Method for opening emergency lane in section under large traffic flow

Abstract

The invention provides a method for opening a section emergency lane under large traffic flow, which comprises the following steps: when the traffic flow density of a target section reaches a first saturation threshold value, starting an elastic lane dynamic decision engine, matching real-time traffic data with a starting criterion to generate an initial control decision, broadcasting the initial control decision, and triggering a first observation window; based on the section occupancy rate, generating a resource configuration scheme containing a starting gradient, issuing an intelligence mark updating instruction and triggering a second window; reconstructing an optimization strategy according to the blocking coefficient and setting a decision period, and triggering a third window after generating a dynamic configuration command broadcast; generating a final control instruction according to the millimeter wave radar response data and triggering a fourth window; and integrating the traffic efficiency indexes, determining an optimal elastic matching scheme through multi-cycle iteration, reconstructing a strategy, and returning to a strategy reconfiguration point to finally serve as an execution basis. According to the invention, the road network traffic efficiency under large traffic flow can be improved, and regional cooperative control and optimal resource configuration are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent traffic control, and more particularly, to a method for opening an emergency lane in a section under heavy traffic flow. Background Art

[0002] In today's society, with the acceleration of urbanization and the continuous increase in the number of motor vehicles, traffic congestion has become a key factor hindering urban development and improving residents' quality of life. Traffic congestion is particularly severe on roads with high traffic volumes, leading to inefficient traffic flow and potentially causing traffic accidents, further exacerbating traffic conditions. To alleviate this problem, existing traffic management measures primarily focus on optimizing signal timing, increasing road capacity, and implementing traffic control. Some regions are experimenting with opening emergency lanes for regular vehicles during specific hours in an effort to alleviate traffic pressure by increasing available road resources. However, these emergency lane opening measures often lack sophisticated control mechanisms and are typically based on manual judgment or simple traffic threshold triggering. These measures are difficult to dynamically adjust based on real-time traffic conditions, resulting in limited effectiveness in practice and potentially even introducing new traffic safety hazards.

[0003] Existing traffic flow control technologies primarily rely on fixed traffic rules and preset lane allocation schemes. These schemes are often inflexible when faced with sudden traffic peaks or unusual traffic events, and are unable to adapt promptly to rapid changes in traffic flow. Furthermore, while existing traffic monitoring equipment can provide certain traffic data, it still lacks real-time and accuracy, making it difficult to meet the needs of refined traffic control. Technically, existing traffic control systems often use static models and algorithms, lacking dynamic adaptability for traffic flow prediction and control, and failing to fully consider the spatiotemporal characteristics of traffic flow and the mutual influence between different road sections.

[0004] First, existing emergency lane opening measures lack intelligent and dynamic management and control mechanisms, and are unable to accurately allocate lane resources based on real-time traffic conditions; second, existing traffic monitoring equipment and data processing methods are insufficient in terms of data accuracy and real-time performance, making it difficult to meet the needs of refined traffic control; finally, the existing traffic control system lacks effective regional collaborative control capabilities when faced with complex traffic networks and changing traffic flows, and is unable to achieve global optimization of the entire traffic system. Summary of the Invention

[0005] The present invention provides a method for opening an emergency lane in a section with heavy traffic flow, comprising: After detecting that the traffic density of the target section reaches the first saturation threshold, the elastic lane dynamic decision engine is activated, matching the real-time traffic situation data with the elastic activation criteria, generating an initial control decision and broadcasting it to the roadside perception unit, while triggering the first observation window; After the first observation window closes, a lane resource allocation plan is generated based on the section occupancy index reported by the roadside sensing unit, and a status update instruction is issued to the variable intelligence sign to trigger the second observation window. The resource allocation plan includes a flexible lane activation gradient; After the second observation window closes, the lane optimization strategy is reconstructed based on the real-time congestion coefficient, and the current decision cycle is set to 1. The strategy reconfiguration point is entered. Based on the optimization strategy and decision cycle, a dynamic lane configuration command is generated and broadcast to the millimeter-wave radar, triggering the third observation window. After the third observation window closes, the final lane control instruction is generated based on the status response data of the millimeter-wave radar and broadcast to the signal controller, triggering the fourth observation window; After the fourth observation window is closed, the optimal elastic allocation scheme is determined through multi-cycle iteration based on the integrated vehicle traffic efficiency indicators. After reconstructing the optimization strategy during the iteration process, the strategy reconfiguration point is returned, and the optimal elastic allocation scheme is used as the basis for the execution of the dynamic lane control system.

[0006] Furthermore, based on the section occupancy rate indicators reported by the roadside sensing units, a lane resource allocation plan is generated, including: verifying the validity of the original data transmitted by the roadside sensing units. If the verification passes, the difference between the section occupancy rate and the output value of the dynamic baseline model is calculated to generate an elastic expansion coefficient; When the elastic expansion coefficient exceeds the second saturation threshold, the elastic lane activation gradient is mapped to a piecewise function of the expansion coefficient. The lane alignment optimization algorithm is used to calculate the channelization parameters corresponding to the gradient, and a resource allocation plan containing the activation gradient and channelization parameters is generated. When the elastic expansion coefficient does not exceed the second saturation threshold, the elastic lane enabling gradient is set to zero and a lane state maintaining instruction is generated.

[0007] Furthermore, it also includes: Cooperate with adjacent section control nodes to run the short-term traffic situation simulation model and jointly generate regional linkage control parameters as boundary constraints for dynamic decision-making.

[0008] Furthermore, a lane optimization strategy is reconstructed based on the real-time congestion coefficient, including: verifying the integrity of the cross-section queue length data collected by the millimeter-wave radar. If the integrity is verified, the queue length is entered into the congestion assessment buffer; If the congestion assessment buffer meets the first activation condition, the minimum activation interval of the elastic lane is calculated using the congestion diffusion dynamics model. This minimum activation interval is used as the core decision variable of the optimization strategy, and the congestion level is marked as 1. The first activation condition is that the queue length growth rate exceeds the dynamic threshold in three consecutive observation windows. If the first activation condition is not met, the optimization strategy variables are reset to the baseline value and the blocking level is marked as 0.

[0009] Furthermore, dynamic lane configuration commands are generated based on the optimization strategy and decision cycle, including: using a rolling horizon optimization algorithm to perform multi-objective solutions on core decision variables and generate phase priority weights; If the decision cycle is 1 and the congestion level is 1, the core variables, phase priority weights, and prediction results of the congestion diffusion model are encoded into a binary control instruction stream; If the decision period is not 1 or the congestion level is not 1, only the phase priority weight is converted into a lane configuration command.

[0010] Furthermore, based on the status response data of the millimeter-wave radar, a final lane control instruction is generated, including: conducting a compliance audit on the lane switching action completion rate returned by the millimeter-wave radar; When the audit fails, isolate the abnormal data and activate the device self-check process; When the audit passes, if the status response data meets the second activation condition, the effective switching rate is analyzed for deviation from the expected index, and a control instruction containing a phase difference compensation parameter is generated; the second activation condition is that the number of valid data packets in a single decision cycle exceeds the confidence threshold; If the second activation condition is not met, a lane state keeping instruction is generated.

