Multi-source data interaction traffic light control optimization method and system

Abstract

The invention discloses a traffic light control optimization method and system based on multi-source data interaction, and relates to the technical field of intelligent traffic, and the method comprises the steps: obtaining a real-time traffic information data set of a target road section; constructing a real-time traffic twin model based on the real-time traffic information data set, and embedding a traffic prediction model for traffic jam prediction to obtain a jam result; dynamically determining a vehicle passing priority, and generating a traffic light control target based on the congestion result and the vehicle passing priority; randomly simulating different signal timing schemes through a real-time traffic twin model, determining a traffic efficiency index evaluation result set, and selecting an optimal control strategy according to the traffic efficiency index evaluation result set; and adjusting traffic light signals of the target road section based on the optimal control strategy. The technical problems that traffic light signal timing is not flexible and traffic flow changes cannot be adapted in real time in the prior art are solved, and the technical effects of improving the traffic flow efficiency, reducing traffic congestion and improving the priority traffic capacity of emergency vehicles are achieved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation technology, and in particular to a traffic light control optimization method and system with multi-source data interaction. Background Art

[0002] With the continuous expansion of urban traffic scale and the increasing traffic flow, traditional traffic light control systems can no longer effectively cope with the rapid changes in daily traffic flow. Existing traffic light signal timing methods are mostly fixed modes or simple periodic adjustments, which leads to a lack of flexibility in signal timing and the inability to adapt to traffic needs in different time periods in real time. In addition, traditional methods fail to make full use of real-time traffic data and cannot accurately predict changes in traffic flow, resulting in traffic congestion, increased delays, and poor passage of emergency vehicles, which in turn affects the efficiency and safety of traffic management. Summary of the invention

[0003] The present application provides a traffic light control optimization method and system with multi-source data interaction, which is used to solve the technical problems in the prior art that traffic light signal timing is inflexible and cannot adapt to traffic flow changes in real time.

[0004] In view of the above problems, the present application provides a traffic light control optimization method and system with multi-source data interaction.

[0005] In a first aspect of the present application, a traffic light control optimization method with multi-source data interaction is provided, the method comprising:

[0006] Acquire a real-time traffic information data set of the target road section, wherein the real-time traffic information data set includes at least real-time traffic flow data and vehicle speed; construct a real-time traffic twin model based on the real-time traffic information data set, and embed the traffic prediction model to perform traffic congestion prediction and obtain congestion results; dynamically determine vehicle traffic priority, and generate traffic light control targets based on the congestion results and vehicle traffic priority; randomly simulate different signal timing schemes through the real-time traffic twin model to determine a traffic efficiency index evaluation result set, and select an optimal control strategy based on the traffic efficiency index evaluation result set; adjust the traffic light signal of the target road section based on the optimal control strategy.

[0007] A second aspect of the present application provides a traffic light control optimization system with multi-source data interaction, the system comprising:

[0008] A data acquisition module for acquiring a real-time traffic information dataset of a target road section, where the real-time traffic information dataset at least includes real-time traffic flow data and vehicle speeds; a congestion result acquisition module for constructing a real-time traffic twin model based on the real-time traffic information dataset, embedding a traffic prediction model, performing traffic congestion prediction, and obtaining congestion results; a control target generation module for dynamically determining vehicle passing priorities and generating traffic light control targets based on the congestion results and vehicle passing priorities; an optimal control strategy determination module for randomly simulating different signal timing schemes through the real-time traffic twin model, determining a traffic efficiency index evaluation result set, and selecting an optimal control strategy according to the traffic efficiency index evaluation result set; and a traffic light signal control module for adjusting the traffic light signals of the target road section based on the optimal control strategy.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] This application acquires a real-time traffic information dataset of a target road section, where the real-time traffic information dataset at least includes real-time traffic flow data and vehicle speeds; constructs a real-time traffic twin model based on the real-time traffic information dataset, embeds a traffic prediction model, performs traffic congestion prediction, and obtains congestion results; dynamically determines vehicle passing priorities, and generates traffic light control targets based on the congestion results and vehicle passing priorities; randomly simulates different signal timing schemes through the real-time traffic twin model, determines a traffic efficiency index evaluation result set, and selects an optimal control strategy according to the traffic efficiency index evaluation result set; and adjusts the traffic light signals of the target road section based on the optimal control strategy. This invention solves the technical problems in the prior art that the traffic light signal timing is inflexible and cannot adapt to traffic flow changes in real time, and achieves the technical effects of improving traffic flow efficiency, reducing traffic congestion, and enhancing the priority passing ability of emergency vehicles through real-time collection of multi-source traffic data and dynamic optimization in combination with a traffic prediction model. Description of the Drawings

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for description in the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0012] Figure 1 It is a schematic flowchart of a traffic light control optimization method for multi-source data interaction provided in an embodiment of this application;

[0013] Figure 2 It is a schematic structural diagram of a traffic light control optimization system for multi-source data interaction provided in an embodiment of this application.

