Dynamic intelligent expressway capacity expansion method and system based on supply-demand relationship

Abstract

The invention relates to the technical field of intelligent traffic, in particular to an expressway dynamic intelligent capacity expansion method and system based on a supply-demand relationship, and the method comprises the steps: carrying out the traffic control unit division of an expressway; collecting real-time traffic data, and performing level division on traffic states according to the traffic data; according to the historical data and the real-time traffic data, carrying out supply and demand analysis based on a machine learning algorithm, and calculating the traffic capacity and short-time traffic flow prediction of the current section road; according to the supply and demand prediction result, the gap traffic volume of the traffic control nodes is calculated, and the traffic management strategy of each traffic control node is formulated and adjusted; and monitoring the implementation effect of the traffic management strategy based on the real-time traffic data, and if an expected target is not reached, optimizing the traffic management strategy. According to the invention, the problems of high cost and long period of a traditional expressway capacity expansion mode are effectively solved, the road traffic capacity is obviously improved, the congestion is reduced, and the traffic management efficiency is optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent transportation, and particularly to a method and system for dynamically and intelligently expanding a highway based on supply and demand relationships. Background Art

[0002] With the continuous growth of the number of automobiles, the traffic pressure on highways is increasing. Especially during holidays, peak hours, and some important sections, the vehicle flow often exceeds the design capacity of the road, resulting in frequent congestion. The congestion on highways not only reduces the traffic efficiency but also increases the fuel consumption and carbon emissions of vehicles, affecting the driving experience and social and economic development.

[0003] Currently, the expansion of highways mainly relies on building new or widening lanes. However, this method is costly, has a long cycle, and is restricted by land resources, making it impossible to quickly respond to sudden traffic flow changes. Traditional traffic control measures, such as fixed speed limits, ramp control, and toll station regulation, are mostly statically set and lack flexible adjustment according to real-time traffic conditions, making it difficult to effectively relieve congestion in different situations. Although existing intelligent transportation management systems can provide certain monitoring and early warning functions, they usually lack supply and demand analysis and dynamic optimization capabilities, unable to quickly adjust control strategies according to changes in real-time traffic flow. Different control measures often operate independently and lack coordinated optimization, resulting in poor overall management effects. Summary of the Invention

[0004] The present invention provides a method and system for dynamically and intelligently expanding a highway based on supply and demand relationships, thus effectively solving the problems pointed out in the background art.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is:

[0006] A method for dynamically and intelligently expanding a highway based on supply and demand relationships, comprising:

[0007] Taking the distribution device as a traffic control node and dividing the traffic control units of the highway;

[0008] Collecting real-time traffic data and classifying the traffic status according to the traffic data to obtain an evaluation result of the road operation status;

[0009] Based on historical data and the real-time traffic data, performing supply and demand analysis based on a machine learning algorithm, predicting the traffic flow and traffic capacity in the future time, and calculating the traffic capacity of the current section of the road and the short-term traffic flow prediction;

[0010] According to the supply and demand prediction results, calculating the gap traffic volume of the traffic control node and formulating and adjusting the traffic management strategies of each traffic control node based on the gap traffic volume;

[0011] Monitor the implementation effect of the traffic management strategy based on the real-time traffic data. If the expected goal is not achieved, optimize the traffic management strategy.

[0012] Further, the machine learning algorithm includes:

[0013] Select characteristic variables of traffic capacity prediction and short-term traffic flow.

[0014] Construct a data matrix according to the historical data and the traffic data collected in real time. The data matrix contains multiple data entries and characteristic dimensions.

[0015] Model the data matrix based on a time series neural model, and predict the traffic capacity and short-term traffic flow by learning historical traffic patterns.

[0016] Further, calculate the gap traffic volume and configure the control strategy, including:

[0017] Calculate the gap traffic volume, which is equal to the predicted traffic capacity in the next cycle minus the predicted value of the short-term traffic flow in the next cycle.

[0018] If the gap traffic volume is greater than or equal to 0, it indicates that the traffic capacity in the next cycle meets the traffic flow demand, and no additional control measures are required.

[0019] If the gap traffic volume is less than 0, it indicates that the traffic capacity in the next cycle cannot meet the traffic flow demand, and adjustment is required through the control means of each traffic control node.