[0011] Furthermore, an optimal flexible allocation scheme is determined through multi-cycle iteration, including: constructing a traffic efficiency evaluation matrix based on historical decision logs, wherein the matrix stores a mapping relationship between traffic efficiency and lane activation gradient in each cycle; If the current decision cycle is 1, the benchmark traffic improvement rate is set to the industry standard value; If the current decision cycle is not 1, the dynamic diversion algorithm is executed in collaboration with the adjacent section nodes to jointly generate the regional efficiency improvement threshold; Based on the efficiency threshold and evaluation matrix, the elastic ratio corresponding to the extreme value of traffic efficiency is solved by the gradient descent method, and the strategy reconfiguration point is returned after reconstructing the optimization strategy.

[0012] Furthermore, when constructing the traffic efficiency evaluation matrix, it includes: conducting trend analysis on outlier data in historical decision logs; When the analysis finds data anomalies, the Kalman filter algorithm is used to repair the data; When the data are normal, the traffic efficiency of each cycle and the corresponding enabled gradient are subjected to multivariate linear fitting analysis to generate the efficiency-gradient response surface and store it in the evaluation matrix.

[0013] Furthermore, the optimal elastic ratio scheme is solved by the gradient descent method, including: if the evaluation matrix satisfies the third activation condition, the ratio scheme corresponding to the extreme point of the surface is used as the optimal solution candidate set; the third activation condition is that the efficiency gain rate of two adjacent iterations is lower than the gradient convergence threshold; If the traffic efficiency corresponding to the candidate set exceeds the regional efficiency threshold, the solution is determined to be the optimal flexible allocation solution; If the efficiency of the candidate set does not reach the threshold, the current decision cycle is incremented by 1, and the candidate set is used as the new optimization strategy to return to the strategy reconfiguration point; If the evaluation matrix does not meet the third activation condition, the decision cycle is incremented by 1, and the regional effectiveness threshold is used as the strategy parameter to return to the strategy reconfiguration point.

[0014] Furthermore, it also includes: Real-time detection of whether regional collaborative control instructions of adjacent road sections have been received; If an instruction is received, the optimal matching plan is coupled with the regional control strategy to generate a wide-area collaborative control code stream and broadcast it to the networked joint control devices.

[0015] The above embodiments of the present invention have at least the following beneficial effects: 1. Dynamically decide the opening timing and activation gradient of emergency lanes based on real-time traffic conditions. Continuously optimize control strategies through a closed-loop feedback mechanism using multiple observation windows, thereby accurately matching fluctuating traffic demands, effectively alleviating peak-hour road congestion, and improving road network capacity. 2. Combining multiple traffic parameters such as section occupancy rate and queue length, a rolling time domain optimization algorithm is used to generate a lane resource allocation plan. The optimal elastic allocation ratio is determined through multi-cycle iterative calculation to achieve refined management and control of lane resources, avoiding the resource mismatch problem caused by traditional fixed management and control models. 3. Optimize regional traffic flow through a collaborative control mechanism with adjacent road sections, use a short-term traffic situation simulation model to predict congestion propagation trends, and cooperate with equipment status monitoring and data verification systems to ensure the reliable execution of control instructions, thereby improving the coordination and stability of the entire road network system. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily apparent by reading the following detailed description with reference to the accompanying drawings, in which several embodiments of the present invention are shown by way of example and not limitation, in which: Figure 1A flowchart of a method for opening an emergency lane in a section under heavy traffic flow provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0017] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided solely to enable those skilled in the art to better understand and implement the present invention, and are not intended to limit the scope of the present invention in any way. Rather, these embodiments are provided to make the present invention more thorough and complete, and to fully convey the scope of the present invention to those skilled in the art.

[0018] Those skilled in the art will appreciate that the embodiments of the present invention may be implemented as a system, apparatus, device, method, or computer program product. Therefore, the present invention may be implemented in the following forms: entirely in hardware, entirely in software (including firmware, resident software, microcode, etc.), or in a combination of hardware and software.

[0019] It should be noted that any number of elements in the drawings is for illustration only and not for limitation, and any naming is only for distinction and does not have any limiting meaning.

[0020] Reference below Figure 1 , Figure 1 This is a flow chart of a method for opening an emergency lane in a section with heavy traffic flow provided by one embodiment of the present invention. Figure 1 As shown, a method for opening an emergency lane in a section with heavy traffic flow includes: S1. After detecting that the traffic density of the target section reaches the first saturation threshold, the elastic lane dynamic decision engine is activated, matching the real-time traffic situation data with the elastic activation criteria, generating an initial control decision and broadcasting it to the roadside perception unit, while triggering the first observation window; S2. After the first observation window closes, a lane resource allocation plan is generated based on the section occupancy index reported by the roadside sensing unit, and a status update instruction is issued to the variable intelligence sign to trigger a second observation window. The resource allocation plan includes a flexible lane activation gradient. S3. After the second observation window closes, the lane optimization strategy is reconstructed based on the real-time blocking coefficient, and the current decision cycle is set to 1. The strategy reconfiguration point is entered. Based on the optimization strategy and decision cycle, a dynamic lane configuration command is generated and broadcast to the millimeter-wave radar, triggering the third observation window. S4. After the third observation window is closed, a final lane control instruction is generated based on the status response data of the millimeter-wave radar and broadcast to the signal controller, triggering a fourth observation window. S5. After the fourth observation window is closed, the optimal elastic allocation scheme is determined through multi-cycle iteration based on the integrated vehicle traffic efficiency indicators. After reconstructing the optimization strategy during the iteration process, the strategy reconfiguration point is returned, and the optimal elastic allocation scheme is used as the execution basis of the dynamic lane control system.

[0021] It should be noted that the elastic lane dynamic decision engine is activated when the traffic density at the target section reaches the first saturation threshold. The target section refers to a specific cross-sectional location on the road used to monitor traffic density. The first saturation threshold is a preset traffic density value. When the actual traffic density reaches or exceeds this value, it indicates that traffic flow has approached or reached the road's carrying capacity, and measures are needed to alleviate traffic flow. At this time, the elastic lane dynamic decision engine is activated. It is an intelligent decision-making system that matches real-time traffic situation data with elastic activation criteria, generates initial control decisions, and broadcasts them to the roadside sensing units. Roadside sensing units are sensor devices installed on both sides of the road that collect traffic data such as vehicle speed and volume. At the same time, the system triggers the first observation window, a time window for collecting and analyzing traffic data during that time period to further assess traffic conditions and make appropriate decisions.

[0022] Specifically, the section occupancy rate (SOC) reported by the roadside sensing unit is a key parameter for measuring traffic flow. It indicates the proportion of vehicles occupying the road at a specific section. When this metric reaches a certain value, the system generates a lane resource allocation plan based on pre-set rules. The flexible lane activation gradient here refers to a strategy that gradually activates or closes emergency lanes based on changes in traffic flow. For example, when traffic flow increases, some or all of the emergency lanes can be gradually opened to regular vehicles; when traffic flow decreases, the emergency lanes can be gradually restored to their original state. This gradient can be flexibly adjusted based on actual traffic conditions to achieve optimal traffic flow management. Simultaneously, the system triggers a second observation window, which further collects and analyzes traffic data to optimize the lane resource allocation plan. After the second observation window closes, the system reconstructs the lane optimization strategy based on the real-time congestion coefficient. The real-time congestion coefficient is a parameter that reflects the degree of traffic congestion and is calculated based on section queue length data collected by millimeter-wave radar. Millimeter-wave radar is a sensor installed on the road surface that detects vehicle traffic and provides real-time traffic data to the system. With this data, the system can more accurately assess traffic congestion and adjust lane optimization strategies accordingly.