[0014] Explanation of reference numerals: data acquisition module 11, congestion result acquisition module 12, control target generation module 13, optimal control strategy determination module 14, traffic signal control module 15. Specific implementation mode

[0015] The present application provides a traffic light control optimization method and system with multi-source data interaction, aiming to solve the technical problems in the prior art that the traffic signal timing is inflexible and cannot adapt to traffic flow changes in real time. By collecting multi-source traffic data in real time and combining with a traffic prediction model for dynamic optimization, the technical effects of improving traffic flow efficiency, reducing traffic congestion, and enhancing the priority passage ability of emergency vehicles are achieved.

[0016] Next, the technical solutions in the embodiments of the present application will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0017] It should be noted that any variations of the terms "comprising" and "having" are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server comprising a series of steps or units is not necessarily limited to those clearly listed steps or units, but may include other steps or modules not clearly listed or inherent to these processes, methods, products or devices.

[0018] Embodiment 1, as Figure 1 shown, the present application provides a traffic light control optimization method with multi-source data interaction, and the method includes:

[0019] Step S100: Obtain a real-time traffic information data set of the target road section, and the real-time traffic information data set at least includes real-time traffic flow data and vehicle speed.

[0020] In the embodiment of the present application, first, a series of traffic monitoring devices deployed on the target road section, such as cameras, sensors or radars, are used to collect traffic flow data and vehicle speed information in real time. Traffic flow data represents the number of vehicles passing through a certain road section per unit time, while vehicle speed reflects the speed at which vehicles travel on this road section. By using traffic monitoring devices to collect data on the target road section, a real-time traffic information data set is obtained.

[0021] Step S200: Based on the real-time traffic information data set, construct a real-time traffic twin model, embed a traffic prediction model, perform traffic congestion prediction, and obtain a congestion result.

[0022] In the embodiments of the present application, based on the real-time traffic information dataset, a real-time traffic twin model is constructed through data preprocessing and fusion with the topological map of the target road section. Then, a traffic prediction model is embedded therein, and the future traffic congestion situation is predicted using the real-time traffic state characteristics, and a congestion probability is generated. Finally, the congestion probability is compared with a preset threshold to obtain a congestion result including the congestion location and level.

[0023] Further, in the method provided by the application embodiments, based on the real-time traffic information dataset, a real-time traffic twin model is constructed, a traffic prediction model is embedded, and traffic congestion prediction is performed, and it further includes:

[0024] Perform data preprocessing on the real-time traffic information dataset, fuse the preprocessed real-time traffic information dataset with the topological map of the target road section to construct a real-time traffic twin model, where the real-time traffic twin model includes a road network topological structure and a vehicle trajectory simulation module; embed the traffic prediction model into the real-time traffic twin model, where the traffic prediction model is used to receive the real-time traffic state characteristics output by the real-time traffic twin model and generate the congestion probability in each direction within a future time period; compare the congestion probability with a preset threshold to generate a congestion result including the congestion location and level.

[0025] In the embodiments of the present application, to construct a real-time traffic twin model based on the real-time traffic information dataset and perform traffic congestion prediction, first, data preprocessing is performed on the real-time traffic information dataset. Data preprocessing includes steps such as removing invalid or abnormal data, filling in missing values, and normalizing the data. This process usually uses data cleaning methods, such as outlier detection and interpolation methods, to process incomplete or incorrect traffic data. After preprocessing, key data such as traffic flow and vehicle speed will be organized into a format that can be used for further analysis. Subsequently, the real-time traffic information dataset is fused with the topological map of the target road section. This step uses a fusion algorithm, such as dynamic time warping (DTW), to combine the real-time traffic data with the road network topological map of the target road section. The road network topological map describes the structure of the road network, including intersections, the number of lanes, and the connection relationships between roads, which is pre-determined. Through this fusion, the model can simultaneously consider traffic flow, vehicle speed, and the spatial characteristics of the road network, ensuring the coordination between traffic data and the road network structure. This process enables traffic data to be combined with the spatial layout of the road to form a complete description of the traffic system.

[0026] Next, based on the fused data, a traffic twin modeling method is used to construct a real-time traffic twin model. The twin model is a digital replica of the real traffic environment, aiming to simulate the changes in real traffic flow. During the construction process, the twin model includes a road network topology and a vehicle trajectory simulation module. The road network topology reflects the layout of the roads, while the vehicle trajectory simulation module can dynamically simulate the changes and development of traffic flow by simulating factors such as the driving paths and speed changes of vehicles.

