Green wave traffic optimization method and system for urban traffic

Abstract

The present application provides a green wave traffic optimization method and system for urban traffic, which relates to the field of intelligent traffic technology, including: obtaining M green wave traffic sections; mapping and associating road traffic operation data streams with green wave traffic sections, obtaining M section operation data streams, and performing congestion feature identification respectively to obtain M section congestion feature sets, obtaining N green wave coordination periods by dividing the green wave period, performing green wave strategy analysis according to the N green wave coordination periods, and constructing N green wave traffic control strategy solution spaces; constructing a green wave traffic reward function to perform traffic control optimization analysis, determining N green wave traffic control strategy parameters, and performing green wave traffic control and dynamic optimization regulation on the target green wave section area. The present application solves the technical problems that the existing methods are difficult to perform green wave control and adjustment according to real-time traffic conditions and the dynamic response capability is insufficient, and achieves the technical effect of improving the overall road traffic efficiency.

Description

Technical Field

[0001] The present application relates to the field of intelligent transportation technology, and in particular to a green wave traffic optimization method and system for urban transportation. Background Art

[0002] Green wave traffic is a way of passing that coordinates multiple adjacent traffic lights so that vehicles can pass at a certain speed without encountering red lights in a continuous route. This method can effectively reduce the number of vehicle stops, improve road traffic efficiency, and reduce traffic congestion.

[0003] Existing green wave traffic methods mainly rely on fixed signal light cycles and preset traffic flow data for traffic control. This type of method usually sets the green wave traffic period based on historical traffic data or specific peak hours, and controls it according to the established cycle within a fixed time. However, urban traffic flow fluctuates greatly, and is affected by factors such as morning and evening peaks and emergencies, and traffic conditions are often difficult to accurately predict. Traditional green wave traffic solutions are difficult to respond and adjust quickly when faced with dynamically changing traffic flows, resulting in poor green wave traffic effects, and even some sections of the road are unobstructed while other sections are severely congested. In addition, existing green wave traffic methods usually lack accurate identification of traffic congestion characteristics and real-time optimization mechanisms, and cannot be intelligently controlled according to actual road conditions, resulting in insufficient overall optimization of the traffic system. Summary of the invention

[0004] The present application provides a green wave traffic optimization method and system for urban traffic, which solves the technical problems that the existing green wave traffic methods usually use fixed cycles or historical data for green wave control, lack real-time control and adjustment means, and are difficult to dynamically respond to changes in traffic conditions, thereby achieving the technical effect of improving the overall road traffic efficiency.

[0005] In view of the above problems, on the one hand, the present application provides a green wave traffic optimization method for urban traffic, the method comprising: using road information equipment to collect and obtain road traffic operation data streams of target green wave road section areas, performing traffic flow analysis and key section identification on the target green wave road section areas based on the road traffic operation data streams, and obtaining M green wave traffic sections; mapping and associating the road traffic operation data streams with the M green wave traffic sections to obtain M section operation data streams, and performing congestion feature identification on the M section operation data streams respectively to obtain M section congestion feature sets; based on the The M road section congestion feature sets are divided into green wave time periods to obtain N green wave coordination time periods, and green wave strategy analysis is performed on the M road section congestion feature sets according to the N green wave coordination time periods to construct N green wave traffic control strategy solution spaces; a green wave traffic reward function is constructed according to the green wave traffic balance target, and the green wave traffic reward function is used to perform traffic control optimization analysis on the N green wave traffic control strategy solution spaces to determine N green wave traffic control strategy parameters; green wave traffic control and dynamic optimization regulation are performed on the target green wave road section area based on the N green wave traffic control strategy parameters.

[0006] On the other hand, the present application also provides a green wave traffic optimization system for urban traffic, the system comprising: a green wave traffic section identification module, the green wave traffic section identification module is used to use road information equipment to collect and obtain the road traffic operation data flow of the target green wave section area, and perform traffic flow analysis and key section identification on the target green wave section area based on the road traffic operation data flow to obtain M green wave traffic sections; a congestion feature identification module, the congestion feature identification module is used to map and associate the road traffic operation data flow with the M green wave traffic sections, obtain M section operation data flows, and perform congestion feature identification on the M section operation data flows respectively to obtain M section congestion feature sets; a green wave strategy analysis module, the green wave strategy analysis module The analysis module is used to divide the green wave time periods based on the M road section congestion feature sets to obtain N green wave coordination time periods, and perform green wave strategy analysis on the M road section congestion feature sets according to the N green wave coordination time periods to construct N green wave traffic control strategy solution spaces; the traffic control optimization analysis module is used to construct a green wave traffic reward function according to the green wave traffic balance target, and use the green wave traffic reward function to perform traffic control optimization analysis on the N green wave traffic control strategy solution spaces to determine N green wave traffic control strategy parameters; the green wave traffic control module is used to perform green wave traffic control and dynamic optimization regulation on the target green wave road section area based on the N green wave traffic control strategy parameters.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] The road traffic operation data stream of the target green wave section area is collected and obtained by using the road information equipment to provide a real-time data basis for the entire plan, ensuring that the green wave control plan is based on the actual traffic flow and can flexibly respond to dynamic traffic flow changes. Based on the road traffic operation data stream, the target green wave section area is analyzed for traffic flow and key sections are identified to obtain M green wave traffic sections. By specifically identifying traffic bottlenecks and determining the key points that affect traffic efficiency, it is ensured that resources and strategies are concentrated on the sections with the greatest impact when optimizing green wave traffic, thereby achieving key control and improving overall traffic efficiency. The road traffic operation data stream and the M green wave traffic sections are mapped and associated to obtain M section operation data streams, and the congestion characteristics of the M section operation data streams are respectively identified to obtain M section congestion feature sets. The specific congestion situation of each section is accurately grasped through the congestion feature set, so that the green wave traffic control can be adjusted based on the actual road conditions, thereby more effectively alleviating congestion. Based on the congestion feature set of the M road sections, the green wave time period is divided to obtain N green wave coordination time periods. According to the N green wave coordination time periods, the green wave strategy analysis is performed on the congestion feature set of the M road sections respectively, and N green wave traffic control strategy solution spaces are constructed. Accurate control of different time periods is achieved through time period division, avoiding the lack of flexibility of the control scheme caused by the fixed cycle, and improving the traffic efficiency of different road sections in different time periods. According to the green wave traffic balance target, a green wave traffic reward function is constructed, and the traffic control optimization analysis of the N green wave traffic control strategy solution spaces is performed using the green wave traffic reward function to determine N green wave traffic control strategy parameters. This step ensures that the green wave strategy achieves optimal balance in the global scope, improves the overall traffic efficiency in each green wave time period, and reduces the traffic imbalance between sections. Based on the N green wave traffic control strategy parameters, the target green wave road section area is green wave traffic controlled and dynamically optimized, and the control strategy is continuously adjusted according to the real-time traffic conditions to improve the flexibility and adaptability of the overall traffic system and ensure continuous optimization of traffic flow.

