Regional Green Wave Scheduling Method, System and Storage Medium Based on Traffic Flow Prediction

Abstract

The present invention discloses a regional green wave scheduling method, system and storage medium based on traffic flow prediction, which relates to the field of traffic control systems. The method includes: constructing a road network topology by extracting road vectors, traffic facility data and POI information within a region. Collecting the real-time traffic flow of roads based on the road network topology, and using a traffic flow prediction model with POI information as input to predict the traffic flow, so as to obtain the predicted traffic flow of the roads. Aligning the data according to the real-time traffic flow and the predicted traffic flow of the roads, constructing a dynamic adjacency weight matrix to reflect the priority change of the main road - branch road. And combining with the road network topology, adjusting and optimizing the phase difference and time window of the main road and the branch road to obtain a regional green wave scheduling strategy. It solves the technical problems that in the prior art, the traffic scheduling system lacks dynamic response to real-time traffic flow and predicted traffic flow, and cannot effectively adjust the green wave band strategy according to the change of traffic flow, resulting in low traffic efficiency and congestion during peak hours.

Description

Technical Field

[0001] The present invention relates to the field of traffic control systems, and in particular to a regional green wave scheduling method, system and storage medium based on traffic flow prediction. Background Art

[0002] With the continuous advancement of the urbanization process, the traffic flow in cities is increasing day by day, causing a large number of traffic congestion problems. Especially during peak traffic hours, the challenges of traffic management are becoming increasingly prominent. The traditional traffic signal scheduling method is often fixed, lacking flexibility and adaptability, and unable to effectively respond to the changes in traffic flow, resulting in low traffic efficiency and increased delays. To alleviate this problem, adopting the green wave scheduling strategy has become an important means to improve the smoothness of urban traffic. The green wave scheduling strategy coordinates the traffic signals at intersections to ensure that a vehicle can continuously maintain a green light when passing through multiple intersections, reducing the stopping time and improving the traffic efficiency. However, the traditional green wave scheduling method mainly relies on fixed time settings and lacks dynamic response to real-time traffic flow and predicted traffic flow changes.

[0003] Therefore, in the prior art, the traffic scheduling system lacks dynamic response to real-time traffic flow and predicted traffic flow, and cannot effectively adjust the green wave band strategy according to the changes in traffic flow, resulting in low traffic efficiency and congestion during peak hours. Summary of the Invention

[0004] This application provides a regional green wave scheduling method, system and storage medium based on traffic flow prediction, and solves the technical problem that in the prior art, the traffic scheduling system lacks dynamic response to real-time traffic flow and predicted traffic flow, and cannot effectively adjust the green wave band strategy according to the changes in traffic flow, resulting in low traffic efficiency and congestion during peak hours. The regional green wave scheduling method based on traffic flow prediction dynamically adjusts the priority, phase difference and green light time window of road signals through the combination of real-time traffic data collection and predicted traffic flow models, realizes the optimized scheduling of the regional green wave band, significantly improves the traffic smoothness, and reduces traffic congestion.

[0005] In the first aspect of the embodiments of the present application, a regional green wave scheduling method based on traffic flow prediction is provided. The method includes: extracting road vectors, traffic facility data, and POI information within a region to construct a road network topology structure, where the road network topology structure includes main roads and branch roads; collecting real-time road traffic flow based on the road network topology structure, and using a traffic flow prediction model with POI information as input to perform traffic flow prediction to obtain predicted road traffic flow, where the traffic flow prediction model is trained and converged using historical data; aligning data according to the real-time road traffic flow and the predicted road traffic flow to construct a dynamic adjacency weight matrix, reflecting the priority change between the main road and the branch road; and adjusting and optimizing the phase difference and time window of the main road and the branch road according to the priority change between the main road and the branch road in combination with the road network topology structure to obtain a regional green wave scheduling strategy.

[0006] In an implementation manner, vector data of all roads within a region is extracted from map data, including road geometry, number of lanes, and turning restrictions; traffic facility data within the region is collected, including the positions and attribute information of traffic lights, isolation fences, bus stops, crosswalks, and cameras; the name, category, coordinates, address data, service radius, peak hours, and event data of POI points within the region are obtained to establish the POI information; the road network is defined as a directed graph, and nodes and edges are extracted according to the positioning relationship of all road vector data, traffic facility data, and POI information to construct the road network topology structure.

[0007] In an implementation manner, constructing the road network topology structure according to the positioning relationship of all road vector data, traffic facility data, and POI information to extract nodes and edges includes: identifying road intersections, confluence / diversion points, and defining nodes; according to the road vector data, defining the connection relationship between each node as an edge, where the number of lanes, speed limit, and turning restrictions of each edge define the edge attributes; and connecting the nodes, edges, and edge attributes according to the road geometry connection relationship to construct the road network topology structure, and performing attribute marking according to the positioning relationship of the traffic facility data and POI information.

[0008] In an implementation manner, constructing the road network topology structure further includes: defining a determination rule for main roads and branch roads according to the number of lanes; determining the road grade as a main road lane or a branch road lane according to the road grade determination of the number of lanes of each lane, and marking the main roads and branch roads on the road network topology structure according to the road grade.

[0009] In an implementation manner, data alignment is performed based on the real-time traffic flow and the predicted traffic flow of the road, and a dynamic adjacency weight matrix is constructed, including: performing time-series alignment of traffic flow data according to the time relationship between the real-time traffic flow and the predicted traffic flow of the road; setting the update frequencies of the real-time traffic flow and the predicted traffic flow of the road, configuring a sliding window based on the update frequencies, and updating the traffic flow time-series data according to the sliding window; dynamically adjusting the adjacency weight matrix according to the updated traffic flow time-series data.

