Urban traffic congestion relief method and system driven by internet of vehicles big data

Abstract

The application relates to the technical field of urban traffic, and provides a vehicle networking big data driven urban traffic congestion relieving method and system.The method comprises the following steps: collecting target area road network distribution, performing road congestion correlation identification based on historical congestion records, and establishing a congestion correlation network; monitoring road traffic data of each road through vehicle networking, identifying congestion lanes and generating congestion degree identification; extracting correlation lanes in the congestion correlation network, identifying signal lights and tidal lane distribution thereof; establishing a traffic flow guiding network, combining the congestion degree, the signal light and the tidal lane distribution, and performing control optimization.The application solves the technical problem that a traditional urban traffic management method cannot effectively identify congestion correlation between roads, leading to congestion diffusion and low relieving efficiency, achieves the technical effect that a congestion correlation network is driven by vehicle networking big data, dynamic control is combined with signal lights and tidal lanes, accurate identification and efficient relief of urban road network congestion are realized, and road passing efficiency is improved.

Description

Technical Field

[0001] This application relates to the field of urban transportation technology, specifically to urban traffic congestion mitigation methods and systems driven by vehicle-to-everything (V2X) big data. Background Technology

[0002] Against the backdrop of accelerating modern urbanization, urban road traffic demand is growing rapidly, and the number of motor vehicles continues to rise. Traffic congestion has become a prominent problem restricting sustainable urban development. Traditional traffic management methods mainly rely on manual experience or fixed-time traffic light timing strategies, lacking real-time perception and dynamic control of complex traffic flow changes, and are difficult to adapt to the ever-changing road network environment and sudden congestion propagation trends. Especially during peak hours or when special events occur, congestion on local road sections can easily spread to surrounding roads through the road network structure, leading to regional or even global traffic paralysis. With the development of vehicle-to-everything (V2X), Internet of Things (IoT), and big data technologies, vehicles can interconnect with road infrastructure through sensors and communication devices, enabling the real-time collection and analysis of massive amounts of traffic flow data. However, existing big data-based traffic management research mostly focuses on congestion detection or traffic light optimization at single points on roads, lacking the identification of overall road network congestion propagation, and is unable to effectively coordinate traffic lights and tidal lane scheduling on related roads, resulting in low efficiency in traffic resource utilization and limited congestion relief effects. Summary of the Invention

[0003] This application provides a method and system for alleviating urban traffic congestion driven by vehicle-to-everything (V2X) big data. It aims to solve the technical problem that traditional urban traffic management methods cannot effectively identify congestion correlations between roads, leading to congestion spread and low alleviation efficiency.

[0004] The first aspect disclosed in this application provides a method for alleviating urban traffic congestion driven by vehicle-to-everything (V2X) big data. The method includes: collecting data on the urban road network distribution within a target area; identifying congestion associations for each road based on historical congestion records to establish a congestion association network; monitoring traffic flow data for each road in the urban road network distribution using a V2X architecture; identifying congested lanes and generating congestion level indicators; extracting associated lanes of the congested lanes from the congestion association network; identifying the distribution of traffic lights and tidal flow lanes in the congested lanes and associated lanes; establishing a traffic flow guidance network for the congested lanes and associated lanes; and performing optimal control of traffic lights and tidal flow lanes based on the congestion level indicators, traffic light distribution, and tidal flow lane distribution.

[0005] Another aspect of this application discloses a vehicle-to-everything (V2X) big data-driven urban traffic congestion mitigation system. The system includes: a congestion association identification module: collecting data on the urban road network distribution within a target area, identifying congestion associations for each road based on historical congestion records, and establishing a congestion association network; a traffic flow monitoring module: monitoring traffic flow data for each road in the urban road network distribution using a V2X architecture, identifying congested lanes and generating congestion level indicators; a lane identification module: extracting associated lanes of the congested lanes from the congestion association network, identifying the congested lanes and the distribution of traffic lights and tidal flow lanes within the associated lanes; and a control optimization module: establishing a traffic flow guidance network for the congested lanes and the associated lanes, and combining the congestion level indicators with the distribution of traffic lights and tidal flow lanes to perform control optimization for traffic lights and tidal flow lanes.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] The aforementioned vehicle-to-everything (V2X) big data-driven urban traffic congestion mitigation method first acquires urban road network information for the target area and combines it with historical congestion data to identify congestion correlations between roads, thereby establishing a congestion correlation network. Then, using V2X, it monitors traffic flow on each road in real time, identifies congested lanes, and marks their congestion levels. Next, it identifies roads associated with congested lanes from the congestion correlation network, and identifies the distribution of traffic lights and tidal flow lanes on these roads. Finally, it constructs a traffic flow guidance network for congested lanes and their associated lanes, comprehensively considering congestion levels, traffic light control, and tidal flow lane distribution, and implements dynamic optimization of traffic light and tidal flow lane regulation to alleviate traffic congestion.