[0027] After the traffic twin model is constructed, the traffic prediction model is then embedded into it. The function of the traffic prediction model is to predict future traffic conditions by using the real-time traffic state features (such as traffic flow, vehicle speed, etc.) provided by the traffic twin model. Through algorithms such as machine learning or deep learning, the traffic prediction model can analyze and learn historical and real-time data, predict the traffic flow changes of each road section in the future for a period of time, and thus calculate the congestion probability in each direction in the future. The prediction model generates the congestion conditions of different directions or road sections by processing real-time data, and then provides information on possible future traffic congestion.

[0028] Finally, the predicted congestion probability is compared with a preset congestion threshold. The preset threshold is set by technical experts based on historical traffic data and the system. There are multiple congestion thresholds, and each threshold corresponds to a different congestion level. For example, the threshold corresponding to a low congestion probability is less than 30%, indicating only a light traffic flow on the road section; the threshold for a medium congestion probability is between 30% and 70%, indicating that medium-level congestion may occur on the road section; while a high congestion probability corresponds to a threshold greater than 70%, indicating that the road section may be severely congested. By comparing with these different thresholds, specific congestion results are generated, and the congestion location and congestion level are clearly identified. The congestion level is divided into three levels, level 1 is light congestion, level 2 is medium congestion, and level 3 is severe congestion.

[0029] Furthermore, in the method provided by the application embodiment, embedding the traffic prediction model further includes:

[0030] Obtaining a sample traffic state feature set and a corresponding sample congestion probability set; using the sample traffic state feature set as the input and the sample congestion probability set as the output for model training to obtain the traffic prediction model; and embedding the traffic prediction model into the real-time traffic twin model.

[0031] In the embodiments of the present application, first, a sample traffic state feature set and a corresponding sample congestion probability set are obtained from a preset database. The sample traffic state feature set includes various key data extracted from real-time traffic information, such as traffic flow, vehicle speed, vehicle density, etc., which are characteristic variables reflecting the current traffic conditions of the road. The sample congestion probability set is the congestion probability value corresponding to these traffic state characteristics, marked by technical experts, indicating the probability of congestion occurring on a section of the road under specific traffic conditions.

[0032] Next, the sample traffic state feature set is used as the input, and the sample congestion probability set is used as the output for model training. This process adopts the method of supervised learning and uses machine learning or deep learning algorithms, such as decision trees, support vector machines (SVMs), neural networks, etc. During the training process, the model analyzes a large amount of sample data and learns the relationship between traffic state characteristics and congestion probabilities. By optimizing the model parameters, the model can accurately predict the future traffic congestion probability based on the input traffic state characteristics. The goal of model training is to minimize the error between the predicted value and the actual value, thereby obtaining a traffic prediction model that can effectively predict traffic congestion probabilities.

[0033] Once the traffic prediction model is trained, the next step is to embed the model into the real-time traffic twin model. During this process, the traffic prediction model is docked with the output results of the real-time traffic twin model (such as traffic state characteristics such as traffic flow and vehicle speed). The real-time traffic twin model provides simulated traffic state characteristics that reflect the current traffic conditions of the road in real time. The traffic prediction model then uses these real-time characteristics to predict the traffic congestion probability in the future time period. By embedding the traffic prediction model, the twin model can not only reflect the current traffic state but also dynamically predict future congestion situations, thereby providing decision-making support for traffic management.

[0034] Step S300: Dynamically determine the vehicle passing priority, and generate a traffic light control target based on the congestion result and the vehicle passing priority.

[0035] In the embodiments of the present application, it starts with obtaining the real-time vehicle types of the target section, and different types of vehicles, such as emergency vehicles, public transportation vehicles, and ordinary vehicles, are identified in real time through sensors or other traffic monitoring devices. According to different vehicle types, preset priorities are assigned, and corresponding weights are set according to each type, where the weights are preset.

[0036] After obtaining the real-time vehicle priority information, the priority control target is calculated in combination with the congestion result. The congestion result reflects the traffic conditions of each road section. By analyzing the congestion location and level, it is determined which road sections have a large traffic flow and which road sections may experience severe congestion. Based on this information, the priority control needs to release the road sections for emergency or high-priority vehicles to avoid further traffic stagnation or congestion. Finally, based on the real-time vehicle priority information and the congestion result, the traffic light control target is generated.

