Traffic flow and vehicle speed based road congestion determination and regulation method and system

Abstract

The disclosure provides a traffic flow and vehicle speed-based road congestion determination and adjustment method and system, relates to the technical field of traffic engineering, and comprises the following steps: acquiring the traffic flow and vehicle average speed of a current road section, and historical traffic flow and vehicle average speed; based on the historical traffic flow and vehicle average speed information, a mixed density network is used to model the probability distribution of the traffic flow-vehicle speed point cloud based on the historical traffic flow and vehicle average speed information, and a traffic flow-vehicle speed relationship curve is obtained; the maximum traffic volume and the congestion time period of the current road section are determined based on the traffic flow-vehicle speed curve; a traffic congestion charge is introduced, the minimum total travel cost of users is taken as an optimization objective, the historical traffic flow and vehicle average speed are taken as constraint conditions, a bottleneck mathematical model for traffic adjustment is constructed, the bottleneck mathematical model is solved, the optimal solution is used for a corresponding traffic control strategy, the equivalent travel cost is given to the users, and the corresponding road traffic adjustment target is achieved.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of traffic engineering, in particular to a road congestion determination and regulation method and system based on traffic flow and vehicle speed. BACKGROUND

[0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute the prior art.

[0003] The current traffic infrastructure construction speed is slower than the growth speed of traffic demand, and the continuously increasing traffic flow leads to frequent highway traffic congestion, which in turn causes a series of serious subsequent problems, and it is urgent to regulate and control road traffic flow to govern it.

[0004] Traffic congestion discriminates accurately define the traffic state and grasp the traffic control opportunity, which is an important prerequisite for formulating effective induction strategies. The current evaluation of road traffic operation state is mainly based on the ratio V / C of road traffic flow V and road capacity C, and this method divides the road service state into congestion, stable flow and free flow states by discretization. Although this method has certain reference value in practical application, it generally relies on static data and fixed threshold, and it is difficult to reflect the dynamic change characteristics of traffic operation state, and it is also difficult to effectively identify and analyze the frequently congested area and its time distribution law, so it is difficult to provide strong support for precise traffic regulation and management. With the continuous improvement of the complexity of the traffic system, it is difficult to meet the actual needs of efficient traffic management by relying only on traditional methods.

[0005] Meanwhile, the development of big data technology provides strong support for dynamic perception and accurate analysis of traffic conditions. For example, by analyzing the toll and traffic data collected by the highway gantry system, the key parameters such as traffic flow and vehicle speed of the road section can be obtained in real time. This provides data basis and technical support for the upgrading of traffic condition recognition methods. However, the above methods are based on manually set traffic characteristics to carry out traffic state prediction research, and the traffic state parameters are not screened during the research, but the traffic state is set as congestion, congestion, and smooth, and the collected large amount of traffic state data is described as the corresponding traffic state vector by using the discrete traffic state coding method, and a multi-classification algorithm for traffic state discrimination is proposed combined with deep learning algorithm, which will lead to a large amount of data calculation, increase the time cost, and cannot quickly obtain the recognition of the road state. In addition, the existing method usually only relies on single parameters such as flow and speed for fitting, ignoring the differences of traffic state under different time, space and environmental conditions. For example, under the same flow condition, the running speed of double-lane and multi-lane road sections in the morning peak and at night, in sunny and rainy days may be significantly different. If these context factors are not considered, the model may be too idealized and cannot accurately reflect the diversity and non-linear characteristics of traffic operation. In addition, in the method of model optimization solution, the traditional model optimization is usually modeled as a bi-level programming problem: the upper layer takes the minimization of the total travel cost of the system as the objective, and the lower layer takes the user equilibrium as the constraint. Although this method can obtain an equilibrium solution in theory, it has some shortcomings in practical application: first, the model structure is complex, and the solution often depends on large-scale iterative calculation, which is difficult to meet the real-time requirement; second, when the traffic demand has randomness or there are accidents, weather and other uncertain disturbances, the bi-level programming is difficult to adjust in time, resulting in insufficient stability of the results; third, the optimization process needs to make idealized assumptions about the behavior of travelers, which deviates from the actual situation. SUMMARY