[0009] In summary, this application uses the above-mentioned traffic data collection, congestion feature identification, time period division to strategy optimization to achieve refined and intelligent control of green wave traffic. This solution can flexibly divide green wave time periods according to real-time traffic conditions, and optimize strategies based on reward functions, so that the traffic efficiency in each section and time period is optimized, significantly improving the flexibility and response speed of green wave traffic control, thereby effectively improving the overall traffic efficiency of the road, reducing congestion, and making the entire traffic system more adaptable and dynamic. Control capability.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A schematic diagram of a flow chart of a green wave traffic optimization method for urban traffic provided in an embodiment of the present application;

[0012] Figure 2 A schematic diagram of a process for obtaining M green wave traffic sections in a green wave traffic optimization method for urban traffic provided in an embodiment of the present application;

[0013] Figure 3 A schematic diagram of a process for determining N green wave traffic control strategy parameters in a green wave traffic optimization method for urban traffic provided in an embodiment of the present application;

[0014] Figure 4 A schematic diagram of the structure of a green wave traffic optimization system for urban transportation provided in an embodiment of the present application.

[0015] Explanation of reference numerals: green wave traffic section identification module 10 , congestion feature identification module 20 , green wave strategy analysis module 30 , traffic control optimization analysis module 40 , green wave traffic control module 50 . DETAILED DESCRIPTION

[0016] The embodiments of the present application provide a green wave traffic optimization method and system for urban traffic, thereby solving the technical problems that the existing green wave traffic methods usually use fixed cycles or historical data for green wave control, lack real-time control and adjustment means, and are difficult to dynamically respond to changes in traffic conditions, thereby achieving the technical effect of improving the overall road traffic efficiency.

[0017] Embodiment 1, as Figure 1 As shown, the embodiment of the present application provides a green wave traffic optimization method for urban traffic, the method comprising:

[0018] Step S1: Use road information equipment to collect and obtain road traffic operation data flow in the target green wave section area, perform traffic flow analysis and key section identification on the target green wave section area based on the road traffic operation data flow, and obtain M green wave traffic sections.

[0019] Specifically, road information equipment refers to various electronic devices used to monitor and collect road traffic data, such as cameras, traffic sensors, geomagnetic induction coils, and traffic detectors. These devices can record traffic information such as vehicle flow, speed, and lane occupancy in real time. The target green wave section area can be any section of road or area where the green wave traffic control strategy is implemented.

[0020] Through various road information equipment deployed on the road, traffic operation data of the target green wave area is continuously collected in real time, including dynamic information such as vehicle flow, vehicle speed, lane occupancy, etc. This information is collectively referred to as road traffic operation data flow, which can reflect the real-time traffic status of the road section. For example, the geomagnetic induction coil records the number of passing vehicles, the camera monitors the flow of vehicles on the lane, and the traffic sensor can provide information such as vehicle speed and lane occupancy.

[0021] The acquired road traffic operation data stream is counted and analyzed to identify information such as traffic density, speed changes, and traffic bottlenecks, so as to determine the road sections that play a key role in the traffic flow. These key sections may be the main places where traffic congestion occurs, or important channels connecting different areas. For example, the data of a main road shows that the traffic volume during the morning rush hour is very large and the vehicle speed is slow. Based on this data, an in-depth analysis is conducted to identify a certain section of road that has become the key to upstream and downstream road congestion due to improper signal light intervals or excessive traffic volume, and it is recorded as a key section. The identified key sections are M green wave traffic sections, where M is a positive integer. These M green wave traffic sections are the main areas of traffic problems, and special green wave traffic strategies need to be designed.

[0022] Step S1 identifies key green wave sections that need to be optimized through real-time data collection and analysis, providing specific goals for subsequent green wave traffic optimization.

[0023] Step S2: Map and associate the road traffic operation data stream and the M green wave traffic sections to obtain M section operation data streams, perform congestion feature identification on the M section operation data streams respectively, and obtain a set of M section congestion features.

[0024] Specifically, the road section congestion feature set refers to the set of all congestion features of each road section summarized after congestion feature identification, including all data features related to congestion, which is the basis for subsequent green wave strategy optimization.

[0025] The road traffic operation data stream obtained in step S1 is matched one by one with the M green wave traffic sections to form an independent operation data stream for each section, i.e., M section operation data streams. According to the operation data stream of each section, the specific congestion condition of each section is analyzed, including key information such as vehicle speed, congestion duration, and waiting time. For example, during the morning rush hour on a certain section, the vehicle speed drops to 10 kilometers per hour, and serious traffic congestion occurs. These phenomena are recorded and marked as congestion characteristics. Through congestion feature identification, a section congestion feature set is generated for each section to clarify the congestion nature of each section, and provide a detailed problem description and optimization target for the subsequent green wave traffic strategy, so as to formulate optimization strategies more accurately and improve the effect of green wave traffic.

[0026] Step S3: dividing the M road section congestion feature sets into green wave time periods to obtain N green wave coordination time periods, performing green wave strategy analysis on the M road section congestion feature sets according to the N green wave coordination time periods, and constructing N green wave traffic control strategy solution spaces.

[0027] Specifically, the congestion feature set of the M road sections obtained in step S2 is analyzed to preliminarily determine the changing trends of traffic characteristics at different time periods in a day. Based on these changing trends, the green wave time periods are divided. The time of a day is divided into N green wave coordination time periods that require green wave strategy optimization, such as the morning peak (7:00-9:00), the midday flat peak (12:00-13:00) and the evening peak (17:00-9:00), etc. Each time period corresponds to different traffic demands.