[0008] The above description is merely an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are given below. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 This is a flowchart illustrating a method for alleviating urban traffic congestion driven by vehicle-to-everything (V2X) big data in one embodiment.

[0011] Figure 2This is a diagram of an urban traffic congestion mitigation system architecture driven by vehicle-to-everything (V2X) big data in one embodiment.

[0012] Figure labeling: 11. Congestion association identification module; 12. Traffic flow monitoring module; 13. Lane identification module; 14. Control optimization module. Detailed Implementation

[0013] This application provides a method and system for alleviating urban traffic congestion driven by vehicle-to-everything (V2X) big data. This addresses the technical problem that traditional urban traffic management methods cannot effectively identify congestion correlations between roads, leading to congestion spread and low alleviation efficiency.

[0014] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0015] It should be noted that 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 includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or modules that are not explicitly listed or that are inherent to such process, method, product, or device.

[0016] Example 1, as Figure 1 As shown, this application provides a method for alleviating urban traffic congestion driven by vehicle-to-everything (V2X) big data, the method comprising:

[0017] Collect data on the urban road network distribution within the target area, identify congestion correlations for each road based on historical congestion records, and establish a congestion correlation network.

[0018] In this embodiment, the overall road network distribution within the target area is first comprehensively collected, including basic information such as road geometry, intersection locations, road grades, and the number of lanes, to construct a complete urban road network distribution. Then, for each road in the urban road network, congestion correlation is identified based on its corresponding historical traffic operation data, and the identification results are compared with a preset correlation degree. When the identification results between two roads exceed this preset correlation degree, they are determined to have a significant congestion correlation. Subsequently, these roads with congestion correlation are aggregated, and corresponding nodes and edges are set to establish the final congestion correlation network. This congestion correlation network can clearly reflect the dependence and influence of roads within the target area on congestion propagation, providing a foundation for subsequent real-time monitoring and dynamic control.

[0019] Furthermore, this application provides information on the urban road network distribution within the target area, identifies congestion associations for each road based on historical congestion records, and establishes a congestion association network, including:

[0020] Extract the first congestion record of the first road from the historical congestion records; analyze the congestion propagation relationship based on the first congestion record, identify the distribution of associated roads with a congestion propagation correlation greater than a preset correlation based on the urban road network distribution, and establish the first congestion association network of the first road; add the first congestion association network into the congestion association network.

[0021] Preferably, the process begins by extracting historical congestion records for the target area from the historical congestion database. Then, based on the unique ID of the first road among all roads, the corresponding congestion data is extracted from the historical congestion records as the first congestion record. This first congestion record typically includes information such as the time period of congestion, duration, road operating parameters (e.g., speed, flow rate, density), and congestion range. Subsequently, this first congestion record is used to analyze the congestion propagation effect of the first road in the actual road network. In this process, based on the collected urban road network distribution, other roads connected to or potentially affected by the first road are analyzed one by one, calculating their congestion propagation correlation with the first road. This correlation can be measured using indicators such as time-lag correlation and flow fluctuation consistency. When the congestion propagation correlation of a road exceeds a preset correlation, it is determined that the road has a congestion propagation relationship with the first road, and at this point, the road is included in the associated road distribution. Next, based on the associated roads stored in the associated road distribution, corresponding nodes and edges are set, and a first congestion association network corresponding to the first road is formed based on these nodes and edges. This first congestion association network consists of the first road and all its associated roads that meet the conditions. Finally, the first congestion association network is integrated into the congestion association network of the entire target area, and the above steps are repeated for other roads to gradually improve the congestion association network of the entire target area, thereby providing reliable data support for global congestion monitoring and mitigation strategies.

[0022] Furthermore, this application provides a method for analyzing the propagation relationship of congestion based on the first congestion record, and identifying associated road distributions with a congestion propagation correlation greater than a preset correlation based on the urban road network distribution, including:

[0023] The urban road network distribution is abstracted into a graph structure to generate a road network structure, wherein intersections, the start and end points of roads are nodes, and road segments are edges; the first congestion record is mapped to the road network structure, and the time-delay correlation between the remaining roads in the road network structure and the first road is analyzed, with the time-delay correlation index as the congestion propagation correlation degree; based on the time-delay correlation analysis results, the associated road distribution is established with roads whose congestion propagation correlation degree is greater than a preset correlation degree.