[0037] Further, in the method provided by the application embodiment, the vehicle passing priority is dynamically determined, and the traffic light control target is generated based on the congestion result and the vehicle passing priority, and further includes:

[0038] Obtain the real-time vehicle types of the target road section, assign preset priorities according to the real-time vehicle types, and set predetermined weights to obtain the real-time vehicle priority information; based on the real-time vehicle priority information, calculate the priority control target in combination with the congestion result to determine the traffic light control target.

[0039] In the embodiment of the present application, first, the real-time vehicle types of the target road section are obtained, and different types of vehicles are identified in real time through sensors or other traffic monitoring devices. Specifically, the vehicle recognition model is used to identify the vehicles. The vehicle recognition model is trained by a convolutional neural network through a vehicle sample photo set and the corresponding vehicle model label set.

[0040] Next, preset priorities are assigned to each type of vehicle according to the real-time vehicle types. Emergency vehicles are given the highest priority (for example, level 3) to ensure their priority passage in case of emergency. Public transportation vehicles usually obtain medium priority (for example, level 2) according to traffic strategies and actual needs. Ordinary private cars usually have a lower priority (for example, level 1). In addition to assigning priorities, predetermined weights are also set to adjust the priority weights of various types of vehicles, and these weights are preset.

[0041] Subsequently, based on the real-time vehicle priority information and the congestion result, the priority control target is calculated. In this step, the real-time vehicle priority information on each road section is combined with the congestion level in the congestion result. First, the number of vehicles on each route is multiplied by the corresponding vehicle priority, then multiplied by the preset weight, and finally weighted calculation is performed according to the congestion level of each road section. In this way, the control level of each route is obtained. Then, all the calculated control levels are compared, and the road section with the highest control level is selected as the object of priority control, so as to determine the traffic light control target of this road section.

[0042] Step S400: Randomly simulate different signal timing plans through the real-time traffic twin model, determine the evaluation result set of traffic efficiency indicators, and select the optimal control strategy according to the evaluation result set of traffic efficiency indicators.

[0043] In the embodiment of the present application, first, a historical signal timing plan set is obtained and a signal timing plan space is established. This space contains all the feasible signal timing plans in history, and each plan includes parameters such as green light duration, red light duration, and signal switching sequence. Next, different signal timing plans are iteratively and randomly extracted from this signal timing plan space, and these plans are applied to the real-time traffic twin model for simulation. Through this simulation, the actual impact of each signal timing plan on the traffic flow is evaluated, and relevant traffic efficiency indicators are calculated, such as the average vehicle delay time, traffic volume, and congestion level. These evaluation results form the evaluation result set of traffic efficiency indicators. Based on these evaluation results, all the plans are compared, and the optimal control strategy is selected.

[0044] Furthermore, in the method provided by the embodiment of the application, randomly simulating different signal timing plans through the real-time traffic twin model to determine the evaluation result set of traffic efficiency indicators further includes:

[0045] Obtain a historical signal timing plan set, establish a signal timing plan space; iteratively and randomly extract signal timing plans from the signal timing plan space, apply them to the real-time traffic twin model for simulation, and conduct traffic efficiency indicator evaluation to determine the evaluation result set of traffic efficiency indicators.

[0046] In the embodiment of the present application, first, a historical signal timing plan set is obtained, which includes different signal timing strategies implemented in the past, such as the green light time, red light time, and the switching sequence between each phase at each intersection. The historical signal timing plan set is collected by the traffic management department according to the actual road conditions and traffic flow data, covering a variety of different traffic signal timing methods, and these historical signal timing plan sets constitute the signal timing plan space.

[0047] Next, iterative random signal timing plans are extracted from the signal timing plan space and applied to the real-time traffic twin model for simulation to simulate the performance of each plan under actual traffic conditions. Next, quantitative analysis is carried out on the performance of each signal timing plan through traffic efficiency index evaluation. Traffic efficiency indexes include average vehicle delay time, traffic volume, congestion level, etc. The average vehicle delay time is an important index to measure the waiting time of vehicles at intersections, representing the average time for vehicles to enter the red-light section and leave the intersection. It is obtained by calculating the waiting time of all vehicles passing through the intersection and then taking the average value. If a signal timing plan causes vehicles to wait for a long time, the delay time is longer; conversely, if the waiting time is shorter, it indicates that the plan is more efficient. For example, if a signal timing plan results in an average waiting time of 15 seconds per vehicle, while another plan is 30 seconds, the former has a lower delay time and higher traffic efficiency. The traffic volume is an index to measure traffic flow, representing the number of vehicles passing through the intersection per unit time. The larger the traffic volume, the smoother the traffic flow. For example, if a signal timing plan allows 100 vehicles to pass through the intersection per minute, while another plan only allows 80 vehicles, the former has a larger traffic volume, indicating that the plan is more favorable for traffic flow. The congestion level is an index to measure the traffic conditions of road sections or intersections, usually evaluated by traffic flow density and vehicle queue length. A plan with a high congestion level means dense traffic flow and long vehicle detention. For example, some signal timing plans may lead to excessive traffic flow, resulting in long vehicle queues and backlogs, generating a high congestion level; while other plans may effectively alleviate these problems and reduce congestion.