[0028] For each green wave coordination period, according to the set of road congestion characteristics of each period, a green wave strategy analysis is conducted on the traffic conditions in different periods, and the time interval and phase of traffic lights are adjusted to maximize the smooth passage of vehicles and reduce the number of stops. Through the green wave strategy analysis, a corresponding green wave traffic control strategy is constructed for each period. These strategies form a solution space, which includes several possible green wave control schemes for different sections. N green wave coordination periods correspond to N green wave traffic control strategy solution spaces. Among them, N is a positive integer, representing the number of green wave coordination periods.

[0029] Step S3 constructs the optimal signal control strategy in each time period through green wave time period division and green wave strategy analysis, forms a strategy solution space, provides rich strategy options for subsequent real-time regulation, and ensures that green wave traffic control is more refined and efficient.

[0030] Step S4: construct a green wave traffic reward function according to the green wave traffic balance target, use the green wave traffic reward function to perform traffic control optimization analysis on the N green wave traffic control strategy solution spaces respectively, and determine N green wave traffic control strategy parameters.

[0031] Specifically, the green wave traffic balance target refers to the optimization target planned to be achieved during the optimization of the green wave traffic control strategy, which can be maximizing traffic efficiency or minimizing congestion. The green wave traffic reward function is a mathematical model that is constructed based on the green wave traffic balance target. It evaluates the effects of different green wave traffic control strategies by scoring each control strategy. The green wave traffic control strategy parameters are the optimal green wave traffic control parameters for each green wave coordination period determined after optimization analysis. These parameters include the green and red light durations, phase timing, etc. of the traffic lights.

[0032] Based on the equilibrium goal of green wave traffic, a green wave traffic reward function is constructed to evaluate different traffic schemes. The purpose of this function is to score different signal light configuration schemes. The construction of the reward function needs to consider many factors, such as the average waiting time of vehicles, the speed of vehicles, the smoothness of traffic flow, etc. If a certain signal light configuration can significantly reduce the waiting time of vehicles and make the speed more uniform, then the reward value of the scheme will be higher.

[0033] The reward function is used to evaluate the N green wave traffic control strategy solution spaces generated in step S3. For each solution space, the reward value of each control strategy is calculated to evaluate its effect in achieving traffic efficiency and balance. The control strategy parameter with the highest reward function score in the solution space is determined as the green wave traffic control strategy parameter corresponding to the green wave coordination period. N green wave traffic control strategy solution spaces correspond to N green wave traffic control strategy parameters.

[0034] Step S4 constructs a reward function for optimization analysis, selects the best strategy from multiple possible green wave control strategies, and determines specific control strategy parameters to provide strategic guidance for the actual implementation of green wave traffic.

[0035] Step S5: performing green wave traffic control and dynamic optimization regulation on the target green wave road section area based on the N green wave traffic control strategy parameters.

[0036] Specifically, according to the N green wave traffic control strategy parameters determined in step S4, green wave traffic control is implemented in the actual target green wave road section area to ensure the smooth passage of vehicles and avoid traffic congestion caused by frequent parking. After the control strategy is executed, the traffic conditions of the road section are continuously monitored, and the strategy parameters are adjusted and optimized according to the actual traffic conditions after execution to cope with the fluctuations of the actual traffic conditions, ensuring that vehicles can always pass through the road section smoothly, thereby effectively reducing overall traffic delays.

[0037] Step S5 ensures the flexibility and adaptability of green wave traffic control through a dynamic optimization control mechanism, which can respond to various changes in traffic conditions in a timely manner and significantly improve road traffic conditions.

[0038] Further, such as Figure 2 As shown, step S1 of the embodiment of the present application also includes:

[0039] The target green wave road section area is divided into sections according to the intersection information to obtain multiple area road section information, and the flow data association extraction is performed on the multiple area road section information based on the road traffic operation data flow to obtain multiple road section traffic flow association data flow; flow trend analysis is performed on the multiple road section traffic flow association data flow to obtain multiple road section flow trend parameter information, and the multiple road section flow trend parameter information includes average flow, speed and density; traffic characteristics are identified and impact degree is evaluated based on the multiple road section flow trend parameter information to obtain multiple road section traffic impact factors; the multiple area road section information is subdivided into key sections according to the multiple road section traffic impact factors to obtain the M green wave traffic sections.

[0040] Specifically, the intersection information includes the intersection's latitude and longitude, traffic light information, number of lanes, etc. The entire target green wave section area is refined according to the intersection information and divided into multiple small section units. Each section unit consists of one or more intersections and the sections between them, including the entrance and exit intersection information, i.e., regional section information. For example, a main road is divided into three adjacent sections, each of which corresponds to a different traffic light intersection. The road traffic operation data corresponding to each section unit is extracted from the road traffic operation data stream to obtain multiple regional section information.

[0041] From the road traffic operation data stream, according to the road section and intersection information, the flow data of multiple regional sections are extracted, and the flow data related to each section is extracted to form multiple section traffic flow related data streams. By analyzing the traffic flow relationship between different sections, the flow of vehicles from one section to the next section can be understood, so as to understand the mutual influence relationship between the traffic flow of each section, so as to better optimize the green wave control. If it is found that the traffic flow of the first section is highly correlated with the second section, then the signal light control between the two sections needs to be specially optimized.

[0042] According to the traffic flow correlation data stream of the road section, the changing trend of traffic flow in different time periods is analyzed, and the traffic trend parameters such as average flow, vehicle speed and density of each road section in different time periods are extracted. Based on the traffic trend parameter information, the traffic characteristics such as the capacity, congestion level, and traffic flow betweenness of the road section are identified to fully understand the traffic operation of each road section. Among them, the capacity refers to the maximum number of vehicles that a road section can accommodate and pass within a unit of time (such as per hour). The congestion level reflects the traffic conditions of the road section in a specific time period, which is usually measured by parameters such as average speed and vehicle density. The traffic flow betweenness includes indicators such as vehicle flow, speed and density, and is an important parameter for measuring traffic fluidity.