[0024] Optionally, the collected urban road network distribution is first subjected to structured abstraction. This involves abstracting intersections, the starting and ending points of each road as nodes in a graph structure, and the road segments between different nodes as edges, thus generating a complete road network structure. Next, the historical congestion records of the first road are mapped to the corresponding road edges as the starting reference for analysis. Then, time-lag correlation analysis is performed on the remaining roads in the road network structure one by one. In this process, the correlation coefficient is calculated by comparing the traffic state of the first road at a certain moment with the traffic states of other roads after a certain time lag. The maximum value of the correlation coefficient is found by adjusting the lag time, and this maximum value is used as the time-lag correlation index to reflect the degree to which the congestion state of the first road propagates to other roads. Finally, the calculated time-lag correlation index is used as the congestion propagation correlation degree. Roads with a congestion propagation correlation degree greater than a preset correlation degree are selected and identified as having a significant dependency on the first road in congestion propagation. These roads are then included in the distribution of associated roads of the first road, thus providing a data foundation for the subsequent establishment of a congestion correlation network.

[0025] Furthermore, this application provides a time-delay correlation analysis that calculates the correlation between the state of the first road at time t and the state of the remaining roads at time t+Δt, and generates a time-delay correlation index by adjusting the time delay Δt and filtering the correlation coefficient corresponding to the maximum correlation value.

[0026] Optionally, when performing time-lag correlation analysis, traffic operation status data of the first road over a continuous time period, such as vehicle speed, flow rate, and lane occupancy, are first acquired. These status parameters are then organized into a time series format. Simultaneously, the corresponding status parameters of other remaining roads in the road network within the same time range are extracted, forming multiple sets of comparable time series data. Subsequently, for these operation status data, the difference between each data point and its corresponding mean is calculated, and then divided by the corresponding standard deviation to adjust these operation status data to the same dimension. Then, using the status data of the first road at time t as a benchmark, the status data of one of the remaining roads at time t+Δt is selected for Pearson correlation calculation. Here, Δt is a time lag parameter, which can be set from 1 minute to 30 minutes, with an adjustment step size of two minutes, which can be set according to actual needs. For example, when the extracted data for the first road are t, t1, and t2, and Δt is one time unit, the data for the other road are t1, t2, and t3. By calculating the Pearson correlation between these two sets of data, the correlation coefficient between the two roads can be obtained. Then, the time delay parameters are iteratively adjusted, and the corresponding correlation coefficients are calculated to measure the responsiveness of the remaining roads to the congestion state of the first road under different time delays. The maximum correlation coefficient is then selected from all the calculation results; this maximum correlation coefficient represents the strength of the congestion propagation association between the remaining roads and the first road. Finally, this maximum correlation coefficient is defined as the time-delay correlation index and used as the basis for judging the degree of congestion propagation association, determining which remaining roads have a congestion propagation relationship with the first road, and accurately revealing the temporal and propagational nature of congestion states between roads.

[0027] Table 1: Example Table of Running Status Data

[0028]

[0029] As shown above, Table 1 is an example table of operational status data. This table displays the operational status data of Road A and Road B within the same time period, including three indicators: vehicle speed, traffic flow, and lane occupancy rate, providing data support for subsequent time-lag correlation analysis.

[0030] The vehicle-to-everything (V2X) architecture is used to monitor traffic flow data on each road in the city's road network, identify congested lanes, and generate congestion level indicators.