[0010] In an implementation manner, dynamically adjusting the adjacency weight matrix includes: configuring static weights for each road according to the historical traffic flow of the main road and the branch road; dividing the real-time traffic flow and the predicted traffic flow of the road by the maximum traffic flow of the road respectively, and performing dimensionless conversion to interval values in the range of [0, 1] to obtain a real-time traffic flow coefficient and a predicted traffic flow coefficient; configuring weight coefficients for different traffic time periods, and performing weighted calculation on the static weights, the real-time traffic flow coefficient, and the predicted traffic flow coefficient according to the weight coefficients to obtain the adjacency weight of each road section, and constructing the adjacency weight matrix.

[0011] In an implementation manner, according to the change of the main-branch priority and the road network topology structure, the phase difference and time window of the main road and the branch road are adjusted and optimized to obtain a regional green wave scheduling strategy, including: evaluating the vehicle platoon propagation speed in the road within a preset time period according to the real-time traffic flow and the predicted traffic flow of the road; obtaining the priorities of the main road and the branch road from the dynamic adjacency weight matrix, and calculating the phase difference between adjacent intersection roads according to the priorities of the main road and the branch road and the vehicle platoon propagation speed; optimizing the green light time window of the main road and the branch road according to the traffic flow prediction result to ensure the continuity of the green wave band; obtaining the regional green wave scheduling strategy according to the phase difference and the green light time window.

[0012] In an implementation manner, obtaining the regional green wave scheduling strategy further includes: screening target scheduling roads according to the dynamic adjacency weight matrix, where the target scheduling roads are roads whose priorities meet a preset threshold; performing multi-cross partition of the main-branch based on the distribution of the target scheduling roads; verifying the execution state partition of the regional target green wave band through the tracking difference between the real-time traffic flow and the predicted traffic flow of the road. When the regional target green wave band is not met, the adjacency weight matrix is reset for optimizing and adjusting the regional green wave scheduling strategy, where the optimization and adjustment of the regional green wave scheduling strategy include dynamic adjustment of the phase difference and the green light time window; when the regional target green wave band is met, evaluating and verifying the regional global green wave band based on the real-time traffic flow of the road.

[0013] In the second aspect of the embodiments of the present application, a regional green wave scheduling system based on traffic flow prediction is provided. The system includes: a topology construction module configured to extract road vectors, traffic facility data, and POI information within a region and construct a road network topology, where the road network topology includes main roads and branch roads; a road traffic flow prediction module configured to collect real-time road traffic flow based on the road network topology and use a traffic flow prediction model with POI information as input to perform traffic flow prediction to obtain predicted road traffic flow, where the traffic flow prediction model is trained and converged using historical data; a weight matrix acquisition module configured to perform data alignment based on the real-time road traffic flow and the predicted road traffic flow and construct a dynamic adjacency weight matrix to reflect the change in the priority of the main - branch roads; a scheduling strategy acquisition module configured to, based on the change in the priority of the main - branch roads and in combination with the road network topology, adjust and optimize the phase difference and time window of the main roads and branch roads to obtain a regional green wave scheduling strategy.

[0014] In the third aspect of the embodiments of the present application, a computer - readable storage medium is provided, storing a computer program, where the computer program is used to execute the regional green wave scheduling method based on traffic flow prediction provided by the present application.

[0015] It is intended to solve the technical problem in the prior art that the traffic scheduling system lacks dynamic response to real - time traffic flow and predicted traffic flow, and cannot effectively adjust the green wave band strategy according to the change in traffic flow, resulting in low traffic efficiency and congestion during peak hours. The regional green wave scheduling method based on traffic flow prediction, through the combination of real - time traffic flow data collection and a predicted traffic flow model, dynamically adjusts the priority, phase difference, and green light time window of road signals, realizes the optimized scheduling of the regional green wave band, significantly improves traffic fluency, and reduces traffic congestion.

[0016] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the description. And in order to make the above and other purposes, features, and advantages of the present application more obvious and understandable, the specific embodiments of the present application are hereinafter specifically exemplified. Brief Description of the Drawings

[0017] To more clearly illustrate the technical solutions of the embodiments of the present disclosure, the accompanying drawings of the embodiments of the present disclosure will be briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the systems according to the embodiments of the present application. It should be understood that the operations described above or below do not necessarily need to be executed precisely in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more steps can be removed from these processes.

[0018] Figure 1 It is a schematic flowchart of the regional green wave scheduling method based on traffic flow prediction provided by the embodiments of the present application;

[0019] Figure 2 It is a schematic flowchart of constructing a road network topology for the regional green wave scheduling method based on traffic flow prediction provided by the embodiments of the present application;

[0020] Figure 3 It is a schematic structural diagram of the regional green wave scheduling system based on traffic flow prediction provided by the embodiments of the present application.

[0021] Explanation of reference numerals: topology construction module 11, road traffic flow prediction module 12, weight matrix acquisition module 13, scheduling strategy acquisition module 14. Detailed implementation manners

[0022] The above description is only an overview of the technical solutions of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the description. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the following specifically gives the detailed implementation manners of the present application.

[0023] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations of the present application. All other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present application.

[0024] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments. However, it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict. The terms "first" and "second" are only used to distinguish similar objects and do not represent a specific order of the objects. The terms "comprising" and "having", and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server that comprises a series of steps or units need not be limited to those steps or units clearly listed, but may include other steps or modules not clearly listed or inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application.