[0023] Preferably, when generating a lane resource allocation plan, the raw data transmitted by the roadside sensing unit is validated. This means the system checks the accuracy and completeness of this data to ensure the reliability of subsequent decisions. If the verification passes, the system calculates the difference between the section occupancy rate and the output of the dynamic baseline model to generate an elastic expansion coefficient. The dynamic baseline model is built based on historical traffic data and is used to predict section occupancy rates under normal traffic conditions. By comparing the actual section occupancy rate with the model's predicted value, the elastic expansion coefficient is calculated. This coefficient reflects the degree of deviation between the current traffic flow and normal traffic flow. When the elastic expansion coefficient exceeds the second saturation threshold, the system maps the elastic lane activation gradient to a piecewise function of the expansion coefficient and uses a lane alignment optimization algorithm to calculate the corresponding channelization parameters. These channelization parameters are used to optimize lane layout and traffic flow, such as lane width and lane divider position. By optimizing these parameters, road capacity can be improved. Simultaneously, the system triggers a third observation window, which further collects and analyzes traffic data to adjust the lane optimization strategy. After the third observation window closes, the system generates final lane control instructions based on the millimeter-wave radar's status response data and broadcasts them to the signal controller. This status response data refers to lane-switch completion rate data returned by the millimeter-wave radar. The system then generates final lane control instructions based on this data to effectively control traffic flow.

[0024] In some embodiments, a lane resource allocation plan is generated based on the section occupancy index reported by the roadside sensing unit, including: verifying the validity of the original data transmitted by the roadside sensing unit, and if the verification passes, calculating the difference between the section occupancy and the output value of the dynamic baseline model to generate an elastic expansion coefficient; When the elastic expansion coefficient exceeds the second saturation threshold, the elastic lane activation gradient is mapped to a piecewise function of the expansion coefficient. The lane alignment optimization algorithm is used to calculate the channelization parameters corresponding to the gradient, and a resource allocation plan containing the activation gradient and channelization parameters is generated. When the elastic expansion coefficient does not exceed the second saturation threshold, the elastic lane enabling gradient is set to zero and a lane state maintaining instruction is generated.

[0025] It should be noted that the process of generating lane resource allocation plans based on the section occupancy rate indicators reported by roadside sensing units is a key step in the entire traffic flow control method. The section occupancy rate indicator is a key parameter for measuring traffic flow density, reflecting the proportion of vehicles occupying the road on a specific road section. Using this indicator, the system can determine whether the current traffic flow has reached a level that requires lane configuration adjustment. When generating the resource allocation plan, the system verifies the validity of the raw data transmitted by the roadside sensing units to ensure the accuracy and reliability of the data. If the verification passes, the system further calculates the elastic expansion coefficient, a parameter that measures the extent to which traffic flow exceeds the normal carrying capacity. When the elastic expansion coefficient exceeds the preset second saturation threshold, the system uses this coefficient to determine the activation gradient of the elastic lane and generates a corresponding resource allocation plan, including the activation gradient and channelization parameters, to optimize the lane layout and improve road capacity.

[0026] Specifically, roadside sensing units are sensors installed on both sides of the road that monitor traffic flow, vehicle speed, and other traffic data in real time and transmit this data to the control center. The section occupancy ratio (SCR) is calculated by analyzing this data. It is a value between 0 and 1, with higher values ​​indicating a greater proportion of road occupied by vehicles. The elastic expansion coefficient (ESC) is calculated by comparing the SCR with the output of a dynamic baseline model, which is built based on historical traffic data and is used to predict SCR under normal traffic conditions. The second saturation threshold is a preset threshold. When the ESC exceeds this value, traffic flow has exceeded the road's normal carrying capacity, and the use of flexible lanes is necessary to alleviate traffic pressure. The ESC activation gradient refers to a strategy that gradually activates or deactivates emergency lanes based on the ESC. For example, when the ESC is low, only some emergency lanes are activated; when the ESC is high, all emergency lanes are activated. Channelization parameters, such as lane width and lane divider position, are used to optimize lane layout. Adjusting these parameters can improve road traffic efficiency.

[0027] When generating a lane resource allocation plan, the system preferably employs a series of algorithms and models to ensure its scientific and effective nature. First, the system verifies the validity of the raw data transmitted by the roadside sensing unit, checking its integrity, accuracy, and conformance to the expected traffic model. If verified, the system calculates the difference between the section occupancy rate and the output of the dynamic baseline model to generate an elastic expansion coefficient. The construction of the dynamic baseline model involves collecting historical traffic data, such as traffic flow and vehicle speeds over different time periods and weather conditions. Then, through data analysis and modeling techniques, a model is established that reflects normal traffic conditions. When calculating the elastic expansion coefficient, the system compares the current section occupancy rate with the model's predicted normal section occupancy rate and calculates the difference between the two. When the elastic expansion coefficient exceeds the second saturation threshold, the system maps the elastic lane activation gradient to a piecewise function of the expansion coefficient according to pre-set rules. For example, the elastic expansion coefficient can be divided into several intervals, each corresponding to a different degree of elastic lane activation. The system also uses a lane alignment optimization algorithm to calculate the channelization parameters corresponding to the gradient. This algorithm considers factors such as road geometry and traffic flow distribution to optimize lane layout parameters. These parameters are then used to generate the final resource allocation plan to effectively manage and optimize traffic flow.

[0028] In some embodiments, it further includes: Cooperate with adjacent section control nodes to run the short-term traffic situation simulation model and jointly generate regional linkage control parameters as boundary constraints for dynamic decision-making.

[0029] It should be noted that the method mentioned the collaborative operation of the short-term traffic situation simulation model with the adjacent section control nodes and the joint generation of regional linkage control parameters as boundary constraints for dynamic decision-making, which is an important link in achieving regional traffic collaborative optimization. The adjacent section control nodes here refer to other traffic control nodes that are geographically adjacent to the current target section in the traffic network. Together, they constitute a regional traffic control system. The short-term traffic situation simulation model is a model used to predict the trend of traffic flow changes in the short term in the future. By analyzing and processing current traffic data, it can predict traffic conditions in the future. Regional linkage control parameters refer to the parameters used to coordinate the actions between the control nodes in regional traffic collaborative control. These parameters can ensure that the traffic flow in the entire area is effectively managed and optimized. Boundary constraints refer to the restrictions that need to be considered when making dynamic decisions. These conditions can ensure the feasibility and effectiveness of the decision.

