solve the problem that existing traffic signal control methods still have poor control effects when facing complex and ever-changing traffic environments.

[0006] In a first aspect, embodiments of this application provide a method for dynamic signal control at intersections, including:

[0007] The system acquires the phase set, lane index set, current queuing information, speed-up information set, and headway information for each lane at the intersection to be controlled in the road network. The speed-up information set includes the speed-up information of each lane at the intersection to be controlled in multiple time periods before the current time, stored in the database. Each speed-up information is determined based on the lane queue length and collection time collected at the intersection to be controlled in the corresponding time period, and is used to indicate the rate of change of the queue length of the corresponding lane at the intersection to be controlled during the red light process.

[0008] Based on the current queuing information, phase set, and lane index set, determine the target phase to be controlled at the intersection to be controlled;

[0009] For each lane corresponding to the target phase, the current queuing information of the lane is adjusted according to the lane's speed-up information set to obtain the target queuing information;

[0010] Based on the target phase, as well as the headway information and target queuing information of all lanes corresponding to the target phase, the signal at the intersection to be controlled is controlled.

[0011] In one possible implementation, the current queuing information of a lane is adjusted based on a set of lane speed-up information to obtain target queuing information, including:

[0012] Based on the historical growth rate information of all lanes in the road network, lane correlation parameters are determined. The historical growth rate information of each lane is the growth rate information of the corresponding lane stored in the database before the current time. The lane correlation parameters are used to indicate the traffic impact relationship between lanes.

[0013] Based on the lane speedup information set and lane correlation parameters, the current queuing information of the lane is adjusted to obtain the target queuing information.

[0014] In one possible implementation, lane correlation parameters are determined based on historical growth rate information for all lanes in the road network, including:

[0015] Obtain multiple historical growth rate information for each lane in the road network within a preset first time period;

[0016] Based on multiple historical growth rate information for all lanes, a sample set is constructed, wherein each sample includes a second time period in the first time period, and the historical growth rate information of all lanes in the corresponding second time period;

[0017] Based on the adjacency relationships in the road network, a road network adjacency matrix is ​​constructed. The road network adjacency matrix is ​​used to indicate the connectivity between every two lanes in the road network.

[0018] Based on the sample set and the road network adjacency matrix, the preset correlation parameters are adjusted to obtain the lane correlation parameters.

[0019] In one possible implementation, the current queuing information of a lane is adjusted based on a set of lane speed-up information and lane correlation parameters to obtain target queuing information, including:

[0020] The total speed increase information is obtained from the subset of speed increase information in the set of speed increase information of lanes. The subset of speed increase information includes multiple speed increase information obtained by sampling the speed increase information of lanes stored in the database within a preset third time period.

[0021] Based on the lane correlation parameters and the first growth rate information in the lane growth rate information set, the second growth rate information is determined. The first growth rate information is the growth rate information of the lane in a second time period before the current time, which is stored in the database.

[0022] Based on the sum of growth rate information, the second growth rate information, the current queuing information, and the signal decision time, the target queuing information is determined. The signal decision time is the time when the step of obtaining the phase set, lane index set, current queuing information, growth rate information set, and headway information of each lane corresponding to the intersection to be controlled in the road network is triggered.

[0023] In one possible implementation, before acquiring the phase set, lane index set, and current queuing information, speed-up information set, and headway information of each lane corresponding to the intersection to be controlled in the road network, the method further includes:

[0024] Obtain signal control decision requests, which include the signal decision time and the intersection to be controlled as set by the user;

[0025] Accordingly, when acquiring the phase set, lane index set, and current queuing information, speed-up information set, and headway information of each lane corresponding to the intersection to be controlled in the road network, the intersection to be controlled is the intersection to be controlled in the decision request.

[0026] or,

[0027] Determine the green light countdown length for all intersections in the road network, and the green light end time for each intersection at the current time;

[0028] For each intersection, if the time from the current time to the end of the green light at the intersection is greater than or equal to the countdown time of the green light at the intersection, then the current time is used as the signal decision time, and the intersection is designated as the intersection to be controlled.

[0029] In one possible implementation, the method further includes:

[0030] Obtain the phase status of traffic lights at all intersections in the road network;

[0031] For each intersection, when the traffic light phase status indicator signal at the intersection starts red, obtain the first queue length and the first acquisition time for each lane corresponding to the intersection;

[0032] When the traffic light phase status indicates that the green light has started, the second queue length and second acquisition time, as well as the headway data for each lane at the intersection, are obtained. After the traffic light phase status indicates that the red light has started again, the average headway for each lane is determined based on the headway data. The headway information includes the headway data and the average headway for each lane.

[0033] For each lane corresponding to the intersection, the lane's speed-up information within the second time period is determined based on the lane's first queue length, first acquisition time, second queue length, and second acquisition time.

[0034] Store the speed increase information for all lanes at all intersections in the database.

[0035] In one possible implementation, determining the lane speedup information within a second time period based on the lane's first queue length, first acquisition time, second queue length, and second acquisition time includes:

[0036] Determine the intermediate moment between the first and second acquisition times of the lane;

[0037] If the intermediate time is within the second time period, the lane speedup information within the second time period is determined based on the first difference between the second queue length and the first queue length of the lane, and the second difference between the second acquisition time and the first acquisition time.

[0038] If the intermediate time is after the second time period, the third speed-up information of the lane is determined based on the first difference between the second queue length and the first queue length of the lane and the second difference between the second acquisition time and the first acquisition time.

[0039] Based on the third and fourth growth rate information, the growth rate information of the lanes within the second time period is determined. The fourth growth rate information is the growth rate information of the lanes within the second historical time period stored in the database. The second historical time period is the second time period corresponding to the storage of lane growth rate information before the first acquisition time.

[0040] In one possible implementation, the target phase to be controlled at the intersection to be controlled is determined based on the current queuing information, the phase set, and the lane index set, including:

[0041] Based on the phase set and lane index set, lane flow direction information is determined. The lane flow direction information is used to indicate the mapping relationship between upstream and downstream lanes in the intersection to be controlled.

[0042] Based on the current queuing information and lane flow information, determine the queuing difference between the upstream lane queuing length and the downstream lane queuing length for each phase;

[0043] The target phase in the phase set is determined based on the queuing difference values ​​corresponding to all phases.

[0044] In one possible implementation, the signal at the intersection to be controlled is controlled based on the target phase, the headway information of all lanes corresponding to the target phase, and the target queuing information, including:

[0045] For each lane corresponding to the target phase, the start time of the lane and the number of vehicles passing through the start time are determined based on the headway information of the lane.

[0046] Based on the target queue information, number of vehicles, start time, and headway information, determine the lane's passage time;

[0047] The target passage time for the target phase is determined based on the passage time of all lanes corresponding to the target phase, as well as the maximum and minimum phase times of the target phase.

[0048] Based on the target phase and the target passage time of the target phase, the signals at the intersection to be controlled are controlled.

[0049] Secondly, embodiments of this application provide a dynamic signal control device for intersections, comprising:

[0050] The acquisition module is used to acquire the phase set, lane index set, current queuing information, speed-up information set, and headway information of each lane corresponding to the intersection to be controlled in the road network. The speed-up information set includes the speed-up information of each lane of the intersection to be controlled in multiple time periods before the current time stored in the database. Each speed-up information is determined according to the lane queue length and collection time collected at the intersection to be controlled in the corresponding time period, and is used to indicate the rate of change of the queue length of the corresponding lane at the intersection to be controlled during the red light process.

[0051] The determination module is used to determine the target phase to be controlled in the intersection to be controlled based on the current queuing information, phase set, and lane index set;

[0052] The adjustment module is used to adjust the current queuing information of each lane corresponding to the target phase based on the lane's speed-up information set, so as to obtain the target queuing information.

[0053] The control module is used to control the signals at the intersection to be controlled based on the target phase, the headway information of all lanes corresponding to the target phase, and the target queuing information.

[0054] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0055] The memory stores the instructions that the computer executes;

[0056] The processor executes the computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0057] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0058] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed, implements the first aspect and / or various possible implementations of the first aspect.