[0025] Embodiment 1, as Figure 1 shown, the embodiment of the present application provides a regional green wave scheduling method based on traffic flow prediction, and the method includes:

[0026] Extracting the road vectors, traffic facility data and POI information in the region, and constructing a road network topology structure, where the road network topology structure includes main roads and branch roads; collecting the real-time traffic flow of the roads based on the road network topology structure, and using a traffic flow prediction model with the POI information as the input to perform traffic flow prediction to obtain the predicted traffic flow of the roads, where the traffic flow prediction model is trained and converged using historical data.

[0027] Extract the road vector, traffic facility data, and POI information within the extraction area. The road vector data is the vector data of all roads within the area extracted from map data, including the geometric shape, number of lanes, and turning restrictions of each road. POI stands for "Point of Interest", which refers to a location on the map with specific geographical coordinates. The traffic facility data is obtained by collecting the specific information of traffic facilities within the area, including the location and attribute information of traffic lights, isolation fences, bus stops, crosswalks, cameras, etc. The POI information is the name, category, address, etc. of important locations such as shopping malls, schools, and hospitals within the area. Construct a road network topology structure based on the extracted information. The road network topology structure includes main roads and branch roads. Further, collect the real-time traffic flow of the roads based on the road network topology structure, and perform traffic flow prediction with the POI information as the input based on the constructed traffic flow prediction model to predict the traffic flow of each road within a certain period in the future and obtain the predicted road traffic flow. Among them, the traffic flow prediction model is trained and converged using historical data. When constructing the traffic flow prediction model, according to the POI information recorded in the historical data and the traffic flow data of the roads affected by the corresponding POI information within a certain period in the future. Further, use the POI information in the historical data as training data and the traffic flow change data of the roads affected by the corresponding POI information within a certain period in the future as supervised data to supervise and train the neural network model, so as to obtain the traffic flow change data of each affected road predicted by the model. Further, sum up the traffic flow data of each affected road to obtain the predicted road traffic flow.

[0028] As Figure 2 shown, the method provided by the embodiment of the present application further includes: extracting the vector data of all roads within the area from map data, including road geometric shapes, number of lanes, and turning restrictions; collecting the traffic facility data within the area, including the location and attribute information of traffic lights, isolation fences, bus stops, crosswalks, cameras; obtaining the name, category, coordinates, address data, service radius, peak hours, and event data of POI points within the area, and establishing the POI information; defining the road network as a directed graph, and extracting nodes and edges according to the vector data of all roads, traffic facility data, and POI information according to the positioning relationship to construct the road network topology structure.

[0029] Construct a road network topology structure, including: Extract the vector data of all roads in the region from the geographical information system in the map data, including road geometry, number of lanes, and turning restrictions. The geometry of the road includes the starting point, ending point, curves, intersections, etc. of the road. For each road, extract its number of lanes information. The number of lanes is crucial for traffic flow prediction and green wave scheduling because roads with different numbers of lanes require different scheduling strategies. Some roads have turning restrictions. For example, at certain intersections, only left turns or right turns may be allowed. These information need to be extracted through vector data so that the impact of turning behavior on traffic flow can be considered during subsequent traffic flow prediction and scheduling. Collect traffic facility data in the region, including the location and attribute information of traffic lights, isolation fences, bus stops, crosswalks, and cameras. Obtain the name, category, coordinates, address data, service radius, peak hours, and event data of POIs in the region, and establish the POI information. The service radius is the area covered by the POI, and the event data is the event information frequently occurring for the POI object, such as events that will affect the traffic flow like school dismissal, concert performances, etc. The peak hours are the peak time periods with large traffic volumes, such as morning rush hour, evening rush hour, etc. Finally, after integrating all the above information, construct the road network topology structure through a directed graph. Extract nodes and edges according to the vector data of all roads, traffic facility data, and POI information according to the positioning relationship, and construct the road network topology structure.

[0030] The method provided by the embodiment of the present application further includes: Identify road intersections, merge / split points, and define nodes; According to the road vector data, define the connection relationship between each node as an edge, where the number of lanes, speed limit, and turning restriction of each edge define the edge attributes; According to the road geometric connection relationship, connect the nodes, edges, and edge attributes to construct the road network topology structure, and perform attribute marking according to the positioning relationship of the traffic facility data and POI information.

[0031] Extracting nodes and edges according to the vector data of all roads, traffic facility data, and POI information according to the positioning relationship to construct the road network topology structure includes: Identifying the road intersections, merge / split points therein, and defining nodes. The road intersection is the location where two or more roads intersect. Merge means that multiple roads converge into one road, and the split point is the location where one road branches out into multiple roads. Define the road intersections, merge / split points as nodes. Subsequently, define the connection relationship between nodes according to the vector data of the road as an edge. Among them, the number of lanes, speed limit, and turning restriction of each edge define the edge attributes. Exemplarily, a certain section of the road from node X to node Y can be defined as edge XY; this edge XY has two-way 4 lanes, a speed limit of 50 kilometers per hour, and there is a turning restriction at node Y, that is, a left turn is prohibited. The above information will be clearly recorded as the attributes of edge XY in the road network topology structure.

[0032] Furthermore, after defining the nodes and edges, based on the geometric connection relationships of the actual roads, connect the above nodes and edges according to the actual spatial position relationships of the roads to form a complete, clear, and orderly directed graph. And according to the spatial positioning relationships, further mark the attributes of the nodes and edges in the road network with traffic facility data such as traffic lights, bus stops, crosswalks, cameras, and POI information such as shopping malls, hospitals, schools, etc. Suppose there is a shopping mall near node Z, and there are traffic lights and crosswalks at this intersection. When defining node Z, mark these attribute information so that the subsequent traffic flow prediction model can perform more accurate prediction and analysis.