[0031] In one embodiment, real-time traffic flow data is first collected from various roads in the urban road network within the target area, relying on a vehicle-to-everything (V2X) architecture. Vehicles, through installed onboard terminals, GPS positioning devices, and vehicle-to-infrastructure (V2I) communication modules, upload their operational information (including instantaneous speed, acceleration, location, direction of travel, and traffic flow data) to the V2X platform. Simultaneously, roadside monitoring equipment, such as video detectors, geomagnetic sensors, and roadside units (RSUs), also collect traffic flow data, forming the traffic flow data for each road. Subsequently, the collected traffic flow data is analyzed in real time, using speed thresholds and vehicle density thresholds as criteria to determine whether a road is congested. For example, if the average vehicle speed is <30 km / h and the density is ≥30 vehicles / km, the road is considered congested and designated as a congested lane. Subsequently, based on the specific values ​​of average vehicle speed and vehicle density, corresponding congestion level indicators are generated for congested lanes. For example, when 20 km / h ≤ average speed < 30 km / h and 30 vehicles / km ≤ density < 40 vehicles / km, it is considered lightly congested; when 10 km / h ≤ average speed < 20 km / h and 40 vehicles / km ≤ density < 60 vehicles / km, it is considered moderately congested; and when average speed < 10 km / h and 60 vehicles / km ≤ density, it is considered heavily congested. Through these steps, not only can congested lanes within the road network be automatically identified, but quantifiable congestion level data can also be provided for subsequent congestion correlation analysis and optimization of control measures.

[0032] Extract the associated lanes of the congested lane from the congestion association network, and identify the traffic light distribution and tidal lane distribution in the congested lane and the associated lanes.

[0033] In one embodiment, after identifying congested lanes within a target area through vehicle-to-everything (V2X) monitoring, the node corresponding to the congestion lane is located in the congestion association network. Other nodes connected to this node through congestion propagation are then read to obtain related lanes that may be affected or have an impact on it. Subsequently, traffic facility elements are identified in the extracted congested lanes and their related lanes in the road infrastructure database. This involves obtaining the distribution of traffic lights and tidal flow lanes for these lanes, providing a comprehensive understanding of the traffic light control patterns and tidal flow lane usage for the congested lanes and their related lanes. This provides the necessary basic information and environmental parameters for subsequently constructing a traffic flow guidance network and implementing dynamic control.

[0034] Establish a traffic flow guidance network for the congested lanes and the associated lanes, and combine the congestion level indicators with the distribution of traffic lights and tidal flow lanes to perform optimal control of traffic lights and tidal flow lanes.

[0035] In one embodiment, after identifying congested lanes and their associated lanes, a traffic flow guidance network is established according to the direction of vehicle travel to reflect the direction of vehicle flow and their connection relationships. Subsequently, within this traffic flow guidance network, combined with the generated congestion level indicators, traffic light distribution, and tidal lane distribution, iterative simulations are performed on different traffic light timing schemes and tidal lane direction adjustments to evaluate the degree of improvement of each scheme in congestion relief. An optimal set of combined traffic light and tidal lane control schemes is determined, and this scheme is applied to the actual road network to achieve dynamic control and efficient guidance of congested lanes and their associated lanes.

[0036] Furthermore, this application provides a traffic flow guidance network for establishing the congested lanes and the associated lanes, and, in conjunction with the congestion level indicators, traffic light distribution, and tidal flow lane distribution, performs optimized regulation of traffic lights and tidal flow lanes, including:

[0037] For the congested lanes and the associated lanes, lanes are connected according to traffic flow guidance to generate the traffic flow guidance network; according to the traffic light distribution, lanes are divided according to the control lane groups controlled by each traffic light to generate a traffic light-lane group mapping; according to the tidal lane distribution, the current directional status of each tidal lane is detected; based on the traffic light-lane group mapping, the current directional status of each tidal lane, and the congestion level indicator, regulation simulation optimization is performed to generate a congestion mitigation scheme; the regulation of traffic lights and tidal lanes is implemented according to the congestion mitigation scheme.

[0038] Preferably, for the identified congested lanes and their associated lanes, lanes are connected according to the actual driving direction of vehicles on the road network and the reachable path. Each lane is treated as a node, and the traffic flow guidance relationship is treated as directed edges, constructing a traffic flow guidance network that can fully reflect the flow patterns and connectivity of vehicles in and around congested areas. Subsequently, based on the collected traffic light distribution, the lanes controlled by each traffic light are grouped, generating a mapping relationship between traffic lights and lane groups to clarify the actual control range of different traffic lights on traffic flow. Then, based on the positions of each tidal lane recorded in the tidal lane distribution, the status information of roadside units, video surveillance cameras, geomagnetic sensors, etc., at each tidal lane location is obtained to detect the current directional status of each tidal lane and identify whether each tidal lane is in forward or reverse traffic. Finally, the above traffic light-lane group mapping relationship, the directional status of each tidal lane, and the lane congestion level indicators are input into the simulation module to perform regulation optimization in the digital twin model. In this optimization process, the timing parameters of traffic lights and the directional status of tidal lanes are iteratively adjusted to calculate the improvement effect of different schemes on congestion relief. Based on the calculation results, the congestion relief scheme that can reduce the congestion level to or above the preset threshold is selected and sent to the traffic control system. Specifically, the timing of the corresponding traffic lights and the switching of the tidal lane direction are implemented to achieve dynamic control and efficient guidance of congested lanes and their related lanes in the target area.