[0048] By calculating these traffic efficiency indexes, the evaluation results of each signal timing plan are generated. Specifically, according to the simulation results, the average vehicle delay time, traffic volume, and congestion level under each signal timing plan are calculated, and these indexes are combined to form an evaluation result set. Suppose there are two signal timing plans, Plan A and Plan B. The average vehicle delay time of Plan A is 15 seconds, the traffic volume is 100 vehicles / minute, and the congestion level is low; the average vehicle delay time of Plan B is 30 seconds, the traffic volume is 80 vehicles / minute, and the congestion level is high. From these two indexes, Plan A is significantly better than Plan B because it not only has a lower delay time but also can ensure a larger traffic volume and a lower congestion level.

[0049] Finally, based on all the calculated traffic efficiency index evaluation result sets, these plans are compared, and the optimal traffic light control strategy is selected.

[0050] Furthermore, in the method provided by the application embodiment, the iterative random signal timing plan extraction from the signal timing plan space and its application to the real-time traffic twin model for simulation further includes:

[0051] Generate an initial population based on the signal timing plan space. Each individual represents a timing plan, including phase difference, green light duration ratio, and phase switching sequence encoding. Input each timing plan into the real-time traffic twin model for simulation, calculate traffic efficiency indicators, including average vehicle delay time, traffic volume, and emergency vehicle priority passing rate, and generate a fitness score. Select high-score individuals according to the fitness score, generate offspring plans through single-point crossover operations, and retain the excellent parameter combinations of the parent generation. Perform Gaussian mutation on the phase difference and green light duration ratio in the offspring plans. When the fitness score improvement rate for three consecutive iterations is less than the preset threshold, output the current optimal timing plan as the optimal control strategy.

[0052] In the embodiment of the present application, first, an initial population is generated based on the signal timing plan space. Each individual represents a signal timing plan, which includes the phase difference (i.e., the time interval between different traffic signals), the green light duration ratio (indicating the proportion of the green light duration in the entire cycle), and the phase switching sequence encoding (determining the order of signal switching). These factors are the basic parameters for optimizing signal timing, and by adjusting these parameters, the efficiency of the traffic flow can be affected.

[0053] Next, each timing plan is input into the real-time traffic twin model for simulation. The traffic twin model is a digital replication of the actual traffic environment, which can reflect dynamic factors such as traffic flow, vehicle speed, and congestion level in real time. By applying the signal timing plan to the twin model, the effects of each plan under real traffic conditions can be simulated. During the simulation, multiple traffic efficiency indicators are calculated, including the average vehicle delay time (i.e., the average waiting time of vehicles during the red light period), the traffic volume (i.e., the number of vehicles passing through the intersection per unit time), and the emergency vehicle priority passing rate (i.e., the passing priority of emergency vehicles under traffic light control, which is evaluated by tracking the passing situation of emergency vehicles under each signal timing plan and calculating the ratio of emergency vehicles passing through the intersection).

[0054] Subsequently, the index values of each plan are calculated through the simulation results, and then a fitness score is generated. The fitness score is used to measure the quality of the signal timing plan by converting these efficiency indicators into a comprehensive score. Specifically, the fitness score calculation method usually synthesizes the results of each index through a weighted average method. When calculating the fitness score, it is calculated through the formula where w1, w2, and w3 are preset weights.

[0055] After that, high-scoring individuals are selected according to the fitness score. In the genetic algorithm, the selection operation is based on the fitness of individuals. The higher the fitness of an individual, the greater the probability of being selected. Through single-point crossover operation, some parameters are selected from two parent individuals for exchange to generate offspring individuals. For example, assume that the green light duration ratio and phase switching order of two signal timing plans are A and B respectively. In the crossover operation, the green light duration ratio of A is combined with the phase switching order of B to generate a new offspring plan. In this way, the high-quality parameter combinations in the parents are passed on to the offspring for further optimization of the signal timing strategy.

[0056] Next, Gaussian mutation is performed on the generated offspring plans. The mutation operation enhances the exploration ability of the algorithm and avoids falling into local optimal solutions by making small random adjustments to certain parameters (such as phase difference and green light duration ratio). Gaussian mutation means fine-tuning these parameters according to the normal distribution (Gaussian distribution), that is, generating new parameter values by adding a random number drawn from the normal distribution to the original parameters. Mutation can explore new signal timing combinations and increase the diversity of the search.