[0030] Specifically, the short-term traffic situation simulation model is constructed based on historical and real-time traffic data, and it can predict the changing trends of traffic flow. The construction of this model requires the input of multiple parameters, including but not limited to real-time traffic data such as current traffic density, vehicle speed, and section occupancy, as well as parameters in historical traffic data that reflect the changing patterns of traffic flow. Through these parameters, the model can predict the changing trends of traffic flow in the short term in the future. Regional linkage control parameters are generated based on the prediction results of the simulation model. These parameters include but are not limited to signal coordination parameters and lane allocation parameters between each control node. They can ensure the coordinated actions of each control node, thereby achieving traffic flow optimization for the entire region. Boundary constraints refer to the restrictions that need to be considered when making dynamic decisions. These conditions include but are not limited to road capacity restrictions and traffic regulations. They can ensure the feasibility and effectiveness of the decision.

[0031] Preferably, when running the short-term traffic situation deduction model in collaboration with adjacent section control nodes, the following steps can be adopted: First, collect real-time traffic data of the current target section and adjacent section control nodes, including traffic density, vehicle speed, section occupancy, etc. Then, input these real-time data into the short-term traffic situation deduction model. The model will predict the changing trend of traffic flow in the short term in the future based on historical traffic data and real-time traffic data. Then, based on the prediction results of the deduction model, generate regional linkage control parameters. These parameters will be used to coordinate the actions between the various control nodes. Finally, these regional linkage control parameters are used as boundary constraints for dynamic decision-making and input into the elastic lane dynamic decision engine to ensure the scientific and rationality of the decision. In actual application, the parameters and algorithms of the model can be adjusted and optimized according to specific traffic conditions and needs to improve the prediction accuracy of the model and the effectiveness of the decision.

[0032] In some embodiments, reconstructing a lane optimization strategy based on a real-time congestion coefficient includes: performing integrity verification on cross-section queue length data collected by the millimeter-wave radar, and if the integrity verification passes, inputting the queue length into a congestion assessment buffer; If the congestion assessment buffer meets the first activation condition, the minimum activation interval of the elastic lane is calculated using the congestion diffusion dynamics model. This minimum activation interval is used as the core decision variable of the optimization strategy, and the congestion level is marked as 1. The first activation condition is that the queue length growth rate exceeds the dynamic threshold in three consecutive observation windows. If the first activation condition is not met, the optimization strategy variables are reset to the baseline value and the blocking level is marked as 0.

[0033] It should be noted that the process of reconstructing lane optimization strategies based on real-time congestion coefficients is a crucial component of traffic flow control methods, used to dynamically adjust lane configurations to address traffic congestion. The real-time congestion coefficient is a parameter that reflects the current level of traffic congestion. It assesses the congestion state of traffic flow by analyzing cross-sectional queue length data collected by millimeter-wave radar. During this process, the system verifies the integrity of the collected data to ensure its accuracy and completeness. If the verification passes, the system calculates the congestion coefficient based on the queue length data and determines whether the lane optimization strategy needs to be adjusted based on pre-set activation conditions. The core of this process lies in dynamically adjusting lane configurations through scientific models and algorithms to improve road efficiency.

[0034] Specifically, millimeter-wave radar is a sensor installed on the road surface that monitors vehicle traffic in real time, including speed, number, and queue length. Queue length data refers to the length of vehicles waiting in a queue at a specific section and is an important basis for assessing traffic congestion levels. Integrity verification checks the collected queue length data to ensure that there are no missing or abnormal data. The congestion assessment buffer temporarily stores queue length data for further analysis and processing. The first activation condition is a preset condition used to determine whether to initiate adjustments to the lane optimization strategy. For example, if the queue length growth rate exceeds a preset dynamic threshold within three consecutive observation windows, the first activation condition is considered met, and the lane optimization strategy needs to be adjusted. The congestion diffusion dynamics model is a model used to predict the spread of traffic congestion. It calculates the minimum activation interval of elastic lanes based on queue length data. This interval is the core decision variable of the optimization strategy. The congestion level is a parameter used to indicate the current traffic congestion status. When the first activation condition is met, the congestion level is marked as 1, indicating that the lane optimization strategy needs to be adjusted; otherwise, the congestion level is marked as 0, indicating that the current lane configuration should be maintained.

[0035] Preferably, the following steps can be employed to refine the lane optimization strategy based on the real-time congestion coefficient reconstruction process. First, the queue length data collected by the millimeter-wave radar is verified for integrity. This verification process includes checking the data's continuity, rationality, and the presence of outliers. If the verification passes, the queue length data is entered into the congestion assessment buffer. Next, a determination is made as to whether the data in the congestion assessment buffer meets the first activation condition: namely, whether the growth rate of the queue length within three consecutive observation windows exceeds a preset dynamic threshold. If the condition is met, the minimum activation interval for the elastic lane is calculated using a congestion diffusion dynamics model. This model requires inputs such as queue length data, road geometry, and traffic flow data. By simulating the diffusion process of traffic congestion, the minimum activation interval is calculated. The minimum activation interval is then used as the core decision variable of the optimization strategy, and the congestion level is marked as 1. If the first activation condition is not met, the optimization strategy variables are reset to baseline values, and the congestion level is marked as 0. Finally, a corresponding lane optimization strategy is generated based on the congestion level and core decision variables to achieve effective management and optimization of traffic flow.

[0036] In some embodiments, generating a dynamic lane configuration command based on an optimization strategy and a decision cycle includes: performing a multi-objective solution on core decision variables using a rolling horizon optimization algorithm to generate phase priority weights; If the decision cycle is 1 and the congestion level is 1, the core variables, phase priority weights, and prediction results of the congestion diffusion model are encoded into a binary control instruction stream; If the decision period is not 1 or the congestion level is not 1, only the phase priority weight is converted into a lane configuration command.

[0037] It should be noted that the process of generating dynamic lane configuration commands based on the optimization strategy and decision cycle is a key step in achieving dynamic traffic flow control. This process uses a rolling horizon optimization algorithm to solve multiple objectives for core decision variables and generate phase priority weights. The rolling horizon optimization algorithm here is a dynamic optimization method that can optimize traffic flow within a limited timeframe. Phase priority weight refers to the weight assigned to right-of-way based on traffic flow in different directions in traffic signal control. When the decision cycle is 1 and the congestion level is 1, the system encodes the core variables, phase priority weights, and the prediction results of the congestion diffusion model into a binary control command stream to quickly respond to traffic congestion. If the decision cycle is not 1 or the congestion level is not 1, only the phase priority weights are converted into lane configuration commands to maintain stable traffic flow.

[0038] Specifically, the rolling horizon optimization algorithm is a dynamic optimization algorithm that optimizes traffic flow within a limited timeframe to achieve dynamic adjustment of traffic signals. Core decision variables are key parameters that require adjustment during the optimization process, such as the degree of flexible lane activation and signal phase duration. Phase priority weights are the priority weights assigned to traffic flows in different directions based on traffic flow volume. The decision cycle is the time it takes for the system to make a complete optimization decision, which determines the system's response speed to changes in traffic flow. The congestion level is a parameter used to indicate the current state of traffic congestion. When the congestion level is 1, it indicates that traffic flow has reached a level that requires urgent adjustment. The binary control instruction stream encodes the optimization results into binary form, facilitating rapid system execution. When the decision cycle and congestion level are both 1, the system encodes the core variables, phase priority weights, and the predictions from the congestion diffusion model into a binary control instruction stream to achieve rapid traffic flow adjustment. If the decision cycle or congestion level are not 1, only the phase priority weights are converted into lane configuration commands to maintain stable traffic flow.