[0043] By identifying the traffic characteristics of each road section, the impact of each road section on the overall traffic flow is evaluated, and the traffic impact factor corresponding to each regional road section is generated. The traffic impact factor is a comprehensive indicator used to quantify the contribution and negative impact of each regional road section on the traffic system. Road sections with higher impact factors are often traffic bottlenecks or key sections, and should be optimized and controlled first. According to the size of the traffic impact factor, the regional sections are prioritized, and the key sections that have an important impact on the overall traffic flow, namely M green wave traffic sections, are identified. By identifying the key sections, the control target objects are refined to ensure that the traffic flow is smoother at the key nodes, thereby improving the traffic efficiency of the entire target green wave section area.

[0044] Furthermore, step S3 of the embodiment of the present application also includes:

[0045] Performing a change trend analysis on the M road section congestion feature sets to obtain M road section congestion feature parameters, wherein the M road section congestion feature parameters include congestion occurrence frequency, duration, impact scope and congestion degree level; coordinating and formulating strategies for the M road section congestion feature parameters according to the N green wave coordination time periods through the traffic green wave expert system to obtain N green wave traffic strategy parameter sets; constructing a road section traffic effect simulation module according to a green wave traffic evaluation index set, performing effect simulation evaluation on the N green wave traffic strategy parameter sets based on the road section traffic effect simulation module to obtain N green wave traffic parameter effect sets; performing mutation, expansion and update and effect ratio optimization on the N green wave traffic strategy parameter sets based on the N green wave traffic parameter effect sets to construct the N green wave traffic control strategy solution space.

[0046] Specifically, the traffic green wave expert system is a system based on artificial intelligence or rule engine, which is specially used to analyze and formulate traffic green wave passage strategies. It can automatically generate green wave control plans suitable for each time period based on the congestion characteristics of the road section, combined with historical data and traffic laws.

[0047] First, the congestion feature set of M road sections is analyzed in detail, and the congestion feature parameters of each road section, such as the congestion frequency, duration, impact range and congestion level, are calculated using data analysis tools (such as Pandas and NumPy in Python). Time series analysis, such as autoregressive model (ARIMA) or long short-term memory (LSTM) neural network, is used to analyze the change trend of congestion characteristics of each road section over time. Among them, the congestion frequency refers to the number of times traffic congestion occurs on a road section within a certain period of time, which can be calculated by counting the number of times the speed drops below a certain threshold within a certain period of time. For example, during the morning rush hour, the speed of a road section drops three times, and the congestion frequency is three times. The duration refers to the time from the beginning to the end of a congestion, which is calculated by analyzing the time from the beginning of each congestion to the restoration of normal vehicle speed. The impact range refers to the size of the area affected by a congestion on surrounding roads and vehicles, which is obtained by analyzing the vehicle congestion data of adjacent roads. The congestion level is to quantify the severity of congestion, which is usually divided into mild, moderate and severe. The severity is quantified by combining the frequency, duration and impact range of congestion, combined with preset rules or machine learning models (such as decision trees). For example, if a road section is congested three times a day, each time lasting 30 minutes, and the impact range is large, the road section will be marked as "severely congested".

[0048] Using the traffic green wave expert system, the trend of congestion characteristic parameters of each road section is analyzed, and the strategy coordination and integration analysis of the congestion characteristic parameters of M road sections is carried out in turn according to N green wave coordination periods such as morning peak, noon flat peak and evening peak, and the corresponding green wave traffic strategy is formulated. The green wave traffic strategy includes the green light cycle of the road section, phase difference, green light time, recommended driving speed, etc. All green wave traffic strategies of each green wave coordination period are summarized separately to obtain N green wave traffic strategy parameter sets.

[0049] Next, use traffic simulation software (such as VISSIM or SUMO) to build a road section traffic effect simulation module to simulate traffic conditions under different green wave traffic strategies. Set a set of green wave traffic evaluation indicators according to the expected traffic effect, including average waiting time, traffic efficiency, emissions, etc., to measure the effect of the green wave strategy. Use the effect simulation module to simulate each strategy in the N green wave traffic strategy parameter sets in turn, test the performance of each strategy in the actual traffic environment, collect corresponding traffic flow, average vehicle speed, waiting time and other indicators, and integrate to generate N green wave traffic parameter effect sets corresponding to the N green wave traffic strategy parameter sets.

[0050] Analyze the parameter effect set, and use optimization methods such as genetic algorithms to mutate (fine-tune) and cross (combine) the green wave traffic strategy parameters, such as changing the length of the green light time, adding different vehicle priorities, etc., to generate more possible green wave traffic strategies. Collect the traffic parameter effects of the newly added green wave traffic strategy through the effect simulation module, select the traffic strategy parameters that perform best in the simulation test through effect ratio optimization, and construct N green wave traffic control strategy solution spaces.

[0051] Through the above-mentioned strategy optimization, simulation and optimization steps, N green wave traffic control strategy solution spaces are gradually constructed, providing a sufficient selection basis for subsequent strategy optimization.

[0052] Further, such as Figure 3 As shown, step S4 of the embodiment of the present application also includes:

[0053] Based on the congestion characteristic parameters of the M road sections, the congestion levels of the M green wave traffic sections are compared to determine the first green wave traffic section; the strategy parameters of the N green wave traffic control strategy solution spaces are evaluated respectively using the green wave traffic reward function to obtain N green wave traffic strategy reward sets; based on the N green wave traffic control strategy solution spaces, N first green wave traffic control strategy sets of the first green wave traffic section are obtained; based on the N green wave traffic strategy reward sets, the N first green wave traffic control strategy sets are compared and optimized to determine the N first green wave traffic strategy parameters with the largest rewards; based on the N first green wave traffic strategy parameters, the N green wave traffic control strategy solution spaces are respectively optimized for strategy balance to determine the N green wave traffic control strategy parameters.

[0054] Specifically, based on the congestion characteristic parameters of the M sections obtained above, a weighted scoring method or a hierarchical analysis method is used to comprehensively consider various congestion characteristic parameters such as congestion frequency, duration, impact range, and congestion level, and the congestion conditions of the M green wave traffic sections are calculated and compared to determine the section with the most serious congestion, namely the first green wave traffic section. This section has the greatest impact on traffic in the entire area and needs to be optimized first.

[0055] All possible green wave control strategies (i.e., N green wave control strategy solution spaces) are evaluated through the green wave reward function. Each strategy is scored according to its performance in different time periods based on different parameters (such as signal light duration, phase time, green light time ratio, etc.), forming a set of N green wave strategy rewards.