[0057] When the improvement rate of the fitness score in three consecutive iterations is lower than the preset threshold, it is considered that convergence has occurred and the search process is close to the optimal solution. At this time, the current timing plan with the highest fitness score is output as the optimal control strategy to end the optimization process. This optimal plan can provide the best signal timing strategy in reducing traffic delays, increasing traffic volume, and giving priority to emergency vehicles.

[0058] Step S500: Adjust the traffic lights of the target road section based on the optimal control strategy.

[0059] In the embodiment of the present application, the traffic light signal timing of this road section is adjusted according to the signal timing plan (such as green light duration, red light duration, phase switching order, etc.) in the optimal control strategy. Through this process, the road traffic efficiency is optimized, traffic congestion is reduced, and the priority passing ability of emergency vehicles can also be improved, ultimately realizing intelligent and dynamic traffic management.

[0060] Further, in the method provided by the embodiment of the application, after adjusting the traffic lights of the target road section based on the optimal control strategy, it further includes:

[0061] Real-time collect the adjusted traffic flow data, and calculate the actual traffic efficiency index under the current control strategy; conduct deviation analysis on the actual traffic efficiency index and the simulated prediction index. If the deviation exceeds the preset deviation threshold, trigger the dynamic correction mechanism, re-extract the real-time traffic information data set, update the real-time traffic twin model; generate a corrected control strategy based on the updated twin model and replace the current traffic light signal timing plan.

[0062] In the embodiment of the present application, first, traffic monitoring devices installed on the road section, such as geomagnetic sensors, video monitoring systems, and radar sensors, are used to obtain information such as traffic flow, vehicle speed, and vehicle density on the road in real time. Then, the actual traffic efficiency index under the current control strategy is calculated by the same method as described above.

[0063] Next, the deviation analysis is carried out on the calculated actual traffic efficiency index and the traffic efficiency index predicted by the real-time traffic twin model before. The real-time traffic twin model is a digital replication of the target road section. By simulating factors such as traffic flow and signal timing, it predicts the traffic performance under different traffic light timing schemes. The prediction results usually include vehicle delay, traffic volume, and congestion prediction, etc. By comparing the actual traffic efficiency index and the simulated prediction index, the deviation value is calculated, usually through error analysis methods such as mean square error. If the deviation exceeds the preset deviation threshold, it means that the current traffic light timing scheme fails to achieve the expected effect, and the dynamic correction mechanism is triggered.

[0064] After the dynamic correction mechanism is triggered, the real-time traffic information dataset is re-extracted, and the latest data such as traffic flow, vehicle speed, and vehicle type are re-collected and processed. These data are used to update the real-time traffic twin model, which is corrected based on the new traffic information, and the effects of different signal timing schemes are re-evaluated. Through real-time feedback and data adjustment, the traffic twin model can simulate the current traffic environment and provide more accurate traffic prediction results.

[0065] Based on the updated twin model, a new corrected control strategy is generated, and the optimal traffic light control strategy is recalculated through signal timing optimization algorithms (such as genetic algorithms, particle swarm optimization, etc.). Finally, the new control strategy replaces the current signal timing scheme, so as to achieve more efficient traffic management, further optimize traffic flow, reduce congestion, and improve traffic efficiency.

[0066] In the embodiment of the present application, in summary, the embodiment of the present application has at least the following technical effects:

[0067] This application obtains a real-time traffic information dataset for a target road section. The real-time traffic information dataset at least includes real-time traffic flow data and vehicle speeds. Based on the real-time traffic information dataset, a real-time traffic twin model is constructed and embedded into a traffic prediction model to perform traffic congestion prediction and obtain congestion results. The vehicle passing priority is dynamically determined, and a traffic light control target is generated based on the congestion results and the vehicle passing priority. Different signal timing schemes are randomly simulated through the real-time traffic twin model to determine a traffic efficiency index evaluation result set, and an optimal control strategy is selected according to the traffic efficiency index evaluation result set. The traffic lights of the target road section are adjusted based on the optimal control strategy. The present invention solves the technical problems in the prior art that the signal timing of traffic lights is inflexible and cannot adapt to traffic flow changes in real time. By collecting multi-source traffic data in real time and combining with a traffic prediction model for dynamic optimization, the technical effects of improving traffic flow efficiency, reducing traffic congestion, and enhancing the priority passing ability of emergency vehicles are achieved.

