Intelligent traffic dynamic green wave control method and system, storage medium and program product

Abstract

The invention provides an intelligent traffic dynamic green wave control method and system, a storage medium and a program product, and relates to the field of traffic control systems.The method comprises the steps that real-time traffic data of all lanes and emergency data published by a traffic management department are obtained; obtaining traffic flow prediction results of different directions of each road section in a future preset time based on a neural network model; outputting the congestion level and the congestion duration of each road section in combination with the emergency situation data and a traffic flow theoretical model, and further determining an adjustment sequence; and on the basis of the traffic flow prediction result, calculating the optimal green wave bandwidth of the signal lamp at each intersection in each target road section by using a particle swarm optimization algorithm to obtain an optimal timing combination scheme of the signal lamp in each target road section, and performing real-time timing control. By implementing the method, the traffic flow can be dredged more efficiently, the parking frequency and delay time of vehicles on the road are reduced, the overall traffic capacity of the urban road is improved, and energy consumption and environmental pollution are reduced.

Description

Technical Field

[0001] This application relates to the field of traffic control systems, and particularly to an intelligent traffic dynamic green wave control method, system, storage medium, and program product. Background Art

[0002] In recent years, with the acceleration of the urbanization process and the continuous increase in the number of motor vehicles, the problem of urban traffic congestion has become increasingly serious, posing great challenges to people's daily travel and the operation efficiency of cities. To relieve urban traffic pressure, various intelligent traffic management technologies have been widely applied. Among them, the green wave control technology, as an effective traffic signal coordination control method, can optimize the signal timing, reduce the number of stops and waiting time of vehicles during driving, improve the traffic efficiency, reduce fuel consumption and exhaust emissions, and has become one of the important research directions in the field of traffic management.

[0003] In related technologies, signal control schemes are usually formulated based on fixed historical traffic data or pre-set traffic flow rules. For example, some green wave control systems statistically analyze the traffic flow of a road section, and combine the geometric structure of the road, the layout of signal lights, and the vehicle running speed to pre-set fixed green wave bandwidths and signal timing schemes. These systems can, to a certain extent, meet the traffic demands during specific time periods, reduce traffic congestion, and improve the overall traffic capacity of the road network.

[0004] However, related technologies mainly rely on historical data or simple statistical rules to formulate signal timing schemes, and it is difficult to cope with the dynamic changes of real-time traffic flow. Especially when sudden traffic conditions (such as traffic accidents, bad weather, or temporary control) occur, the existing schemes lack flexibility and it is difficult to effectively adjust traffic signals, resulting in low road traffic efficiency. Summary of the Invention

[0005] This application provides an intelligent traffic dynamic green wave control method, system, storage medium, and program product, which are used to solve the problem of how to optimize the signal timing of urban road traffic lights and improve the road traffic efficiency.

[0006] In a first aspect, this application provides an intelligent traffic dynamic green wave control method, which is applied to a traffic green wave control system. The method is characterized in that it includes: Obtain the real-time traffic data of each lane and the sudden situation data announced by the traffic management department, where the real-time traffic data is collected by sensors installed at intersections; Input the pre-processed real-time traffic data into a neural network model trained based on historical traffic data and relevant influencing factor data, and output the traffic flow prediction results in different directions of each road section within a preset future time; Input the traffic flow prediction result and the emergency data into a traffic flow theory model, and output the congestion levels and congestion durations in different directions of each road section; Determine the adjustment priorities in different directions of target road sections that meet preset conditions based on the congestion levels and congestion durations, and obtain the adjustment sequences in different directions of each target road section; In the corresponding order of the adjustment sequences, successively calculate the optimal green wave bandwidths of the signal lights at each intersection in each target road section based on the traffic flow prediction result by using the particle swarm optimization algorithm, and obtain the optimal signal timing combination scheme for the signal lights in each target road section; Send the optimal signal timing combination scheme to the traffic signal controller for real-time signal timing control.

[0007] Through the above embodiments, the traffic green wave control system dynamically adjusts the green wave parameters of the signal lights at each intersection in the target road section according to the real-time traffic flow, road conditions and other relevant factors, so as to achieve more efficient traffic flow guidance, reduce the number of vehicle stops and delay time on the road, improve the overall traffic capacity of urban roads, and reduce energy consumption and environmental pollution.

[0008] In some embodiments, the step of calculating the optimal green wave bandwidths of the signal lights at each intersection in each target road section by using the particle swarm optimization algorithm based on the traffic flow prediction result to obtain the optimal signal timing combination scheme for the signal lights in each target road section specifically includes: Determine the constraint conditions of the particle swarm optimization algorithm based on the traffic flow prediction result, the phase difference between the signal lights at each intersection and the preset saturation flow; Construct the objective function of the particle swarm optimization algorithm based on minimizing the average vehicle delay time, the number of stops and the maximum queue length; Calculate the optimal green wave bandwidth according to the constraint conditions and the objective function to obtain the optimal signal timing combination scheme.