[0020] Further, the calculation method of the traffic capacity of the controlled supply is:

[0021] C = F 1 -F 2

[0022] where C is the traffic capacity that can be supplied by the current strategy, F 1 is the traffic flow that needs to enter the main line after control, and F 2 is the traffic flow that has entered the main line before control and cannot reach the bottleneck point within a strategy refresh cycle.

[0023] Further, the toll station control strategy includes:

[0024] There is no queue at the outer square of the current toll station:

[0025]

[0026] c close is the number of closed lanes, and c total is the total number of released lanes, and flownext_pre To predict the traffic flow in the next cycle;

[0027] There is a queue at the outer square of the current toll station:

[0028]

[0029] flow max is the maximum traffic flow per unit time, time queue_clear is the queue dissipation time, T is the strategy refresh period, flow pre is the predicted flow after queue dissipation;

[0030]

[0031] where dis is the distance from the current position to the congestion point, speed previous is the average speed before control, flow is the quantity in the corresponding period.

[0032] Furthermore, the ramp control strategy includes:

[0033] There is no queue at the current ramp:

[0034] F 1 = flow next_pre ,

[0035] flow next_pre is the predicted traffic flow in the next cycle;

[0036] There is a queue at the current ramp:

[0037]

[0038] flow max is the maximum traffic flow per unit time, time queue_clear is the queue dissipation time, T is the strategy refresh period, flow pre is the predicted flow after queue dissipation;

[0039]

[0040] dis is the distance from the current position to the congestion point, speed previous is the average speed before control, flow is the quantity in the corresponding period.

[0041] Furthermore, the speed limit control strategy includes:

[0042]

[0043] flow now is the traffic flow at the current section, is the average speed in the previous n cycles, vlimit is the policy speed limit value, λ is the personnel compliance, and T is the policy refresh period;

[0044]

[0045] dis is the distance from the current location to the congestion point, speed previous is the average speed before control, and flow is the quantity within the corresponding period.

[0046] Further, the emergency lane opening policy includes:

[0047]

[0048] flow lane_100 is the traffic flow passing through the current 100-meter unit section, lane n is the number of currently open lanes, T is the policy refresh period, time open is the total opening duration, length open is the total opening length;

[0049] F 2 = 0.

[0050] Further, the diversion policy includes:

[0051] F 1 = (α 1 - α 2 ) * flow now ,

[0052] flow now is the traffic flow passing through the current section, α 1 is the diversion ratio after the diversion control is turned on, α 2 is the diversion ratio after the diversion control is turned on;

[0053] F 2 = 0.

[0054] A dynamic intelligent highway expansion system based on supply and demand relationships, the system includes:

[0055] A control unit division module that uses the publishing device as a traffic control node to divide the traffic control units of the highway;

[0056] A road condition assessment module that collects real-time traffic data and classifies the traffic status according to the traffic data to obtain the road operation condition assessment result;

[0057] The algorithm analysis and calculation module conducts supply-demand analysis based on historical data and the real-time traffic data, predicts the traffic flow and traffic capacity in the future time using machine learning algorithms, and calculates the traffic capacity of the current section of the road and the short-term traffic flow prediction.

[0058] The management strategy formulation module calculates the gap traffic volume of the traffic control nodes according to the supply-demand prediction results, and formulates and adjusts the traffic management strategies of each traffic control node based on the gap traffic volume.

[0059] The management strategy optimization module monitors the implementation effect of the traffic management strategy based on the real-time traffic data. If the expected goal is not achieved, the traffic management strategy is optimized.

[0060] Through the technical solution of the present invention, the following technical effects can be achieved:

[0061] Effectively solves the problems of high cost and long cycle in the traditional highway expansion method, significantly improves the traffic capacity of the road, reduces congestion, and optimizes the traffic management efficiency. Brief Description of the Drawings

[0062] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0063] Figure 1 It is a schematic flowchart of a dynamic intelligent highway expansion method based on the supply-demand relationship; Detailed Embodiments

[0064] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments.