[0068] Embodiment 2, based on the same inventive concept as the traffic light control optimization method with multi-source data interaction in the foregoing embodiment, as Figure 2 shown, this application provides a traffic light control optimization system with multi-source data interaction. The system in the embodiments of this application and the method embodiments are based on the same inventive concept. Among them, the system includes:

[0069] A data acquisition module 11, configured to obtain a real-time traffic information dataset for a target road section. The real-time traffic information dataset at least includes real-time traffic flow data and vehicle speeds; a congestion result acquisition module 12, configured to construct a real-time traffic twin model based on the real-time traffic information dataset, embed a traffic prediction model, perform traffic congestion prediction, and obtain congestion results; a control target generation module 13, configured to dynamically determine the vehicle passing priority, and generate a traffic light control target based on the congestion results and the vehicle passing priority; an optimal control strategy determination module 14, configured to randomly simulate different signal timing schemes through the real-time traffic twin model, determine a traffic efficiency index evaluation result set, and select an optimal control strategy according to the traffic efficiency index evaluation result set; a traffic light signal control module 15, configured to adjust the traffic lights of the target road section based on the optimal control strategy.

[0070] Furthermore, the system is also used to implement the following functions:

[0071] Perform data preprocessing on the real-time traffic information dataset, fuse the preprocessed real-time traffic information dataset with the target road section topology map to construct a real-time traffic twin model, where the real-time traffic twin model includes a road network topology structure and a vehicle trajectory simulation module; embed the traffic prediction model into the real-time traffic twin model, where the traffic prediction model is used to receive the real-time traffic state features output by the real-time traffic twin model and generate the congestion probability in each direction within a future time period; compare the congestion probability with a preset threshold to generate a congestion result including the congestion location and level.

[0072] Furthermore, the system is also used to implement the following functions:

[0073] Obtain a sample traffic state feature set and a corresponding sample congestion probability set; use the sample traffic state feature set as the input and the sample congestion probability set as the output for model training to obtain the traffic prediction model; embed the traffic prediction model into the real-time traffic twin model.

[0074] Furthermore, the system is also used to implement the following functions:

[0075] Obtain the real-time vehicle types on the target road section, assign preset priorities according to the real-time vehicle types, and set predetermined weights to obtain real-time vehicle priority information; based on the real-time vehicle priority information, combine with the congestion result to calculate the priority control target and determine the traffic light control target.

[0076] Furthermore, the system is also used to implement the following functions:

[0077] Obtain a historical signal timing plan set, establish a signal timing plan space; extract iterative random signal timing plans from the signal timing plan space, apply them to the real-time traffic twin model for simulation, and conduct traffic efficiency index evaluation to determine the traffic efficiency index evaluation result set.

[0078] Furthermore, the system is also used to implement the following functions:

[0079] Generate an initial population based on the signal timing plan space, where each individual represents a timing plan, including phase difference, green light duration ratio, and phase switching sequence encoding; input each timing plan into the real-time traffic twin model for simulation, calculate traffic efficiency indexes, including average vehicle delay time, traffic volume, and emergency vehicle priority passing rate, and generate fitness scores; select high-score individuals according to the fitness scores, generate offspring plans through single-point crossover operations, and retain the high-quality parameter combinations of the parent generation; perform Gaussian mutation on the phase difference and green light duration ratio in the offspring plans, and when the fitness score improvement rate for three consecutive iterations is less than the preset threshold, output the current optimal timing plan as the optimal control strategy.

[0080] Furthermore, the system is also used to implement the following functions:

[0081] Collect the adjusted traffic flow data in real time, calculate the actual traffic efficiency index under the current control strategy; conduct deviation analysis on the actual traffic efficiency index and the simulated prediction index. If the deviation exceeds the preset deviation threshold, trigger the dynamic correction mechanism, re-extract the real-time traffic information dataset, and update the real-time traffic twin model; generate a corrected control strategy based on the updated twin model and replace the current traffic signal timing plan.

[0082] It should be noted that the above order of the embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above description of specific embodiments of this specification has been made. The processes depicted in the drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0083] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included within the protection scope of the present application.

[0084] This specification and the drawings are only exemplary descriptions of the present application and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. A traffic light control optimization method with multi-source data interaction, characterized in that: The method comprises: Acquire a real-time traffic information data set of a target road section, wherein the real-time traffic information data set at least includes real-time traffic flow data and vehicle speed; Based on the real-time traffic information data set, a real-time traffic twin model is constructed, and a traffic prediction model is embedded to perform traffic congestion prediction and obtain congestion results; Dynamically determine vehicle traffic priority, and generate a traffic light control target based on the congestion result and the vehicle traffic priority; By randomly simulating different signal timing schemes through the real-time traffic twin model, a traffic efficiency index evaluation result set is determined, and an optimal control strategy is selected according to the traffic efficiency index evaluation result set; The traffic light signal of the target road section is adjusted based on the optimal control strategy.