[0009] Through the above embodiments, the traffic green wave control system sets constraint conditions and an objective function in the optimization process, takes minimizing the average vehicle delay time, the number of stops and the maximum queue length as the optimization goal, realizes the precise adjustment of traffic signal timing, improves the traffic capacity of the entire road network, and reduces the traffic pressure during peak periods.

[0010] In some embodiments, before the step of determining the constraint conditions of the particle swarm optimization algorithm based on the traffic flow prediction result, the phase difference between the signal lights at each intersection and the preset saturation flow, it further includes: Obtain the first distance values between each intersection in the target road section; Calculate the speed mean value according to the historical driving speeds of the vehicles between each intersection in the target road section; Determine the phase difference between the traffic lights at each intersection within the target section based on the first distance value and the corresponding average speed.

[0011] Through the above embodiments, the traffic green wave control system determines the phase difference between traffic lights by calculating the average speed and the corresponding distance value, which can accurately match the actual traffic conditions, enabling vehicles to pass through the target section at a more efficient speed. At the same time, this technology combines the actual running speed of vehicles, which can better reduce the number of stops and delay time, improving the driving efficiency.

[0012] In some embodiments, the step of determining the phase difference between the traffic lights at each intersection within the target section based on the first distance value and the corresponding average speed specifically includes: Determine the minimum phase difference corresponding to the shortest section based on the first distance value and the average speed; Determine the other phase differences of other sections based on the ratio of the first distance value of other sections within the target section to that of the shortest section, and the other phase differences are integer multiples of the minimum phase difference.

[0013] Through the above embodiments, the traffic green wave control system ensures that the phase difference between traffic lights can meet the requirements of continuous vehicle passage based on the actual road length and speed data, minimizing the parking frequency and delay time of vehicles within the target section to the greatest extent. Through this hierarchical phase difference adjustment method, it can better adapt to the diversity of each section in the road network and improve the overall effect of green wave control.

[0014] In some embodiments, before the step of constructing the objective function of the particle swarm optimization algorithm based on minimizing the average vehicle delay time, the number of stops, and the maximum queue length, it further includes: Determine the peak phase based on the congestion level and congestion duration, and the peak phase includes the peak period and the off-peak period; If the peak phase is the peak period, set the first preset length threshold as the maximum queue length in the objective function, and the maximum queue length includes the first preset length threshold and the second preset length threshold, where the first preset length threshold is less than the second preset length threshold; If the peak phase is the off-peak period, set the first preset number threshold as the number of stops in the objective function, and the number of stops includes the first preset number threshold and the second preset number threshold, where the first preset number threshold is less than the second preset number threshold.

[0015] Through the above embodiments, the traffic green wave control system sets the maximum queue length as the optimization parameter of the objective function for the peak period, which can effectively alleviate the congestion during the traffic peak; while in the off-peak period, the vehicle passing efficiency is further improved through the optimized adjustment of the number of stops. This dynamic phased optimization method effectively adapts to the requirements under different traffic flow conditions, enabling the green wave control scheme to achieve the best effect in each stage. At the same time, based on the flexible adjustment of the objective function, the signal timing plan can be optimized more precisely, reducing the vehicle's stop and delay time, improving the passing efficiency, and reducing fuel consumption and carbon emissions.

[0016] In some embodiments, before the step of determining the adjustment priorities in different directions of the target road section that meets the preset conditions according to the congestion level and congestion duration, the method further includes: Obtain the second distance values between each intersection; Determine the road sections where a continuous preset number of the second distance values are less than or equal to the preset distance threshold as the target road sections that meet the preset conditions.

[0017] Through the above embodiments, the traffic green wave control system calculates the distance between intersections and determines the continuous road sections that meet the preset conditions as the target road sections. This method can better focus on optimizing and adjusting the road sections with greater traffic pressure. It can avoid the dispersion of resources in unnecessary areas, improving the pertinence and priority of signal optimization. At the same time, the dynamic target road section screening mechanism can also adapt to the changes in traffic flow in real time, making the green wave control system more flexible and intelligent, and improving the operation efficiency of the entire road network while alleviating traffic congestion.

[0018] In some embodiments, after the step of sending the optimal timing combination scheme to the traffic signal controller for real-time timing control, the method further includes: Determine the guiding vehicle speed between the adjacent intersections within the target road section according to the optimal timing combination scheme and the distance between the adjacent intersections within the target road section; Send the guiding vehicle speed to the mobile terminals of the drivers at the corresponding positions through the intelligent transportation guidance system for voice prompts.

[0019] Through the above embodiments, the guiding vehicle speed between the adjacent intersections within the target road section is jointly determined by the optimal timing combination scheme and the intersection distance, and is sent to the mobile terminals of the drivers in real time through the intelligent transportation guidance system. This way can effectively guide the drivers to pass through the green wave road sections at a reasonable speed, avoiding stops or delays caused by speed mismatches. In addition, through the voice prompt function, the drivers can obtain driving guidance information more intuitively, reducing decision-making delays and improving driving safety and comfort.