[0059] The intersection dynamic signal control method, electronic device, storage medium, and program product provided in this application acquire relevant information about the intersection, including a phase set, a lane index set, and current queuing information, speed-up information, and headway information for each lane. The speed-up information is calculated based on historical data and is used to indicate the rate of change of lane queue length during red lights. Based on the current queuing information, phase set, and lane index set, the target phase that needs to be adjusted is determined to ensure that signal control can focus on the traffic flow that needs the most optimization at the current time. For each lane under the target phase, the current queuing information is adjusted using the speed-up information to obtain more accurate target queuing information. Based on the target phase, lane headway information, and target queuing information, the traffic lights are optimized and controlled. This method can dynamically adapt to changes in traffic flow, more accurately predict and adjust the switching timing of traffic lights, reduce vehicle waiting time at intersections and traffic congestion, and improve traffic flow efficiency. Attached Figure Description

[0060] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0061] Figure 1 A flowchart illustrating a dynamic signal control method for intersections provided in this application;

[0062] Figure 2 A flowchart illustrating a method for determining lane correlation parameters provided in this application;

[0063] Figure 3 A flowchart illustrating another intersection dynamic signal control method provided in this application;

[0064] Figure 4 A flowchart illustrating a signal decision timing determination method provided in this application;

[0065] Figure 5 A flowchart illustrating the process of collecting red light queue increments and headway distances provided in this application;

[0066] Figure 6 A schematic diagram of the intersection dynamic signal control device provided in this application;

[0067] Figure 7 A schematic diagram of the structure of the electronic device provided in this application.

[0068] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0069] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0070] In existing technologies, traffic signal control technologies typically include: early fixed-time-cycle control, which presets the signal light change cycle based on historical traffic flow data. This is simple to operate but lacks flexibility and is difficult to cope with real-time traffic changes; critical road green wave control strategies, which coordinate the green light times of main road traffic lights to form a "green wave" and reduce the frequency of vehicle stops and starts; inductive control technology, which uses detection equipment to monitor traffic flow at intersections in real time and dynamically adjusts the signal light phase accordingly; and the maximum pressure rule, which calculates the difference in vehicle traffic entering and exiting lanes at intersections and prioritizes allocating green lights to directions with higher pressure.

[0071] However, fixed-time-cycle signal control suffers from poor adaptability, failing to adjust flexibly based on real-time traffic flow, resulting in wasted waiting time during off-peak hours and congestion during peak hours, as well as unreasonable resource allocation. Key-road green wave control strategies have limited applicability, only applicable to specific arterial roads, performing poorly in complex and ever-changing traffic networks, and heavily reliant on precise time synchronization, making them difficult to adapt quickly to unexpected situations. Sensor-based control technology is highly dependent on equipment, with high installation and maintenance costs, and requires significant data processing, limiting it to single-intersection control. Manual threshold setting relies on experience, is prone to errors, and requires extensive monitoring and trial-and-error. The maximum pressure method easily leads to uneven waiting times, lacks a learning mechanism, and struggles to adapt to new situations; similarly, it is limited to single intersections and has poor performance in road network coordinated control.

[0072] With the development of artificial intelligence technology, existing traffic signal control methods have also incorporated reinforcement learning techniques. For example, online reinforcement learning iteratively optimizes control strategies through trial and error and reward feedback, relying on large amounts of real-time interactive data and stable, effective learning algorithms to achieve traffic signal control optimization. Alternatively, offline reinforcement learning involves collecting and organizing historical data and training the model; once trained, the model executes control according to a predetermined strategy. However, online reinforcement learning has high trial-and-error costs, easily leading to delays and safety risks in traffic systems. It is also difficult to train, requiring large amounts of interactive data, and real-time adjustments to the training cycle are difficult to determine. Offline reinforcement learning suffers from data dependency and leakage risks, slow updates and iterations, and an inability to respond in real-time to changes in traffic structure or flow.

[0073] To address the aforementioned issues, the intersection dynamic signal control method provided in this application collects the phase set, lane index set, current lane queuing information, growth rate information derived from historical time period data, and headway information of the intersection to be controlled. It constructs growth rate information by recording and analyzing lane queue lengths and collection times at different time periods, laying the foundation for subsequent decision-making. Next, combining the current actual queuing situation with the intersection phase and lane layout information, it determines the target phase to be controlled, emphasizing key areas for management. Then, for the lanes involved in the target phase, it dynamically adjusts the current queuing information using the growth rate information set, comprehensively considering traffic flow inertia and trends, rather than just the immediate state. Finally, based on the adjusted target queuing information and headway information, it regulates the traffic lights at the intersection to be controlled. Therefore, by leveraging multi-dimensional information, especially growth rate information, this application can accurately capture the dynamic characteristics of traffic flow changes in each lane and quickly adapt to changes in traffic flow. Especially during peak hours, it can effectively reduce traffic congestion and improve intersection efficiency. Furthermore, it can focus on the target phase and corresponding lane for targeted control, avoiding resource waste caused by indiscriminate uniform control. It can also rationally allocate green light time based on factors such as headway, reduce waiting time, and maximize road utilization efficiency.

[0074] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0075] The execution entity of the intersection dynamic signal control method provided in this application embodiment can be a server. The server can be a mobile phone, computer, tablet, or other device. This application embodiment does not impose any particular restrictions on the implementation method of the execution entity, as long as the execution entity can obtain the phase set, lane index set, and current queuing information, speed-up information set, and headway information of each lane corresponding to the intersection to be controlled in the road network. The speed-up information set includes speed-up information of each lane of the intersection to be controlled in multiple time periods before the current time, stored in the database. Each speed-up information is determined based on the lane queue length and collection time collected at the intersection to be controlled in the corresponding time period, and is used to indicate the rate of change of the queue length of the corresponding lane at the intersection to be controlled during the red light process. Based on the current queuing information, phase set, and lane index set, the target phase to be controlled in the intersection to be controlled is determined. For each lane corresponding to the target phase, the current queuing information of the lane is adjusted according to the lane speed-up information set to obtain the target queuing information. Based on the target phase, and the headway information and target queuing information of all lanes corresponding to the target phase, the signal of the intersection to be controlled can be controlled.

[0076] It should be noted that the database can be a general term for any local storage database that stores the data required for implementing dynamic signal control methods at intersections. This database can include traffic state databases, red light queue speed-up databases, headway databases, and lane correlation databases. Specifically, the traffic state database can store various types of traffic data collected from the road network, such as queue length and the number of vehicles in the queue; the red light queue speed-up database can store speed-up information for each lane at each intersection within the road network across multiple time periods; the headway database can store headway information collected and calculated from the road network; and the lane correlation database can store lane correlation parameters from the road network. Based on dynamic time changes, the lane correlation database can contain lane correlation parameters for multiple time periods.

[0077] Figure 1 This is a flowchart illustrating a dynamic signal control method for intersections provided in this application. The executing entity of this method can be a server storing the dynamic signal control method for intersections or other servers; this embodiment does not impose any particular limitation. Figure 1 As shown, the method may include:

[0078] S101. Obtain the phase set, lane index set, and current queuing information, speed-up information set, and headway information of each lane corresponding to the intersection to be controlled in the road network. The speed-up information set includes the speed-up information of each lane of the intersection to be controlled in multiple time periods before the current time stored in the database. Each speed-up information is determined according to the lane queue length and collection time collected at the intersection to be controlled in the corresponding time period, and is used to indicate the rate of change of the queue length of the corresponding lane at the intersection to be controlled during the red light process.

[0079] In this context, a phase set refers to the different combinations of states presented by traffic lights within a single traffic light cycle. For example, at a common intersection, the simultaneous illumination of the green light for east-west straight traffic and the green light for north-south left turns constitutes one phase. Different combinations of traffic light illumination form a phase set, used to regulate the traffic flow order of vehicles traveling in different directions at the intersection.

[0080] A lane index set can be a set of identifiers for all lanes at an intersection to be controlled, used to distinguish different lanes for data collection and signal control. For example, the eastbound straight lane at an intersection can be numbered 1, the eastbound left-turn lane 2, and so on. These indexes can accurately point to specific lanes.