[0039] Furthermore, this application provides that, during the optimization of the control simulation, the control priority of traffic lights is higher than that of tidal flow lanes.

[0040] Optionally, when performing control simulation optimization, a preset control priority strategy needs to be followed. This control priority strategy stipulates that the control priority of traffic lights is higher than that of tidal lanes. In other words, the timing optimization of traffic lights will be prioritized, and then the direction adjustment of tidal lanes will be performed as needed. In this way, a more efficient traffic congestion relief effect can be achieved while ensuring traffic safety and control stability.

[0041] Furthermore, this application provides a method for optimizing congestion mitigation through simulation based on the traffic light-lane group mapping, the current directional state of each tidal flow lane, and the congestion level indicator, including:

[0042] A road traffic twin is constructed using the traffic light-lane group mapping, the current directional status of each tidal lane, and the congestion level identifier. The pedestrian crossing length of each traffic light in the traffic light distribution is collected to configure a minimum green light time constraint. Under the minimum green light time constraint, the traffic lights are iteratively controlled and optimized through the road traffic twin to determine a first traffic light control scheme that meets the congestion reduction value of a preset threshold, and the congestion mitigation scheme is generated.

[0043] Optionally, based on the mapping relationship between traffic lights and lane groups, the current directional status of each tidal lane, and the congestion level indicators of the lanes, a road traffic twin that can realistically reflect the traffic operation of the target area is constructed. This road traffic twin is a digital simulation model that maps the actual road network structure, traffic light control logic, tidal lane operation direction, and real-time congestion level into the virtual environment, allowing subsequent regulation and optimization to be verified and evaluated in the virtual simulation. Subsequently, the distribution of traffic lights in the target area is analyzed, and the pedestrian crossing length information at each intersection where the traffic lights are located is collected. This pedestrian crossing length information is divided by the preset average safe walking speed of pedestrians to obtain the minimum green light time required to ensure safe pedestrian crossing. The minimum green light time is used as a rigid constraint in the regulation and optimization process to ensure that pedestrian safety is guaranteed under any optimization scheme. Subsequently, under this constraint, the traffic lights are iteratively controlled and optimized using a road traffic twin. This involves dynamically adjusting the green light duration, traffic light switching sequence, and phase coordination methods for each phase, and recording the simulated average vehicle speed, vehicle density, and traffic flow after the adjustments. The difference between the adjusted data (such as average vehicle speed and traffic flow) and the original data is calculated, and the difference between the adjusted and original data is used for the data that should decrease. The calculated differences are then normalized and weighted summed to obtain the congestion reduction values ​​under different control schemes. When the congestion reduction value of a certain scheme reaches or exceeds a preset threshold, this scheme is identified as the first traffic light control scheme and output as a congestion mitigation scheme to guide traffic light control in the actual road network, thereby effectively alleviating road traffic congestion while ensuring pedestrian safety.

[0044] Furthermore, this application provides that after iterative regulation and optimization of traffic lights through the aforementioned road traffic twin, it also includes:

[0045] If the iterative control optimization meets the preset convergence condition, but the congestion reduction value does not meet the preset threshold, a second traffic light control scheme is generated at the convergence point, and the diversion lane of the congested lane is identified in the associated lane; based on the current direction state of each tidal flow lane, the marked tidal flow lane whose current direction is opposite to the direction of entering the diversion lane is located; through the road traffic twin, based on the second traffic light control scheme, the tidal flow lane control scheme that meets the preset threshold is identified by changing the direction state of the marked tidal flow lane; the congestion relief scheme is generated using the second traffic light control scheme and the tidal flow lane control scheme.