[0033] The method provided by the embodiment of the present application further includes: defining the determination rules for main roads and branch roads according to the number of lanes; performing road grade determination on the number of lanes of each lane according to the determination rules to determine that the road grade is a main lane or a branch lane, and marking the main roads and branch roads on the road network topology according to the road grade.

[0034] When constructing the road network topology, it also includes: after clarifying the basic structure and attributes of the nodes and edges, it is necessary to define the determination rules for the main roads or branch roads of the roads according to the number of lanes. Main road determination rule: Roads with four or more lanes in both directions are defined as main roads. Branch road determination rule: Roads with less than four lanes in both directions are defined as branch roads. According to the defined determination rules, analyze the number of lanes of all edges, that is, roads, in the road network structure one by one, complete the classification after road grade determination, so as to determine that the road grade is a main lane or a branch lane, and mark the main roads and branch roads on the road network topology according to the road grade. Thus, a complete, accurate, and orderly road network topology is formed. This refined structure lays a solid data and structure foundation for the next step of real-time traffic flow data collection, traffic flow prediction, and regional green wave traffic dispatching strategy based on dynamic adjustment, making the subsequent traffic dispatching more accurate, efficient, and reliable.

[0035] Align the data according to the real-time traffic flow and the predicted traffic flow of the road, construct a dynamic adjacency weight matrix to reflect the change of the priority of the main - branch; combine the change of the priority of the main - branch with the road network topology, and adjust and optimize the phase difference and time window of the main and branch to obtain the regional green wave dispatching strategy.

[0036] Align the data based on the real-time road traffic flow and the predicted road traffic flow, so that the real-time traffic flow data and the predicted traffic flow data are synchronized in time series, ensuring that the data has the same time dimension. Furthermore, construct a dynamic adjacency weight matrix to reflect the priority changes between the main roads and the branch roads. The dynamic adjacency weight matrix records the adjacency weight values of each road. Finally, based on the priority changes between the main roads and the branch roads and in combination with the road network topology, recalculate the phase differences of the main roads and the branch roads, and use the predicted road traffic flow to adjust and optimize the green light time window to obtain a regional green wave scheduling strategy. This solves the technical problem in the prior art that the traffic scheduling system lacks dynamic response to real-time traffic flow and predicted traffic flow, and cannot effectively adjust the green wave band strategy according to the changes in traffic flow, resulting in low traffic efficiency and congestion during peak hours. The regional green wave scheduling method based on traffic flow prediction dynamically adjusts the priority, phase difference, and green light time window of road signals through the combination of real-time traffic flow data collection and predicted traffic flow models, realizes the optimized scheduling of the regional green wave band, significantly improves traffic fluency, and reduces traffic congestion.

[0037] The method provided by the embodiment of the present application further includes: aligning the time series of traffic flow data according to the time relationship between the real-time road traffic flow and the predicted road traffic flow; setting the update frequencies of the real-time road traffic flow and the predicted road traffic flow, configuring a sliding window based on the update frequencies, and updating the traffic flow time series data according to the sliding window; dynamically adjusting the adjacency weight matrix according to the updated traffic flow time series data.

[0038] Aligning the data according to the real-time road traffic flow and the predicted road traffic flow and constructing a dynamic adjacency weight matrix includes: aligning the time series of traffic flow data according to the time relationship between the real-time road traffic flow and the predicted road traffic flow. The real-time traffic flow refers to the road traffic flow data collected in real time through devices such as sensors and cameras, usually collected at regular time intervals such as every 1 minute or every 5 minutes. Align the real-time road traffic flow and the predicted road traffic flow in time. Subsequently, set the update frequencies of the real-time road traffic flow and the predicted road traffic flow, such as updating the data every 5 minutes or every 30 seconds. Further, set the size of the sliding window according to the update frequency. Exemplarily, when the update frequency is 5 minutes, the size of the sliding window can be set to 30 minutes. The sliding window will gradually slide within a 30-minute time range to update the traffic flow data within this period. The current window is the real-time traffic flow data of the past 30 minutes. As time goes by, the sliding window will slide from the data of 00:00 - 00:30 to the data of 00:05 - 00:35, ensuring that each window contains the latest traffic information. Finally, dynamically adjust the adjacency weight matrix according to the updated traffic flow time series data.

[0039] The method provided by the embodiments of the present application further includes: configuring static weights for each road according to the historical traffic flow of the main roads and branch roads; dividing the real-time traffic flow and the predicted traffic flow of the road by the maximum traffic flow of the road respectively, and performing dimensionless conversion to interval values in the range of [0, 1] to obtain a real-time traffic flow coefficient and a predicted traffic flow coefficient; configuring weight coefficients for different traffic time periods, and performing weighted calculation on the static weights, real-time traffic flow coefficients, and predicted traffic flow coefficients according to the weight coefficients to obtain the adjacency weights of each road section, and constructing the adjacency weight matrix.

