Oversaturation road congestion treatment regulation and control method and system

Abstract

The invention relates to the technical field of traffic road regulation and control, and discloses an over-saturation road congestion governance regulation and control method, which comprises the following steps: acquiring road traffic data, performing congestion analysis on the acquired road traffic data, and identifying a congested road section, the traffic data comprising traffic flow, vehicle speed, position and time information; in combination with collected traffic data and a recognized congested road section, an intelligent signal control algorithm is adopted to optimize signal lamps close to intersections of the congested road section, and the signal duration and phase are dynamically adjusted to realize rapid defibering of the congested road section; road network information and congestion road section intersection signal lamp control strategies are combined, other signal lamp control strategies of a road network are dynamically regulated and controlled through cascade analysis, road section vehicles of the whole network are dynamically regulated and controlled, congestion of the whole network is avoided, and road section passing efficiency is improved; and performing dynamic regulation and control according to the calculated whole-network signal lamp control strategy, thereby realizing over-saturation road congestion regulation and control.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic road regulation, and in particular to a method and system for managing and regulating supersaturated road congestion. Background Art

[0002] The acceleration of urbanization and the rapid population growth have led to increasing urban traffic pressure, especially during peak hours on weekdays, when road traffic often presents serious congestion. Supersaturated road congestion not only affects people's travel efficiency, but also leads to an increase in traffic accident rates, increased environmental pollution and reduced economic benefits. Therefore, how to effectively manage supersaturated road congestion has become one of the focuses of traffic management departments. In response to this problem, the present invention proposes an intelligent control method for supersaturated road congestion, which comprehensively considers multiple factors, including road planning, traffic signal control, public transportation priority and other aspects, to improve the control effect of road congestion management. Summary of the invention

[0003] In view of this, the present invention provides a method for managing and controlling congestion on super-saturated roads, the purpose of which is to: 1) accurately identify congested sections by collecting road traffic data, and at the same time, optimize the traffic lights at intersections near congested sections by using an intelligent signal control algorithm, dynamically adjust the signal duration and phase, and quickly relieve congested sections, so as to more accurately respond to real-time traffic conditions and improve the traffic efficiency of sections; 2) combine road network information and traffic light control strategies at intersections of congested sections, dynamically control other traffic light control strategies of the road network through cascade analysis, and dynamically control vehicles on sections of the entire network. Dynamic control from a global perspective can avoid the overall incoordination caused by local optimization, avoid congestion on the entire network, and improve the overall traffic efficiency of sections; 3) control intersection traffic lights through SAC that maximizes the policy entropy, improve the model training efficiency, and achieve rapid road control.

[0004] To achieve the above-mentioned purpose, the present invention provides a method for managing and controlling supersaturated road congestion, comprising the following steps:

[0005] S1: collecting road traffic data, and performing congestion analysis on the collected road traffic data to identify congested road sections, wherein the traffic data includes traffic flow, vehicle speed, location and time information;

[0006] S2: Combined with the collected traffic data and the identified congested sections, the intelligent signal control algorithm is used to optimize the traffic lights at the intersections near the congested sections, dynamically adjust the signal duration and phase, and realize the rapid relief of congested sections;

[0007] S3: Combine the road network information and the traffic light control strategy of the intersection of the congested road section, dynamically adjust the control strategy of other traffic lights in the road network through cascade analysis, and dynamically adjust the vehicles on the road section of the whole network to avoid congestion in the whole network and improve the traffic efficiency of the road section;

[0008] S4: Dynamically adjust the traffic light control strategy of the entire network according to the calculated strategy to achieve congestion control on super-saturated roads.

[0009] As a further improvement method of the present invention:

[0010] Optionally, collecting road traffic data in step S1, and performing congestion analysis on the collected road traffic data to identify congested road sections include:

[0011] S11: Use navigation and positioning equipment and vehicle-mounted sensors to collect real-time road traffic data, including vehicle quantity, speed, location and time information;

[0012] S12: Clean and process the collected raw data, remove outliers and noise, and standardize the data in time and space to ensure the consistency and comparability of the data;

[0013] S13: Calculate a congestion index as a basis for identifying congested road sections, wherein the congestion index includes road vehicle density and road average vehicle speed, wherein the road vehicle density calculation formula is:

[0014]

[0015] in:

[0016] N represents the number of vehicles passing through the road segment;

[0017] L represents the length of the road segment to be analyzed;

[0018] The formula for calculating the average road speed is:

[0019]

[0020] in:

[0021] N represents the number of vehicles on the road segment;

[0022] V i represents the speed of the i-th vehicle;

[0023] S14: Based on the calculation result of the congestion index, if the road vehicle density is higher than a specified threshold and the road average vehicle speed is lower than a specified threshold, the current road section is identified as a congested section.