[0006] To solve the above problems, the present disclosure proposes a road congestion determination and adjustment method and system based on traffic flow and speed, which fits the traffic flow-speed curve by analyzing real-time traffic data and historical data, determines the service level change and congestion period of the road section, uses an improved bottleneck model, introduces traffic congestion toll, and recalculates the toll scheme by taking the historical road traffic flow data as a new constraint condition, to achieve the corresponding road traffic adjustment target by giving the equivalent travel cost to the user.

[0007] According to some embodiments, the present disclosure adopts the following technical solutions:

[0008] The road congestion determination and adjustment method based on traffic flow and speed comprises:

[0009] obtaining the traffic flow, average vehicle speed of the current road section, and historical traffic flow, average vehicle speed;

[0010] Based on historical traffic flow and vehicle average speed information, a mixed density network is used to model the conditional probability distribution of the flow-speed point cloud, and the traffic flow-speed relationship curve of the current road section is obtained;

[0011] Based on the traffic flow-speed curve, the maximum traffic volume of the current road section and the congestion time period of the current road section are determined;

[0012] The traffic congestion charge is introduced, the minimum total travel cost of the user is taken as the optimization objective, the historical traffic flow and the vehicle average speed are taken as the constraint conditions, a bottleneck mathematical model for traffic regulation is constructed, a reinforcement learning method is introduced to solve the bottleneck mathematical model, and the optimal solution is used for the corresponding traffic control strategy to give the user an equivalent travel cost, and the corresponding road traffic regulation target is achieved.

[0013] According to some embodiments, the present disclosure adopts the technical scheme as follows:

[0014] The road congestion determination and regulation system based on flow and speed comprises:

[0015] A data acquisition module is configured to acquire the traffic flow, vehicle average speed, historical traffic flow and vehicle average speed of the current road section;

[0016] A curve fitting module is configured to model the conditional probability distribution of the flow-speed point cloud based on historical traffic flow and vehicle average speed information using a mixed density network, and obtain the traffic flow-speed relationship curve of the current road section;

[0017] A judgment module is configured to determine the maximum traffic volume of the current road section and the congestion time period of the current road section based on the traffic flow-speed curve;

[0018] A regulation module is configured to introduce the traffic congestion charge, take the minimum total travel cost of the user as the optimization objective, take the historical traffic flow and the vehicle average speed as the constraint conditions, construct a bottleneck mathematical model for traffic regulation, introduce a reinforcement learning method to solve the bottleneck mathematical model, and use the optimal solution for the corresponding traffic control strategy to give the user an equivalent travel cost, and achieve the corresponding road traffic regulation target.

[0019] According to some embodiments, the present disclosure adopts the technical scheme as follows:

[0020] A computer program product comprises a computer program, which, when executed by a processor, implements the road congestion determination and regulation method based on flow and speed.

[0021] According to some embodiments, the present disclosure adopts the technical scheme as follows:

[0022] The application discloses a non-transitory computer readable storage medium for storing computer instructions, which, when executed by a processor, implement the road congestion determination and adjustment method based on traffic flow and vehicle speed.

[0023] According to some embodiments, the present disclosure adopts the technical solutions as follows:

[0024] An electronic device comprises a processor, a memory and a computer program; wherein the processor is connected with the memory, and the computer program is stored in the memory; when the electronic device is running, the processor executes the computer program stored in the memory, so that the electronic device implements the road congestion determination and adjustment method based on traffic flow and vehicle speed.