[0040] Dynamically adjusting the adjacency weight matrix includes: before constructing the dynamic adjacency weight matrix, configuring a static weight for each road, and the static weight is set according to the attributes of the road, i.e., the main road or the branch road, and the historical traffic flow. The weight of the main road will be higher than that of the branch road, and the weight of the road with a large traffic flow is also higher than that of the road with a small traffic flow, because the main road bears more traffic flow and is usually a more prioritized road in traffic scheduling. Subsequently, for each road, obtain its maximum traffic flow, and then divide the real-time traffic flow and the predicted traffic flow by the maximum traffic flow of the road respectively, so as to convert the real-time traffic flow and the predicted traffic flow into dimensionless coefficients with interval values in the range of [0, 1], and obtain a real-time traffic flow coefficient and a predicted traffic flow coefficient. For example, if the maximum traffic flow of a certain road is 1000 vehicles per hour and the current real-time traffic flow is 500 vehicles per hour, then the real-time traffic flow coefficient is 500 / 1000 = 0.5. If the predicted traffic flow of this road is 700 vehicles per hour, then the predicted traffic flow coefficient is 700 / 1000 = 0.7. Finally, configure weight coefficients for different traffic time periods, and the weight coefficients of the traffic time periods are weight configuration parameters for the static weights, real-time traffic flow coefficients, and predicted traffic flow coefficients at different times. The specific weight coefficients can be set based on the actual time periods. For example, at midnight, the influence ability of the predicted traffic flow on the overall traffic flow is relatively small, so the weight coefficient of the predicted traffic flow can be reduced. Another example is that during the school dismissal period in the school area, the influence ability of the predicted traffic flow on the overall traffic flow is relatively large, so the weight coefficient of the predicted traffic flow can be increased. Perform weighted calculation on the static weights, real-time traffic flow coefficients, and predicted traffic flow coefficients according to the weight coefficients to obtain the adjacency weights of each road section, and the adjacency weights are used to measure the comprehensive traffic-carrying capacity and priority of the corresponding road. Construct the adjacency weight matrix according to the adjacency weights of each road section.

[0041] The method provided by the embodiments of this application further includes: evaluating the platoon propagation speed on a road within a preset time period according to the real-time traffic flow and the predicted traffic flow of the road; obtaining the priorities of the main roads and branch roads from the dynamic adjacency weight matrix, and calculating the phase difference between adjacent intersection roads according to the priorities of the main roads and branch roads and the platoon propagation speed; optimizing the green light time windows of the main roads and branch roads according to the traffic flow prediction results to ensure the continuity of the green wave band; and obtaining the regional green wave scheduling strategy according to the phase difference and the green light time window.

[0042] Adjust and optimize the phase difference and time window of the main roads and branch roads according to the change of the priority of the main-branch combination and the road network topology structure to obtain the regional green wave scheduling strategy, including: evaluating the platoon propagation speed on a road within a preset time period according to the real-time traffic flow and the predicted traffic flow of the road. The platoon propagation speed is calculated based on the current traffic flow data obtained by devices such as sensors and cameras and the future traffic flow data calculated by a traffic flow prediction model. Further, calculate the average speed of the platoon passing through each section within the preset time period, and then obtain the platoon propagation speed according to the average speed. When the platoon propagation speed is determined, obtain the priorities of the main roads and branch roads from the dynamic adjacency weight matrix, and the priority is the adjacency weight value of the corresponding road in the dynamic adjacency weight matrix. Then, calculate the phase difference between adjacent intersection roads according to the priorities of the main roads and branch roads and the platoon propagation speed. The phase difference refers to the time difference between the signal light switches of two adjacent intersections, that is, the time difference between the green light of one intersection and the green light of the next intersection. A reasonable phase difference can ensure that when a vehicle passes through multiple intersections, the green lights are continuous, avoiding red light interference, thereby improving the traffic efficiency. The formula for calculating the phase difference is the result of dividing the road length by the platoon propagation speed minus the green light time of the previous intersection multiplied by 1 plus the difference in the road priorities of the red and green light intersections. Further, optimize the green light time windows of the main roads and branch roads according to the traffic flow prediction results to ensure the continuity of the green wave band. The green light time window is set correspondingly based on the traffic flow prediction result. The larger the traffic flow prediction result, the longer the green light time window of the corresponding road to meet the driving of high-flow vehicles. Specifically, a corresponding table of the vehicle flow in each lane and the green light time window can be set, and the green light time window can be determined based on the corresponding table. The green light time window is the duration of the green light at the road intersection. Finally, obtain the regional green wave scheduling strategy according to the phase difference and the green light time window.

[0043] The method provided by the embodiment of the present application further includes: screening target scheduling roads according to the dynamic adjacency weight matrix, where the target scheduling roads are roads whose priorities meet a preset threshold; performing main-trunk and branch-trunk multi-intersection zoning based on the distribution of the target scheduling roads; verifying the execution status zoning of the regional target green wave band through the tracking difference between the real-time traffic flow and the predicted traffic flow of the roads. When the regional target green wave band is not satisfied, reset the adjacency weight matrix to optimize and adjust the regional green wave scheduling strategy, where the optimization and adjustment of the regional green wave scheduling strategy includes dynamic adjustment of the phase difference and the green light time window; when the regional target green wave band is satisfied, perform evaluation and verification of the regional global green wave band based on the real-time traffic flow of the roads.

[0044] Obtaining the regional green wave scheduling strategy further includes: screening target scheduling roads according to the dynamic adjacency weight matrix, where the target scheduling roads are roads whose priorities meet a preset threshold, that is, the priority parameter is greater than or equal to the preset priority threshold. These roads are the key objects of the green wave band scheduling to ensure that the traffic fluency of these roads can be optimized. Based on the distribution of the target scheduling roads, perform main-trunk and branch-trunk multi-intersection zoning, where the main-trunk and branch-trunk multi-intersection zoning is: taking the intersections of the target scheduling roads as nodes, and dividing them into several relatively independent optimization control regions according to the mutual relationship between the main roads and the branch roads.