[0065] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs. The terms used in the description of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0066] Embodiment 1

[0067] As Figure 1As shown in the figure, the present invention provides a dynamic intelligent expansion method for expressways based on supply and demand relationships. The method includes:

[0068] S1: Taking the publishing device as a traffic control node, dividing the expressway into traffic control units;

[0069] Specifically, the publishing devices include traffic management devices such as information boards, ramp traffic lights, toll stations, etc. Through these devices, the expressway is divided into multiple traffic control units, and each unit serves as an independent traffic management area. These control units can independently implement traffic management measures according to the actual traffic flow, road congestion conditions, and other relevant factors, such as adjusting the speed limit, controlling the ramp flow, diverting traffic, etc. By dividing the traffic control units, refined management of different sections can be achieved, ensuring the dynamic adjustment and optimization of traffic flow, improving the traffic capacity and safety of the entire expressway network. In addition, the publishing devices can also real-time publish traffic information to drivers, guiding vehicles to drive according to the control strategy, thereby further enhancing the effect of traffic management.

[0070] S2: Collecting real-time traffic data and classifying the traffic status according to the traffic data to obtain the evaluation result of the road operation status;

[0071] Specifically, a variety of sensors and monitoring devices installed on the expressway, such as millimeter-wave radars, high-definition cameras, vehicle counters, etc., are used to collect real-time traffic data, including vehicle speed, traffic flow, lane occupancy rate, vehicle type, traffic density, etc. Based on these data, preset standards and algorithms are used to classify the traffic status. The traffic status is usually divided into four levels: unobstructed, slightly congested, moderately congested, and severely congested, and each level corresponds to different vehicle speed and traffic flow ranges. Refer to the "Evaluation Method for Road Traffic Congestion Degree" (GA / T 115-2020) to classify the traffic levels, as shown in the table.

[0072] Traffic level classification of a single sensing device

[0073] Traffic condition Average speed Level Unobstructed ≥70 1 Slight congestion [50,70) 2 Moderate congestion [30,50) 3 Severe congestion [0,30) 4

[0074] It should be noted that for continuous sensing devices on the road, the congestion length is calculated, and continuous congested sections need to be merged. Through this classification, the current road operation status can be accurately evaluated, potential congested sections can be identified in a timely manner, providing data support for subsequent control strategy adjustment and optimization. The implementation of this process can achieve dynamic monitoring and evaluation of traffic status, thereby improving the management efficiency and traffic flow scheduling ability of expressways.

[0075] S3: Based on historical data and real-time traffic data, conduct supply-demand analysis using machine learning algorithms, predict traffic flow and traffic capacity in the future time, and calculate the traffic capacity and short-term traffic flow prediction of the current section of the road.

[0076] Specifically, first, combine historical traffic data (such as daily traffic volume, seasonal changes, etc.) with real-time traffic data (such as current traffic volume, vehicle speed, traffic density, etc.), and construct a training dataset through data preprocessing and cleaning. Then, use machine learning algorithms (such as regression analysis, support vector machine (SVM), deep learning algorithms, etc.) to conduct supply-demand analysis and predict traffic flow and road traffic capacity in the future period. This process takes into account various characteristic factors, such as holiday effects, weather impacts, special events, etc., to obtain more accurate prediction results. Next, based on the results predicted by the model, calculate the traffic capacity of the current section of the road (such as the number of vehicles passing through per unit time, the maximum carrying capacity of the road, etc.). At the same time, use the short-term traffic flow prediction model to predict the traffic flow in the short term in the future, further refine the traffic flow changes, predict the gap between traffic demand and road supply. Through these prediction results, traffic management strategies can be adjusted in real time to ensure the balance between road traffic volume and traffic capacity in the future period and improve the overall traffic efficiency.

[0077] S4: According to the supply-demand prediction results, calculate the gap traffic volume of traffic control nodes, and formulate and adjust the traffic management strategies of each traffic control node based on the gap traffic volume.

[0078] Specifically, first, according to the supply-demand prediction results, calculate the gap traffic volume of each traffic control node. Through this calculation, it is possible to determine whether there is a problem of insufficient traffic capacity at each control node and quantify this gap. Based on the gap traffic volume, corresponding traffic management strategies will be formulated and adjusted next, specifically including:

[0079] Adjust speed limit: When demand is too high, reduce the speed limit to reduce traffic volume and improve the traffic capacity of the road.

[0080] Ramp control: Control the ramp traffic volume, allocate appropriate ramp signals according to real-time traffic flow, and reduce the pressure on the main line.

[0081] Diversion strategy: Divert part of the traffic flow by guiding some vehicles to change lanes, opening the emergency lane, etc., to relieve the pressure on the main road.

[0082] Toll station regulation: Adjust the number of lanes or toll collection strategies of the toll station according to the traffic conditions to avoid large-scale queues at the toll station.