[0025] Compared with the prior art, the present disclosure has the beneficial effects as follows:

[0026] The road congestion determination and adjustment method based on traffic flow and vehicle speed of the present disclosure can comprehensively analyze traffic flow and vehicle speed data, learn conditional probability distribution by adopting a mixed density network to probabilistically model traffic flow-vehicle speed point clouds based on historical traffic flow and vehicle average speed information, and obtain a traffic flow-vehicle speed relationship curve of a current road section, which can represent multimodal speed distribution under different traffic phases, so that the maximum traffic volume and the critical speed can be more accurately identified; the maximum traffic volume of the current road section and the congestion time period of the current road section can be determined based on the traffic flow-vehicle speed curve, the traffic volume-vehicle speed curve can be accurately fitted, the capacity of the road can be better understood, the overall traffic efficiency can be improved, and the congestion time can be reduced; and the frequently occurring congestion nodes can be accurately identified, and the traffic bottlenecks can be timely found.

[0027] The road congestion determination and adjustment method based on traffic flow and vehicle speed of the present disclosure introduces traffic congestion charging, takes the minimum total travel cost of users as an optimization target, takes historical traffic flow and vehicle average speed as constraint conditions, constructs a bottleneck mathematical model for traffic adjustment, and analyzes historical and real-time data, which is helpful for formulating a more accurate traffic flow adjustment scheme and optimizing the service level of the road; a reinforcement learning method is introduced to solve the bottleneck mathematical model, and the optimal solution is used for a corresponding traffic control strategy to give the users equivalent travel costs, so as to achieve the corresponding road traffic adjustment target; through the reinforcement learning-based solving method, the bottleneck model can be adaptively optimized in a complex and uncertain traffic environment, and compared with a traditional mathematical programming method, the reinforcement learning-based solving method has stronger real-time performance, self-learning ability and generalization ability, so as to provide more efficient and intelligent technical support for traffic congestion adjustment.

[0028] The traffic flow and vehicle speed based road congestion determination and regulation method of the present disclosure utilizes historical and current traffic data to provide early warning of possible congestion, and provides a scientific basis for preventive traffic management and diversion. Through effective traffic flow regulation and congestion management, the occurrence of traffic accidents can be reduced, and road traffic safety can be improved. BRIEF DESCRIPTION OF DRAWINGS

[0029] The accompanying drawings, which form a part of this disclosure, are intended to provide further understanding of the present disclosure and are incorporated herein in conjunction with the description of the present disclosure. The schematic embodiments of the present disclosure and their descriptions are used to explain the present disclosure, and do not constitute an improper limitation on the present disclosure.

[0030] Figure 1 Traffic flow-vehicle speed relationship curve for an embodiment of the present disclosure;

[0031] Figure 2 Flowchart of the traffic flow and vehicle speed based road congestion determination and regulation method of an embodiment of the present disclosure. DETAILED DESCRIPTION

[0032] The present disclosure will be further described below in conjunction with the accompanying drawings and embodiments.

[0033] It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the present disclosure. Unless otherwise indicated, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present disclosure belongs.

[0034] It should be noted that the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit the exemplary embodiments according to the present disclosure. As used herein, the singular form is intended to include the plural form unless the context clearly indicates otherwise, and it should be further understood that when the terms "comprise" and / or "include" are used in the specification, there is a presence of a feature, step, operation, device, component, and / or combinations thereof.

[0035] Embodiment 1

[0036] In one embodiment of the present disclosure, a traffic flow and vehicle speed based road congestion determination and regulation method is provided, and the method steps include:

[0037] Step 1: Obtain the current traffic flow, average vehicle speed, and historical traffic flow, average vehicle speed of the road section;

[0038] Step 2: Based on the historical traffic flow and average vehicle speed information, use a hybrid density network to model the conditional probability distribution of the flow-vehicle speed point cloud, and obtain the traffic flow-vehicle speed relationship curve of the current road section;

[0039] Step three: determine the maximum traffic volume of the current road section and the congestion time period of the current road section based on the traffic flow-vehicle speed curve;

[0040] Step four: introduce traffic congestion charges, take the minimum total travel cost of users as the optimization objective, take the historical traffic flow and vehicle average speed as the constraint condition, construct a bottleneck mathematical model for traffic regulation, introduce a reinforcement learning method to solve the bottleneck mathematical model, and use the optimal solution for the corresponding traffic control strategy to give the equivalent travel cost to the user, and realize the corresponding road traffic regulation goal.