[0039] Preferably, the following steps can be used to refine the generation of dynamic lane configuration commands. First, the initial values ​​of the core decision variables are determined based on real-time and historical traffic data. Then, a multi-objective solution is applied to the core decision variables using a rolling horizon optimization algorithm to generate phase priority weights. This process requires inputs such as real-time traffic flow data, road geometry parameters, and traffic signal control parameters. By simulating traffic flow trends, the optimal phase priority weights are calculated. Next, the current decision cycle and congestion level are determined. If the decision cycle is 1 and the congestion level is 1, the core variables, phase priority weights, and the prediction results of the congestion diffusion model are encoded into a binary control instruction stream. This encoding process involves converting the optimization results into binary form and adding the necessary control instruction headers and trailers to facilitate rapid system recognition and execution. If the decision cycle is not 1 or the congestion level is not 1, only the phase priority weights are converted into lane configuration commands to maintain stable traffic flow. Finally, the generated dynamic lane configuration commands are sent to the corresponding traffic control devices, such as signal controllers and lane indicators, to achieve dynamic adjustment of traffic flow.

[0040] In some embodiments, generating a final lane control instruction based on the status response data of the millimeter-wave radar includes: performing a compliance audit on the lane switching action completion rate returned by the millimeter-wave radar; When the audit fails, isolate the abnormal data and activate the device self-check process; When the audit passes, if the status response data meets the second activation condition, the effective switching rate is analyzed for deviation from the expected index, and a control instruction containing a phase difference compensation parameter is generated; the second activation condition is that the number of valid data packets in a single decision cycle exceeds the confidence threshold; If the second activation condition is not met, a lane state keeping instruction is generated.

[0041] It's important to note that the process of generating final lane control instructions based on the millimeter-wave radar's status response data is a critical step in ensuring the effective implementation of traffic flow control measures. This process first involves a compliance audit of the lane switch completion rate reported by the millimeter-wave radar to ensure data accuracy and reliability. If the audit fails, the system isolates the abnormal data and activates a device self-check process to rule out device malfunction or data transmission errors. If the audit passes, the system further determines whether the status response data meets the second activation condition: whether the number of valid data packets within a single decision cycle exceeds a confidence threshold. If so, the system analyzes the deviation between the effective switch rate and the expected indicator and generates a control instruction containing phase difference compensation parameters. If not, a lane state hold instruction is generated to maintain the current traffic flow configuration.

[0042] Specifically, millimeter-wave radar is a sensor installed on the road surface that monitors lane change completion in real time, such as whether vehicles are switching lanes correctly as instructed. Status response data refers to data returned by the millimeter-wave radar on the lane change completion rate, reflecting the actual effectiveness of lane control measures. Compliance audits examine this data to ensure it meets pre-set standards and specifications. If the audit fails, the system isolates the abnormal data and activates a device self-check process to determine whether there is a device malfunction or data transmission error. The second activation condition is a preset condition used to determine whether the status response data is sufficiently reliable, such as whether the number of valid data packets within a single decision cycle exceeds a confidence threshold. Phase difference compensation parameters are parameters used in traffic signal control to adjust the phase difference between traffic flows in different directions to optimize traffic flow. If the status response data meets the second activation condition, the system analyzes the deviation between the effective switch rate and the expected indicator and generates a control instruction containing the phase difference compensation parameter to adjust the lane configuration. If the condition is not met, a lane state hold instruction is generated to maintain the current traffic flow configuration.

[0043] Preferably, the following steps can be used to refine the generation of the final lane control instructions. First, the status response data returned by the millimeter-wave radar undergoes a compliance audit, which includes checking the data's integrity, accuracy, and timeliness. If the audit fails, the system isolates the abnormal data and activates a device self-check process to troubleshoot device failures or data transmission errors. This self-check process includes checking the sensor's operating status and the integrity of the data transmission link. If the audit passes, the system further determines whether the status response data meets the second activation condition: whether the number of valid data packets within a single decision cycle exceeds a confidence threshold. The confidence threshold is a preset value used to determine data reliability. If the condition is met, the system analyzes the deviation between the effective switching rate and the expected indicator, calculates the deviation value, and generates a control instruction containing phase difference compensation parameters based on the deviation value. The calculation of the phase difference compensation parameters involves a comprehensive analysis of parameters such as current traffic flow, lane switching rate, and signal light phase duration to determine the optimal phase difference adjustment value. Finally, the generated control instruction is sent to the corresponding traffic control devices, such as signal light controllers and lane indicators, to achieve dynamic adjustment of traffic flow.

[0044] In some embodiments, determining an optimal flexible allocation scheme through multi-cycle iteration includes: constructing a traffic efficiency evaluation matrix based on historical decision logs, wherein the matrix stores a mapping relationship between traffic efficiency and lane activation gradient in each cycle; If the current decision cycle is 1, the benchmark traffic improvement rate is set to the industry standard value; If the current decision cycle is not 1, the dynamic diversion algorithm is executed in collaboration with the adjacent section nodes to jointly generate the regional efficiency improvement threshold; Based on the efficiency threshold and evaluation matrix, the elastic ratio corresponding to the extreme value of traffic efficiency is solved by the gradient descent method, and the strategy reconfiguration point is returned after reconstructing the optimization strategy.

[0045] It should be noted that the process of determining the optimal flexible allocation scheme through multiple iterations is a core component of the entire traffic flow control method, used to dynamically adjust lane configurations to achieve optimal traffic flow management. This process first involves constructing a traffic efficiency evaluation matrix based on historical decision logs. This matrix stores the mapping between traffic efficiency and lane activation gradients for each cycle. The traffic efficiency evaluation matrix is ​​a data structure used to evaluate traffic efficiency under different lane configuration schemes. It analyzes historical data to predict traffic performance under different configurations. When the decision cycle is 1, the system sets the baseline traffic improvement rate to the industry standard value as the initial performance indicator. For non-initial cycles, the system collaborates with adjacent section nodes to execute a dynamic diversion algorithm and jointly generate regional efficiency improvement thresholds to evaluate the effectiveness of the current configuration scheme. Based on the efficiency thresholds and the evaluation matrix, the system uses gradient descent to determine the flexible allocation corresponding to the extreme traffic efficiency value. After reconstructing the optimization strategy, it returns the strategy reconfiguration point to achieve dynamic adjustment.

[0046] Specifically, the traffic efficiency evaluation matrix is ​​a multidimensional data structure that records the traffic efficiency data of each cycle under different lane configuration schemes. The lane activation gradient refers to the degree of activation of the emergency lane under different traffic flow conditions, such as different stages from completely non-activation to fully activation. The benchmark traffic improvement rate is a preset performance indicator used to measure the effectiveness of traffic diversion measures. It is usually set based on industry standards or historical data. The dynamic diversion algorithm is an algorithm used to optimize traffic flow distribution. It dynamically adjusts the traffic flow distribution of each section node according to the current traffic conditions and historical data. The regional efficiency improvement threshold is a parameter used to evaluate the effect of regional traffic improvement. It determines whether the lane configuration needs to be adjusted by comparing the traffic efficiency under the current configuration scheme with historical data or standard values. The gradient descent method is an optimization algorithm used to find the optimal lane configuration scheme in a multi-cycle iterative process, and to maximize traffic efficiency by gradually adjusting the elastic ratio.