[0083] S5: Monitor the implementation effect of traffic management strategies based on real-time traffic data. If the expected goal is not achieved, optimize the traffic management strategies.

[0084] Specifically, by collecting and analyzing traffic data on highways in real time (such as traffic flow, vehicle speed, road occupancy rate, etc.), the implemented traffic management strategies are monitored. These data can be obtained through sensors, cameras, and other traffic monitoring devices and transmitted to the traffic control center in real time. After implementing traffic control measures, the system will compare the actual effects with the expected goals.

[0085] If the monitoring results show that the traffic flow has not been effectively reduced, or the traffic capacity of some sections still fails to reach the expectation, the system will optimize the existing traffic management strategies. The optimization measures include:

[0086] Toll station control: Continuing until the congestion ends;

[0087] Ramp control: When the congestion spreads to the intersecting highway;

[0088] Speed limit control: 1) The congestion continues to escalate; 2) The continuous supply capacity < (5% of the supply-demand gap); 3) The continuous compliance rate < 5%

[0089] Emergency lane opening: Continuing until the congestion ends;

[0090] Diversion: 1) The congestion continues to escalate; 2) The continuous supply capacity < (5% of the supply-demand gap); 3) The continuous compliance rate < 5%. At this time, further optimization is required. The optimization start time is when the toll station control, ramp control, and emergency lane opening strategies all fail. The optimization strategies include traffic police setting up checkpoints for forced diversion and traffic police cars on the road for forced speed reduction.

[0091] Through the present invention, the problems of high cost and long cycle in the traditional highway expansion method are effectively solved, the road traffic capacity is significantly improved, congestion is reduced, and the traffic management efficiency is optimized.

[0092] As an optimization of the above embodiments, the machine learning algorithm includes:

[0093] Selecting characteristic variables for traffic capacity prediction and short-term traffic flow;

[0094] Constructing a data matrix according to historical data and real-time collected traffic data. The data matrix contains multiple data entries and characteristic dimensions;

[0095] Modeling the data matrix based on a time series neural model and predicting the traffic capacity and short-term traffic flow by learning historical traffic patterns.

[0096] Specifically, the following characteristics are selected for constructing the traffic capacity prediction model and the short-term traffic flow prediction model, respectively from time characteristics, data statistical characteristics, driving behavior distribution, associated road section characteristics, environmental characteristics, road condition characteristics, road occupancy, and special events

[0097] Time characteristics: holidays, weekdays, time periods;

[0098] Data statistical characteristics: traffic flow statistical sequence, driving speed, space occupancy rate, time occupancy rate, vehicle type proportion;

[0099] Driving behavior characteristics: distribution characteristics of aggressive and conservative types

[0100] Related road section characteristics: upstream main road traffic flow, downstream main road traffic flow, upstream ramp traffic flow, downstream ramp traffic flow;

[0101] Environmental characteristics: temperature, humidity, visibility, weather, wind force, air quality;

[0102] Road condition characteristics: number of pavement cracks, number of potholes, etc.

[0103] Occupation characteristics: number and length of occupied roads

[0104] Special events: number of major conferences, celebrations, etc.;

[0105] The input data consists of multi-dimensional data of historical data, forming a matrix X of i * j:

[0106]

[0107] Among them, i represents the number of data items, and j represents the number of features.

[0108] The passing capacity prediction model selects the maximum cycle passing flow of the day as the label, and the short-term traffic flow prediction model selects the passing flow of the next cycle as the label. The model uses time series neural network models such as RNN, LSTM, GRU, etc. and their improved versions. In the training stage, the time series neural network (such as RNN, LSTM, GRU and their improved versions) will use the constructed data matrix (matrix X of i×j) for learning. The learning goal is to identify historical traffic patterns and their impact on future traffic flow and passing capacity. The model will iteratively optimize its internal parameters to accurately predict future traffic flow and road passing capacity.

[0109] As an optimization of the above embodiment, calculate the gap passing volume and configure the control strategy, including:

[0110] Calculate the gap passing volume, which is equal to the predicted passing capacity of the next cycle minus the predicted value of the short-term traffic flow of the next cycle;

[0111] If the gap passing volume is greater than or equal to 0, it indicates that the passing capacity of the next cycle meets the traffic flow demand, and no additional control measures are required;

[0112] If the gap throughput is less than 0, it indicates that the traffic capacity in the next cycle cannot meet the traffic demand, and adjustment is required through the control measures at each traffic control node.