[0045] Furthermore, by comparing the tracking difference between the real-time traffic flow and the predicted traffic flow on the road, the actual implementation of the target green wave band is judged. The tracking difference is the difference between the real-time traffic flow value and the predicted traffic flow value, which is used to evaluate the effectiveness of the current traffic control strategy. For example, if the predicted traffic flow shows that the "Central Avenue" should be 1,200 vehicles per hour during the morning rush hour, while the real-time traffic flow shows 1,400 vehicles per hour, a difference of 200 vehicles is generated, indicating that the actual traffic pressure exceeds the prediction and the current signal strategy needs to be optimized and adjusted. The execution status of the regional target green wave band is verified according to the tracking difference, and it is judged whether the tracking difference is less than or equal to the preset tracking difference value. When it is less, it means that the traffic pressure is small and the regional target green wave band can be satisfied; otherwise, the traffic pressure is large and the regional target green wave band cannot be satisfied. When the regional target green wave band is not satisfied, the latest real-time traffic flow data is collected again, the output of the traffic flow prediction model is updated, and the dynamic adjacency weight matrix is reset. The road priority is recalculated according to the new data. Exemplarily, during the school dismissal period, the measured traffic flow and the predicted traffic flow on the branch roads are close to saturation. The dynamic adjacency weight matrix is dynamically increased to 0.6 based on the updated data, which is significantly higher than the main road priority. At this time, the corresponding green light time window is obtained based on the traffic flow data, and the main road green wave bandwidth is compressed: the main road green wave bandwidth is adjusted from 60 seconds to 57 seconds according to the traffic flow data to balance the traffic flow between the main road and the branch roads. According to the phase difference and the green light time window, the regional green wave scheduling strategy is obtained to ensure the priority of the branch road vehicles. The green wave scheduling strategy is a linkage adjustment strategy set according to the obtained phase difference and the green light time window of the corresponding cross road. For example, if the phase difference is 50 seconds, the green light start time interval of the corresponding adjacent road should be 50 seconds to ensure that vehicles can pass through adjacent intersections quickly and efficiently. By dynamically adjusting the phase difference and the green light time window of the roads in the region, the execution effect of the green wave band is optimized. Among them, the optimization and adjustment of the regional green wave scheduling strategy include the dynamic adjustment of the phase difference and the green light time window. When the regional target green wave band is satisfied, it means that the current implemented green wave scheduling strategy has a significant effect, and the existing plan is maintained and executed stably. And the regional global green wave band evaluation and verification are carried out based on the real-time traffic flow on the road, that is, the traffic flow data is monitored in real time and the status partition verification is looped.

[0046] The technical solution provided by the embodiments of the present invention constructs a road network topology by extracting road vectors, traffic facility data, and POI information within a region. The road network topology includes main roads and branch roads. Based on the road network topology, real-time road traffic flow is collected, and a traffic flow prediction model is used with POI information as the input for traffic flow prediction to obtain predicted road traffic flow, where the traffic flow prediction model is trained and converged using historical data. Data alignment is performed based on the real-time road traffic flow and the predicted road traffic flow to construct a dynamic adjacency weight matrix, reflecting the priority change between the main road and the branch road. Based on the priority change between the main road and the branch road and in combination with the road network topology, phase difference and time window adjustment and optimization are performed on the main road and the branch road to obtain a regional green wave scheduling strategy. This solves the technical problem in the prior art that the traffic scheduling system lacks dynamic response to real-time traffic flow and predicted traffic flow, and cannot effectively adjust the green wave band strategy according to the change of traffic flow, resulting in low traffic efficiency and congestion during peak hours. The regional green wave scheduling method based on traffic flow prediction combines real-time traffic flow data collection with a predicted traffic flow model to dynamically adjust the priority, phase difference, and green light time window of road signals, achieving optimized scheduling of the regional green wave band, significantly improving traffic smoothness, and reducing traffic congestion.

[0047] Embodiment 2, based on the same inventive concept as the regional green wave scheduling method based on traffic flow prediction in the foregoing embodiment, as Figure 3 shown, the present application provides a regional green wave scheduling system based on traffic flow prediction. The system in the embodiments of the present application and the method embodiments are based on the same inventive concept. Among them, the system includes: a topology construction module 11, configured to extract road vectors, traffic facility data, and POI information within a region to construct a road network topology, where the road network topology includes main roads and branch roads; a road traffic flow prediction module 12, configured to collect real-time road traffic flow based on the road network topology, and use a traffic flow prediction model with POI information as the input for traffic flow prediction to obtain predicted road traffic flow, where the traffic flow prediction model is trained and converged using historical data; a weight matrix acquisition module 13, configured to perform data alignment based on the real-time road traffic flow and the predicted road traffic flow to construct a dynamic adjacency weight matrix, reflecting the priority change between the main road and the branch road; a scheduling strategy acquisition module 14, configured to perform phase difference and time window adjustment and optimization on the main road and the branch road based on the priority change between the main road and the branch road in combination with the road network topology to obtain a regional green wave scheduling strategy.

[0048] Next, the specific configuration of the topology construction module 11 will be described in detail. The topology construction module 11 may further include: extracting vector data of all roads within the area from map data, including road geometries, number of lanes, and turning restrictions; collecting traffic facility data within the area, including the positions and attribute information of traffic lights, isolation fences, bus stops, crosswalks, and cameras; obtaining the names, categories, coordinates, address data, service radii, peak hours, and event data of POI points within the area, and establishing the POI information; defining the road network as a directed graph, and extracting nodes and edges according to the vector data of all roads, traffic facility data, and POI information according to the positioning relationship to construct the road network topology structure.