[0041] As an embodiment, the road congestion determination and regulation method based on traffic flow and vehicle speed of the present disclosure can accurately determine the service level change and congestion period of the road section by analyzing the real-time data and historical data collected by the traffic detector, fitting the traffic flow-vehicle speed curve, and formulating a targeted traffic regulation scheme to improve the road traffic efficiency and management level. The specific implementation process is as follows:

[0042] Step 1: Obtain the traffic flow, vehicle average speed of the current road section, and historical traffic flow, vehicle average speed;

[0043] Specifically, taking the traffic data of a certain highway gantry as an example, the PeMS dataset is selected as a substitute. PeMS (Performance Measurement System) is an open-source road traffic data platform that contains 4,681 detectors, reporting data every 30 seconds. The data content of the PeMS system is rich, covers a wide time period, and has high research value. The system compiles data into 30-second interval records and continuously aggregates into 5-minute incremental data, with small detection errors and high intelligence.

[0044] Select a certain traffic node on a certain road and the corresponding time period (from January 2023 to December 2023), and use an automated program to download the historical traffic flow and speed data of the node. Then, organize the traffic data, convert the data obtained at a certain collection frequency (e.g., every five minutes) into hourly traffic flow, and calculate the average speed of all vehicles in the current period. Integrate these historical traffic data, aggregate the historical data of each week (e.g., every Monday), each month (30-day average), and specific holidays together, and calculate the average traffic flow and speed.

[0045] Further, obtain the road traffic data at a certain collection frequency (e.g., every five minutes), and convert it into hourly traffic flow and the average speed of all vehicles collected in the current period;

[0046] Step 2: Based on historical traffic flow and vehicle average speed information, a hybrid density network is used to model the conditional probability distribution of the flow- speed point cloud, and the traffic flow- speed relationship curve of the current road section is obtained;

[0047] Specifically, the sorted traffic data is plotted into a coordinate system graph with vehicle speed as the vertical axis and traffic flow as the horizontal axis. The historical traffic data of a node in a specific time period is represented in the form of points in the coordinate system graph. A hybrid density network is used to model the conditional probability distribution of the flow- speed point cloud, and the conditional probability distribution is learned to obtain the traffic flow- speed relationship curve of the current road section, which specifically includes:

[0048] The traffic flow is taken as the input feature, and the vehicle average speed is taken as the output variable. The neural network outputs the mixing parameters of multiple Gaussian distributions , and the parameter set is , where is the weight, is the mean, and is the covariance matrix. The model is trained by the maximum likelihood method to obtain the conditional probability distribution:

[0049] (1)

[0050] where is the weight of the K th Gaussian component, is the mean of the K th Gaussian component, is the th Gaussian component under the condition. K

[0051] In the inference stage, by inputting the given flow and the context feature , the corresponding speed distribution is generated, and a multimodal traffic flow- speed relationship curve can be plotted. The peak value of the curve and its corresponding speed are used to determine the maximum traffic volume and the critical speed. Different modes correspond to different traffic operation phases (such as free flow, transition flow, and congested flow). The context feature here refers to information related to traffic operation, such as time period, spatial road section, environmental conditions, real-time operation characteristics, and sudden events. The model not only learns the “average curve”, but also learns a set of different curves under different times, places, and environments, truly achieving “adjusting measures to local conditions and times”.

[0052] Through this traffic flow- speed curve, the peak value of the curve is taken as the maximum traffic volume, and the speed corresponding to the peak value is taken as the critical speed. According to the determined maximum traffic volume​ and critical speed This allows us to determine the maximum traffic capacity of the current road segment.