[0047] Preferably, when determining the optimal flexible allocation scheme through multi-cycle iteration, the following steps can be employed for refinement. First, a traffic efficiency evaluation matrix is ​​constructed based on data from historical decision logs. This involves collecting and organizing traffic efficiency data for each cycle and the corresponding lane activation gradient data. Then, trend analysis is performed on outlier data in the evaluation matrix to identify and address abnormal data. If data anomalies are detected, a Kalman filter algorithm is used to repair the data to ensure data accuracy and reliability. Next, depending on whether the current decision cycle is 1, a baseline traffic improvement rate is set or a dynamic traffic diversion algorithm is executed in collaboration with adjacent section nodes to generate a regional efficiency improvement threshold. In each iteration, based on the efficiency threshold and the evaluation matrix, a gradient descent method is used to determine the elastic allocation corresponding to the extreme traffic efficiency value. The implementation of the gradient descent method involves calculating the traffic efficiency gradient under the current configuration scheme and adjusting the elastic allocation based on the gradient until a preset convergence condition or efficiency threshold is reached. Finally, the optimal elastic allocation scheme is used as the basis for executing the dynamic lane control system to achieve dynamic optimization management of traffic flow.

[0048] In some embodiments, constructing a traffic effectiveness evaluation matrix includes: performing trend analysis on outlier data in historical decision logs; When the analysis finds data anomalies, the Kalman filter algorithm is used to repair the data; When the data are normal, the traffic efficiency of each cycle and the corresponding enabled gradient are subjected to multivariate linear fitting analysis to generate the efficiency-gradient response surface and store it in the evaluation matrix.

[0049] It should be noted that when constructing the traffic efficiency evaluation matrix, trend analysis of outlier data in historical decision logs is a key step in ensuring data quality. This process aims to identify and address inaccurate data caused by abnormal conditions, thereby improving the reliability and effectiveness of the evaluation matrix. When the analysis reveals data anomalies, the Kalman filter algorithm is used for data repair. This effective data smoothing technique can predict and correct abnormal data based on historical data and current observations. When the data is normal, a multivariate linear fit analysis is performed on the traffic efficiency of each cycle and the corresponding enabled gradient to generate an efficiency-gradient response surface and store it in the evaluation matrix. This process not only reflects the changing trends of traffic efficiency under different lane configurations but also provides data support for subsequent optimization strategies.

[0050] Specifically, the historical decision log refers to all decision data recorded by the system during its previous operation, including lane configuration plans, traffic efficiency and other information. Outlier data refers to data points that deviate significantly from the normal range and are caused by equipment failure, data transmission errors or abnormal traffic events. Trend analysis is a data analysis method used to identify long-term trends and patterns in data, and to determine whether the data is abnormal by calculating the moving average or regression line of the data. The Kalman filter algorithm is a recursive filter that estimates the state of the system by combining predicted and observed data, and can effectively handle noise and abnormal data. Multivariate linear fitting analysis is a statistical method used to establish a linear relationship between multiple independent variables and dependent variables, and to fit the best linear model through methods such as least squares. The efficiency-gradient response surface is a three-dimensional graph that represents the relationship between traffic efficiency and changes in lane activation gradient and other parameters. It can intuitively show the changes in traffic efficiency under different configurations.

[0051] Preferably, when constructing a traffic efficiency evaluation matrix, the following steps can be used for refinement. First, collect and organize the data in the historical decision log, including the lane configuration plan, traffic efficiency and other information for each decision cycle. Then, perform trend analysis on these data, and calculate the moving average or regression value of each data point to identify possible outlier data. If outlier data is found, use the Kalman filter algorithm to repair the data, and predict and correct the abnormal data points by combining historical data and current observations. When the data is normal, use multivariate linear fitting analysis to fit the traffic efficiency of each cycle as the dependent variable, and the lane activation gradient and other related parameters as independent variables to fit the best linear model. Based on the fitting results, generate an efficiency-gradient response surface and store it in the evaluation matrix. This process not only ensures the data quality of the evaluation matrix, but also provides accurate data support for subsequent optimization strategies, thereby realizing dynamic optimization management of traffic flow.

[0052] In some embodiments, the optimal elastic ratio scheme is solved by the gradient descent method, including: if the evaluation matrix satisfies a third activation condition, taking the ratio scheme corresponding to the surface extreme point as the optimal solution candidate set; the third activation condition is that the efficiency gain rate of two adjacent iterations is lower than the gradient convergence threshold; If the traffic efficiency corresponding to the candidate set exceeds the regional efficiency threshold, the solution is determined to be the optimal flexible allocation solution; If the efficiency of the candidate set does not reach the threshold, the current decision cycle is incremented by 1, and the candidate set is used as the new optimization strategy to return to the strategy reconfiguration point; If the evaluation matrix does not meet the third activation condition, the decision cycle is incremented by 1, and the regional effectiveness threshold is used as the strategy parameter to return to the strategy reconfiguration point.

[0053] It should be noted that the process of solving the optimal flexible allocation scheme using the gradient descent method is a key step in achieving dynamic traffic flow optimization. This process first determines whether the evaluation matrix meets the third activation condition, namely, whether the efficiency gain rate between two consecutive iterations is below the gradient convergence threshold. If the condition is met, the allocation scheme corresponding to the surface extreme point is selected as the optimal solution candidate set. The surface extreme point here refers to the point on the efficiency-gradient response surface where the traffic efficiency reaches its maximum value, and the corresponding allocation scheme is the possible optimal solution. If the traffic efficiency corresponding to the candidate set exceeds the regional efficiency threshold, the solution is determined to be the optimal flexible allocation scheme. If it does not reach the threshold, the decision cycle is increased and the strategy reconfiguration point is returned with the candidate set as the new optimization strategy. If the evaluation matrix does not meet the third activation condition, the decision cycle is also increased and the strategy reconfiguration point is returned with the regional efficiency threshold as the strategy parameter, and the optimization process continues.

[0054] Specifically, the gradient descent method is an optimization algorithm used to find the optimal lane configuration scheme in multi-cycle iterations, maximizing traffic efficiency by gradually adjusting the elastic ratio. The evaluation matrix is ​​a data structure that stores the mapping relationship between the traffic efficiency of each cycle and the lane activation gradient, and is used to evaluate the effects of different configuration schemes. The third activation condition is a preset condition used to determine whether the iterative process has converged, that is, whether the efficiency gain rate of two adjacent iterations is lower than a set gradient convergence threshold. The surface extreme point refers to the point on the efficiency-gradient response surface where the traffic efficiency reaches the maximum value, and the corresponding ratio scheme is the possible optimal scheme. The regional efficiency threshold is a parameter used to evaluate the effect of regional traffic improvement. It determines whether the lane configuration needs to be adjusted by comparing the traffic efficiency under the current configuration scheme with historical data or standard values. The decision cycle refers to the time required for the system to make a complete optimization decision. It determines the system's response speed to changes in traffic flow.