[0024] Optionally, in step S2, the collected traffic data and the identified congested road sections are combined to optimize the traffic lights at intersections near the congested road sections using an intelligent signal control algorithm to dynamically adjust the signal duration and phase, including:

[0025] S21: Constructing a congested road section coordinated control optimization objective function based on the collected traffic data and the identified congested road section. The objective function aims to minimize the total amount of traffic delays in the congested road section. The calculation formula is:

[0026]

[0027] in:

[0028] J represents the objective function;

[0029] M represents the number of traffic lights at the nearest intersection of the congested road section;

[0030] D i represents the average traffic delay time of the i-th intersection;

[0031] C i represents the number of vehicles passing through the i-th intersection;

[0032] The average delay time D of vehicles at the i-th intersection i It is calculated by the waiting time model based on queuing theory, and the calculation formula is:

[0033]

[0034] in:

[0035] L i represents the total number of vehicles near the congested section of the i-th intersection;

[0036] λ i represents the average vehicle arrival rate at the i-th intersection.

[0037] S22: Optimizing and solving the constructed congested road section coordinated control optimization objective function to obtain the optimal control duration and phase of the adjacent intersection signal lights of the congested road section, wherein the improved grey wolf algorithm is an implementation method of the optimization solution;

[0038] S23: Control the traffic lights at the intersections adjacent to the congested road section according to the solved optimal control duration and phase of the intersection traffic lights, so as to quickly relieve the congested road section.

[0039] Optionally, in step S22, the constructed congested road section collaborative control optimization objective function is optimized to obtain the optimal control duration and phase of the adjacent intersection signal lights of the congested road section, including:

[0040] S221: Randomly initialize a preset number of gray wolf individuals and parameters, each gray wolf individual represents a solution to the optimization objective function of the coordinated regulation of congested road sections, and the parameters include the population size and the maximum number of iterations;

[0041] S222: Calculate the fitness value of each individual gray wolf, that is, the objective function value;

[0042] S223: According to the fitness values ​​of the gray wolf individuals, the positions of the three gray wolves Alpha, Beta and Delta are updated, which represent the individual with the highest fitness, the individual with the second highest fitness and the individual with the third highest fitness in the population respectively;

[0043] S224: According to the positions of Alpha, Beta and Delta gray wolves, update the positions of other gray wolves using the social behavior rules between gray wolves. The calculation formula is:

[0044] X new =X old -A×P

[0045] in:

[0046] X new Indicates the updated position;

[0047] X old Indicates the original position;

[0048] A represents a random number in the range [0,2];

[0049] P represents the difference between the position of the Alpha, Beta or Delta gray wolf and the current position, and the calculation formula is:

[0050] P=|C×X * -X|

[0051] in:

[0052] C represents a random coefficient, with a value range of [0,1], which is used to control the step length of the individual gray wolf's movement;

[0053] X * represents the target position, and its value range is the position of the Alpha, Beta or Delta gray wolf, which is determined by random sampling;

[0054] X indicates the current position of the gray wolf;

[0055] S225: Calculate the fitness value of the updated gray wolf individual.

[0056] S226: Determine whether the convergence condition is met, if not, return to step S223 to continue iteration, otherwise proceed to step S227, the convergence condition being the maximum number of iterations;

[0057] S227: Output the optimal solution after convergence as the optimal control duration and phase of the intersection signal lights near the congested road section.

[0058] Optionally, in step S3, dynamically regulating other signal light control strategies of the road network through cascade analysis to dynamically regulate vehicles on the entire network section includes:

[0059] S31: establishing a road network topology structure in combination with the road network information, wherein the road network topology structure includes intersections, road segments, and connection relationships between them, and constructing a directed graph by taking each intersection as a node and the road segment as an edge;

[0060] S32: Calculate the traffic flow impact range of each intersection, and calculate the impact of each intersection on its adjacent intersections. The calculation formula is:

[0061]

[0062] Among them: Impact ij It indicates the influence degree of intersection i on intersection j;

[0063] F i represents the traffic flow of the road section near intersection i;

[0064] d ij represents the distance from intersection i to intersection j;

[0065] C j represents the road capacity of intersection j;

[0066] S33: sorting the calculated influence of the adjacent intersections of the congested road section on the remaining intersections in reverse order, and dynamically regulating the traffic lights of the remaining intersections in reverse order, wherein deep reinforcement learning is an implementation method of the dynamic regulation.