[0056] N first green wave traffic control strategy sets matching the first green wave traffic section are extracted from the N green wave traffic control strategy solution spaces. The rewards of all traffic control strategies in each first green wave traffic control strategy set are compared, and the control strategy parameters corresponding to the traffic control strategy with the largest reward in each set are determined as the first green wave traffic strategy parameters, and finally N first green wave traffic strategy parameters are screened out.

[0057] Based on the N first green wave traffic strategy parameters, continue to search for strategy equilibrium in the N green wave traffic control strategy solution space, weigh between multiple strategies to achieve global optimality, and ensure that the green wave traffic control strategies of each road section are coordinated with each other to achieve a balanced effect.

[0058] The above steps achieve fine optimization of the green wave traffic control strategy through congestion level comparison, reward evaluation and strategy balance optimization, ensuring that the final implemented strategy balances the traffic effects of other sections while giving priority to the most congested sections, thereby maximizing the traffic efficiency of urban roads.

[0059] Furthermore, step S4 of the embodiment of the present application also includes:

[0060] Construct a strategy equilibrium cost function: ;in, is the first green wave traffic control strategy set for the first green wave traffic section i The set of strategic parameters relative to other green wave traffic sections The cost function of A green wave traffic strategy parameter set is missing. , M is the total number of green wave traffic sections, j={0,1...M}; S is the green wave traffic control strategy solution space, including the green wave traffic control strategy set integrated by the strategy parameter set of M green wave traffic sections, represents the set of available strategy parameters in the jth green wave traffic section, Indicated in The next j-th green wave traffic section selection strategy parameters The probability of is the payment cost of reward loss in the solution space S of the green wave traffic control strategy under the first green wave traffic section i, let Minimum convergence output green wave traffic control strategy parameters; based on the strategy balance cost function, the N first green wave traffic strategy parameters are respectively used to perform strategy balance optimization in the N green wave traffic control strategy solution spaces to determine the N green wave traffic control strategy parameters.

[0061] Specifically, a strategic equilibrium cost function is constructed for each green wave traffic section (i-th section) , the cost function is used to evaluate the overall cost (or loss) of the green wave control strategy of a road section under the current situation, that is, the efficiency loss of the road section when a specific strategy is selected given the control strategy parameters of the first green wave traffic section. Through the cost function, while ensuring the optimal strategy parameters of the first green wave traffic section, the performance of different strategy combinations in different green wave coordination periods is evaluated.

[0062] Using the above cost function, given the control strategy parameters of the first green wave traffic section, the Nash equilibrium optimization of the green wave traffic control strategy solution space is performed. For each green wave coordination period, the strategies of each section are continuously adjusted until a globally optimal strategy combination is found, that is, an equilibrium control strategy that maximizes the reward of all sections while ensuring that the strategy parameters of the first green wave traffic section are optimal. The strategy parameters that minimize the cost function are used as the green wave traffic control strategy parameters of each section during the green wave coordination period. The N green wave traffic control strategy solution spaces are optimized in equilibrium, and finally the N green wave traffic control strategy parameters are determined. This optimization process ensures the smoothness of the overall traffic network and avoids the problem of reduced global traffic efficiency due to local optimization.

[0063] Furthermore, step S4 of the embodiment of the present application also includes:

[0064] Obtain the upper green wave traffic section set and the lower green wave traffic section set of the first green wave traffic section from the remaining green wave traffic sections; based on the N first green wave traffic strategy parameters, traverse the strategy parameter set of the upper green wave traffic section based on the strategy equilibrium cost function to calculate the payment cost of reward loss, and obtain N upper section control strategy parameters; based on the N first green wave traffic strategy parameters, use the strategy equilibrium cost function to traverse the strategy parameter set of the lower green wave traffic section to calculate the payment cost of reward loss, and obtain N lower section control strategy parameters; determine the N green wave traffic control strategy parameters based on the N first green wave traffic strategy parameters, the N upper section control strategy parameters and the N lower section control strategy parameters.

[0065] Specifically, according to the flow of traffic vehicles, the remaining sections are divided into upper and lower sections of the first section. The upper section refers to the section connected to the first green wave section and the vehicle will pass through first, while the lower section is the section where the vehicle continues to travel after passing the first green wave section. The upper and lower sections are respectively summarized to generate the upper green wave traffic section set and the lower green wave traffic section set, so as to calculate and screen the minimum cost strategy.

[0066] Based on the N first green wave traffic strategy parameters, the aforementioned strategy equilibrium cost function is used to traverse all strategy parameter sets of the upper-level section, evaluate the reward loss of different strategy combinations on the upper-level section, and the cost of these losses, and find the N upper-level section control strategy parameters that can minimize the impact on the upper-level section.

[0067] Similarly, according to the N first green wave traffic strategy parameters, the strategy parameter set of the lower-level road section is traversed, the payment cost of its reward loss is calculated, and the N lower-level road section control strategy parameters that can minimize the impact on the upper-level road section are found.

[0068] The N strategy parameters of the first green wave section, the N control strategy parameters of the upper section and the N control strategy parameters of the lower section are integrated to determine the final N green wave traffic control strategy parameters. These parameters will ensure that the traffic signals of all relevant sections are coordinated and consistent, achieving overall optimization.

[0069] The above steps use the strategy equilibrium cost function to calculate the reward loss in the upper and lower sections, and optimize the green wave traffic strategy of the entire traffic network based on these calculation results, so that the traffic efficiency of these sections will not be affected too much by the strategy adjustment of the first green wave section, so as to achieve the optimization of the entire traffic flow.

[0070] Furthermore, step S5 of the embodiment of the present application further includes:

[0071] Based on the N green wave traffic control strategy parameters, green wave traffic control monitoring is performed on the target green wave road section area to obtain green wave traffic control feedback parameters; traffic optimization analysis is performed on the green wave traffic control feedback parameters to obtain strategy parameter variation rules, and based on the strategy parameter variation rules, the N green wave traffic control strategy parameters are mutated and optimized to obtain N green wave traffic optimization control strategy parameters; based on the N green wave traffic optimization control strategy parameters, dynamic optimization traffic control is performed on the target green wave road section area.