[0055] Preferably, when solving the optimal elastic ratio scheme by the gradient descent method, the following steps can be used for refinement. First, based on the data in the evaluation matrix, calculate the efficiency gain rate of two adjacent iterations to determine whether the third activation condition is met. If the condition is met, find the extreme point on the efficiency-gradient response surface, and use the corresponding ratio scheme as the optimal solution candidate set. Next, compare the traffic efficiency corresponding to the candidate set with the regional efficiency threshold. If the traffic efficiency of the candidate set exceeds the regional efficiency threshold, then determine that the scheme is the optimal elastic ratio scheme; if the threshold is not reached, increase the decision cycle, and use the candidate set as the new optimization strategy to return to the strategy reconfiguration point, and continue the optimization process. If the evaluation matrix does not meet the third activation condition, also increase the decision cycle, and use the regional efficiency threshold as the strategy parameter to return to the strategy reconfiguration point, and continue the optimization process. Throughout the process, the gradient descent method gradually adjusts the elastic ratio and updates the optimization strategy according to the efficiency gain rate of each iteration until the optimal lane configuration scheme is found.

[0056] In some embodiments, it further includes: Real-time detection of whether regional collaborative control instructions of adjacent road sections have been received; If an instruction is received, the optimal matching plan is coupled with the regional control strategy to generate a wide-area collaborative control code stream and broadcast it to the networked joint control devices.

[0057] It should be noted that this method involves real-time detection of whether regional collaborative control instructions from adjacent road sections are received, and when instructions are received, the optimal matching scheme is coupled with the regional control strategy to generate a wide-area collaborative control code stream and broadcast it to the networked joint control equipment. The regional collaborative control instructions here refer to control instructions from adjacent road sections, which are used to coordinate traffic flow between different road sections to achieve optimized management of regional traffic. Coupling operation refers to combining the optimal matching scheme with the regional control strategy, and generating a collaborative control strategy applicable to the entire area through calculation and adjustment. The wide-area collaborative control code stream is an instruction stream used to control networked joint control equipment. It contains an optimized traffic control strategy and can achieve collaborative control of multiple road sections.

[0058] Specifically, the regional collaborative control instruction is an instruction used to coordinate traffic flows on different road sections. It contains traffic condition information and control requirements of adjacent road sections. Coupling operation is a process of combining different control strategies. Through mathematical models and algorithms, the optimal matching scheme is integrated with the regional control strategy to generate a collaborative control strategy applicable to the entire area. The wide-area collaborative control code stream is a control instruction stream that contains optimized traffic control strategies and can achieve collaborative control of multiple road sections. Networked joint control equipment refers to traffic control equipment that can receive and execute wide-area collaborative control code streams, such as traffic light controllers, lane indicators, etc. These devices are connected through a network to achieve collaborative control of regional traffic.

[0059] Preferably, when implementing this method, the following steps can be used for refinement. First, the system detects in real time whether it has received regional collaborative control instructions for adjacent sections of road. If an instruction is received, the system will parse the instruction content to obtain traffic condition information and control requirements for the adjacent sections of road. Then, the optimal matching scheme is coupled with the regional control strategy. This step includes establishing a mathematical model, inputting the optimal matching scheme and regional control strategy as parameters, and generating a collaborative control strategy applicable to the entire area through calculation and adjustment. Finally, the generated wide-area collaborative control code stream is broadcast to the networked joint control devices. After receiving the instructions, these devices will adjust the traffic signals and lane configurations according to the instructions to achieve collaborative control of regional traffic. Throughout the process, the system needs to ensure the real-time and accuracy of the instructions to achieve effective management of regional traffic.

[0060] The above embodiments of the present invention have the following beneficial effects: 1. The system can dynamically decide the opening timing and activation gradient of emergency lanes based on real-time traffic conditions. Through a closed-loop feedback mechanism with multiple observation windows, it can continuously optimize the control strategy, thereby accurately matching the fluctuating demand of traffic flow, effectively alleviating road congestion during peak hours and improving the traffic capacity of the road network. 2. By combining multiple traffic parameters such as section occupancy rate and queue length, a rolling time domain optimization algorithm can be used to generate a lane resource allocation plan. The optimal elastic ratio can be determined through multi-cycle iterative calculation to achieve refined management and control of lane resources and avoid the resource mismatch problem caused by the traditional fixed management model. 3. Regional traffic flow optimization can be achieved through a collaborative control mechanism with adjacent road sections. The short-term traffic situation simulation model can be used to predict the spread of congestion. In conjunction with the equipment status monitoring and data verification system, the reliable execution of control instructions can be ensured, thereby improving the coordination and stability of the entire road network system.

[0061] In terms of smart expansion of highways, we can achieve this through: 1. Intelligent upgrade of highway infrastructure, including: Road surface sensing system: uses advanced sensor technology to monitor road conditions in real time, such as traffic flow, vehicle speed, accident warning and other information.

[0062] License plate recognition system: License plate recognition equipment is installed at the entrances and exits of highways to realize automatic identification, classification and statistics of vehicles.

[0063] Highway lighting system: uses intelligent lighting technology to automatically adjust the brightness of street lights according to traffic volume and weather conditions, improving road lighting effects.

[0064] Highway signs and guidance systems: Utilize smart display screens to display traffic information, route guidance, accident warnings, and other content in real time.

[0065] 2. Construction of intelligent traffic management system, including: Traffic signal control system: Dynamically adjusts the timing of traffic lights based on real-time traffic volume to optimize traffic flow.

[0066] Electronic police system: uses video surveillance and intelligent analysis technology to automatically identify and punish illegal acts.

[0067] Intelligent dispatching system: Through data analysis, it can realize the rational dispatching of highway operation resources and improve operation efficiency.

[0068] Intelligent monitoring system: Real-time monitoring of key parts of the highway to ensure safe and smooth traffic.

[0069] 3. Intelligent transportation information services and decision support, including: Real-time traffic information service: Provide users with real-time traffic information, route planning and other services through mobile apps, in-vehicle navigation systems and other channels.

[0070] Smart travel suggestions: Provide personalized travel suggestions based on user travel needs, such as the best travel time, optimal route, etc.

[0071] Traffic big data analysis: Collect and analyze highway operation data to provide scientific basis for decision makers.

[0072] Prediction and warning system: Based on big data analysis, it predicts the operating status of highways in the future and issues warning information in advance.

[0073] 4. Intelligent transportation operation and maintenance management, including: Resource management system: Unified management of highway infrastructure, equipment, personnel and other resources to improve operation and maintenance efficiency.

[0074] Fault monitoring and prediction: Through intelligent monitoring equipment, the operating status of infrastructure can be grasped in real time, and faults can be discovered and handled in advance.

[0075] Intelligent maintenance decision-making: Based on data analysis, scientific maintenance plans are formulated to increase road service life.

[0076] Personnel training and assessment: Use virtual reality, online training and other means to improve the skills of operation and maintenance personnel and ensure the safe operation of highways.