[0081] Current queuing information can refer to the length of the queue waiting to pass through the intersection in each lane at the current time, which can be obtained through detection methods such as cameras or geomagnetic sensors. Queueing information can also include the number of vehicles in each lane; correspondingly, the speed-up information is determined based on the number of vehicles in each lane collected at the intersection to be controlled within the corresponding time period and the collection time.

[0082] The growth rate information set can be a dataset containing changes in lane queue length over multiple past time periods. For example, the growth rate information for the minute closest to the current time within the past 30 minutes, along with the growth rate information for each minute within the past 30 minutes, constitutes the growth rate information set, used to analyze lane congestion trends. Optionally, the growth rate information is obtained by dividing the difference in queue length collected at adjacent times by the time interval, resulting in the growth rate information per minute.

[0083] Headway information refers to the time interval between the front and rear heads of two adjacent vehicles in the same lane. When traveling in a certain lane, if the front vehicle passes a certain observation point and the rear vehicle's head reaches that observation point 3 seconds later, those 3 seconds are the headway at that moment, which can be used to measure the density and speed of traffic flow.

[0084] S102. Based on the current queuing information, phase set, and lane index set, determine the target phase to be controlled in the intersection to be controlled.

[0085] In this step, based on the current queuing information monitored at the current time, the congestion level of each lane is determined, such as long queues and severe congestion in certain lanes. Then, by combining the phase set and lane index set, it is determined which phases are involved in these severely congested lanes, and the phases that are key to alleviating the current congestion are prioritized as target phases. For example, if the east-west straight lanes are severely congested, and the east-west straight green light phase can directly regulate the flow in that direction, then the east-west straight green light phase is determined as the target phase.

[0086] S103. For each lane corresponding to the target phase, adjust the current queuing information of the lane according to the lane speed-up information set to obtain the target queuing information.

[0087] Furthermore, based on the growth rate information in the growth rate information set, the current queuing information is predicted and adjusted to obtain more accurate target queuing information. For example, data from the past hour can be used to predict queuing changes in the next five minutes, and traffic lights can be adjusted to reduce queue length.

[0088] S104. Based on the target phase, the headway information of all lanes corresponding to the target phase, and the target queuing information, control the signal at the intersection to be controlled.

[0089] Specifically, the switching time and sequence of traffic lights can be dynamically adjusted based on the adjusted target queue information and headway information. For example, if the headway of a lane is small, indicating dense traffic flow, the green light time for that lane can be appropriately extended. Furthermore, based on the target queue information and headway information, the green light duration for each lane is calculated using a preset optimization algorithm or calculation rule, and a traffic light control command is generated. This command is then executed by the traffic signal controller to optimize intersection traffic.

[0090] The intersection dynamic signal control method provided in this application collects multi-dimensional information about the intersection, uses historical growth rates to predict traffic flow changes, accurately locates key control phases, and then dynamically adjusts the queuing situation of each lane to implement refined signal light control. This can improve the accuracy and adaptability of intersection traffic signal control, flexibly allocate green light time according to real-time traffic conditions, reduce vehicle waiting time, improve intersection traffic efficiency, and alleviate urban traffic congestion.

[0091] Based on the above embodiments, the method described in S103 for adjusting the current queuing information of a lane according to the set of lane speed-up information to obtain target queuing information may include: determining lane correlation parameters based on the historical speed-up information of all lanes in the road network, wherein the historical speed-up information of each lane is the speed-up information of the corresponding lane stored in the database before the current time, and the lane correlation parameters are used to indicate the traffic influence relationship between lanes; adjusting the current queuing information of the lane according to the set of lane speed-up information and the lane correlation parameters to obtain target queuing information.

[0092] Historical growth rate information refers to the rate of change in queue length for each lane over a certain period of time. This data is stored in a database and used to analyze traffic flow trends in the lanes.

[0093] In this step, historical growth rate information of each lane in the road network over a longer period of time before the current time can be extracted from the database. Then, data analysis algorithms, such as correlation coefficient algorithms, are used to calculate the correlation between all lanes pairwise to obtain a lane correlation matrix. Each element in the matrix is ​​a lane correlation parameter, which comprehensively reflects the traffic impact relationship between lanes.

[0094] For example, suppose the current queue length for lane A corresponding to a target phase is 30 meters. Its growth rate data shows fluctuations over the past few periods. Simultaneously, lane correlation parameters indicate a strong positive correlation between lane A and the adjacent lane B, and lane B is currently experiencing increasing congestion (judged from its growth rate data). Considering all these factors, it is predicted that lane A will be affected by lane B, potentially increasing the number of vehicles in the queue. Therefore, the current queue length is adjusted upwards to obtain the target queue length, for example, 35 meters. Conversely, if lanes strongly correlated with lane A are experiencing easing congestion, and lane A's own growth rate is slowing down, the current queue length is adjusted downwards.

[0095] It should be noted that lane correlation parameters can include one or more parameters, without any particular limitation. For example, lane correlation parameters include the correlation matrix W parameter and the bias b parameter. Among them, the b parameter can reflect some basic traffic characteristics or initial state of each lane itself without considering the mutual influence between lanes (represented by the W parameter), such as the lane's design capacity and the inherent traffic flow tendency caused by its location in the traffic network (e.g., lanes near commercial areas may have higher base traffic flow).

[0096] By introducing lane correlation parameters, the mutual influence between traffic in different lanes can be considered more comprehensively, rather than viewing traffic changes in a single lane in isolation. This allows for a comprehensive prediction of lane queuing conditions when adjusting target queuing information, making the prediction of lane queuing more accurate. Consequently, in subsequent signal control, green light time can be allocated based on target queuing information that is more in line with actual traffic dynamics, further improving the accuracy of traffic signal control at intersections, reducing vehicle waiting time more efficiently, and enhancing the overall traffic efficiency of the intersection and even the road network.

[0097] Based on the above embodiments, the method for determining lane correlation parameters according to the historical growth rate information of all lanes in the road network may include: obtaining multiple historical growth rate information of each lane in the road network within a preset first time period; constructing a sample set based on the multiple historical growth rate information of all lanes, wherein each sample includes a second time period in the first time period and the historical growth rate information of all lanes in the corresponding second time period; constructing a road network adjacency matrix based on the adjacency relationship in the road network, the road network adjacency matrix being used to indicate the connectivity between every two lanes in the road network; and adjusting the preset correlation parameters based on the sample set and the road network adjacency matrix to obtain the lane correlation parameters.

[0098] The first time period can be a relatively long time range used to collect historical growth rate information, such as a day, a week, or a month. The second time period can be a shorter time segment used to construct samples, such as one minute. Optionally, the time period corresponding to the growth rate information stored in the database can be used as the second time period.

[0099] The adjacency relationship in the road network can be determined by the channelization state of the lanes. Lane channelization refers to the reasonable division and guidance of lanes on the road by setting up facilities such as traffic signs, markings, and traffic islands. In the channelized state, each lane has a clear function and flow direction. For example, at an intersection, some lanes are specifically used for left turns, while others are used for straight-through traffic. Furthermore, there are specific connection relationships between lanes in different directions and lanes in other directions.

[0100] The preset correlation parameters can be adjusted through statistical analysis or machine learning algorithms. For example, elastic network regression, time series analysis, linear regression, or neural network models can be used, with the input sample set and adjacency matrix, to output the adjusted correlation parameters. There are no particular restrictions on the adjustment method here.

[0101] In one example, nonlinear regression methods (such as multinomial regression, radial basis function regression, etc.) are used to estimate the rate of increase in red light queues. These models are better able to capture the complex relationships between variables and may provide more accurate predictions. For instance, by collecting traffic flow data, including vehicle queue lengths and time intervals, a nonlinear regression model can be trained using this data. The trained model can then be used to predict queue growth rates in real time and adjust current queue information accordingly to optimize traffic light control. This improves the accuracy of model predictions and allows the model to adapt to more complex traffic patterns.

[0102] In another example, time series analysis techniques (such as ARIMA models, seasonal decomposition, etc.) are used to predict the growth rate of red light queues. This can improve prediction accuracy by leveraging the time dependencies of historical data. For example, traffic flow data over a period of time is collected; a time series analysis model is trained; and the model output is used for real-time traffic control. This utilizes trends and seasonal patterns in historical data and performs better on time-dependent data.