[0046] Optionally, during iterative optimization of traffic lights, if the optimization process has met preset convergence conditions, such as convergence of congestion reduction value or maximum number of iterations, but the calculated congestion reduction value still has not reached the set preset threshold, the traffic light control result at the convergence point will be automatically retained and used as the second traffic light control scheme. Subsequently, the topological relationship between congested lanes and their associated lanes will be further analyzed in the established congestion association network to identify diversion lanes that can alleviate some traffic pressure, i.e., those roads that can provide alternative travel paths for vehicles in congested lanes. Then, combining the real-time directional status of each tidal flow lane, tidal flow lanes with directions opposite to the traffic flow direction entering the diversion lanes will be located and marked as controllable objects. Based on the road traffic twin, while keeping the second traffic light control scheme unchanged, the directional status of the marked tidal flow lanes will be dynamically simulated by changing them sequentially, and the congestion reduction value under different adjustment schemes will be evaluated using the same method described above. When a scheme can make the congestion reduction value reach or exceed the preset threshold, the scheme is considered an effective tidal flow lane control scheme. Finally, the second traffic light control scheme is combined with the determined tidal lane control scheme to generate a complete congestion mitigation scheme, which is then sent to the traffic control system to achieve efficient traffic management and overall optimization of congested road sections.

[0047] Furthermore, this application provides a method to change the directional state of the indicated tidal flow lanes, prioritizing the lane with the lowest traffic flow until the congestion reduction value meets a preset threshold.

[0048] Optionally, when adjusting the direction of tidal flow lanes is needed to further alleviate congestion, priority will be given to changing the direction of the tidal flow lane with the lowest traffic volume. This is because changing the direction of low-volume lanes has less disturbance to the overall traffic operation, and can maximize diversion efficiency while ensuring traffic safety and stability. Specifically, all marked adjustable tidal flow lanes will be sorted according to real-time traffic volume, and the direction will be changed one by one starting from the lane with the lowest traffic volume. The adjusted operation will be simulated and calculated in the road traffic twin to evaluate its improvement effect on congestion reduction. When an adjustment scheme is detected to reduce congestion to or above a preset threshold, further direction adjustment will be stopped, and the scheme will be directly identified as the tidal flow lane control scheme, which will form the final congestion relief scheme together with the traffic light control scheme. If the congestion reduction still does not meet the preset threshold after the maximum number of iterations, the adjustment scheme with the largest congestion reduction during the adjustment process will be output as the tidal flow lane control scheme, ensuring that a relatively optimal relief measure can be provided under the existing conditions. This scheme will be combined with the second traffic light control scheme to form a complete congestion relief scheme for actual implementation.

[0049] In summary, the embodiments of this application have at least the following technical effects:

[0050] This application first collects data on the urban road network distribution within the target area, identifies congestion correlations for each road based on historical congestion records, and establishes a congestion correlation network. Then, using a vehicle-to-everything (V2X) architecture, it monitors traffic flow data for each road within the urban road network distribution, identifies congested lanes, and generates congestion level indicators. Next, it extracts associated lanes from the congested lanes within the congestion correlation network, identifies the distribution of traffic lights and tidal flow lanes within the congested lanes and their associated lanes, and finally establishes a traffic flow guidance network for the congested lanes and their associated lanes. Combining the congestion level indicators with the distribution of traffic lights and tidal flow lanes, it optimizes the control of traffic lights and tidal flow lanes. These technical effects collectively solve the problem that traditional urban traffic management methods cannot effectively identify congestion correlations between roads, leading to congestion spread and inefficient mitigation. This achieves the technical effect of using a congestion correlation network driven by V2X big data, combined with dynamic control of traffic lights and tidal flow lanes, to accurately identify and efficiently alleviate urban road network congestion, thereby improving road traffic efficiency.

[0051] Example 2, based on the same inventive concept as the vehicle-to-everything (V2X) big data-driven urban traffic congestion mitigation method described in the previous examples, such as... Figure 2As shown, this application provides a vehicle-to-everything (V2X) big data-driven urban traffic congestion mitigation system. The system includes: a congestion association identification module 11: collecting urban road network distribution within a target area, identifying congestion associations for each road based on historical congestion records, and establishing a congestion association network; a traffic flow monitoring module 12: monitoring traffic flow data for each road in the urban road network distribution through a V2X architecture, identifying congested lanes and generating congestion level indicators; a lane identification module 13: extracting associated lanes of the congested lanes from the congestion association network, identifying the congested lanes and the distribution of traffic lights and tidal lanes in the associated lanes; and a regulation optimization module 14: establishing a traffic flow guidance network for the congested lanes and the associated lanes, and performing regulation optimization of traffic lights and tidal lanes in conjunction with the congestion level indicators, traffic light distribution, and tidal lane distribution.

[0052] Furthermore, the congestion association identification module 11 is also used to perform the following method:

[0053] Extract the first congestion record of the first road from the historical congestion records; analyze the congestion propagation relationship based on the first congestion record, identify the distribution of associated roads with a congestion propagation correlation greater than a preset correlation based on the urban road network distribution, and establish the first congestion association network of the first road; add the first congestion association network into the congestion association network.