[0049] Next, the specific configuration of the topology construction module 11 will be described in detail. The topology construction module 11 may further include: extracting nodes and edges according to the vector data of all roads, traffic facility data, and POI information according to the positioning relationship to construct the road network topology structure, including: identifying road intersections, merge / split points, and defining nodes; defining the connection relationships between the nodes according to the road vector data as edges, where the number of lanes, speed limit, and turning restrictions of each edge define the edge attributes; connecting the nodes, edges, and edge attributes according to the road geometric connection relationship to construct the road network topology structure, and performing attribute marking according to the positioning relationship of the traffic facility data and POI information.

[0050] Next, the specific configuration of the topology construction module 11 will be described in detail. The topology construction module 11 may further include: constructing the road network topology structure, and further including: defining the determination rules for main roads and branch roads according to the number of lanes; determining the road grades of each lane according to the determination rules to determine whether the road grade is a main lane or a branch lane, and marking the main roads and branch roads on the road network topology structure according to the road grades.

[0051] Next, the specific configuration of the weight matrix acquisition module 13 will be described in detail. The weight matrix acquisition module 13 may further include: aligning the data according to the real-time road traffic flow and the predicted road traffic flow to construct a dynamic adjacency weight matrix, including: performing time-series alignment of the traffic flow data according to the time relationship between the real-time road traffic flow and the predicted road traffic flow; setting the update frequencies of the real-time road traffic flow and the predicted road traffic flow, configuring a sliding window based on the update frequencies, and updating the traffic flow time-series data according to the sliding window; dynamically adjusting the adjacency weight matrix according to the updated traffic flow time-series data.

[0052] Next, the specific configuration of the weight matrix acquisition module 13 will be further described in detail. The weight matrix acquisition module 13 further includes: dynamically adjusting the adjacency weight matrix, including: configuring the static weights of each road according to the historical traffic flow of the main roads and branch roads; dividing the real-time traffic flow and the predicted traffic flow of the road by the maximum traffic flow of the road respectively, and performing dimensionless conversion to interval values in the range of [0, 1] to obtain the real-time traffic flow coefficient and the predicted traffic flow coefficient; configuring the weight coefficients for different traffic time periods, and performing weighted calculations on the static weights, the real-time traffic flow coefficient, and the predicted traffic flow coefficient according to the weight coefficients to obtain the adjacency weights of each road section, and constructing the adjacency weight matrix.

[0053] Next, the specific configuration of the scheduling strategy acquisition module 14 will be described in detail. The scheduling strategy acquisition module 14 may further include: adjusting and optimizing the phase difference and time window of the main roads and branch roads according to the change of the priority of the main - branch and the road network topology structure to obtain the regional green wave scheduling strategy, including: evaluating the platoon propagation speed in the road within a preset time period according to the real-time traffic flow and the predicted traffic flow of the road; obtaining the priorities of the main roads and branch roads from the dynamic adjacency weight matrix, and calculating the phase difference between adjacent intersection roads according to the priorities of the main roads and branch roads and the platoon propagation speed; optimizing the green light time windows of the main roads and branch roads according to the traffic flow prediction result to ensure the continuity of the green wave band; obtaining the regional green wave scheduling strategy according to the phase difference and the green light time window.

[0054] Next, the specific configuration of the scheduling strategy acquisition module 14 will be described in detail. The scheduling strategy acquisition module 14 may further include: obtaining the regional green wave scheduling strategy, further including: screening the target scheduling roads according to the dynamic adjacency weight matrix, where the target scheduling roads are the roads whose priorities meet the preset threshold; performing multi - intersection zoning of the main - branch based on the distribution of the target scheduling roads; verifying the execution status zoning of the regional target green wave band through the tracking difference between the real-time traffic flow and the predicted traffic flow of the road. When the regional target green wave band is not satisfied, reset the adjacency weight matrix to optimize and adjust the regional green wave scheduling strategy, where the optimization and adjustment of the regional green wave scheduling strategy include the dynamic adjustment of the phase difference and the green light time window; when the regional target green wave band is satisfied, perform the evaluation and verification of the regional global green wave band based on the real-time traffic flow.

[0055] The various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0056] Embodiment 3. Based on the same inventive concept as the regional green wave scheduling method based on traffic flow prediction in the foregoing embodiment, this embodiment provides a computer-readable storage medium, which can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the regional green wave scheduling method based on traffic flow prediction in the embodiments of the present application. The processor executes various functional applications and data processing of the computer device by running the software programs, instructions, and modules stored in the memory, that is, implements the above-mentioned regional green wave scheduling method based on traffic flow prediction.