[0053] Step 3: Determine the maximum traffic volume and the congestion period of the current road segment based on the traffic flow-vehicle speed curve;

[0054] Specifically, firstly, the changes in road service levels are classified, and the classification content is shown in Table 1.

[0055] Table 1. Classification of Road Service Level Changes

[0056]

[0057] Furthermore, based on the criteria in Table 1, and using the determined road capacity and traffic flow data for each time period, the changes in road service levels every five minutes are analyzed weekly, monthly, and on specific holidays. Time periods with service levels below level four for more than one consecutive hour are identified as congested periods for the current road segment. Corresponding traffic flow adjustment plans are then developed for these congested periods and road segments to optimize road traffic efficiency and reduce congestion.

[0058] Step 4: Introduce congestion pricing, taking the minimization of total user travel costs as the optimization objective, and using historical traffic flow and average vehicle speed as constraints, construct a bottleneck mathematical model for traffic regulation. Introduce reinforcement learning methods to solve the bottleneck mathematical model, and apply the optimal solution to the corresponding traffic control strategy to assign users equivalent travel costs, thereby achieving the corresponding road traffic regulation objectives.

[0059] Specifically, traditional bottleneck-based road traffic management schemes assume that travelers have complete departure time information (i.e., users know the road conditions at various times on a given road segment) and use this constraint to solve for the equilibrium road traffic flow. This assumption clearly contradicts reality (users rarely know the traffic conditions of every segment on their chosen path at the moment of departure). Therefore, this disclosure proposes an improved scheme that uses historical road traffic flow data as a new constraint, introduces congestion pricing, and recalculates the pricing scheme. The specific strategy is as follows:

[0060] It is known that passage is possible at a given node per unit time. Vehicles (maximum capacity), when commuter arrival rate at the bottleneck exceeds At this time, queues will form on the road section. The queue length at the bottleneck is... The rate of change at time t can be expressed as:

[0061] (2)

[0062] wherein: the queue length at the bottleneck at time t; the inflow rate of commuters at the bottleneck at time t; is the unit time capacity of the bottleneck. After the introduction of congestion pricing, the total cost of a commuter for a trip is composed of three parts, which are the total travel time cost (including queuing and travel time), the early or late arrival penalty, and the congestion pricing, so The total trip cost of a commuter who departs at time t can be expressed as:

[0063] (3)

[0064] wherein: is the time value coefficient; is the early arrival penalty coefficient; is the late arrival penalty coefficient; is the travel time of the commuter from the residence to the workplace; is the start time of work; is the earliest departure time of the traveler; is the latest departure time of the traveler; is the departure time for the commuter to arrive at the workplace on time; is the cumulative cost at time t; is the variable cost that the traveler should bear when departing at time t; is the queuing time of the commuter at the bottleneck. Using historical traffic flow data as , the additional cost that should be given to a certain period of time can be obtained:

[0065] (4)

[0066] In combination with the subsequent adjustment mechanism, the corresponding traffic control strategy is used to give the user an equivalent trip cost, which can achieve the corresponding goal of road traffic regulation.

[0067] In some embodiments of the present disclosure, for the solving process of the proposed bottleneck mathematical model, a reinforcement learning method is introduced to realize intelligent dynamic optimization. Specifically, it includes:

[0068] (1) Environment modeling:

[0069] (1) Environment modeling:

[0070] ​​​The bottleneck model is constructed as a reinforcement learning environment, where the environment state is composed of current traffic flow, vehicle average speed, queue length, historical toll level, and contextual features such as time period, weather, road conditions, etc.; the environment transition is determined by the bottleneck queuing dynamic formula, i.e., updating the queue length and delay according to the vehicle arrival rate, road service capacity, and toll level in each time slice.

[0071] (2) Action space:

[0072] The agent selects the toll level adjustment amount at each discrete time slice. The action can be discrete (e.g., setting several toll levels) or continuous (arbitrarily selecting a toll value within the allowed range).