[0054] Furthermore, the congestion association identification module 11 is also used to perform the following method:

[0055] The urban road network distribution is abstracted into a graph structure to generate a road network structure, wherein intersections, the start and end points of roads are nodes, and road segments are edges; the first congestion record is mapped to the road network structure, and the time-delay correlation between the remaining roads in the road network structure and the first road is analyzed, with the time-delay correlation index as the congestion propagation correlation degree; based on the time-delay correlation analysis results, the associated road distribution is established with roads whose congestion propagation correlation degree is greater than a preset correlation degree.

[0056] Furthermore, the congestion association identification module 11 is also used to perform the following method:

[0057] Time-delay correlation analysis calculates the correlation between the state of the first road at time t and the state of the remaining roads at time t+Δt. By adjusting the time delay Δt, the correlation coefficient corresponding to the maximum correlation value is selected to generate a time-delay correlation index.

[0058] Furthermore, the regulation optimization module 14 is also used to perform the following method:

[0059] For the congested lanes and the associated lanes, lanes are connected according to traffic flow guidance to generate the traffic flow guidance network; according to the traffic light distribution, lanes are divided according to the control lane groups controlled by each traffic light to generate a traffic light-lane group mapping; according to the tidal lane distribution, the current directional status of each tidal lane is detected; based on the traffic light-lane group mapping, the current directional status of each tidal lane, and the congestion level indicator, regulation simulation optimization is performed to generate a congestion mitigation scheme; the regulation of traffic lights and tidal lanes is implemented according to the congestion mitigation scheme.

[0060] Furthermore, the regulation optimization module 14 is also used to perform the following method:

[0061] When optimizing the control through simulation, the control priority of traffic lights is higher than that of tidal flow lanes.

[0062] Furthermore, the regulation optimization module 14 is also used to perform the following method:

[0063] A road traffic twin is constructed using the traffic light-lane group mapping, the current directional status of each tidal lane, and the congestion level identifier. The pedestrian crossing length of each traffic light in the traffic light distribution is collected to configure a minimum green light time constraint. Under the minimum green light time constraint, the traffic lights are iteratively controlled and optimized through the road traffic twin to determine a first traffic light control scheme that meets the congestion reduction value of a preset threshold, and the congestion mitigation scheme is generated.

[0064] Furthermore, the regulation optimization module 14 is also used to perform the following method:

[0065] If the iterative control optimization meets the preset convergence condition, but the congestion reduction value does not meet the preset threshold, a second traffic light control scheme is generated at the convergence point, and the diversion lane of the congested lane is identified in the associated lane; based on the current direction state of each tidal flow lane, the marked tidal flow lane whose current direction is opposite to the direction of entering the diversion lane is located; through the road traffic twin, based on the second traffic light control scheme, the tidal flow lane control scheme that meets the preset threshold is identified by changing the direction state of the marked tidal flow lane; the congestion relief scheme is generated using the second traffic light control scheme and the tidal flow lane control scheme.

[0066] Furthermore, the regulation optimization module 14 is also used to perform the following method:

[0067] When changing the direction of the indicated tidal lane, priority is given to starting with the lane with the least traffic flow, and the process continues until the congestion reduction value meets a preset threshold.