[0020] Second aspect, the present application provides a traffic green wave control system, which includes: one or more processors and a memory; The memory is coupled to the one or more processors. The memory is used to store computer program code, and the computer program code includes computer instructions. The one or more processors call the computer instructions so that the traffic green wave control system can implement an intelligent traffic dynamic green wave control method provided in the above embodiments, which will not be elaborated here.

[0021] Third aspect, the present application provides a computer-readable storage medium, including instructions, characterized in that when the instructions run on a traffic green wave control system, the traffic green wave control system can implement an intelligent traffic dynamic green wave control method provided in the above embodiments, which will not be elaborated here.

[0022] Fourth aspect, the present application provides a computer program product, which, when running on a traffic green wave control system, enables the traffic green wave control system to implement an intelligent traffic dynamic green wave control method provided in the above embodiments, which will not be elaborated here.

[0023] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. By integrating real-time traffic data, historical traffic data, and emergency data, and combining a neural network model and a traffic flow theory model, accurate prediction and dynamic adjustment of future traffic flow are achieved. Compared with the traditional green wave control method that relies on fixed historical data, it significantly improves the flexibility and adaptability of control. Especially when dealing with emergencies such as traffic accidents and bad weather, it can quickly adjust the signal timing plan, reduce congestion time, improve road traffic efficiency, and effectively reduce vehicle fuel consumption and pollution emissions.

[0024] 2. By introducing the particle swarm optimization algorithm, and combining the traffic flow prediction results of the target section, the green wave bandwidth and timing combination plan of the signal lights are dynamically optimized, and the signal light phase difference is adjusted by using the section distance and vehicle speed data. This optimization method based on constraint conditions and objective functions greatly reduces the vehicle delay time, stop times, and queue length, improves the accuracy of green wave control and the dynamic response ability of the system, adapts to complex traffic flow changes, and significantly improves the traffic efficiency and traffic fluency of the target section.

[0025] 3. By integrating the dynamic calculation of the guiding vehicle speed and the intelligent transportation guidance system, the green wave control effect is further optimized and the driving experience is improved. The guiding vehicle speed is generated in real time according to the signal timing plan and the intersection spacing, and is transmitted to the driver through voice prompts, effectively guiding the vehicle to pass through the target section at the optimal speed and avoiding stops and delays. This not only improves the adaptability of the green wave control in the dynamic traffic environment, but also strengthens the interaction between people and vehicles through intelligent means, significantly enhancing driving safety and traffic efficiency, and at the same time reflecting the intelligent development direction of the traffic management system. Brief Description of the Drawings

[0026] Figure 1 is a flowchart of an intelligent traffic dynamic green wave control method in an embodiment of the present application; Figure 2 is another flowchart of an intelligent traffic dynamic green wave control method in an embodiment of the present application; Figure 3 is a schematic structural diagram of an entity device of a traffic green wave control system in an embodiment of the present application. Detailed Embodiments

[0027] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification and appended claims of the present application, the singular forms "a", "an", "the", "above-mentioned", "the foregoing", "this" are intended to include the plural forms as well, unless the context clearly dictates otherwise. It should also be understood that the term "and / or" used in the present application refers to any and all possible combinations including one or more of the listed items.

[0028] Hereinafter, the terms "first" and "second" are used only for descriptive purposes and cannot be construed as implying or suggesting relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present application, unless otherwise specified, the meaning of "a plurality" is two or more.

[0029] For ease of understanding, the method provided in this embodiment is described in terms of a process below. Please refer to Figure 1 , which is a flowchart of an intelligent traffic dynamic green wave control method in an embodiment of the present application.

[0030] S101. Obtain the real-time traffic data of each lane and the emergency data announced by the traffic management department.

[0031] Real-time traffic data is collected through a variety of sensor devices deployed at intersections. Specifically, but not limited to: video detectors capture images of vehicles passing through, which are used to identify information such as traffic flow, vehicle types, and vehicle speeds; geomagnetic detectors are buried under the road surface to detect the magnetic field changes generated when vehicles pass through, and to count traffic flow and occupancy; microwave radar detectors are installed on street lamp poles or signal lamp poles, and can detect the driving status of vehicles all-weather. The data collected by these sensors is preprocessed and then uploaded to the traffic control center. At the same time, the system real-time accesses data on emergencies such as traffic accidents, road construction, major events, and bad weather released by the traffic management department.

[0032] S102. Input the preprocessed real-time traffic data into a neural network model trained based on historical traffic data and relevant influencing factor data, and output the traffic flow prediction results for different directions of each road section within a preset future time.

[0033] The traffic green wave control system preprocesses the collected real-time traffic data, including outlier processing, data standardization, time alignment, etc. Then the processed data is input into a pre-trained deep neural network model. Optionally, the deep neural network model adopts a long short-term memory network (LSTM) structure and is trained through a large amount of historical traffic data. Optionally, the training data includes multi-dimensional information such as traffic flow data, weather data, holiday information, and major event records in the past 3 years. Through training, the deep neural network model can capture the spatio-temporal correlation and periodic change rules of traffic flow.