[0057] Note that the above is only a preferred embodiment of the present invention and the technical principles applied. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein. Various obvious changes, re-adjustments, and substitutions can be made by those skilled in the art without departing from the protection scope of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments. Without departing from the inventive concept of the present invention, more other equivalent embodiments can be included, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A regional green wave scheduling method based on traffic flow prediction, characterized in that, Including: Extract the road vector, traffic facility data and POI information within the area, and construct a road network topology structure, where the road network topology structure includes main roads and branch roads; Collect the real-time traffic flow of the roads based on the road network topology structure, and use a traffic flow prediction model with the POI information as the input for traffic flow prediction to obtain the predicted traffic flow of the roads, where the traffic flow prediction model is trained and converged using historical data; Align the data according to the real-time traffic flow and the predicted traffic flow of the roads, and construct a dynamic adjacency weight matrix to reflect the priority change of the main - branch; According to the priority change of the main - branch and combined with the road network topology structure, adjust and optimize the phase difference and time window of the main roads and branch roads to obtain a regional green wave scheduling strategy; Among them, aligning the data according to the real-time traffic flow and the predicted traffic flow of the roads and constructing a dynamic adjacency weight matrix includes: Perform time - series alignment of traffic flow data according to the time relationship between the real-time traffic flow and the predicted traffic flow of the roads; Set the update frequencies of the real-time traffic flow and the predicted traffic flow of the roads, configure a sliding window based on the update frequencies, and update the traffic flow time - series data according to the sliding window; Dynamically adjust the adjacency weight matrix according to the updated traffic flow time - series data; Dynamically adjusting the adjacency weight matrix includes: Configure the static weights of each road according to the historical traffic flow of the main roads and branch roads; Divide the real-time traffic flow and the predicted traffic flow of the roads by the maximum traffic flow of the roads respectively, and perform dimensionless conversion to interval values in the range of [0, 1] to obtain the real-time traffic flow coefficient and the predicted traffic flow coefficient; Configure the weight coefficients for different traffic time periods, and perform weighted calculation on the static weights, real-time traffic flow coefficients, and predicted traffic flow coefficients according to the weight coefficients to obtain the adjacency weights of each road section, and construct the adjacency weight matrix; Among them, according to the priority change of the main - branch and combined with the road network topology structure, adjusting and optimizing the phase difference and time window of the main roads and branch roads to obtain a regional green wave scheduling strategy includes: Evaluate the platoon propagation speed in the roads within a preset time period according to the real-time traffic flow and the predicted traffic flow of the roads; Obtain the priorities of the main roads and branch roads from the dynamic adjacency weight matrix, and calculate the phase difference between adjacent intersection roads according to the priorities of the main roads and branch roads and the platoon propagation speed; Optimize the green light time windows of the main roads and branch roads according to the traffic flow prediction results to ensure the continuity of the green wave band; Obtain the regional green wave scheduling strategy according to the phase difference and the green light time window; 2. The regional green wave scheduling method based on traffic flow prediction according to claim 1, wherein Constructing a road network topology structure includes: Extract the vector data of all roads within the area from the map data, including road geometry, number of lanes, and turning restrictions; Collect the traffic facility data within the area, including the location and attribute information of traffic signal lights, isolation fences, bus stops, crosswalks, and cameras; Obtain the name, category, coordinates, address data, service radius, peak hours, and event data of the POI points within the area, and establish the POI information; Define the road network as a directed graph, and extract nodes and edges according to the vector data of all roads, traffic facility data, and POI information based on the positioning relationship to construct the topological structure of the road network.

3. The regional green wave scheduling method based on traffic flow prediction according to claim 2, characterized in that Extracting nodes and edges according to the vector data of all roads, traffic facility data, and POI information based on the positioning relationship to construct the topological structure of the road network includes: Identify road intersections, confluence / divergence points, and define nodes; According to the road vector data, define the connection relationship between each node as an edge, and define the edge attributes such as the number of lanes, speed limit, and turning restriction for each edge; Connect nodes, edges, and edge attributes according to the road geometric connection relationship to construct the topological structure of the road network, and perform attribute marking according to the positioning relationship of the traffic facility data and POI information.

4. The regional green wave scheduling method based on traffic flow prediction according to claim 3, characterized in that, Constructing the topological structure of the road network further includes: Define the determination rules for main roads and branch roads according to the number of lanes; Judge the road level according to the number of lanes of each lane according to the determination rules, determine the road level as the main lane or the branch lane, and mark the main roads and branch roads on the topological structure of the road network according to the road level.

5. The regional green wave scheduling method based on traffic flow prediction according to claim 1, wherein Obtaining the regional green wave scheduling strategy further includes: According to the dynamic adjacency weight matrix, screen the target scheduling roads, and the target scheduling roads are the roads whose priorities meet the preset threshold; Based on the distribution of the target scheduling roads, perform main-branch multi-cross partitioning; Through the tracking difference between the real-time traffic flow and the predicted traffic flow of the road, the tracking difference is the difference between the real-time traffic flow value and the predicted traffic flow value, which is used to evaluate the effectiveness of the current traffic control strategy, and perform the execution status partitioning verification on the regional target green wave band. Among them, the partitioning verification is to divide the target scheduling roads into several relatively independent optimization control regions according to the mutual relationship between the main roads and the branch roads, and compare whether the tracking difference is within the preset error range. When the regional target green wave band is not met, reset the adjacency weight matrix to optimize and adjust the regional green wave scheduling strategy. Among them, the optimization and adjustment of the regional green wave scheduling strategy include the dynamic adjustment of the phase difference and the green light time window; When the regional target green wave band is met, perform the evaluation and verification of the regional global green wave band based on the real-time traffic flow of the road.

6. Regional green wave scheduling system based on traffic flow prediction, characterized in that, The system is used to implement the regional green wave scheduling method based on traffic flow prediction according to any one of claims 1-5. The system includes: A topological structure construction module for extracting road vectors, traffic facility data, and POI information in the region and constructing a road network topological structure, where the road network topological structure includes main roads and branch roads; A road traffic flow prediction module for collecting the real-time traffic flow of the road based on the topological structure of the road network, and using a traffic flow prediction model with POI information as input to perform traffic flow prediction to obtain the predicted traffic flow of the road, where the traffic flow prediction model is trained and converged using historical data; A weight matrix acquisition module for aligning data according to the real-time traffic flow of the road and the predicted traffic flow of the road, and constructing a dynamic adjacency weight matrix to reflect the priority change of the main-branch; The scheduling strategy acquisition module is used to adjust and optimize the phase difference and time window of the main roads and branch roads according to the priority change of the main roads - branch roads in combination with the road network topology, so as to obtain the regional green wave scheduling strategy.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by a processor, it implements the regional green wave scheduling method based on traffic flow prediction as described in any one of claims 1 - 5.

Images