[0072] Specifically, N green wave traffic control strategy parameters are executed to control green wave traffic in the target green wave road section, and the traffic conditions after the execution of N green wave traffic control strategy parameters are monitored in real time through road information equipment to collect green wave traffic control feedback parameters. These feedback data include the average speed of vehicles after the execution of N green wave traffic control strategy parameters, vehicle waiting time, actual effect of signal timing, and congestion level of the road section.

[0073] The collected green wave control feedback parameters are analyzed through traffic data analysis tools to evaluate whether the current control strategy is effective, identify potential problems in the existing green wave control strategy, and determine the severity of the problem. For example, congestion in certain periods of time is aggravated or the timing of specific signals is unreasonable. Based on these feedback parameters, methods to improve the existing green wave control strategy are analyzed and strategy parameter variation rules are formulated. These rules define how to adjust the current strategy according to actual traffic conditions. For example, if the signal light duration of a green wave section is too short, resulting in a decrease in traffic efficiency, the variation rule will recommend extending the green light time.

[0074] Based on the mutation rules obtained by analysis, the genetic algorithm or differential evolution algorithm is used to perform multiple rounds of mutation on the existing N green wave traffic control strategy parameters to find the optimal or suboptimal solution and obtain N green wave traffic optimization control strategy parameters. Based on these optimized N green wave traffic strategy parameters, the target green wave road section area is optimized and controlled. The monitoring, analysis, and mutation processes are repeated to dynamically adjust the green wave traffic strategy parameters to ensure that the traffic efficiency is continuously optimized as traffic conditions change.

[0075] Through the above-mentioned variation optimization and dynamic adjustment process, the green wave control strategy is dynamically adjusted to ensure that the green wave traffic strategy can be self-optimized according to the real-time traffic conditions, thereby improving the road traffic efficiency and avoiding the aggravation of traffic congestion.

[0076] In summary, the green wave traffic optimization method for urban traffic provided by the embodiment of the present application has the following technical effects:

[0077] The road traffic operation data stream of the target green wave section area is collected and obtained by using the road information equipment to provide a real-time data basis for the entire plan, ensuring that the green wave control plan is based on the actual traffic flow and can flexibly respond to dynamic traffic flow changes. Based on the road traffic operation data stream, the target green wave section area is analyzed for traffic flow and key sections are identified to obtain M green wave traffic sections. By specifically identifying traffic bottlenecks and determining the key points that affect traffic efficiency, it is ensured that resources and strategies are concentrated on the sections with the greatest impact when optimizing green wave traffic, thereby achieving key control and improving overall traffic efficiency. The road traffic operation data stream and the M green wave traffic sections are mapped and associated to obtain M section operation data streams, and the congestion characteristics of the M section operation data streams are respectively identified to obtain M section congestion feature sets. The specific congestion situation of each section is accurately grasped through the congestion feature set, so that the green wave traffic control can be adjusted based on the actual road conditions, thereby more effectively alleviating congestion. Based on the congestion feature set of the M road sections, the green wave time period is divided to obtain N green wave coordination time periods. According to the N green wave coordination time periods, the green wave strategy analysis is performed on the congestion feature set of the M road sections respectively, and N green wave traffic control strategy solution spaces are constructed. Accurate control of different time periods is achieved through time period division, avoiding the lack of flexibility of the control scheme caused by the fixed cycle, and improving the traffic efficiency of different road sections in different time periods. According to the green wave traffic balance target, a green wave traffic reward function is constructed, and the traffic control optimization analysis of the N green wave traffic control strategy solution spaces is performed respectively using the green wave traffic reward function to determine N green wave traffic control strategy parameters, ensuring that the green wave strategy achieves optimal balance in the global scope, improving the overall traffic efficiency in each green wave time period, and reducing the traffic imbalance between sections. Based on the N green wave traffic control strategy parameters, the target green wave road section area is green wave traffic controlled and dynamically optimized, and the control strategy is continuously adjusted according to the real-time traffic conditions to improve the flexibility and adaptability of the overall traffic system and ensure continuous optimization of traffic flow.

[0078] In general, the embodiment of the present application utilizes the above-mentioned traffic data collection, congestion feature identification, time period division to strategy optimization to achieve refined and intelligent control of green wave traffic. The method can flexibly divide the green wave time period according to the real-time traffic conditions, and optimize the strategy based on the reward function, so that the traffic efficiency in each section and time period is optimized, which significantly improves the flexibility and response speed of green wave traffic control, thereby effectively improving the overall traffic efficiency of the road, reducing congestion, and making the entire traffic system more adaptable and dynamic. Control capability.

[0079] Embodiment 2, as Figure 4 As shown, the embodiment of the present application provides a green wave traffic optimization system for urban traffic, the system comprising:

[0080] A green wave traffic section identification module 10 is used to collect and obtain the road traffic operation data flow of the target green wave section area by using the road information equipment, and perform traffic flow analysis and key section identification on the target green wave section area based on the road traffic operation data flow to obtain M green wave traffic sections.

[0081] The congestion feature identification module 20 is used to map and associate the road traffic operation data stream and the M green wave traffic sections, obtain M section operation data streams, perform congestion feature identification on the M section operation data streams respectively, and obtain M section congestion feature sets.

[0082] A green wave strategy analysis module 30 is used to divide the green wave time periods based on the M road section congestion feature sets to obtain N green wave coordination time periods, and to perform green wave strategy analysis on the M road section congestion feature sets according to the N green wave coordination time periods to construct N green wave traffic control strategy solution spaces.

[0083] The traffic control optimization analysis module 40 is used to construct a green wave traffic reward function according to the green wave traffic balance target, and use the green wave traffic reward function to perform traffic control optimization analysis on the N green wave traffic control strategy solution spaces respectively to determine N green wave traffic control strategy parameters.

[0084] A green wave traffic control module 50 is used to perform green wave traffic control and dynamic optimization regulation on the target green wave road section area based on the N green wave traffic control strategy parameters.