[0034] In a specific embodiment, the traffic green wave control system takes features such as the traffic flow time series data in the most recent 30 minutes, the historical data in the same period of the current time period, the weather conditions, and the date type. After being processed by a multi-layer neural network, it outputs the traffic flow prediction values for each road section within the next 15 - 30 minutes. The model adopts a sliding time window method and updates the prediction results every 5 minutes.

[0035] S103. Input the traffic flow prediction results and emergency data into a traffic flow theory model, and output the congestion levels and congestion durations for different directions of each road section.

[0036] Specifically, the traffic green wave control system inputs the future traffic flow prediction results output by the neural network model in step S102 and the emergency data (such as traffic accidents, road construction, major events, etc.) released by the traffic management department in real time into the traffic flow theory model for analysis, and outputs the congestion levels and congestion durations for different directions of each road section. Among them, the traffic flow theory model is a type of mathematical model used to describe the operation rules of traffic flow and reveal the internal mechanism of traffic phenomena, including macroscopic traffic flow models (such as the LWR model, PW model, etc.) and microscopic traffic flow models (such as vehicle following models, lane-changing models, etc.).

[0037] In a specific embodiment, it is assumed that on a certain east-west road, the traffic flow prediction results show that the eastbound traffic volume will continue to increase within the next 30 minutes, and there is construction causing the eastbound two-lane to be reduced to a single lane. After inputting this information into the traffic flow theory model, the traffic green wave control system calculates the ratio of the traffic capacity to the traffic demand of this section of the road and outputs that the congestion level in the eastbound direction is "congested", and the expected congestion duration is "45 minutes"; while the westbound direction maintains a "smooth" state.

[0038] It can be understood that the congestion level reflects the traffic operation state of each section of the road, usually divided into multiple levels such as smooth, slow, congested, and severely congested; and the congestion duration represents the length of time that the congestion condition is expected to last from the current moment.

[0039] S104. Determine the adjustment priorities for different directions of the target sections that meet the preset conditions based on the congestion level and congestion duration, and obtain the adjustment sequences for different directions of each target section.

[0040] After obtaining the congestion levels and durations for different directions of each section of the road, the traffic green wave control system selects the sections that meet the preset conditions as the optimization targets and determines the priority order in the signal timing adjustment for these target sections, that is, the adjustment priority and adjustment sequence.

[0041] Specifically, the traffic green wave control system selects the sections whose congestion levels and congestion durations meet the conditions as the optimization targets according to the pre-set screening rules. Optionally, the screening conditions include but are not limited to: the congestion level reaches "congested" or "severely congested", the congestion duration exceeds a certain threshold (such as 30 minutes), is located in a key area or a sensitive section, etc. Then, the traffic green wave control system further analyzes the adjustment priorities for different directions of these target sections. This priority determines the degree of attention and adjustment intensity of the system to different directions of each section in the subsequent signal timing optimization. Optionally, the priority judgment rules are as follows: the direction with a higher congestion level and a longer congestion duration has a higher priority; the key guarantee direction (such as a bus lane) has a higher priority; the entrance and exit directions of important areas (such as a business district, a transportation hub) have a higher priority, etc. The system comprehensively evaluates and sorts the priorities of different directions of each section based on multiple factors, which is not limited here.

[0042] Finally, based on the above analysis results, the traffic green wave control system generates adjustment sequences for different directions of each target road section. Among them, the adjustment sequence stipulates in what order the system adjusts the green wave parameters of each direction of each target road section during the signal timing optimization process. The generation of the sequence follows the principle of descending priority, ensuring that under the condition of limited optimization resources, the demands of the road sections and directions with the greatest congestion pressure can be preferentially met. At the same time, the setting of the sequence also provides an adjustment plan for the green wave coordinated control, reducing mutual influence and conflicts.

[0043] In a specific embodiment, assume that three road sections, namely A, B, and C, are selected as optimization targets. Among them, both the east-west directions of Road Section A are "congested", the south direction of Road Section B is "severely congested" and the north direction is "unobstructed", and the east direction of Road Section C is "congested" and the west direction is "slow-moving". After priority analysis, the adjustment sequence obtained by the system is: south direction of Road Section B > east direction of Road Section A > west direction of Road Section A > east direction of Road Section C > west direction of Road Section C > north direction of Road Section B. This sequence ensures that the road section directions with the most severe congestion can be preferentially adjusted.

[0044] S105. According to the corresponding order of the adjustment sequence, based on the traffic flow prediction results in turn, use the particle swarm optimization algorithm to calculate the optimal green wave bandwidth of the signal lights at each intersection within each target road section, and obtain the optimal signal timing combination plan for the signal lights within each target road section.