[0103] In another example, neural networks, particularly recurrent neural networks or long short-term memory networks, are used to predict red light queue growth rates. These networks are particularly well-suited for processing sequential data and can capture long-term dependencies in time series. For example, detailed traffic flow and queue data can be collected; neural network models can be trained to predict future queue growth rates; and the predictions can be applied in real time to adjust traffic signals. This method can handle large numbers of input variables and complex patterns, and the model performance can continuously improve as the amount of data increases.

[0104] Optionally, for the method of determining lane correlation parameters, a parameter calculation cycle can be set so that the correlation parameters can be dynamically updated according to the real-time updated growth rate information, so as to ensure that when adjusting lane queuing information and controlling intersection signals using lane correlation parameters in the future, it can better match the actual traffic conditions.

[0105] Taking the elastic network regression method as an example, Figure 2 This is a flowchart illustrating a method for determining lane correlation parameters provided in this application. Figure 2 As shown, the methods for obtaining lane correlation parameters include: 1) setting the correlation matrix calculation period. Configure the road network adjacency matrix ;2) Every Time (or wait), retrieved from the red light queue speedup database by sending a request. The red light queue speedup H for all lanes within the time period; 3) The speedup speed of each lane i in the N lanes. Other lanes All historical data 4) Use the elastic network regression method to calculate the lane correlation matrix and bias and store them in the lane correlation database.

[0106] The following is about Figure 2 The method shown is illustrated by example:

[0107] 1) Based on the actual traffic data storage situation, The data sample is formed by taking the past 3 hours as the starting point and then extracting data from the same time period within the past week, followed by data cleaning and preprocessing. For example, if the past 3 hours period is from 9:00 AM to 12:00 PM on the current day, then data from 9:00 AM to 12:00 PM on each day of the previous week will be extracted. Using this extraction method, since 3 hours are extracted each day, the total extraction time for 7 days is 21 hours. Due to some data not meeting the requirements or containing null values, the data is cleaned and preprocessed, and finally 11 hours of data are retained. The extracted data is then divided into multiple time steps according to certain rules, resulting in a total of 11 × 60 = 660 time step samples.

[0108] 2) Determine the road network adjacency correlation: First, create a road network adjacency matrix based on the connectivity representation of all lanes in the channelized state. It is a type of A binary space of 0s and 1s represents the connectivity between N lanes and N lanes, where the row sum represents the in-degree and the column sum represents the out-degree in its adjacency matrix; if This indicates that the j-th lane will connect to the i-th lane;

[0109] Based on the configured road network adjacency matrix Construct a multi-order road network adjacency matrix. ,nature express For an nth-order expression, the following configurations can be selected: ( : indicates first-order adjacency), ( : indicates second-order adjacency), ( (This indicates third-order adjacency, etc.; in this embodiment, second-order neighbors are selected.) .

[0110] 3) Adjusting preset correlation parameters: Create a learnable parameter and bias Each element of W is obtained through... Perform a masking operation, where The elements in W corresponding to positions where 0 is a non-learnable parameter are set to 0 and permanently remain at 0. Furthermore, to avoid the influence of autoregression, a second masking operation is performed on W using a mask matrix with 0s on the main diagonal and 1s elsewhere, ensuring that the main diagonal elements of W are also 0. This ensures that the model only learns the interactions between lanes, not its own historical data. Finally, parameters W and b are obtained, which will be used in subsequent elasticity network linear regression analysis.

[0111] Elastic Net Regression: Given the overall dataset The sample was divided into a training set and a test set in an 8:2 ratio; elastic network regression was used to evaluate the training set on parameters... We fit the model to b to obtain a linear regression model; then we validate it on the test set to ensure that we obtain a model with relatively high accuracy. b, which are the lane correlation parameters, are stored in the lane correlation database. Optionally, multiple calculated lane correlation parameters are retained in the lane correlation database, and the corresponding storage time is recorded to prevent the current lane correlation parameters from being incorrect due to external factors such as data loss during the latest calculation. If b is unavailable, and in this case, lane correlation parameters stored in the database with a time close to the latest calculation time can be used for subsequent calculations and processing.

[0112] By reasonably dividing time periods to obtain abundant historical growth rate samples, and combining them with an adjacency matrix that reflects the road network connectivity, the initial parameters are optimized using algorithms, making the determination of lane correlation parameters more accurate and reliable. The dynamic changes in traffic flow at different times and the actual topology of the road network are fully considered, so that the adjusted lane queuing information can better match the actual traffic conditions.

[0113] Based on the above embodiments, the method for adjusting the current queuing information of a lane according to the lane speed-up information set and lane correlation parameters to obtain target queuing information may include: obtaining a sum of speed-up information based on a subset of speed-up information in the lane speed-up information set, wherein the subset of speed-up information includes multiple speed-up information obtained by sampling the lane speed-up information stored in the database within a preset third time period; determining a second speed-up information based on the lane correlation parameters and a first speed-up information in the lane speed-up information set, wherein the first speed-up information is the speed-up information of the lane stored in the database for a second time period before the current time; and determining the target queuing information based on the sum of speed-up information, the second speed-up information, the current queuing information, and the signal decision time, wherein the signal decision time is the time when the step of obtaining the phase set, lane index set, and current queuing information, speed-up information set, and headway information of each lane corresponding to the intersection to be controlled in the road network is triggered.

[0114] In this embodiment, the growth rate information subset is a part of the data in the growth rate information set. For example, data within a preset time period is sampled from the database, such as 30 minutes before the current time (i.e., the third time period). Optionally, the third time period can be set according to the actual analysis situation. Generally, in order to obtain the recent and timely lane growth rate dynamics, the third time period is longer than the second time period and shorter than the first time period.

[0115] The sum of growth rate information can be the cumulative result of all growth rate information in the subset of growth rate information, which is used to quantify the overall queuing change trend of the lane in the third time period.

[0116] Furthermore, the sum of growth rate information and the second growth rate information can satisfy:

[0117] ;

[0118] in, This represents the sum of growth rate information; This is the third time period; This represents the growth rate information for the i-th time period within the third time period. ; This is the second growth rate information; The influencing factor indicates the degree to which the current intersection considers the influence of other intersections, and is usually between 0.2 and 0.5. This is a multiplication operation; This is the first growth rate information. ; and Lane correlation parameters; It is an identity matrix.

[0119] The target queuing information can satisfy:

[0120] ;

[0121] in, Queue information for the target; This is the current queue information; For signal decision time; This is the set of lane indices corresponding to the target phase.

[0122] By combining the sum of growth rate information, lane correlation parameters, and signal decision time, lane queuing information can be predicted and adjusted more accurately.

[0123] Based on the above embodiments, before S101, the intersection dynamic signal control method may further include: acquiring a signal control decision request, the decision request including a signal decision time and the intersection to be controlled set by the user; correspondingly, when acquiring the phase set, lane index set, and current queuing information, speed-up information set, and headway information of each lane corresponding to the intersection to be controlled in the road network, the intersection to be controlled is the intersection to be controlled in the decision request; or, determining the green light countdown length corresponding to all intersections in the road network, and the green light end time corresponding to each intersection at the current time; for each intersection, if the time length from the current time to the green light end time corresponding to the intersection is greater than or equal to the green light countdown length corresponding to the intersection, then the current time is taken as the signal decision time, and the intersection is taken as the intersection to be controlled.

[0124] In this embodiment, the method for determining the signal decision time and the intersection to be controlled can include two types: passive decision-making and active decision-making. The signal control decision request can be triggered by a user or the system to initiate the signal control process. The request includes the user-defined signal decision time and the specific intersection to be controlled. The signal decision time can refer to a time point set by the user or automatically determined by the system, at which the signal control process is initiated.

[0125] For example, Figure 3 A flowchart illustrating another intersection dynamic signal control method provided in this application is shown below. Figure 3 As shown, when an external decision request is detected (passive decision type), data preparation is performed through the database, and the target phase, as well as the headway information and target queuing information (decision result) of all lanes corresponding to the target phase, are determined according to the decision calculation formula (corresponding to the method described in the above embodiments). Then, the decision result is pushed to the signal control unit (traffic signal controller) / signal control platform (traffic signal control platform) to control the signal of the intersection to be controlled. When the signal control process is active decision type, each intersection is traversed, and the current time point is determined by the green light countdown length corresponding to the intersection and the green light end time corresponding to each intersection at the current time. It is then determined whether the intersection needs to make a decision (i.e., execute the signal control process). If so, the execution steps are similar to those in the passive decision type, and will not be repeated here.