[0113] Specifically, first, calculate the gap throughput. The gap throughput is equal to the predicted traffic capacity in the next cycle minus the predicted value of the short-term traffic flow in the next cycle. This calculation step is used to determine whether the currently predicted traffic flow will exceed the road's carrying capacity. If the gap throughput is positive or zero, it means that the existing traffic capacity can meet the future traffic demand, so no additional control measures are required, and the system will continue to monitor the traffic flow condition to ensure that the flow remains within the normal range. However, if the gap throughput is less than zero, it indicates that the future traffic flow will exceed the road's traffic capacity, and the system needs to take corresponding control measures to bridge this gap. In this case, the system will make adjustments based on real-time data.

[0114] As an optimization of the above embodiment, the calculation method for the traffic capacity supplied by control is:

[0115] C = F 1 -F 2

[0116] where C is the traffic capacity that can be supplied by the current strategy, and F 1 is the traffic volume that needs to enter the main line after control, and F 2 is the traffic volume that has entered the main line before control and cannot reach the bottleneck point within a strategy refresh cycle.

[0117] Specifically, in the calculation process, first, it is necessary to calculate the traffic capacity (F1) after implementation according to the current control strategy (such as speed limit, ramp control, etc.); then, it is necessary to consider the traffic volume (F2) that has entered the main line, which cannot be discharged or reach the bottleneck point within the refresh cycle of the current strategy, so it will reduce the effective traffic capacity of the current control measures. By subtracting the occupied traffic volume (F2) from the currently available traffic capacity (F1), the final traffic capacity supplied by control (C) is obtained, thus providing data support for subsequent traffic flow regulation and strategy optimization.

[0118] As an optimization of the above embodiment, the toll station control strategy includes:

[0119] When there is no queue at the outer square of the current toll station:

[0120]

[0121] c close is the number of closed lanes, and c total is the total number of released lanes, and flow next_pre is the predicted traffic volume passing through in the next cycle;

[0122] There is a queue at the outer square of the current toll station:

[0123]

[0124] flow max is the maximum traffic flow per unit time, and time queue_clear is the queue dissipation time, T is the strategy refresh period, and flow pre is the predicted traffic flow after queue dissipation;

[0125]

[0126] where dis is the distance from the current location to the congestion point, and speed previous is the average speed before control, and flow is the quantity within the corresponding period.

[0127] Specifically, when there is no queue at the outer square of the toll station, and when there is a queue at the outer square of the toll station.

[0128] First, when there is no queue at the outer square of the toll station, the control strategy mainly focuses on the effective utilization of the traffic capacity. In this case, the system evaluates the traffic capacity of the toll station based on the current number of closed lanes, the total number of lanes, and the predicted future traffic flow. This evaluation ensures that the existing lane resources can effectively handle the expected traffic flow and avoid unnecessary traffic bottlenecks; however, when there is a queue at the outer square of the toll station, the system enters the optimization mode and improves the current situation through the queue dissipation ability. At this time, the control strategy calculates the maximum traffic flow per unit time of the toll station and combines the queue dissipation time to predict the future traffic flow. During the queue dissipation period, the system adjusts the lane allocation of the toll station according to the historical traffic flow data to ensure that the traffic flow can be discharged smoothly. In addition, by evaluating the distance between the queuing vehicles and the toll station exit, as well as the average driving speed of the vehicles, the system can predict when the queuing vehicles can be cleared and further optimize the control strategy accordingly. Through these measures, the toll station can dynamically adjust the number of lanes, the toll strategy, and the traffic flow guidance according to different traffic flow situations, ensuring that vehicles can pass through the toll station quickly, reducing the queuing time, optimizing the overall traffic flow, and avoiding the decline in traffic efficiency caused by excessive congestion.

[0129] As an optimization of the above embodiment, the ramp control strategy includes:

[0130] There is no queue at the current ramp:

[0131] F 1 = flow next_pre ,

[0132] flow next_pre is the predicted traffic flow in the next period;

[0133] Queue occurs at the current ramp:

[0134]

[0135] flow max is the maximum vehicle flow per unit time, time queue_clear is the queue dissipation time, T is the strategy refresh period, flow pre is the predicted flow after queue dissipation;

[0136]

[0137] dis is the distance from the current position to the congestion point, speed previous is the average speed before control, flow is the quantity within the corresponding period.