[0085] Furthermore, the green wave traffic section identification module 10 of the embodiment of the present application is also used to perform the following steps:

[0086] The target green wave road section area is divided into sections according to the intersection information to obtain multiple area road section information, and the flow data association extraction is performed on the multiple area road section information based on the road traffic operation data flow to obtain multiple road section traffic flow association data flow; flow trend analysis is performed on the multiple road section traffic flow association data flow to obtain multiple road section flow trend parameter information, and the multiple road section flow trend parameter information includes average flow, speed and density; traffic characteristics are identified and impact degree is evaluated based on the multiple road section flow trend parameter information to obtain multiple road section traffic impact factors; the multiple area road section information is subdivided into key sections according to the multiple road section traffic impact factors to obtain the M green wave traffic sections.

[0087] Furthermore, the green wave strategy analysis module 30 of the embodiment of the present application is also used to perform the following steps:

[0088] Performing a change trend analysis on the M road section congestion feature sets to obtain M road section congestion feature parameters, wherein the M road section congestion feature parameters include congestion occurrence frequency, duration, impact scope and congestion degree level; coordinating and formulating strategies for the M road section congestion feature parameters according to the N green wave coordination time periods through the traffic green wave expert system to obtain N green wave traffic strategy parameter sets; constructing a road section traffic effect simulation module according to a green wave traffic evaluation index set, performing effect simulation evaluation on the N green wave traffic strategy parameter sets based on the road section traffic effect simulation module to obtain N green wave traffic parameter effect sets; performing mutation, expansion and update and effect ratio optimization on the N green wave traffic strategy parameter sets based on the N green wave traffic parameter effect sets to construct the N green wave traffic control strategy solution space.

[0089] Furthermore, the traffic control optimization analysis module 40 of the embodiment of the present application is also used to perform the following steps:

[0090] Based on the congestion characteristic parameters of the M road sections, the congestion levels of the M green wave traffic sections are compared to determine the first green wave traffic section; the strategy parameters of the N green wave traffic control strategy solution spaces are evaluated respectively using the green wave traffic reward function to obtain N green wave traffic strategy reward sets; based on the N green wave traffic control strategy solution spaces, N first green wave traffic control strategy sets of the first green wave traffic section are obtained; based on the N green wave traffic strategy reward sets, the N first green wave traffic control strategy sets are compared and optimized to determine the N first green wave traffic strategy parameters with the largest rewards; based on the N first green wave traffic strategy parameters, the N green wave traffic control strategy solution spaces are respectively optimized for strategy balance to determine the N green wave traffic control strategy parameters.

[0091] Furthermore, the traffic control optimization analysis module 40 of the embodiment of the present application is also used to perform the following steps:

[0092] Construct a strategy equilibrium cost function: ;in, is the first green wave traffic control strategy set for the first green wave traffic section i The set of strategic parameters relative to other green wave traffic sections The cost function of A green wave traffic strategy parameter set is missing. , M is the total number of green wave traffic sections, j={0,1...M}; S is the green wave traffic control strategy solution space, including the green wave traffic control strategy set integrated by the strategy parameter set of M green wave traffic sections, represents the set of available strategy parameters in the jth green wave traffic section, Indicated in The next j-th green wave traffic section selection strategy parameters The probability of is the payment cost of reward loss in the solution space S of the green wave traffic control strategy under the first green wave traffic section i, let Minimum convergence output green wave traffic control strategy parameters; based on the strategy balance cost function, the N first green wave traffic strategy parameters are respectively used to perform strategy balance optimization in the N green wave traffic control strategy solution spaces to determine the N green wave traffic control strategy parameters.

[0093] Furthermore, the traffic control optimization analysis module 40 of the embodiment of the present application is also used to perform the following steps:

[0094] Obtain the upper green wave traffic section set and the lower green wave traffic section set of the first green wave traffic section from the remaining green wave traffic sections; based on the N first green wave traffic strategy parameters, traverse the strategy parameter set of the upper green wave traffic section based on the strategy equilibrium cost function to calculate the payment cost of reward loss, and obtain N upper section control strategy parameters; based on the N first green wave traffic strategy parameters, use the strategy equilibrium cost function to traverse the strategy parameter set of the lower green wave traffic section to calculate the payment cost of reward loss, and obtain N lower section control strategy parameters; determine the N green wave traffic control strategy parameters based on the N first green wave traffic strategy parameters, the N upper section control strategy parameters and the N lower section control strategy parameters.

[0095] Furthermore, the green wave traffic control module 50 of the embodiment of the present application is also used to perform the following steps:

[0096] Based on the N green wave traffic control strategy parameters, green wave traffic control monitoring is performed on the target green wave road section area to obtain green wave traffic control feedback parameters; traffic optimization analysis is performed on the green wave traffic control feedback parameters to obtain strategy parameter variation rules, and based on the strategy parameter variation rules, the N green wave traffic control strategy parameters are mutated and optimized to obtain N green wave traffic optimization control strategy parameters; based on the N green wave traffic optimization control strategy parameters, dynamic optimization traffic control is performed on the target green wave road section area.

[0097] Through the above-mentioned detailed description of the green wave traffic optimization method for urban traffic in this specification, those skilled in the art can clearly understand the green wave traffic optimization system for urban traffic in this embodiment. For the system disclosed in Example 2, since it corresponds to the method disclosed in Example 1 and has corresponding functional modules and beneficial effects, the relevant parts can be referred to the description of the method part.