[0126] The green light countdown length refers to the countdown length set for the intersection under the green light status at the current time in the road network, while the green light end time refers to the specific time when the current green light status is expected to end.

[0127] Figure 4 A flowchart illustrating a signal decision timing determination method provided in this application is shown below. Figure 4As shown, when the signal control process is proactive decision-making type, if it is detected that the current time point is exactly at the start time of the green light countdown (that is, the time length from the current time to the end time of the green light at the intersection is equal to the countdown length of the green light at the intersection), then it is considered that a decision needs to be made, and the current time is taken as the signal decision time.

[0128] By introducing decision requests for signal control and a mechanism for automatically identifying intersections to be controlled, it can flexibly respond to user needs and real-time traffic conditions, ensuring that signal control decisions are made at the most appropriate time. This improves the initiative and accuracy of traffic signal control and enables it to adapt more effectively to dynamic traffic environments.

[0129] Based on the above embodiments, the intersection dynamic signal control method may further include: acquiring the traffic light phase status of all intersections in the road network; for each intersection, when the traffic light phase status indicates the start of a red light, acquiring the first queue length and first acquisition time of each lane corresponding to the intersection; when the traffic light phase status indicates the start of a green light, acquiring the second queue length, second acquisition time, and headway data of each lane corresponding to the intersection, and determining the average headway of each lane based on the headway data after the traffic light phase status indicates the start of a red light again; wherein, the headway information includes the headway data and the average headway of each lane; for each lane corresponding to the intersection, determining the lane's speed-up information within a second time period based on the lane's first queue length, first acquisition time, second queue length, and second acquisition time; and storing the speed-up information of all lanes corresponding to all intersections in a database.

[0130] The traffic light phase state refers to the current state of the traffic lights, including different phases such as red, green, and yellow, used to indicate the control status of traffic flow. Queue length refers to the number of vehicles waiting to pass in each lane when the red light or green light begins; acquisition time is the specific time point recorded for the corresponding queue length. For example, a queue increment accumulator is set up in each lane at each intersection. This accumulator can be a first-in, first-out queue structure. Whenever the red light at that intersection begins, the initial queue and time point are recorded; when the green light at the corresponding intersection begins, the queue and time point are recorded again.

[0131] Headway data refers to the time interval between vehicles, collected only during green light periods. The average headway is the average of these intervals, calculated at the end of each green light cycle, and is used to measure traffic flow density and speed. The second time period refers to the time period corresponding to the calculation of growth rate information based on the first and second queue lengths and their acquisition time, and is used to store it in a database, for example, storing growth rate information once per minute.

[0132] In one example, such as Figure 5 The flowchart shown illustrates the process of collecting red light queue increments and headway data. It obtains the current control information from the traffic control unit (i.e., the traffic light phase status); determines whether the current control information indicates a red light at a certain intersection; if it is a red light, it stops collecting headway data for green lights, determines the average headway distance and stores it in the headway distance database, and records the current first queue length. and first acquisition time If the light is green, begin collecting the headway data for vehicles with green lights and record the current second queue length. Second acquisition time If the first queue length and the first acquisition time exist, then... Store the current lane queue change cache; clean the existing data and store it in the red light queue speed-up database.

[0133] Optionally, the red light queue speed-up database is structured as follows: lane identifier (lane_id), start time of the second time period (timepoint_start), and end time of the second time period (timepoint_end). The trigger settings in this database are optional. A queue data structure can be used to store queue speed-up data. For example, 259200 (60 minutes × 24 hours × 180 days) is the actual set value, meaning it stores red light queue speed-up information for each minute over 180 days. If the data for a particular lane exceeds 259200 records, the earliest timestamp record for that lane is automatically deleted to retain the latest data and conserve system resources. Taking storing speed-up information once per minute as an example, each stored record in the red light queue speed-up database includes: lane identifier, the start and end times for the corresponding minute, and the speed-up information for the corresponding intersection.

[0134] By acquiring and analyzing traffic light phase status, queue length, and headway data in real time, the speed-up information for each lane can be accurately calculated and stored for subsequent traffic signal optimization, thus improving the understanding of traffic flow trends.

[0135] Based on the above embodiments, the method for determining the lane speed-up information within a second time period according to the first queue length, first acquisition time, second queue length, and second acquisition time of the lane may include: determining the midpoint between the first acquisition time and the second acquisition time of the lane; if the midpoint is within the second time period, determining the lane speed-up information within the second time period based on the first difference between the second queue length and the first queue length of the lane and the second difference between the second acquisition time and the first acquisition time; if the midpoint is after the second time period, determining the lane speed-up information based on the first difference between the second queue length and the first queue length of the lane and the second difference between the second acquisition time and the first acquisition time; and determining the lane speed-up information within the second time period based on the third speed-up information and the fourth speed-up information, wherein the fourth speed-up information is the lane speed-up information within a second historical time period stored in the database, and the second historical time period is the second time period corresponding to when the lane speed-up information was stored before the first acquisition time.

[0136] Furthermore, for a certain intersection, when adding lane speedup information (target storage record) for a second time period to the database, it is necessary to obtain the start and end times of the latest storage record for that lane in the database corresponding to one minute (i.e., the second historical time period), and use the end time of that storage record corresponding to one minute as the target start time of the target storage record corresponding to one minute. Based on the target start time, add one minute to obtain the target end time of the target storage record corresponding to one minute.

[0137] If the intermediate time Between the target start time and the target end time (within the second time period), the lane speedup information within the second time period satisfies... The target storage record includes: corresponding lane identifier, target start time, and target end time. ;

[0138] If the intermediate time After the second time period, then As the third speed-up information for the lane, and will As a second storage record ,in, The second storage record corresponds to the start time of one minute. , The second storage record corresponds to the end time of one minute. , As growth rate information ;

[0139] Use the latest stored record for this lane in the database as the first stored record. ,in, This is the fourth growth rate information;

[0140] Let's assume the missing time points For is and The data between the two periods indicates that the lane speedup information in the second time period meets the requirements. The target storage record includes: corresponding lane identifier, target start time, and target end time. .

[0141] By introducing the judgment of intermediate moments and combining historical growth rate information, the changes in traffic flow in lanes within a specific time period can be reflected more accurately. At the same time, the differences between inside and outside the time period and the influence of historical data are taken into account, which further improves the accuracy and reliability of growth rate information, thereby optimizing the decision-making process of traffic signal control.

[0142] Based on the above embodiments, the method described in S102 for determining the target phase to be controlled in the intersection to be controlled according to the current queuing information, the phase set, and the lane index set may include: determining lane flow direction information according to the phase set and the lane index set, wherein the lane flow direction information is used to indicate the mapping relationship between the upstream lane and the downstream lane in the intersection to be controlled; determining the queuing amount difference between the upstream lane queuing length and the downstream lane queuing length corresponding to each phase according to the current queuing information and the lane flow direction information; and determining the target phase in the phase set based on the queuing amount difference corresponding to all phases.

[0143] Lane flow direction information can refer to a data structure representing the mapping relationship between upstream and downstream lanes at the intersection to be controlled. It indicates the traffic flow direction of each lane, thus helping to identify which lanes are interconnected. Queue length difference can refer to the difference between the queue length of the upstream lane and the queue length of the downstream lane for each phase.

[0144] Prior to this embodiment, it is necessary to construct an initial queuing quantity difference vector. Its value is initialized by filling it with 0, indicating The queuing difference value of each phase is calculated, and then for each phase of the i-th intersection at this moment, the queuing difference value is calculated. Queue length of the upstream lane and queue length of downstream lanes .

[0145] In this embodiment, based on the phase set (for With phase (corresponding lane index set) and lane index set (i represents the intersection to be controlled), determine lane flow information. (i.e., upstream lane) to the downstream lane (Mapping relationship); based on current queuing information ( Based on lane flow information, calculate the upstream queue length for each phase. and downstream queue length And the difference in queuing volume between the upstream and downstream lanes, and fill it in. In, that is:

[0146] ;

[0147] For filling values The values ​​are sorted (from largest to smallest) to obtain a sorted set of phase indices. The phase ranked first is used as the target phase for the final decision output. ( ).