[0138] Specifically, first, when there is no queue at the ramp, the core of the control strategy is to evaluate the ramp's traffic capacity by predicting future vehicle flows. In this case, the system determines whether the ramp can handle the expected vehicle flow based on the predicted vehicle flow in the next period, ensuring that the ramp's traffic capacity is sufficient to meet the flow demand. If the vehicle flow prediction is within the manageable range, no additional control measures are required; however, when a queue appears at the ramp, it indicates that the vehicle flow exceeds the ramp's traffic capacity, resulting in the occurrence of a queue. At this time, the system evaluates whether the existing lanes can effectively clear the queued vehicles by analyzing the ramp's maximum traffic capacity and the time required to dissipate the queue. Based on this analysis, the system adjusts the strategy, such as increasing the number of lanes, adjusting the ramp signal cycle, or improving the flow through other diversion means. In addition, the system also evaluates the distance between the queued vehicles and the ramp exit, as well as the average driving speed of the vehicles, to predict when the queued vehicles can be discharged and continue to flow. This information will help the system determine the dissipation speed of the queued vehicles and ensure that the queued flow can be smoothly dissipated within the prediction period.

[0139] As an optimization of the above embodiment, the speed limit control strategy includes:

[0140]

[0141] flow now is the vehicle flow at the current section, v is the average speed in the previous n periods, v limit is the strategy speed limit value, λ is the compliance of personnel, T is the strategy refresh period;

[0142]

[0143] dis is the distance from the current position to the congestion point, speed previousThe average speed before control, and flow is the quantity within the corresponding period.

[0144] Specifically, first, in the speed limit control strategy, when the vehicle passing flow of the current section is detected, the system calculates the speed limit most suitable for the current traffic situation based on this flow, the average vehicle speed in the previous n periods, and the speed limit value set by the strategy. The flow represents the number of vehicles passing through this section per unit time. The average speed in the previous n periods helps evaluate the smoothness of the current traffic flow. The strategy speed limit value is a temporary speed limit standard formulated according to the design speed of the road and the traffic conditions. In addition, the compliance of personnel reflects the compliance of drivers with the speed limit instructions, and the system adjusts according to historical data to ensure the effectiveness of the speed limit measures; when there is a situation of large traffic flow and too fast vehicle speed, the system predicts the vehicle speed change in the next period of time based on the distance from the current position to the congestion point, combined with the average speed before control. Through this prediction, the system can dynamically adjust the speed limit value to ensure that the vehicle speed remains within a safe range and avoid collision accidents on the section about to be congested.

[0145] As an optimization of the above embodiment, the emergency lane opening strategy includes:

[0146]

[0147] flow lane_100 is the vehicle passing flow of the current 100-meter unit section, lane n is the number of currently open lanes, T is the strategy refresh period, time open is the total opening duration, length open is the total opening length;

[0148] F 2 = 0.

[0149] Specifically, the implementation of the speed limit control strategy is mainly based on the monitoring of real-time traffic flow and vehicle speed, and optimizes the traffic efficiency by dynamically adjusting the speed limit to avoid traffic accidents caused by excessive congestion or too fast vehicle speed.

[0150] First, in the speed limit control strategy, when the vehicle passing flow of the current section is detected, the system calculates the speed limit most suitable for the current traffic situation based on this flow, the average vehicle speed in the previous n periods, and the speed limit value set by the strategy. The flow represents the number of vehicles passing through this section per unit time. The average speed in the previous n periods helps evaluate the smoothness of the current traffic flow. The strategy speed limit value is a temporary speed limit standard formulated according to the design speed of the road and the traffic conditions. In addition, the compliance of personnel reflects the compliance of drivers with the speed limit instructions, and the system adjusts according to historical data to ensure the effectiveness of the speed limit measures.

[0151] When there is a situation of heavy traffic flow and excessive vehicle speed, the system will predict the vehicle speed change in the next period of time based on the distance from the current location to the congestion point and the average speed before control. Through this prediction, the system can dynamically adjust the speed limit value to ensure that the vehicle speed remains within a safe range and avoid collision accidents on the upcoming congested section.