[0045] After determining the optimization order of the target road sections, the traffic green wave control system performs optimization calculations on the signal timing for each road section. Specifically, use the particle swarm optimization algorithm to solve the optimal green wave bandwidth and phase difference of the signal lights within each road section, so as to obtain the optimal signal timing combination plan for each road section. Among them, the particle swarm optimization (PSO) algorithm is a heuristic optimization algorithm based on swarm intelligence. By simulating the foraging behavior of bird flocks, it searches for the optimal solution in the solution space. In green wave control, the particle swarm algorithm regards the green wave parameters (such as green ratio, phase difference, etc.) of each intersection signal light as a "particle", and the parameter combinations of multiple intersections form a "particle swarm". Through iterative optimization, the particle swarm continuously searches in the solution space and finally converges to the global optimal solution, that is, the best signal timing combination plan.

[0046] Specifically, the traffic green wave control system sets the constraint conditions of the particle swarm optimization algorithm according to the traffic flow prediction results, combined with parameters such as the distance between intersections and the road speed limit. These constraint conditions ensure that the solution space searched by the algorithm conforms to the physical limitations and safety requirements of the actual road traffic, such as the coordination of the green wave bandwidth between adjacent intersections and the reasonable range of signal cycles. Then, the system constructs the fitness function of the particle swarm optimization algorithm according to the optimization objective, which serves as the criterion for evaluating the quality of particles. In green wave control, the optional optimization objectives include but are not limited to minimizing vehicle delay time, stop times, and queue lengths. Through mathematical modeling, the fitness function quantifies these objectives into computable indicators and sets corresponding weight coefficients to balance the importance of different objectives.

[0047] After completing the algorithm parameter settings, the traffic green wave control system executes the particle swarm optimization algorithm for each target road section in sequence according to the order of the adjustment sequence. Through iterative search, the algorithm evaluates the fitness of different signal timing combinations and dynamically adjusts the speed and position of the particles according to the historical best solution and the global best solution of the particles, and finally converges to the optimal green wave bandwidth combination. This combination can maximize the satisfaction of the optimization objectives and achieve the fast and smooth passage of vehicles within the road section.

[0048] S106. Send the optimal timing combination scheme to the traffic signal controller for real-time timing control.

[0049] Specifically, the system converts the optimal timing combination scheme into timing data in a standard format recognizable by the controller, including but not limited to parameters such as the duration of each signal light phase, phase sequence, and repetition period. Then, the traffic green wave control system distributes the timing data to the signal controllers at the corresponding intersections through a wired or wireless communication network using a dedicated communication protocol (such as NTCIP, SCATS, etc.). After receiving the data, the controller checks the integrity and legality according to the established process to ensure that the timing scheme can be executed safely and reliably. The timing data that passes the check is written into the storage unit of the controller and becomes the active control plan.

[0050] In the above embodiment, the traffic green wave control system dynamically adjusts the green wave parameters of the signal lights at each intersection within the target road section according to the real-time traffic flow, road conditions, and other relevant factors, so as to achieve more efficient traffic flow guidance, reduce the stop times and delay time of vehicles on the road, improve the overall traffic capacity of urban roads, and reduce energy consumption and environmental pollution.

[0051] The following is a further and more specific process description of the method provided in this embodiment. Please refer to Figure 2 , which is another process schematic diagram of an intelligent traffic dynamic green wave control method in the embodiment of the present application.

[0052] S201. Obtain the second distance values between each intersection.

[0053] The traffic green wave control system first obtains the distance data between each intersection in the road network, that is, the second distance values. These distance data can be obtained in various ways. For example, using a high-precision electronic map database, which contains detailed geometric structure information of the road network and the coordinate positions of intersections; or obtaining distance data through on-site measurement, construction drawings of the road department, etc. The method is not limited here.

[0054] S202. Determine the road sections where a continuous preset number of second distance values are less than or equal to the preset distance threshold as the target road sections meeting the preset conditions.

[0055] Specifically, the traffic green wave control system sets two parameters according to actual needs: the preset number of consecutive intersections and the distance threshold. In a sliding window manner, it traverses all possible road sections in the road network. For each road section, all the intersections it contains are extracted, and it is calculated whether the distances between adjacent intersections all meet the threshold requirements, and whether the number of consecutive intersections that meet the requirements reaches the preset number. If both conditions are met, the road section is added to the candidate list of target road sections.

[0056] In the above embodiment, the traffic green wave control system determines the target road sections by calculating the distances between intersections and determining the continuous road sections that meet the preset conditions. This method can better focus on the road sections with greater traffic pressure for optimization and adjustment. It can avoid resource dispersion in unnecessary areas, improving the pertinence and priority of signal optimization. At the same time, the dynamic target road section screening mechanism can also adapt to traffic flow changes in real time, making the green wave control system more flexible and intelligent, and improving the operation efficiency of the entire road network while alleviating traffic congestion.

[0057] S203. Determine the adjustment priorities in different directions of the target road sections according to the congestion level and congestion duration, and obtain the adjustment sequences in different directions of each target road section.

[0058] This step is the same as step S104 and will not be elaborated here.