[0148] By incorporating lane flow information and calculating queue size differences, the system can more accurately identify phases with unbalanced traffic flow, thereby optimizing signal control. By prioritizing the adjustment of phases with the largest queue size differences, the system can effectively alleviate traffic congestion and improve traffic flow efficiency, thereby enhancing the intelligence and responsiveness of traffic signal control and further improving the overall efficiency and adaptability of the traffic management system.

[0149] Based on the above embodiments, the method for controlling the signal at the intersection to be controlled, as described in S104, based on the target phase and the headway information and target queuing information of all lanes corresponding to the target phase, may include:

[0150] For each lane corresponding to the target phase, the start time of the lane and the number of vehicles passing through the start time are determined based on the headway information of the lane.

[0151] Based on the target queue information, number of vehicles, start time, and headway information, determine the lane's passage time;

[0152] The target passage time for the target phase is determined based on the passage time of all lanes corresponding to the target phase, as well as the maximum and minimum phase times of the target phase.

[0153] Based on the target phase and the target passage time of the target phase, the signals at the intersection to be controlled are controlled.

[0154] In this step, the start time refers to the time required for vehicles to begin moving and pass through the controlled intersection after the traffic light turns green. The number of vehicles can be the number of vehicles that can pass through the controlled intersection within the start time, typically influenced by the headway and traffic density of the corresponding lane. The passage time refers to the length of time a lane is allowed for vehicles to pass during the target phase. The maximum phase time and minimum phase time are the longest and shortest allowed passage times for the target phase, respectively, used to ensure the safety and efficiency of signal control. The target passage time is the actual passage time determined after considering the passage times of all lanes, the maximum phase time, and the minimum phase time.

[0155] In some examples, a negative exponential distribution model can be used to calculate the start time, assuming that at a certain moment the headway has reached 90% of the minimum headway. When the average headway (from the headway information) is reached, the number of vehicles after that point will follow the minimum headway. In a negative exponential distribution, the headway... The probability distribution function is:

[0156] ;

[0157] Therefore, there exists a starting time. This ensures that the headway is at its minimum with a 90% probability.

[0158] ;

[0159] because Therefore, the final start time is also in vector form. This indicates the start time for each lane. The number of vehicles passing through within that start time. for:

[0160] ;

[0161] in, This refers to the headway information at startup, specifically the headway data within the headway information. .

[0162] Queuing time function This indicates that by inputting a quintuple The calculated travel time is:

[0163] ;

[0164] Finally, regarding the target phase Its travel time is the maximum travel time for all lanes, that is:

[0165] ;

[0166] in, This is the function for finding the maximum value.

[0167] In order to standardize the phase time and push it, it is also necessary to determine the maximum phase time corresponding to the target phase. and minimum phase time Normalized phase time:

[0168] ;

[0169] in, , These are binary operators for finding the minimum and maximum values.

[0170] Finally, the decision results The signal is pushed to the control terminal, such as the signal control unit / signal control platform, to control the signal changes at the intersection to be controlled.

[0171] Optionally, if due to equipment or control limitations, a phase decision for the entire cycle must be provided at once, the lead time for the advance decision can be specified. :

[0172] 1) First, the sorted set of phase indices is obtained based on the method of the above embodiments. ;

[0173] 2) Then, the method described in the above embodiments is used to obtain... , , , , ,as follows:

[0174] ;

[0175] in, A list of times corresponding to the phase decisions throughout the entire cycle;

[0176] 3) Finally, The signal is pushed to the control terminal to control the signal changes at the intersection to be controlled.

[0177] By analyzing headway information and queuing information, the system can more accurately calculate the travel time for each lane, thereby optimizing the signal control of the target phase. By setting a reasonable target travel time, the system can effectively reduce vehicle waiting time and further improve traffic flow efficiency.

[0178] In one example, the intersection dynamic signal control method provided in this application embodiment may include four processes and four databases, wherein process 1 - a data monitoring process, is used to acquire traffic data in the road network (collecting many types of data including queue length, number of vehicles in queue); process 2 - is used to collect red light queue increments, (green light) headway, etc. Figure 5 As shown; Process 3 - Lane correlation parameter calculation process, as follows Figure 2 As shown; Process 4 - Decision Process, which is the process that triggers the execution signal control flow, including active decision-making and passive decision-making types, such as... Figure 3 As shown.

[0179] Furthermore, process 1 monitors and collects traffic data from the road network and stores it in the traffic status database. Process 2 collects red light queue increments and (green light) headway distances, i.e., based on a pre-set acquisition time period or a received data acquisition request, it acquires the traffic light phase status of the traffic signal controller at the corresponding time. If the traffic light phase status changes to red, the acquisition of headway distance data is stopped, the average headway distance is determined and stored in the headway distance database, and the current first queue length and first acquisition time are recorded. If the traffic light phase status changes to green, the acquisition of headway distance data begins, and the current second queue length and second acquisition time are recorded. If the first queue length and first time recorded in this acquisition task already exist, (first acquisition time, second acquisition time, first queue length, second queue length) are stored in the current lane queue change cache. If they do not exist, they are recorded when the traffic light phase status changes to red. The existing data in the cache is cleaned (including removing interference data and calculating the growth rate information) and stored in the red light queue growth rate database.

[0180] Set the correlation matrix calculation cycle through process 3. Set up the road network adjacency matrix; every Time (otherwise wait), retrieved from the red light queue speedup database stored in process 2 by sending a request. The red light queue speedup of all lanes within a time period; the speedup of each lane in the road network and all historical data of other lanes constitute a dataset; the lane correlation matrix and bias are calculated using the elastic network regression method and stored in the lane correlation database.

[0181] The signal control process is executed through process 4. If it's an active decision-making type, it iterates through each intersection in the road network; it determines whether a decision is needed at the current time (the time from the pre-set signal decision time to the end of the green light is greater than or equal to the green light countdown itself, or the current time is about to begin counting down); if not, it updates the current time and continues iterating through each intersection; if yes, it prepares data (i.e., extracts multi-dimensional data for the corresponding intersection from the four databases stored in processes 1, 2, and 3); following the decision calculation formula, it determines the target phase for the final decision output and the target passage time corresponding to the target phase. For example, it initializes the queue length difference vector, calculates the upstream and downstream queue lengths and queue length difference for each phase based on the current queue information and lane flow information, fills and sorts the vector to select the target phase for the final decision output (the one with the largest numerical value); based on the speed increase information subset, it determines the third time... The process involves: summing the growth rate information within a given interval; determining the second growth rate information based on relevant parameters and the first growth rate information; determining the target queuing information based on the sum of the growth rate information, the second growth rate information, the current queuing information, and the signal decision time; calculating the start time using a negative exponential distribution model based on the minimum headway, and determining the number of vehicles passing through the start time based on the start time, minimum headway, and start headway; calculating the passage time for each lane based on the target queuing information, the number of vehicles, the start time, minimum headway, and start headway, and selecting the maximum passage time for all lanes in the target phase as the passage time for that phase; adjusting the passage time for the target phase based on the maximum and minimum phase times corresponding to the target phase to obtain the target passage time; and pushing the target phase and the corresponding target passage time to the signal control unit / platform to control the signal changes at the intersection. For passive decision-making, the process involves receiving a signal control decision request to perform data preparation; obtaining the result according to the decision calculation formula; and pushing the result to the signal control unit / platform (same as active decision-making).