[0077] Furthermore, the storage medium of the embodiment of the present application stores program instructions that can implement all the above methods, wherein the program instructions can be stored in the above storage medium in the form of a software product, including a number of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or a terminal device such as a computer, server, mobile phone, or tablet.

[0078] The above descriptions merely illustrate some preferred embodiments of the present invention and the underlying technical principles. Those skilled in the art should understand that the scope of the invention encompassed by the embodiments of the present invention is not limited to technical solutions formed by specific combinations of the aforementioned technical features. It also encompasses other technical solutions formed by any combination of the aforementioned technical features or their equivalents, without departing from the aforementioned inventive concept. For example, a technical solution formed by replacing the aforementioned features with (but not limited to) technical features with similar functions disclosed in the embodiments of the present invention.

Claims

1. A method for opening emergency lanes in sections with heavy traffic flow, characterized in that: The elastic lane control core applied to the road network management and control platform includes: After detecting that the traffic density of the target section reaches the first saturation threshold, the elastic lane dynamic decision engine is activated, matching the real-time traffic situation data with the elastic activation criteria, generating an initial control decision and broadcasting it to the roadside perception unit, while triggering the first observation window; After the first observation window closes, a lane resource allocation plan is generated based on the section occupancy index reported by the roadside sensing unit, and a status update instruction is issued to the variable intelligence sign to trigger the second observation window. The resource allocation plan includes a flexible lane activation gradient; After the second observation window closes, the lane optimization strategy is reconstructed based on the real-time congestion coefficient, and the current decision cycle is set to 1. The strategy reconfiguration point is entered. Based on the optimization strategy and decision cycle, a dynamic lane configuration command is generated and broadcast to the millimeter-wave radar, triggering the third observation window. After the third observation window closes, the final lane control instruction is generated based on the status response data of the millimeter-wave radar and broadcast to the signal controller, triggering the fourth observation window; After the fourth observation window is closed, the optimal elastic allocation scheme is determined through multi-cycle iteration based on the integrated vehicle traffic efficiency indicators. After reconstructing the optimization strategy during the iteration process, the strategy reconfiguration point is returned, and the optimal elastic allocation scheme is used as the basis for the execution of the dynamic lane control system.

2. The method according to claim 1, wherein Generate a lane resource allocation plan based on the section occupancy rate indicators reported by the roadside sensing unit, including: verifying the validity of the raw data transmitted by the roadside sensing unit. If the verification is passed, calculate the difference between the section occupancy rate and the output value of the dynamic baseline model to generate an elastic expansion coefficient; When the elastic expansion coefficient exceeds the second saturation threshold, the elastic lane activation gradient is mapped to a piecewise function of the expansion coefficient. The lane alignment optimization algorithm is used to calculate the channelization parameters corresponding to the gradient, and a resource allocation plan containing the activation gradient and channelization parameters is generated. When the elastic expansion coefficient does not exceed the second saturation threshold, the elastic lane enabling gradient is set to zero and a lane state maintaining instruction is generated.

3. The method according to claim 1, wherein Also includes: Cooperate with adjacent section control nodes to run the short-term traffic situation simulation model and jointly generate regional linkage control parameters as boundary constraints for dynamic decision-making.

4. The method according to claim 1, wherein Reconstructing lane optimization strategies based on real-time congestion coefficients involves: verifying the integrity of cross-section queue length data collected by millimeter-wave radar. If the integrity is verified, the queue length is entered into the congestion assessment buffer. If the congestion assessment buffer meets the first activation condition, the minimum activation interval of the elastic lane is calculated using the congestion diffusion dynamics model. This minimum activation interval is used as the core decision variable of the optimization strategy, and the congestion level is marked as 1. The first activation condition is that the queue length growth rate exceeds the dynamic threshold in three consecutive observation windows. If the first activation condition is not met, the optimization strategy variables are reset to the baseline value and the blocking level is marked as 0.

5. The method according to claim 4, wherein Generate dynamic lane configuration commands based on the optimization strategy and decision cycle, including: using a rolling horizon optimization algorithm to perform multi-objective solutions to core decision variables and generate phase priority weights; If the decision cycle is 1 and the congestion level is 1, the core variables, phase priority weights, and prediction results of the congestion diffusion model are encoded into a binary control instruction stream; If the decision period is not 1 or the congestion level is not 1, only the phase priority weight is converted into a lane configuration command.

6. The method according to claim 1, wherein Generate final lane control instructions based on the millimeter-wave radar's status response data, including: conducting compliance audits on the lane switching action completion rate returned by the millimeter-wave radar; When the audit fails, isolate the abnormal data and activate the device self-check process; When the audit passes, if the status response data meets the second activation condition, the effective switching rate is analyzed for deviation from the expected index, and a control instruction containing a phase difference compensation parameter is generated; the second activation condition is that the number of valid data packets in a single decision cycle exceeds the confidence threshold; If the second activation condition is not met, a lane state keeping instruction is generated.

7. The method according to claim 1, wherein Determining the optimal flexible allocation scheme through multi-cycle iteration includes: constructing a traffic efficiency evaluation matrix based on historical decision logs, wherein the matrix stores the mapping relationship between traffic efficiency and lane activation gradient in each cycle; If the current decision cycle is 1, the benchmark traffic improvement rate is set to the industry standard value; If the current decision cycle is not 1, the dynamic diversion algorithm is executed in collaboration with the adjacent section nodes to jointly generate the regional efficiency improvement threshold; Based on the efficiency threshold and evaluation matrix, the elastic ratio corresponding to the extreme value of traffic efficiency is solved by the gradient descent method, and the strategy reconfiguration point is returned after reconstructing the optimization strategy.

8. The method according to claim 7, wherein When constructing the traffic efficiency evaluation matrix, it includes: trend analysis of outlier data in historical decision logs; When the analysis finds data anomalies, the Kalman filter algorithm is used to repair the data; When the data are normal, the traffic efficiency of each cycle and the corresponding enabled gradient are subjected to multivariate linear fitting analysis to generate the efficiency-gradient response surface and store it in the evaluation matrix.

9. The method according to claim 7, wherein Solving the optimal elastic matching scheme by the gradient descent method includes: if the evaluation matrix satisfies a third activation condition, taking the matching scheme corresponding to the extreme point of the surface as the optimal solution candidate set; the third activation condition is that the efficiency gain rate of two adjacent iterations is lower than the gradient convergence threshold; If the traffic efficiency corresponding to the candidate set exceeds the regional efficiency threshold, the solution is determined to be the optimal flexible allocation solution; If the efficiency of the candidate set does not reach the threshold, the current decision cycle is incremented by 1, and the candidate set is used as the new optimization strategy to return to the strategy reconfiguration point; If the evaluation matrix does not meet the third activation condition, the decision cycle is incremented by 1, and the regional effectiveness threshold is used as the strategy parameter to return to the strategy reconfiguration point.

10. The method according to claim 9, wherein Also includes: Real-time detection of whether regional collaborative control instructions of adjacent road sections have been received; If an instruction is received, the optimal matching plan is coupled with the regional control strategy to generate a wide-area collaborative control code stream and broadcast it to the networked joint control devices.

Images