[0073] (3) Reward function:

[0074] The negative value of the total travel cost of the system, including the queuing time and travel time of vehicles, early or late arrival penalty, and congestion toll, is taken as the reward function. By maximizing the cumulative reward, it is equivalent to minimizing the total travel cost of the system.

[0075] (4) Agent training:

[0076] Deep reinforcement learning algorithms are used to train the agent. For example, in the discrete action space, a deep Q network (DQN) can be used, and in the continuous action space, a proximal policy optimization (PPO), deep deterministic policy gradient (DDPG), or soft actor-critic (SAC) method can be used. Through repeated interaction with the bottleneck model environment, the agent gradually learns the optimal toll strategy under different traffic conditions.

[0077] (5) Online deployment and rolling optimization:

[0078] In practical applications, the system obtains the latest traffic data at preset time intervals (e.g., 5 minutes or 15 minutes) and inputs it into the trained reinforcement learning agent, which outputs the toll strategy in real time. At the same time, combined with online learning and rolling optimization mechanisms, when traffic conditions are abnormal (e.g., accidents, holiday traffic surge), the agent can quickly adapt and update the strategy, thereby maintaining the robustness of the toll adjustment effect.

[0079] Through the above reinforcement learning-based solution method, the present disclosure can achieve adaptive optimization of the bottleneck model in complex and uncertain traffic environments. Compared with traditional mathematical programming methods, it has stronger real-time performance, self-learning ability, and generalization ability, thereby providing more efficient and intelligent technical support for traffic congestion regulation.

[0080] After the bottleneck mathematical model is solved and the traffic congestion cost function is designed, the key task of the subsequent adjustment mechanism is to convert the optimal tolling result and travel cost allocation strategy into an actual executable traffic control means, specifically including:

[0081] (1) Time-of-day dynamic tolling mechanism

[0082] Based on the optimal congestion tolling values p(t) of different time periods obtained by model solving, a refined time-of-day dynamic tolling table can be designed, which divides a day into multiple 5-minute or 15-minute intervals, sets a higher fee during peak hours, and sets a low fee or even free during off-peak or smooth hours, guiding travelers to staggered travel.

[0083] (2) Induction information publishing system

[0084] Through channels such as traffic induction screens, navigation applications, and mobile terminal Apps, real-time predicted congestion information and travel cost information (including queuing delay, toll amount, etc.) are published to improve user awareness and enable them to adjust their departure time or route based on the cost minimization principle without a "God's eye view".

[0085] (3) Linkage signal control and lane allocation strategy

[0086] When the predicted queue length at a node exceeds the safety threshold, the upstream and downstream intersection signal durations, the main and auxiliary lane allocation, and the emergency lane opening can be linked to release the capacity and relieve the bottleneck pressure without adding infrastructure.

[0087] (4) Feedback correction mechanism

[0088] The system can continuously collect traffic flow and speed data after implementation, adaptively update the model, dynamically correct the estimation error and congestion tolling pricing strategy, and form a "prediction-regulation-feedback-reoptimization" closed loop.

[0089] Embodiment 2

[0090] In an embodiment of the present disclosure, a road congestion determination and adjustment system based on traffic flow and vehicle speed is provided, comprising:

[0091] A data acquisition module for acquiring traffic flow, vehicle average speed, and historical traffic flow and vehicle average speed of a current road section;

[0092] A curve fitting module for modeling the conditional probability distribution of the flow-vehicle speed point cloud using a hybrid density network based on historical traffic flow and vehicle average speed information to obtain the traffic flow-vehicle speed relationship curve of the current road section;

[0093] A judgment module is configured to determine the maximum traffic volume of the current road section and the congestion time period of the current road section based on the traffic flow-vehicle speed curve;

[0094] An adjustment module is configured to introduce traffic congestion charges, take the minimum total travel cost of users as an optimization target, take the historical traffic flow and the average vehicle speed as constraint conditions, construct a bottleneck mathematical model for traffic adjustment, solve the bottleneck mathematical model, and use the optimal solution for corresponding traffic control strategies to give the users equivalent travel costs and achieve the goal of corresponding road traffic adjustment.