2. The traffic light control optimization method with multi-source data interaction as claimed in claim 1, characterized in that: Based on the real-time traffic information dataset, a real-time traffic twin model is constructed and embedded into a traffic prediction model to perform traffic congestion prediction, including: Preprocessing the real-time traffic information data set, fusing the preprocessed real-time traffic information data set with the target road section topology map, and constructing a real-time traffic twin model, wherein the real-time traffic twin model includes a road network topology structure and a vehicle trajectory simulation module; The traffic prediction model is embedded in the real-time traffic twin model, wherein the traffic prediction model is used to receive the real-time traffic status characteristics output by the real-time traffic twin model and generate the congestion probability of each direction in the future time period; The congestion probability is compared with a preset threshold to generate a congestion result including a congestion location and level.

3. The traffic light control optimization method with multi-source data interaction as claimed in claim 2, characterized in that: Embedded traffic prediction models, including: Obtain a sample traffic state feature set and a corresponding sample congestion probability set; Taking the sample traffic state feature set as input and the sample congestion probability set as output to perform model training, thereby obtaining the traffic prediction model; The traffic prediction model is embedded into the real-time traffic twin model.

4. The traffic light control optimization method with multi-source data interaction as claimed in claim 1, characterized in that: Dynamically determine vehicle traffic priority, and generate traffic light control targets based on the congestion results and vehicle traffic priority, including: Acquire the real-time vehicle type of the target road section, assign a preset priority according to the real-time vehicle type, and set a predetermined weight to obtain real-time vehicle priority information; Based on the real-time vehicle priority information and combined with the congestion result, a priority control target is calculated to determine the traffic light control target.

5. The traffic light control optimization method with multi-source data interaction as claimed in claim 1, characterized in that: The real-time traffic twin model is used to randomly simulate different signal timing schemes to determine a set of traffic efficiency index evaluation results, including: Obtain the historical signal timing plan set and establish the signal timing plan space; An iterative random signal timing scheme is extracted from the signal timing scheme space, applied to the real-time traffic twin model for simulation, and a traffic efficiency index evaluation is performed to determine a traffic efficiency index evaluation result set.

6. The traffic light control optimization method with multi-source data interaction as claimed in claim 5, characterized in that: Iteratively extracting random signal timing schemes from the signal timing scheme space and applying them to the real-time traffic twin model for simulation includes: Generate an initial population based on the signal timing scheme space, where each individual represents a timing scheme, including phase difference, green light duration ratio, and phase switching sequence encoding; Each timing plan is input into the real-time traffic twin model for simulation, and traffic efficiency indicators are calculated, including average vehicle delay time, traffic volume, and emergency vehicle priority rate, to generate a fitness score; Select high-scoring individuals based on fitness scores, generate offspring solutions through single-point crossover operations, and retain high-quality parameter combinations of the parent generation; Gaussian mutation is performed on the phase difference and green light duration ratio in the offspring scheme. When the fitness score improvement rate of three consecutive iterations is less than a preset threshold, the current optimal timing scheme is output as the optimal control strategy.

7. The traffic light control optimization method with multi-source data interaction as claimed in claim 1, characterized in that: After adjusting the traffic light signal of the target road section based on the optimal control strategy, the method includes: Collect adjusted traffic flow data in real time and calculate the actual traffic efficiency index under the current control strategy; Perform deviation analysis on the actual traffic efficiency index and the simulated prediction index. If the deviation exceeds a preset deviation threshold, a dynamic correction mechanism is triggered to re-extract the real-time traffic information data set and update the real-time traffic twin model. Generate a revised control strategy based on the updated twin model to replace the current traffic light signal timing plan.

8. A traffic light control optimization system with multi-source data interaction, characterized in that: The system comprises: A data acquisition module, used to acquire a real-time traffic information data set of a target road section, wherein the real-time traffic information data set at least includes real-time traffic flow data and vehicle speed; A congestion result acquisition module is used to build a real-time traffic twin model based on the real-time traffic information data set, and embed the traffic prediction model to perform traffic congestion prediction and obtain congestion results; A control target generation module, used to dynamically determine vehicle traffic priority and generate a traffic light control target based on the congestion result and the vehicle traffic priority; An optimal control strategy determination module, used to randomly simulate different signal timing schemes through the real-time traffic twin model, determine a traffic efficiency index evaluation result set, and select an optimal control strategy according to the traffic efficiency index evaluation result set; The traffic light signal control module is used to adjust the traffic light signal of the target road section based on the optimal control strategy.

Images