[0152] As a preference of the above embodiment, the diversion strategy includes:

[0153] F 1 =(α 1 -α 2 )*flow now ,

[0154] flow now is the traffic flow passing through the current section, α 1 is the diversion ratio after the diversion control is turned on, and α 2 is the diversion ratio after the diversion control is turned on;

[0155] F 2 =0.

[0156] Specifically, the diversion strategy mainly alleviates the traffic pressure on specific sections by reasonably distributing the traffic flow. Especially during traffic peaks or congestion, this strategy controls the diversion ratio to ensure that the traffic flow can be effectively distributed among different sections, thus avoiding excessive congestion on certain sections.

[0157] First, the system will evaluate the density of the traffic flow based on the traffic flow passing through the current section. If the traffic flow at a certain section exceeds the designed carrying capacity of the road, the system will activate the diversion strategy. The diversion ratio after the diversion control is turned on represents the proportion of vehicles that will be guided to other roads or lanes after the diversion measures are implemented. The system determines this ratio based on real-time traffic flow and road condition data to ensure that no new bottlenecks or congestion will be caused.

[0158] Second, in the diversion strategy, the diversion ratio after the diversion control is turned on refers to the ratio of the traffic flow transferred to other roads or lanes to the original traffic flow after the diversion measures are implemented. By adjusting this ratio, the system can flexibly control the diversion effect to ensure that it can effectively relieve the pressure on the current section without transferring the pressure to other unforeseen sections.

[0159] Finally, the diversion strategy optimizes the traffic flow on the road by dynamically adjusting these diversion ratios, improving the traffic capacity of the entire highway, reducing congestion, avoiding overload on a single section, and ensuring smooth traffic flow.

[0160] Embodiment 2

[0161] Based on the same inventive concept as the method for dynamically and intelligently expanding a highway based on supply and demand in the foregoing embodiments, the present invention also provides a system for dynamically and intelligently expanding a highway based on supply and demand. The system includes:

[0162] A control unit division module that uses the publishing device as a traffic control node to divide the traffic control units of the highway;

[0163] A road condition assessment module that collects real-time traffic data and classifies the traffic status according to the traffic data to obtain an assessment result of the road operation condition;

[0164] An algorithm analysis and calculation module that performs supply and demand analysis based on machine learning algorithms according to historical data and real-time traffic data, predicts the traffic flow and traffic capacity in the future time, and calculates the traffic capacity of the current section of the road and the short-term traffic flow prediction;

[0165] A management strategy formulation module that calculates the shortage traffic volume of the traffic control node according to the supply and demand prediction result, and formulates and adjusts the traffic management strategies of each traffic control node based on the shortage traffic volume;

[0166] A management strategy optimization module that monitors the implementation effect of the traffic management strategy based on real-time traffic data. If the expected goal is not achieved, the traffic management strategy is optimized.

[0167] The above evaluation system in the present invention can effectively implement the method for dynamically and intelligently expanding a highway based on supply and demand, and the technical effects that can be achieved are as described in the foregoing embodiments, which will not be elaborated here.

[0168] Similarly, for the above optimization solutions of the system, the corresponding optimization effects of the methods in the first embodiment can also be respectively achieved, which will not be elaborated here either.

[0169] Although the present application has been described in combination with specific features and their embodiments, it is obvious that various modifications and combinations can be made without departing from the spirit and scope of the present application. Accordingly, the present specification and the drawings are merely exemplary descriptions of the present application as defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of the present application.

[0170] 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 method for dynamic intelligent expansion of highways based on supply and demand, characterized in that: include: Use the release equipment as traffic control nodes and divide the highway into traffic control units; Collecting real-time traffic data, and classifying traffic conditions according to the traffic data to obtain road operation status assessment results; Based on the historical data and the real-time traffic data, supply and demand analysis is performed based on machine learning algorithms to predict traffic flow and capacity in the future, and the capacity and short-term traffic flow forecast of the current section road are calculated; Calculate the gap traffic volume of the traffic control node according to the supply and demand forecast results, and formulate and adjust the traffic management strategy of each traffic control node based on the gap traffic volume; The implementation effect of the traffic management strategy is monitored based on the real-time traffic data. If the expected goal is not achieved, the traffic management strategy is optimized.

2. The method for dynamic intelligent expansion of highways based on supply and demand relationship according to claim 1 is characterized in that: The machine learning algorithm includes: Select characteristic variables for capacity prediction and short-term traffic flow; Constructing a data matrix based on the historical data and the real-time collected traffic data, wherein the data matrix includes a plurality of data entries and feature dimensions; The data matrix is ​​modeled based on a time series neural model, and the capacity and short-term traffic flow are predicted by learning historical traffic patterns.