[0067] Optionally, in step S33, dynamically regulating the remaining intersection lights in reverse order includes:

[0068] S331: Use a deep neural network to establish a traffic light control model, the model uses the road traffic data of the intersection vehicle adjacent section as input, uses the traffic light control strategy as output, and uses a multi-objective evaluation function as a reward function. The reward function includes a minimum vehicle delay target and a smooth traffic flow target. The minimum delay target calculation formula is:

[0069] r delay = -β·D

[0070] in:

[0071] β represents the penalty coefficient, which controls the severity of the delay;

[0072] D represents the average vehicle delay time at the intersection;

[0073] The calculation formula for smooth traffic flow target is:

[0074] r smooth =γ·smoothness

[0075] in:

[0076] γ represents the reward coefficient, which controls the intensity of the reward for smooth traffic flow;

[0077] Smoothness is an indicator of the smoothness of traffic flow through the intersection, which is calculated by the average of the average speed of the adjacent road sections;

[0078] S332: Optimize and solve the constructed traffic light control model to obtain the optimal model parameters, and instantiate the model according to the optimal model parameters to dynamically control the traffic lights at other intersections, wherein the improved SAC is the implementation method of the optimization solution.

[0079] Optionally, optimizing and solving the constructed traffic light control model to obtain optimal model parameters includes:

[0080] The SAC based on maximizing policy entropy is the main implementation method of the improved SAC, and the specific process includes:

[0081] A1: Randomly initialize the policy network and target network parameters;

[0082] A2: Use the target network to calculate the target value of the road traffic data of the intersection vehicle adjacent section, and update the target network parameters;

[0083] A3: Based on the calculated target value, the policy network parameters are updated using policy gradients based on the maximum policy entropy constraint, where the maximum policy entropy constraint calculation formula is:

[0084]

[0085] Among them, π(a|s) represents the probability that the strategy network takes the signal light control action a under the road traffic data state s of the intersection vehicle adjacent section; a~π(·|s) represents the sampling of the signal light control action according to the strategy network under the road traffic data state s of the intersection vehicle adjacent section;

[0086] A4: Continue to iterate steps A2 and A3 until the maximum number of iterations is reached.

[0087] In order to solve the above problems, the present invention provides a supersaturated road congestion management and control system, the system comprising:

[0088] The data collection module is used to collect road traffic data, and conduct congestion analysis on the collected road traffic data to identify congested road sections. The traffic data includes traffic volume, speed, location and time information;

[0089] The traffic light optimization module is used to combine the collected traffic data and the identified congested sections, and use the intelligent signal control algorithm to optimize the traffic lights at the intersections near the congested sections, dynamically adjust the signal duration and phase, and realize the rapid relief of congested sections;

[0090] The road congestion control module is used to combine road network information and traffic light control strategies at intersections on congested sections, dynamically control other traffic light control strategies on the road network through cascade analysis, dynamically control vehicles on sections of the entire network, and dynamically control vehicles according to the calculated traffic light control strategies for the entire network to achieve congestion control on super-saturated roads.

[0091] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising:

[0092] A memory storing at least one instruction;

[0093] Communication interface, enabling electronic equipment to communicate; and

[0094] The processor executes the instructions stored in the memory to implement the above-mentioned super-saturated road congestion management and control method.

[0095] In order to solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is executed by a processor in an electronic device to implement the above-mentioned super-saturated road congestion management and control method.

[0096] Compared with the prior art, the present invention proposes a method for managing and controlling supersaturated road congestion, which has the following advantages:

[0097] First, this solution collects road traffic data to accurately identify congested sections. At the same time, it uses intelligent signal control algorithms to optimize traffic lights at intersections near congested sections, dynamically adjust signal duration and phase, and quickly relieve congested sections. It can respond to real-time traffic conditions more accurately and improve road traffic efficiency.