[0095] Embodiment 3

[0096] In an embodiment of the present disclosure, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the road congestion judgment and adjustment method based on traffic flow and vehicle speed.

[0097] Embodiment 4

[0098] In an embodiment of the present disclosure, a non-transitory computer readable storage medium is provided, which is configured to store computer instructions, which, when executed by a processor, implement the road congestion judgment and adjustment method based on traffic flow and vehicle speed.

[0099] Embodiment 5

[0100] In an embodiment of the present disclosure, an electronic device is provided, comprising a processor, a memory, and a computer program; wherein the processor is connected with the memory, and the computer program is stored in the memory; when the electronic device is running, the processor executes the computer program stored in the memory, so that the electronic device implements the road congestion judgment and adjustment method based on traffic flow and vehicle speed.

[0101] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the computer or other programmable data processing devices generate a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 The apparatus for implementing the functions specified in one or more flows and / or blocks Figure 1 The apparatus for implementing the functions specified in one or more flows and / or blocks

[0102] These computer program instructions can also be loaded into a computer or other programmable data processing devices, so that a series of operational steps are performed on the computer or other programmable data processing devices to generate a computer implemented process, so that the instructions executed on the computer or other programmable data processing devices provide a process for implementing the functions specified in the flowchart Figure 1 one flow or multiple flows and / or the functions specified in the block Figure 1 one flow or multiple flows and / or the functions specified in the block

[0103] Although the specific embodiments of the present disclosure are described above with reference to the drawings, the description is not a limitation on the scope of protection of the present disclosure, and those skilled in the art should understand that various modifications or changes made on the basis of the technical solutions of the present disclosure without creative labor are still within the scope of protection of the present disclosure.

Claims

1. A method for determining and regulating road congestion based on traffic flow and vehicle speed, characterized by, Comprise: Obtain the traffic flow, vehicle average speed of the current section, and historical traffic flow, vehicle average speed; Based on the historical traffic flow and vehicle average speed information, the mixed density network is used to model the conditional probability distribution of the flow-speed point cloud, and the traffic flow-speed relationship curve of the current section is obtained; Based on the traffic flow-speed curve, the maximum traffic volume of the current section and the congestion time period of the current section are determined; Introducing traffic congestion charges, taking the minimum total travel cost of users as the optimization objective, taking the historical traffic flow and vehicle average speed as the constraint condition, constructing a bottleneck mathematical model for traffic regulation, introducing a reinforcement learning method to solve the bottleneck mathematical model, and using the optimal solution for the corresponding traffic control strategy to give users equivalent travel cost, and realize the corresponding road traffic regulation goal; Specifically: The maximum passing capacity of the node per unit time is s vehicles, when the arrival rate of commuters at the bottleneck exceeds s, queuing phenomenon will occur on the section, and the change rate of the queue length at the bottleneck at time t can be expressed as: （2） where: is the queue length at the bottleneck at time t; is the inflow rate of commuters at the bottleneck at time t; is the capacity of the bottleneck per unit time. After the introduction of congestion pricing, the total cost of a commuter's trip consists of three parts, which are the total travel time cost, the early or late arrival penalty, and the congestion pricing; The total cost of a commuter who departs at time t can be expressed as: （3） wherein: is the time value coefficient; is the early arrival penalty coefficient; is the late arrival penalty coefficient; is the travel time of the commuter from the residence to the workplace; is the start of work; is the earliest departure time of the traveler; is the latest departure time of the traveler; is the departure time for the traveler to arrive at the workplace on time; is the cumulative cost at time t; is the cumulative cost at time t; is the variable toll cost that the traveler should bear if he departs at time t; is the variable toll cost that the traveler should bear if he departs at time t; represents the queue time of the commuter at the bottleneck.