[0182] Therefore, the intersection dynamic signal control method provided in this application, by setting up a lane queue increment accumulator and a standardized database, records and processes vehicle queue data within the traffic light cycle; it uses historical data to build a model, and fits and corrects the data through elastic network regression to achieve real-time dynamic optimization control of traffic flow at multiple intersections, thereby improving traffic efficiency. Further effects may include: 1) Continuous and real-time traffic data processing and optimization. By collecting traffic flow data in real time and dynamically updating queue growth information using a first-in-first-out queue structure, the problem of continuously acquiring traffic data is effectively solved. This not only improves the real-time performance and accuracy of the data but also enables the traffic control system to quickly respond to actual traffic changes, thus managing traffic flow more effectively. 2) Precise traffic decision support. By introducing the red light queue growth correlation matrix and the road network connectivity adjacency matrix, coordinated vehicle control between multiple intersections becomes possible. By considering the impact of vehicle flow at multiple intersections, the system can more accurately predict and adjust the signal light changes at each intersection, optimizing traffic flow and reducing congestion. This method is particularly suitable for urban areas with high traffic volume and many intersections, and can significantly improve the overall efficiency of the traffic system. 3) Smooth transition from transitional design to fully adaptive control. By retaining the concept of periodicity and gradually introducing a data-driven decision-making mechanism, a robust transition is provided for future fully automated traffic control systems. This design not only ensures the stable operation of the current system but also provides data support and technical verification for future system upgrades, reducing the risks and costs of technology upgrades. 4) Improved scalability and flexibility of the traffic system. Modular design allows for flexible adjustment and expansion under different traffic scenarios and needs. For example, through variant design, the control strategy can be adjusted according to actual hardware and platform limitations, making this technical solution widely applicable to traffic networks of different sizes and types. Based on the methods corresponding to the above embodiments, the existing technologies also solve problems such as difficulty in acquiring traffic data (continuously updating traffic status information through real-time data collection and processing mechanisms to ensure the timeliness and accuracy of decision-making basis), inaccurate advance decision-making (improving the accuracy and reliability of decision-making by introducing correlation analysis between lanes and collaborative control of multiple intersections), and inability to meet the needs of transitioning to fully adaptive control (by gradually introducing data-driven elements and retaining the concept of periodicity, a smooth transition to a more advanced control strategy is achieved, laying the foundation for the implementation of fully adaptive control methods).

[0183] Figure 6 This is a schematic diagram of the intersection dynamic signal control device provided in this application, as shown below. Figure 6 As shown, the intersection dynamic signal control device 60 provided in this embodiment includes:

[0184] The acquisition module 601 is used to acquire the phase set, lane index set, current queuing information, speed-up information set, and headway information of each lane corresponding to the intersection to be controlled in the road network. The speed-up information set includes the speed-up information of each lane of the intersection to be controlled in multiple time periods before the current time stored in the database. Each speed-up information is determined according to the lane queue length and collection time collected at the intersection to be controlled in the corresponding time period, and is used to indicate the rate of change of the queue length of the corresponding lane at the intersection to be controlled during the red light process.

[0185] The determination module 602 is used to determine the target phase to be controlled in the intersection to be controlled based on the current queuing information, phase set and lane index set;

[0186] The adjustment module 603 is used to adjust the current queuing information of each lane corresponding to the target phase based on the lane's speed-up information set, so as to obtain the target queuing information.

[0187] The control module 604 is used to control the signal at the intersection to be controlled based on the target phase, the headway information of all lanes corresponding to the target phase, and the target queuing information.

[0188] In one possible implementation, the adjustment module 603 can also be used for:

[0189] Based on the historical growth rate information of all lanes in the road network, lane correlation parameters are determined. The historical growth rate information of each lane is the growth rate information of the corresponding lane stored in the database before the current time. The lane correlation parameters are used to indicate the traffic impact relationship between lanes. Based on the set of lane growth rate information and the lane correlation parameters, the current queuing information of the lanes is adjusted to obtain the target queuing information.

[0190] In one possible implementation, the adjustment module 603 can also be used for:

[0191] Obtain multiple historical growth rate information for each lane in the road network within a preset first time period; construct a sample set based on the multiple historical growth rate information of all lanes, wherein each sample includes a second time period within the first time period and the historical growth rate information of all lanes in the corresponding second time period; construct a road network adjacency matrix based on the adjacency relationships in the road network, which is used to indicate the connectivity between every two lanes in the road network; adjust the preset correlation parameters based on the sample set and the road network adjacency matrix to obtain the lane correlation parameters.

[0192] In one possible implementation, the adjustment module 603 can also be used for:

[0193] Based on the growth rate information subset in the lane growth rate information set, the total growth rate information is obtained. The growth rate information subset includes multiple growth rate information samples obtained by sampling the lane growth rate information stored in the database within a preset third time period. Based on the lane correlation parameters and the first growth rate information in the lane growth rate information set, the second growth rate information is determined. The first growth rate information is the growth rate information of the lane stored in the database for a second time period before the current time. Based on the total growth rate information, the second growth rate information, the current queuing information, and the signal decision time, the target queuing information is determined. The signal decision time is the time when the step of obtaining the phase set, lane index set, current queuing information, growth rate information set, and headway information of each lane corresponding to the intersection to be controlled in the road network is triggered.

[0194] In one possible implementation, the acquisition module 601 can also be used for:

[0195] The system acquires a signal control decision request, which includes the user-defined signal decision time and the intersection to be controlled. Correspondingly, when acquiring the phase set, lane index set, and current queuing information, acceleration information set, and headway information for each lane corresponding to the intersection to be controlled in the road network, the intersection to be controlled is the one specified in the decision request. Alternatively, it determines the green light countdown length for all intersections in the road network and the green light end time for each intersection at the current time. For each intersection, if the time from the current time to the green light end time is greater than or equal to the green light countdown length, then the current time is used as the signal decision time, and the intersection is designated as the intersection to be controlled.

[0196] In one possible implementation, the acquisition module 601 can also be used for:

[0197] The system acquires the traffic light phase status of all intersections in the road network. For each intersection, when the traffic light phase status indicates the start of a red light, it acquires the first queue length and first acquisition time for each lane corresponding to the intersection. When the traffic light phase status indicates the start of a green light, it acquires the second queue length, second acquisition time, and headway data for each lane corresponding to the intersection. After the traffic light phase status indicates the start of a red light again, it determines the average headway for each lane based on the headway data. The headway information includes the headway data and the average headway for each lane. For each lane corresponding to an intersection, it determines the lane's speed-up information within a second time period based on the lane's first queue length, first acquisition time, second queue length, and second acquisition time. The speed-up information for all lanes corresponding to all intersections is stored in the database.

[0198] In one possible implementation, the acquisition module 601 can also be used for:

[0199] The intermediate moment between the first acquisition time and the second acquisition time of the lane is determined. If the intermediate moment is within the second time period, the lane's speed-up information within the second time period is determined based on the first difference between the second queue length and the first queue length of the lane, and the second difference between the second acquisition time and the first acquisition time. If the intermediate moment is after the second time period, the lane's third speed-up information is determined based on the first difference between the second queue length and the first queue length of the lane, and the second difference between the second acquisition time and the first acquisition time. Based on the third speed-up information and the fourth speed-up information, the lane's speed-up information within the second time period is determined, where the fourth speed-up information is the lane's speed-up information within the second historical time period stored in the database, and the second historical time period is the second time period corresponding to when the lane's speed-up information was stored before the first acquisition time.

[0200] In one possible implementation, the determining module 602 can also be used for:

[0201] Based on the phase set and lane index set, lane flow direction information is determined, which is used to indicate the mapping relationship between upstream and downstream lanes in the intersection to be controlled. Based on the current queuing information and lane flow direction information, the queuing amount difference between the upstream lane queuing length and the downstream lane queuing length corresponding to each phase is determined. Based on the queuing amount difference corresponding to all phases, the target phase in the phase set is determined.

[0202] In one possible implementation, the control module 604 can also be used for:

[0203] For each lane corresponding to the target phase, the start time of the lane and the number of vehicles passing through the start time are determined based on the headway information of the lane. The passage time of the lane is determined based on the target queue information, the number of vehicles, the start time and the headway information. The target passage time of the target phase is determined based on the passage time of all lanes corresponding to the target phase, as well as the maximum phase time and the minimum phase time of the target phase. Based on the target phase and the target passage time of the target phase, the signal of the intersection to be controlled is controlled.

[0204] The intersection dynamic signal control device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0205] Figure 7 A schematic diagram of the structure of the electronic device provided in this application. Figure 7As shown, the electronic device 70 provided in this embodiment includes at least one processor 701 and a memory 702. Optionally, the device 70 further includes a communication component 703. The processor 701, memory 702, and communication component 703 are connected via a bus 704.