[0059] S204. Obtain the first distance values between each intersection within the target road section.

[0060] The system obtains the distance data between each intersection within the target road section, that is, the first distance values. Different from the second distance values at the road network level obtained in step S201, the acquisition of the first distance values is more focused on a single target road section and belongs to refined data collection.

[0061] Furthermore, the method for obtaining the first distance value is similar to that of the second distance value, and it can be obtained by querying the high-precision map database, field measurement, etc., which is not limited here. The system inputs the collected coordinate positions of each intersection into the distance calculation model to generate a distance matrix focused on the target road section.

[0062] S205. Calculate the average speed based on the historical driving speeds of the vehicle between the intersections within the target road section.

[0063] Specifically, the traffic green wave control system will access the historical database of the road monitoring system and extract the vehicle speed records between the intersections within the target road section. These records can come from multiple channels such as video monitoring devices, vehicle detectors, and Internet map navigation platforms within the road section. The system classifies and summarizes the speed data for consecutive days (such as one week) according to different time periods (such as morning and evening rush hours and off-peak hours), and then uses statistical methods to calculate the average value of the driving speeds between the intersections.

[0064] S206. Determine the minimum phase difference corresponding to the shortest road section based on the first distance value and the average speed.

[0065] Specifically, the traffic green wave control system will conduct a comprehensive analysis of the intersection distance matrix and the average speed matrix. First, find the pair of adjacent intersections with the shortest distance in the distance matrix as the reference road section for calculating the minimum phase difference. Then, access the vehicle speed value corresponding to this road section in the average speed matrix and substitute it into the formula "phase difference = distance ÷ speed" to obtain the minimum phase difference. It should be noted that since the average speed matrix contains data for multiple time periods, the speed value during the off-peak period is generally selected when calculating the minimum phase difference to reflect the vehicle speed level under normal traffic conditions within the road section.

[0066] S207. Determine the other phase differences of other road sections within the target road section based on the ratio of the first distance values of other road sections to the shortest road section, and the other phase differences are integer multiples of the minimum phase difference.

[0067] Specifically, the system extracts the first distance values between all other pairs of adjacent intersections within the target road section, and then calculates the ratios of these distance values to the distance of the shortest road section. The ratio results are usually real numbers greater than 1. Considering that the phase difference must be an integer multiple of the minimum phase difference, the system performs rounding processing on the above ratios. Optional rounding strategies include rounding up, rounding down, and rounding to the nearest integer, which are not limited here.

[0068] In some embodiments, it is assumed that the distance of the shortest road section J1-J2 is 200 meters, and the corresponding minimum phase difference is 20 seconds. Now consider another adjacent intersection pair J3-J4 with a distance of 350 meters between them. The distance ratio of the two road sections is 350÷200 = 1.75. After rounding, it is 2, that is, the phase difference of J3-J4 should be set to 2 times the minimum phase difference, which is 40 seconds. Similarly, the phase difference schemes for all other intersections within the target road section can be calculated.

[0069] In the above embodiments, the traffic green wave control system is based on the actual road length and speed data to ensure that the phase difference between signal lights can meet the requirements of continuous vehicle passing, and minimize the parking frequency and delay time of vehicles within the target road section to the greatest extent. Through this hierarchical phase difference adjustment method, it can better adapt to the diversity of each road section in the road network and improve the overall effect of green wave control.

[0070] S208. Determine the constraint conditions of the particle swarm optimization algorithm based on the traffic flow prediction results, the phase difference between signal lights at each intersection, and the preset saturation flow.

[0071] S209. If the peak period is the rush hour, set the first preset length threshold as the maximum queue length in the objective function.

[0072] Specifically, the system determines the peak period to which the current time belongs in real time according to the congestion level and congestion duration. If it is the rush hour, select the first preset length threshold with a lower value as the maximum queue length in the objective function, and try to control the queue length at the lowest level, that is, not exceeding the first preset length threshold. This threshold selection strategy can effectively cope with the traffic pressure during the rush hour, prevent the excessive accumulation of queuing vehicles, quickly disperse the traffic flow, and improve the traffic efficiency.

[0073] It should be noted that the first preset length threshold is less than the second preset length threshold, and the specific value can be determined according to actual needs and is not limited here.

[0074] S210. If the peak period is the off-peak hour, set the first preset number threshold as the number of stops in the objective function.

[0075] Specifically, the system determines the peak period to which the current time belongs in real time according to the congestion level and congestion duration. If it is the off-peak hour, select the first preset number threshold with a lower value as the number of stops in the objective function, and control the number of stops of vehicles within the lowest threshold, and minimize the starting frequency of stops to the greatest extent to ensure the smooth passing of the traffic flow.

[0076] It should be noted that the first preset number threshold is less than the second preset number threshold, and the specific value can be determined according to actual needs and is not limited here.