[0068] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0069] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0070] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. A method for relieving urban traffic congestion driven by Internet of Vehicles big data, characterized in that, The method comprises the following steps: Collect the urban road network distribution in the target area, identify the congestion correlation of each road based on historical congestion records, and establish a congestion correlation network; Through the vehicle networking architecture, the vehicle flow data of each road of the urban road network distribution is monitored to identify the congestion lane and generate a congestion degree identifier; In the congestion correlation network, the correlation lane of the congestion lane is extracted, and the signal light distribution and the tidal lane distribution in the congestion lane and the correlation lane are identified; A vehicle flow guidance network of the congestion lane and the correlation lane is established, and the signal light and the tidal lane are controlled and optimized in combination with the congestion degree identifier, the signal light distribution and the tidal lane distribution, including: For the congestion lane and the correlation lane, the lane connection is performed according to the vehicle flow guidance to generate the vehicle flow guidance network; According to the signal light distribution, each signal light control control lane group is divided to generate a signal light-lane group mapping; According to the tidal lane distribution, the current direction state of each tidal lane is detected; Based on the signal light-lane group mapping, the current direction state of each tidal lane, and in combination with the congestion degree identifier, a congestion relief scheme is generated by control simulation optimization; The congestion relief scheme is used to control the signal light and the tidal lane; Based on the signal light-lane group mapping, the current direction state of each tidal lane, and in combination with the congestion degree identifier, a congestion relief scheme is generated by control simulation optimization, including: A road traffic twin is built with the signal light-lane group mapping, the current direction state of each tidal lane and the congestion degree identifier; Collect the minimum green light time constraint of the sidewalk length configuration of each signal light in the signal light distribution; Under the minimum green light time constraint, the signal light is iteratively controlled and optimized through the road traffic twin to determine a first signal light control scheme in which the congestion degree reduction value meets a preset threshold, and the congestion relief scheme is generated; After the iterative control optimization of the signal light through the road traffic twin, it further comprises: If the iterative control optimization meets a preset convergence condition and the congestion degree reduction value does not meet the preset threshold, a second signal light control scheme at the time of convergence is generated, and a shunt lane of the congestion lane is identified in the correlation lane; According to the current direction state of each tidal lane, an identified tidal lane whose current direction is opposite to the direction of the shunt lane is located; Through the road traffic twin, a tidal lane control scheme meeting the preset threshold is identified by changing the direction state of the identified tidal lane based on the second signal light control scheme; The congestion relief scheme is generated with the second signal light control scheme and the tidal lane control scheme. 2.The IoV big data driven urban traffic congestion mitigation method of claim 1, wherein, Collect the urban road network distribution in the target area, identify the congestion correlation of each road based on historical congestion records, and establish a congestion correlation network, including: Extract the first congestion record of the first road in the historical congestion record; analyzing a propagation relationship of congestion based on the first congestion record, identifying, based on the urban road network distribution, a correlation road distribution in which a congestion propagation correlation degree is greater than a preset correlation degree, and establishing a first congestion correlation network of the first road; adding the first congestion correlation network into the congestion correlation network. 3.The IoV big data driven urban traffic congestion mitigation method of claim 2, wherein, analyzing a propagation relationship of congestion based on the first congestion record, identifying, based on the urban road network distribution, a correlation road distribution in which a congestion propagation correlation degree is greater than a preset correlation degree, and establishing a first congestion correlation network of the first road; abstracting the urban road network distribution into a graph structure to generate a road network structure, in which intersections, starting points and ending points of roads are nodes, and road segments are edges; mapping the first congestion record to the road network structure, analyzing time lag correlation of the remaining roads and the first road in the road network structure, and taking a time lag correlation index as a congestion propagation correlation degree; establishing the correlation road distribution according to a time lag correlation analysis result, in which a road in which a congestion propagation correlation degree is greater than a preset correlation degree. 4.The IoV big data driven urban traffic congestion mitigation method of claim 3, wherein, The time lag correlation analysis calculates a correlation between a state of the first road at time t and a state of the remaining roads at time t+Δt, adjusts a time lag Δt, selects a correlation coefficient corresponding to a maximum correlation value, and generates a time lag correlation index. 5.The IoV big data driven urban traffic congestion mitigation method of claim 1, wherein, In the simulation optimization of regulation and control, the regulation and control priority of the signal lamp is higher than that of the tidal lane. 6.The IoV big data driven urban traffic congestion mitigation method of claim 1, wherein, When changing the direction state of the identified tidal lane, the lane with the smallest traffic flow is preferentially selected until the congestion degree reduction value meets the preset threshold.

7. An Internet of Vehicles big data driven urban traffic congestion mitigation system, characterized in that, The system is used to perform the vehicle networking big data driven urban traffic congestion mitigation method of any one of claims 1-6, and includes: a congestion correlation identification module: collecting urban road network distribution in a target area, identifying congestion correlations of roads based on historical congestion records, and establishing a congestion correlation network; a traffic flow monitoring module: monitoring traffic flow data of roads of the urban road network distribution through a vehicle networking architecture, identifying congestion lanes, and generating congestion degree identifiers; a lane identification module: extracting correlation lanes of the congestion lanes in the congestion correlation network, and identifying signal lamp distribution and tidal lane distribution in the congestion lanes and the correlation lanes; a regulation and control optimization module: establishing a traffic flow guidance network of the congestion lanes and the correlation lanes, combining the congestion degree identifiers and the signal lamp distribution and the tidal lane distribution, and performing regulation and control optimization of the signal lamp and the tidal lane.

Images