[0098] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A green wave traffic optimization method for urban traffic, characterized in that: The method comprises: Using pavement information equipment to collect and obtain road traffic operation data streams in a target green wave road section area, and based on the road traffic operation data streams, performing traffic flow analysis and key section identification on the target green wave road section area to obtain M green wave traffic sections; Mapping and associating the road traffic operation data stream with the M green wave traffic sections to obtain M section operation data streams, and performing congestion feature recognition on the M section operation data streams to obtain M section congestion feature sets; Based on the M road section congestion feature sets, green wave time periods are divided to obtain N green wave coordination time periods. Green wave strategy analysis is performed on the M road section congestion feature sets according to the N green wave coordination time periods, and N green wave traffic control strategy solution spaces are constructed, wherein a corresponding green wave traffic control strategy is constructed for each time period through green wave strategy analysis. These strategies form a solution space, which includes green wave control schemes for different road sections. N green wave coordination time periods correspond to N green wave traffic control strategy solution spaces, wherein N is a positive integer representing the number of green wave coordination time periods; A green wave traffic reward function is constructed according to the green wave traffic balance target, and the green wave traffic reward function is used to perform traffic control optimization analysis on the N green wave traffic control strategy solution spaces respectively to determine N green wave traffic control strategy parameters, wherein the green wave traffic control strategy parameters are the optimal green wave traffic control parameters for each green wave coordination period determined after optimization analysis, and these parameters include the green and red light durations and phase timing of the traffic lights; Based on the N green wave traffic control strategy parameters, green wave traffic control and dynamic optimization regulation are performed on the target green wave road section area; The construction of N green wave traffic control strategy solution spaces includes: Performing change trend analysis on the M road section congestion feature sets to obtain M road section congestion feature parameters, wherein the M road section congestion feature parameters include congestion occurrence frequency, duration, impact range, and congestion degree level; The traffic green wave expert system coordinates and formulates strategies for the congestion characteristic parameters of the M road sections according to the N green wave coordination time periods, thereby obtaining N sets of green wave traffic strategy parameters; Constructing a road section traffic effect simulation module according to the green wave traffic evaluation index set, and performing effect simulation evaluation on the N green wave traffic strategy parameter sets based on the road section traffic effect simulation module to obtain N green wave traffic parameter effect sets; Based on the N green wave travel parameter effect sets, the N green wave travel strategy parameter sets are mutated, expanded, updated, and effect proportion optimized to construct the N green wave travel control strategy solution spaces; The determining of N green wave traffic control strategy parameters includes: Comparing the congestion levels of the M green wave traffic sections based on the congestion characteristic parameters of the M sections, and determining a first green wave traffic section; Using the green wave traffic reward function, respectively evaluate the strategy parameters of the N green wave traffic control strategy solution spaces to obtain N green wave traffic strategy reward sets; According to the N green wave traffic control strategy solution spaces, obtaining N first green wave traffic control strategy sets for the first green wave traffic section; Compare and select the N first green wave traffic control strategy sets based on the N green wave traffic strategy reward degree sets, and determine the N first green wave traffic strategy parameters with the largest reward degrees; Based on the N first green wave traffic strategy parameters, respectively, the N green wave traffic control strategy solution spaces are optimized for strategy balance to determine the N green wave traffic control strategy parameters; The determining of the N green wave traffic control strategy parameters includes: Acquire an upper-level green wave traffic section set and a lower-level green wave traffic section set of the first green wave traffic section from the remaining green wave traffic sections; Based on the N first green wave traffic strategy parameters, the strategy parameter set of the upper green wave traffic section is traversed based on the strategy equilibrium cost function to calculate the payment cost of the reward loss, and N upper section control strategy parameters are obtained; Based on the N first green wave traffic strategy parameters, the strategy equilibrium cost function is used to traverse the strategy parameter set of the lower-level green wave traffic section to calculate the payment cost of the reward loss, and obtain N lower-level section control strategy parameters; The N green wave traffic control strategy parameters are determined based on the N first green wave traffic strategy parameters, the N upper-level road section control strategy parameters and the N lower-level road section control strategy parameters.

2. The green wave traffic optimization method for urban traffic according to claim 1, characterized in that: The obtaining of M green wave traffic sections comprises: Divide the target green wave road section area into sections according to the intersection information to obtain multiple area road section information, and extract the flow data association of the multiple area road section information based on the road traffic operation data flow to obtain multiple road section traffic flow association data flows; Performing traffic flow trend analysis on the traffic flow associated data streams of the plurality of road sections to obtain traffic flow trend parameter information of the plurality of road sections, wherein the traffic flow trend parameter information of the plurality of road sections includes average flow, speed and density; Based on the traffic trend parameter information of the multiple road sections, traffic characteristics are identified and impact degree is evaluated to obtain traffic impact factors of the multiple road sections; The multiple regional road section information is subdivided into key sections according to the multiple road section traffic impact factors to obtain the M green wave traffic sections.

3. The green wave traffic optimization method for urban traffic according to claim 1, characterized in that: The method comprises: Based on the N green wave traffic control strategy parameters, green wave traffic control monitoring is performed on the target green wave road section area to obtain green wave traffic control feedback parameters; Performing traffic optimization analysis on the green wave traffic control feedback parameters to obtain strategy parameter variation rules, and performing variation optimization on the N green wave traffic control strategy parameters based on the strategy parameter variation rules to obtain N green wave traffic optimization control strategy parameters; Dynamically optimize traffic control on the target green wave road section area based on the N green wave traffic optimization control strategy parameters.

4. A green wave traffic optimization system for urban traffic, characterized in that: The system is used to execute the green wave traffic optimization method for urban traffic according to any one of claims 1 to 3, and the system comprises: A green wave traffic section identification module, which is used to collect and obtain road traffic operation data flow of a target green wave section area using road surface information equipment, and perform traffic flow analysis and key section identification on the target green wave section area based on the road traffic operation data flow to obtain M green wave traffic sections; A congestion feature identification module, the congestion feature identification module is used to map and associate the road traffic operation data stream with the M green wave traffic sections, obtain M section operation data streams, and perform congestion feature identification on the M section operation data streams respectively to obtain a set of congestion features of the M sections; A green wave strategy analysis module, the green wave strategy analysis module is used to divide the green wave time periods based on the congestion feature sets of the M road sections to obtain N green wave coordination time periods, and to perform green wave strategy analysis on the congestion feature sets of the M road sections according to the N green wave coordination time periods, and to construct N green wave traffic control strategy solution spaces, wherein a corresponding green wave traffic control strategy is constructed for each time period through green wave strategy analysis, and these strategies form a solution space, which includes green wave control schemes for different road sections, and N green wave coordination time periods correspond to N green wave traffic control strategy solution spaces, wherein N is a positive integer representing the number of green wave coordination time periods; A traffic control optimization analysis module, the traffic control optimization analysis module is used to construct a green wave traffic reward function according to the green wave traffic balance target, and use the green wave traffic reward function to perform traffic control optimization analysis on the N green wave traffic control strategy solution spaces respectively to determine N green wave traffic control strategy parameters. The green wave traffic control strategy parameters are the optimal green wave traffic control parameters for each green wave coordination period determined after optimization analysis. These parameters include the green and red light durations and phase timing of the traffic lights; A green wave traffic control module is used to perform green wave traffic control and dynamic optimization regulation on the target green wave road section area based on the N green wave traffic control strategy parameters.

Images