[0077] In the above embodiments, the traffic green wave control system sets the maximum queue length as an optimization parameter of the objective function for the peak period, which can effectively alleviate the congestion during the traffic peak; while in the off-peak period, the vehicle passing efficiency is further improved through the optimized adjustment of the number of stops. This dynamic phased optimization method effectively adapts to the needs under different traffic flow conditions, enabling the green wave control scheme to achieve the best effect in each stage. At the same time, based on the flexible adjustment of the objective function, the signal timing scheme can be more accurately optimized, reducing the vehicle's stop and delay time, improving the passing efficiency, and reducing fuel consumption and carbon emissions.

[0078] S211. Construct the objective function of the particle swarm optimization algorithm based on minimizing the average vehicle delay time, the number of stops, and the maximum queue length.

[0079] S212. Calculate the optimal green wave bandwidth according to the constraint conditions and the objective function to obtain the optimal timing combination scheme.

[0080] This step has been introduced in step S105 and will not be elaborated here.

[0081] S213. Determine the guiding vehicle speed between adjacent intersections based on the optimal timing combination scheme and the distance between adjacent intersections within the target section.

[0082] After obtaining the optimal timing combination scheme of the signal lights within the target section, the traffic green wave control system further calculates the guiding vehicle speed between adjacent intersections to provide driving reference for drivers. Specifically, the system extracts the green light duration and phase difference data of adjacent intersections in the optimal timing combination scheme. The green light duration represents the allowed time for vehicles to pass through the intersection, while the phase difference reflects the coordination relationship of the signal timing between adjacent intersections. Then, the system accesses the distance matrix to obtain the distance data between adjacent intersections.

[0083] The system further uses the formula "guiding vehicle speed = distance ÷ (green light duration - phase difference)" to calculate the guiding vehicle speed between each adjacent intersection. This guiding vehicle speed can ensure that vehicles pass through the section at an appropriate speed, avoiding the situation of stopping at the next intersection due to arriving too early or too late. It should be noted that when calculating the guiding vehicle speed, the optimal timing combination scheme with the least number of stops in the objective function is usually selected to meet the requirement of smooth and orderly vehicle passage. At the same time, since vehicles are affected by various factors such as traffic flow, vehicle types, and driving habits during actual passage, the system will reserve a certain buffer speed range (such as 10%) during calculation to obtain a guiding vehicle speed range and avoid the guiding vehicle speed being too idealized.

[0084] S214. Send the guiding vehicle speed to the mobile terminals of the corresponding drivers through the intelligent transportation induction system for voice prompts.

[0085] Specifically, the intelligent transportation guidance system performs real-time data docking with the traffic green wave control system to obtain real-time and dynamically updated guiding vehicle speed data. On the premise of obtaining the driver's authorization, the intelligent transportation guidance system real-time obtains the driver's location information through the positioning module. When it detects that the driver is about to enter or has entered the target road section, it pushes the guiding vehicle speed information of the corresponding road section to the driver's mobile terminal. This push is carried out through the mobile network and can adopt various methods such as instant messaging and text messages, which are not limited herein.

[0086] In the above embodiment, the guiding vehicle speed between adjacent intersections within the target road section is jointly determined by the optimal timing combination scheme and the intersection distance, and is sent to the driver's mobile terminal in real time through the intelligent transportation guidance system. This method can effectively guide the driver to pass through the green wave road section at a reasonable speed, avoiding stops or delays caused by speed mismatches. In addition, through the voice prompt function, the driver can obtain driving guidance information more intuitively, reducing decision-making delays and enhancing driving safety and comfort.

[0087] The traffic green wave control system of the embodiment of the present invention is an electronic device. Figure 3 The schematic diagram of the architecture of the electronic device suitable for implementing the embodiment of the present invention is shown.

[0088] It should be noted that Figure 3 The electronic device shown is only an example and should not bring any restrictions to the functions and usage scopes of the embodiments of the present invention.

[0089] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructions (computer programs), or the relevant hardware can be controlled by instructions (computer programs). The instructions can be stored in a computer-readable storage medium and loaded and executed by a processor. The electronic device of this embodiment includes a storage medium and a processor. Among them, multiple instructions are stored in the storage medium, and these instructions can be loaded by the processor to execute any step of the method provided by the embodiment of the present invention.

[0090] Specifically, the storage medium and the processor are electrically connected directly or indirectly to achieve data transmission or interaction. For example, these components can be electrically connected to each other through one or more signal lines. The storage medium stores computer-executable instructions for implementing the data access control method, including at least one software function module that can be stored in the storage medium in the form of software or firmware. The processor executes various functional applications and data processing by running the software programs and modules stored in the storage medium. The storage medium can be, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc. Among them, the storage medium is used to store programs, and the processor executes the programs after receiving the execution instructions.

[0091] Furthermore, the software programs and modules in the above storage medium may further include an operating system, which may include various software components and / or drivers for managing system tasks (such as memory management, storage device control, power management, etc.), and may communicate with various hardware or software components to provide a running environment for other software components. The processor can be an integrated circuit chip with signal processing capabilities. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc., which can implement or execute the various methods, steps, and logic flow block diagrams disclosed in this embodiment. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0092] Since the instructions stored in the storage medium can execute the steps in any of the methods provided in the embodiments of the present invention, the beneficial effects of any of the methods provided in the embodiments of the present invention can be achieved. For details, see the previous embodiments and will not be repeated here.