[0206] In a specific implementation, at least one processor 701 executes computer execution instructions stored in memory 702, causing at least one processor 701 to perform the above-described method.

[0207] The specific implementation process of processor 701 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0208] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0209] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0210] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0211] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0212] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0213] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0214] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0215] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0216] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0217] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0218] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0219] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0220] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for dynamic signal control at intersections, characterized in that, include: The system acquires the phase set, lane index set, current queuing information, speed-up information set, and headway information of each lane corresponding to the intersection to be controlled in the road network. The speed-up information set includes the speed-up information of each lane of the intersection to be controlled in multiple time periods before the current time, stored in the database. Each speed-up information is determined based on the lane queue length and collection time collected at the intersection to be controlled in the corresponding time period, and is used to indicate the rate of change of the queue length of the corresponding lane at the intersection to be controlled during the red light process. Based on the current queuing information, the phase set, and the lane index set, determine the target phase to be controlled at the intersection to be controlled; For each lane corresponding to the target phase, a lane correlation parameter is determined based on the historical growth rate information of all lanes in the road network. The historical growth rate information for each lane is the growth rate information of the corresponding lane stored in the database before the current time. The lane correlation parameter is used to indicate the traffic impact relationship between lanes. A total growth rate information is obtained based on a subset of growth rate information in the lane growth rate information set. This subset includes multiple growth rate information samples obtained by sampling the lane growth rate information stored in the database within a preset third time period. A second growth rate information is determined based on the lane correlation parameter and a first growth rate information in the lane growth rate information set. The first growth rate information is the growth rate information of the lane stored in the database for a second time period before the current time. Target queuing information is determined based on the total growth rate information, the second growth rate information, the current queuing information, and the signal decision time. The signal decision time is the time that triggers the execution of the steps to obtain the phase set, lane index set, and current queuing information, growth rate information set, and headway information of each lane corresponding to the intersection to be controlled in the road network. Based on the target phase, as well as the headway information and target queuing information of all lanes corresponding to the target phase, the signal of the intersection to be controlled is controlled.

2. The method according to claim 1, characterized in that, The step of determining lane correlation parameters based on the historical growth rate information of all lanes in the road network includes: Obtain multiple historical growth rate information for each lane in the road network within a preset first time period; Based on multiple historical growth rate information for all lanes, a sample set is constructed, wherein each sample includes a second time period in the first time period, and the historical growth rate information of all lanes in the corresponding second time period; Based on the adjacency relationships in the road network, a road network adjacency matrix is ​​constructed, which is used to indicate the connectivity between every two lanes in the road network; Based on the sample set and the road network adjacency matrix, the preset correlation parameters are adjusted to obtain the lane correlation parameters.

3. The method according to claim 1, characterized in that, Before acquiring the phase set, lane index set, and current queuing information, acceleration information set, and headway information of each lane corresponding to the intersection to be controlled in the road network, the method further includes: Obtain a signal control decision request, the decision request including the signal decision time and the intersection to be controlled set by the user; Accordingly, when obtaining the phase set, lane index set, and current queuing information, speed-up information set, and headway information of each lane corresponding to the intersection to be controlled in the road network, the intersection to be controlled is the intersection to be controlled in the decision request. or, Determine the green light countdown length for all intersections in the road network, and the green light end time for each intersection at the current time; For each intersection, if the time from the current time to the end time of the green light at the intersection is greater than or equal to the countdown time of the green light at the intersection, then the current time is used as the signal decision time, and the intersection is designated as the intersection to be controlled.

4. The method according to claim 1, characterized in that, The method further includes: Obtain the phase status of traffic lights at all intersections in the road network; For each intersection, when the traffic light phase status indicator signal red light starts at the intersection, the first queue length and the first acquisition time for each lane corresponding to the intersection are obtained; When the traffic light phase status indicates that the green light has started, the second queue length and second acquisition time, as well as the headway data for each lane corresponding to the intersection, are obtained. After the traffic light phase status indicates that the red light has started again, the average headway for each lane is determined based on the headway data. The headway information includes the headway data and the average headway for each lane. For each lane corresponding to the intersection, the speed increase information of the lane in the second time period is determined based on the first queue length, the first acquisition time, the second queue length, and the second acquisition time of the lane. The speed increase information for all lanes corresponding to all intersections is stored in the database.

5. The method according to claim 4, characterized in that, The step of determining the lane's speedup information within the second time period based on the lane's first queue length, first acquisition time, second queue length, and second acquisition time includes: Determine the intermediate time between the first acquisition time and the second acquisition time of the lane; If the intermediate time is within the second time period, then the speed increase information of the lane within the second time period is determined based on the first difference between the second queue length and the first queue length of the lane and the second difference between the second acquisition time and the first acquisition time. If the intermediate time is after the second time period, then the third speed-up information of the lane is determined based on the first difference between the second queue length and the first queue length of the lane and the second difference between the second acquisition time and the first acquisition time. Based on the third and fourth growth rate information, the growth rate information of the lane within the second time period is determined, wherein the fourth growth rate information is the growth rate information of the lane within the second historical time period stored in the database, and the second historical time period is the second time period corresponding to when the growth rate information of the lane was stored before the first acquisition time.

6. The method according to claim 1, characterized in that, The step of determining the target phase to be controlled at the intersection to be controlled based on the current queuing information, the phase set, and the lane index set includes: Based on the phase set and the lane index set, lane flow direction information is determined, and the lane flow direction information is used to indicate the mapping relationship between the upstream lane and the downstream lane in the intersection to be controlled; Based on the current queuing information and the lane flow direction information, determine the queuing difference between the upstream lane queuing length and the downstream lane queuing length corresponding to each phase; The target phase in the phase set is determined based on the queuing difference values ​​corresponding to all phases.

7. The method according to claim 1, characterized in that, The control of the signal at the intersection to be controlled, based on the target phase and the headway information and target queuing information of all lanes corresponding to the target phase, includes: For each lane corresponding to the target phase, based on the headway information of the lane, the start time corresponding to the lane and the number of vehicles passing through the start time are determined; The passage time of the lane is determined based on the target queue information, the number of vehicles, the start time, and the headway information. The target passage time for the target phase is determined based on the passage time of all lanes corresponding to the target phase, as well as the maximum and minimum phase times of the target phase. Based on the target phase and the target travel time of the target phase, the signals at the intersection to be controlled are controlled.

8. A dynamic signal control device for intersections, characterized in that, include: The acquisition module is used to acquire the phase set, lane index set, current queuing information, speed-up information set, and headway information of each lane corresponding to the intersection to be controlled in the road network. The speed-up information set includes the speed-up information of each lane of the intersection to be controlled in multiple time periods before the current time stored in the database. Each speed-up information is determined according to the lane queuing length and collection time collected at the intersection to be controlled in the corresponding time period, and is used to indicate the rate of change of the queuing length of the corresponding lane at the intersection to be controlled during the red light process. The determination module is used to determine the target phase to be controlled in the intersection to be controlled based on the current queuing information, the phase set, and the lane index set; The adjustment module is used to determine lane correlation parameters for each lane corresponding to the target phase, based on the historical growth rate information of all lanes in the road network. The historical growth rate information for each lane is the growth rate information of the corresponding lane stored in the database before the current time. The lane correlation parameters are used to indicate the traffic impact relationship between lanes. The module also obtains a sum of growth rate information based on a subset of growth rate information in the lane growth rate information set. This subset includes multiple growth rate information samples obtained by sampling the lane growth rate information stored in the database within a preset third time period. Furthermore, it determines a second growth rate information based on the lane correlation parameters and a first growth rate information in the lane growth rate information set. The first growth rate information is the growth rate information of the lane stored in the database for a second time period before the current time. Finally, it determines target queuing information based on the sum of growth rate information, the second growth rate information, the current queuing information, and the signal decision time. The signal decision time is the time that triggers the execution of the steps to obtain the phase set, lane index set, and current queuing information, growth rate information set, and headway information of each lane corresponding to the intersection to be controlled in the road network. The control module is used to control the signal of the intersection to be controlled based on the target phase, the headway information of all lanes corresponding to the target phase, and the target queuing information.

Images