2. The traffic flow and vehicle speed based road congestion determination and regulation method according to claim 1, wherein, Obtain the road traffic data at the set collection frequency, and convert it into hourly traffic flow and average speed of all vehicles collected in the current period; Integrate the historical traffic data obtained, aggregate the historical traffic data corresponding to each week, month and specific holiday together, and calculate the historical average traffic flow and average speed.

3. The traffic flow and vehicle speed based road congestion determination and regulation method according to claim 1, wherein, Based on the historical average traffic flow and average speed, the mixed density network is used to model the conditional probability distribution of the flow-speed point cloud, the historical average traffic flow is taken as the input feature of the mixed density network, and the vehicle average speed is taken as the output variable. The mixed parameters of multiple Gaussian distributions are output by using a neural network, the model is trained by using the maximum likelihood method, the corresponding speed distribution is generated, and a multimodal traffic flow-speed relationship curve is drawn.

4. The traffic flow and vehicle speed based road congestion determination and regulation method according to claim 1, wherein, Based on the maximum passing capacity of the current section and the traffic flow data of each time period determined based on the multimodal traffic flow-speed relationship curve, the change of road service level in the set time of each week, month and specific holiday is analyzed, and the time period with service level below the set level for more than a set time period is selected. The time period is identified as the congestion period of the current section.

5. A traffic flow and vehicle speed based road congestion determination and regulation system characterized in that, Comprise: The data acquisition module is used for obtaining the traffic flow, vehicle average speed of the current section, and historical traffic flow, vehicle average speed; The curve fitting module is used for modeling the conditional probability distribution of the flow-speed point cloud based on the historical traffic flow and vehicle average speed information by using the mixed density network, and obtaining the traffic flow-speed relationship curve of the current section; The judgment module is used for determining the maximum traffic volume of the current section and the congestion time period of the current section based on the traffic flow-speed curve; The regulation module is used for introducing traffic congestion charges, taking the minimum total travel cost of users as the optimization objective, taking the historical traffic flow and vehicle average speed as the constraint condition, constructing a bottleneck mathematical model for traffic regulation, introducing a reinforcement learning method to solve the bottleneck mathematical model, and using the optimal solution for the corresponding traffic control strategy to give users equivalent travel cost, and realize the corresponding road traffic regulation goal; Specifically: The maximum traffic capacity of the node per unit time is s vehicles, and when the arrival rate of commuters at the bottleneck exceeds s, queuing occurs on the road segment, and the rate of change of the queue length at the bottleneck at time t can be expressed as: （2） where: is the queue length at the bottleneck at time t; is the queue length at the bottleneck at time t; is the rate at which commuters enter the bottleneck at time t; is the rate at which commuters enter the bottleneck at time t; is the capacity of the bottleneck per unit of time. After the introduction of congestion pricing, the total cost of a commuter's trip consists of three parts, which are the total travel time cost, the early or late arrival penalty, and the congestion pricing; The total cost of a commuter who departs at time t can be expressed as: （3） In the formula: This is the time value coefficient; Penalty coefficient for arriving at work early; Penalty coefficient for being late for work; For commuters, this refers to travel time from their place of residence to their workplace; The start of the workday; The earliest departure time for travelers; The latest departure time for travelers; Departure time to arrive at the workplace on time; for The cumulative cost at each moment; For travelers The variable charges that should be borne for departure at any time; This indicates the queuing time for commuters at bottlenecks.

6. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to realize the traffic and speed based road congestion determination and adjustment method of any one of claims 1-4.

7. A non-transitory computer-readable storage medium, comprising: The non-transitory computer readable storage medium is used to store computer instructions, and the computer instructions are executed by the processor to realize the traffic and speed based road congestion determination and adjustment method of any one of claims 1-4.

8. An electronic device, comprising: Comprise: A processor, a memory and a computer program; wherein the processor is connected with the memory, and the computer program is stored in the memory; when the electronic device is running, the processor executes the computer program stored in the memory, so that the electronic device executes the traffic and speed based road congestion determination and adjustment method of any one of claims 1-4.

Images