[0093] As described above, it is only the preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. An intelligent traffic dynamic green wave control method, applied to a traffic green wave control system, characterized in that: The method comprises: Obtaining real-time traffic data of each lane and emergency data published by the traffic management department, wherein the real-time traffic data is collected by sensors installed at the intersection; The pre-processed real-time traffic data is input into a neural network model trained based on historical traffic data and relevant influencing factor data, and the traffic flow prediction results of each road section in different directions within a preset time in the future are output; Input the traffic flow prediction result and the emergency data into a traffic flow theory model, and output the congestion level and congestion duration of each road section in different directions; Determining the adjustment priorities of different directions of target sections that meet preset conditions according to the congestion level and congestion duration, and obtaining adjustment sequences of different directions of each target section; According to the corresponding order of the adjustment sequence, based on the traffic flow prediction results, the particle swarm optimization algorithm is used to calculate the optimal green wave bandwidth of the traffic lights at each intersection in each target road section, so as to obtain the optimal timing combination scheme of the traffic lights in each target road section; The optimal timing combination scheme is sent to the traffic signal light controller for real-time timing control.

2. The method according to claim 1, characterized in that The step of calculating the optimal green wave bandwidth of each intersection signal light in each target road section by using a particle swarm optimization algorithm based on the traffic flow prediction result to obtain the optimal timing combination scheme of the signal lights in each target road section specifically includes: Determining the constraint conditions of the particle swarm optimization algorithm according to the traffic flow prediction result, the phase difference between the traffic lights at each intersection and the preset saturation flow; The objective function of the particle swarm optimization algorithm is constructed based on minimizing the average vehicle delay time, the number of stops and the maximum queue length; The optimal green wave bandwidth is calculated according to the constraint conditions and the objective function to obtain the optimal timing combination scheme.

3. The method according to claim 2, characterized in that Before the step of determining the constraint conditions of the particle swarm optimization algorithm according to the traffic flow prediction result, the phase difference between the traffic lights at each intersection and the preset saturation flow, the method further includes: Obtaining a first distance value between each intersection in the target road section; Calculating the average speed based on the historical driving speed of the vehicle between the intersections in the target road section; The phase difference between the traffic lights at each intersection in the target road section is determined according to the first distance value and the corresponding speed average.

4. The method according to claim 3, characterized in that: The step of determining the phase difference between the traffic lights at each intersection in the target section according to the first distance value and the corresponding speed average value specifically includes: Determining a minimum phase difference corresponding to the shortest section according to the first distance value and the speed average; Other phase differences of other sections are determined according to the ratio of the first distance value between other sections in the target section and the shortest section, and the other phase differences are integer multiples of the minimum phase difference.

5. The method according to claim 2, characterized in that: Before the step of constructing the objective function of the particle swarm optimization algorithm based on minimizing the average vehicle delay time, the number of stops and the maximum queue length, the step further includes: Determine a peak phase according to the congestion level and congestion duration, wherein the peak phase includes a peak period and a flat peak period; If the peak phase is a peak period, setting the first preset length threshold as the maximum queue length in the objective function, the maximum queue length includes a first preset length threshold and a second preset length threshold, and the first preset length threshold is less than the second preset length threshold; If the peak phase is a flat peak period, the first preset number threshold is set to the number of stops in the objective function, the number of stops includes a first preset number threshold and a second preset number threshold, and the first preset number threshold is less than the second preset number threshold.

6. The method according to claim 1, characterized in that Before the step of determining the adjustment priorities of different directions of the target road section meeting the preset conditions according to the congestion level and the congestion duration, the method further includes: Obtain the second distance value between each intersection; A continuous preset number of road sections whose second distance values ​​are less than or equal to a preset distance threshold are determined as the target road section meeting the preset condition.

7. The method according to claim 1, characterized in that After the step of sending the optimal timing combination scheme to the traffic signal light controller for real-time timing control, the method further includes: Determining the guide speed between the adjacent intersections according to the optimal timing combination scheme and the distance between the adjacent intersections in the target section; The guide vehicle speed is sent to the mobile terminal of the driver at the corresponding position through the intelligent traffic guidance system for voice prompting.

8. A traffic green wave control system, characterized in that: The traffic green wave control system includes: one or more processors and memory; The memory is coupled to the one or more processors, and the memory is used to store computer program codes, wherein the computer program codes include computer instructions, and the one or more processors call the computer instructions to enable the traffic green wave control system to execute the method according to any one of claims 1 to 7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on a traffic green wave control system, the traffic green wave control system is caused to execute the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product runs on a traffic green wave control system, the traffic green wave control system is enabled to execute the method according to any one of claims 1 to 7.

Images