[0098] At the same time, this scheme proposes a traffic light control strategy for intersections that combines road network information and congested sections. This strategy dynamically controls other traffic lights in the road network through cascade analysis, and dynamically controls vehicles on the entire network section. Dynamic control from a global perspective can avoid the overall incoordination caused by local optimization, avoid congestion in the entire network, and improve the overall traffic efficiency of the road section. It also controls intersection traffic lights through SAC that maximizes the strategy entropy, which improves the efficiency of model training and can achieve rapid road control. BRIEF DESCRIPTION OF THE DRAWINGS

[0099] Figure 1 A schematic diagram of a flow chart of a method for managing and regulating supersaturated road congestion provided by an embodiment of the present invention;

[0100] Figure 2 A functional module diagram of a supersaturated road congestion management and control system provided by an embodiment of the present invention;

[0101] Figure 3 A schematic diagram of the structure of an electronic device for implementing a method for managing and regulating super-saturated road congestion provided in one embodiment of the present invention.

[0102] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0103] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0104] The embodiment of the present application provides a method for managing and regulating supersaturated road congestion. The execution subject of the supersaturated road congestion management and regulation method includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the supersaturated road congestion management and regulation method can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0105] Embodiment 1:

[0106] S1: Collecting road traffic data, and performing congestion analysis on the collected road traffic data to identify congested road sections, wherein the traffic data includes vehicle flow, vehicle speed, location and time information.

[0107] In step S1, collecting road traffic data, and performing congestion analysis on the collected road traffic data to identify congested road sections include:

[0108] S11: Use navigation and positioning equipment and vehicle-mounted sensors to collect real-time road traffic data, including vehicle quantity, speed, location and time information;

[0109] S12: Clean and process the collected raw data, remove outliers and noise, and standardize the data in time and space to ensure the consistency and comparability of the data;

[0110] S13: Calculate a congestion index as a basis for identifying congested road sections, wherein the congestion index includes road vehicle density and road average vehicle speed, wherein the road vehicle density calculation formula is:

[0111]

[0112] in:

[0113] N represents the number of vehicles passing through the road segment;

[0114] L represents the length of the road segment to be analyzed;

[0115] The formula for calculating the average road speed is:

[0116]

[0117] in:

[0118] N represents the number of vehicles on the road segment;

[0119] V i represents the speed of the i-th vehicle;

[0120] S14: Based on the calculation result of the congestion index, if the road vehicle density is higher than a specified threshold and the road average vehicle speed is lower than a specified threshold, the current road section is identified as a congested section.

[0121] S2: Based on the collected traffic data and identified congested sections, an intelligent signal control algorithm is used to optimize the traffic lights at intersections near the congested sections, dynamically adjust the signal duration and phase, and achieve rapid relief of congested sections.

[0122] In step S2, based on the collected traffic data and the identified congested road sections, an intelligent signal control algorithm is used to optimize the traffic lights at intersections near the congested road sections, and dynamically adjust the signal duration and phase, including:

[0123] S21: Constructing a congested road section coordinated control optimization objective function based on the collected traffic data and the identified congested road section. The objective function aims to minimize the total amount of traffic delays in the congested road section. The calculation formula is:

[0124]

[0125] in:

[0126] J represents the objective function;

[0127] M represents the number of traffic lights at the nearest intersection of the congested road section;

[0128] D i represents the average traffic delay time of the i-th intersection;

[0129] C i represents the number of vehicles passing through the i-th intersection;

[0130] The average delay time D of vehicles at the i-th intersection i It is calculated by the waiting time model based on queuing theory, and the calculation formula is:

[0131]

[0132] in:

[0133] L i represents the total number of vehicles near the congested section of the i-th intersection;

[0134] λ i represents the average vehicle arrival rate at the i-th intersection.

[0135] S22: Optimizing and solving the constructed congested road section coordinated control optimization objective function to obtain the optimal control duration and phase of the adjacent intersection signal lights of the congested road section, wherein the improved grey wolf algorithm is an implementation method of the optimization solution;

[0136] S23: Control the traffic lights at the intersections adjacent to the congested road section according to the solved optimal control duration and phase of the intersection traffic lights, so as to quickly relieve the congested road section.