3. The method for dynamic intelligent expansion of highways based on supply and demand relationship according to claim 1 is characterized in that: Calculate the gap flow and configure the control strategy, including: Calculate the gap traffic volume, where the gap traffic volume is equal to the predicted traffic capacity of the next cycle minus the predicted value of the short-term traffic flow of the next cycle; If the gap traffic volume is greater than or equal to 0, it means that the traffic capacity of the next cycle meets the traffic demand and no additional control measures are needed; If the gap traffic volume is less than 0, it means that the traffic capacity of the next cycle cannot meet the traffic demand and needs to be adjusted through the control measures of each traffic control node.

4. The method for dynamic intelligent expansion of highways based on supply and demand relationship according to claim 1 is characterized in that: The calculation method for the controlled supply capacity is: C=F1-F2 Among them, C is the traffic capacity that can be supplied by the current strategy, F1 is the traffic flow that needs to enter the main line after control, and F2 is the traffic flow that has entered the main line before control and cannot reach the bottleneck point within a strategy refresh cycle.

5. The method for dynamic intelligent expansion of highways based on supply and demand relationship according to claim 1 is characterized in that: Toll station control strategies include: There is no queue outside the toll station at the moment: c close is the number of lane closures, c total Total number of released lanes, flow next_pre To predict the traffic volume in the next cycle; The current queues outside the toll station are: flow max is the maximum traffic flow per unit time, time queue_clear is the queue elimination time, T is the policy refresh cycle, flow pre Predict traffic flow after queue elimination; Where dis is the distance from the current location to the congestion point, speed previous is the average speed before control, and flow is the number in the corresponding period.

6. The method for dynamic intelligent expansion of highways based on supply and demand relationship according to claim 1 is characterized in that: Ramp control strategies include: There is no queue at the current ramp: F1=flow next_pre , flow next_pre To predict the traffic volume in the next cycle; The current ramp generates queues: flow max is the maximum traffic flow per unit time, time queue_clear is the queue elimination time, T is the policy refresh cycle, flow pre Predict traffic flow after queue elimination; dis is the distance from the current location to the congestion point, speed previous is the average speed before control, and flow is the number in the corresponding period.

7. The method for dynamic intelligent expansion of highways based on supply and demand relationship according to claim 1 is characterized in that: Speed ​​limit control strategies include: flow now is the traffic flow of the current section, is the average speed of the last n cycles, v limit is the policy speed limit value, λ is the personnel compliance, and T is the policy refresh cycle; dis is the distance from the current location to the congestion point, speed previous is the average speed before control, and flow is the number in the corresponding period.

8. The method for dynamic intelligent expansion of highways based on supply and demand relationship according to claim 1 is characterized in that: Emergency lane opening strategies include: flow lane_100 lane is the current traffic volume per 100-meter section, n is the current number of open lanes, T is the strategy refresh cycle, time open is the total opening time, length open is the total length of opening; F2＝0。 9. The method for dynamic intelligent expansion of highways based on supply and demand relationship according to claim 1 is characterized in that: Diversion strategies include: F1=(α1-α2)*flow now , flow now is the current traffic flow of the section, α1 is the diversion ratio after the diversion control is turned on, and α2 is the diversion ratio after the diversion control is turned on; F2＝0。 10. A dynamic intelligent expansion system for highways based on supply and demand, characterized in that: The system comprises: The control unit division module uses the publishing device as a traffic control node to divide the highway into traffic control units; A road condition assessment module collects real-time traffic data and classifies traffic conditions according to the traffic data to obtain a road operation condition assessment result; An algorithm analysis and calculation module performs supply and demand analysis based on historical data and the real-time traffic data, based on a machine learning algorithm, predicts traffic flow and capacity in the future, and calculates the capacity of the current section road and short-term traffic flow prediction; A management strategy formulation module calculates the gap traffic volume of the traffic control node according to the supply and demand forecast results, and formulates and adjusts the traffic management strategy of each traffic control node based on the gap traffic volume; The management strategy optimization module monitors the implementation effect of the traffic management strategy based on the real-time traffic data, and optimizes the traffic management strategy if the expected goal is not achieved.

Images