[0137] In the step S22, the constructed congested road section coordinated control optimization objective function is optimized to obtain the optimal control duration and phase of the adjacent intersection signal lights of the congested road section, including:

[0138] S221: Randomly initialize a preset number of gray wolf individuals and parameters, each gray wolf individual represents a solution to the optimization objective function of the coordinated regulation of congested road sections, and the parameters include the population size and the maximum number of iterations;

[0139] S222: Calculate the fitness value of each individual gray wolf, that is, the objective function value;

[0140] S223: According to the fitness values ​​of the gray wolf individuals, the positions of the three gray wolves Alpha, Beta and Delta are updated, which represent the individual with the highest fitness, the individual with the second highest fitness and the individual with the third highest fitness in the population respectively;

[0141] S224: According to the positions of Alpha, Beta and Delta gray wolves, update the positions of other gray wolves using the social behavior rules between gray wolves. The calculation formula is:

[0142] X new =X old -A×P

[0143] in:

[0144] X new Indicates the updated position;

[0145] X old Indicates the original position;

[0146] A represents a random number in the range [0,2];

[0147] P represents the difference between the position of the Alpha, Beta or Delta gray wolf and the current position, and the calculation formula is:

[0148] P=|C×X * -X|

[0149] in:

[0150] C represents a random coefficient, with a value range of [0,1], which is used to control the step length of the individual gray wolf's movement;

[0151] X * represents the target position, and its value range is the position of the Alpha, Beta or Delta gray wolf, which is determined by random sampling;

[0152] X indicates the current position of the gray wolf;

[0153] S225: Calculate the fitness value of the updated gray wolf individual.

[0154] S226: Determine whether the convergence condition is met, if not, return to step S223 to continue iteration, otherwise proceed to step S227, the convergence condition being the maximum number of iterations;

[0155] S227: Output the optimal solution after convergence as the optimal control duration and phase of the intersection signal lights near the congested road section.

[0156] S3: Combine the road network information and the traffic light control strategy at the intersection of congested sections, dynamically adjust the control strategy of other traffic lights in the road network through cascade analysis, and dynamically adjust the vehicles on the entire network section to avoid congestion in the entire network and improve the traffic efficiency of the section.

[0157] In the step S3, other signal light control strategies of the road network are dynamically regulated through cascade analysis to dynamically regulate vehicles on the entire network, including:

[0158] S31: establishing a road network topology structure in combination with the road network information, wherein the road network topology structure includes intersections, road segments, and connection relationships between them, and constructing a directed graph by taking each intersection as a node and the road segment as an edge;

[0159] S32: Calculate the traffic flow impact range of each intersection, and calculate the impact of each intersection on its adjacent intersections. The calculation formula is:

[0160]

[0161] Among them: Impact ij It indicates the influence degree of intersection i on intersection j;

[0162] F i represents the traffic flow of the road section near intersection i;

[0163] d ij represents the distance from intersection i to intersection j;

[0164] C j represents the road capacity of intersection j;

[0165] S33: sorting the calculated influence of the adjacent intersections of the congested road section on the remaining intersections in reverse order, and dynamically regulating the traffic lights of the remaining intersections in reverse order, wherein deep reinforcement learning is an implementation method of the dynamic regulation.

[0166] In the step S33, the remaining intersection signal lights are dynamically controlled in reverse order, including:

[0167] S331: Use a deep neural network to establish a traffic light control model, the model uses the road traffic data of the intersection vehicle adjacent section as input, uses the traffic light control strategy as output, and uses a multi-objective evaluation function as a reward function. The reward function includes a minimum vehicle delay target and a smooth traffic flow target. The minimum delay target calculation formula is:

[0168] r delay = -β·D

[0169] in:

[0170] β represents the penalty coefficient, which controls the severity of the delay;

[0171] D represents the average vehicle delay time at the intersection;

[0172] The calculation formula for smooth traffic flow target is:

[0173] r smooth =γ·smoothness

[0174] in:

[0175] γ represents the reward coefficient, which controls the intensity of the reward for smooth traffic flow;

[0176] Smoothness is an indicator of the smoothness of traffic flow through the intersection, which is calculated by the average of the average speed of the adjacent road sections;

[0177] S332: Optimize and solve the constructed traffic light control model to obtain the optimal model parameters, and instantiate the model according to the optimal model parameters to dynamically control the traffic lights at other intersections, wherein the improved SAC is the implementation method of the optimization solution.

[0178] The step of optimizing and solving the constructed traffic light control model to obtain the optimal model parameters includes:

[0179] The SAC based on maximizing policy entropy is the main implementation method of the improved SAC, and the specific process includes:

[0180] A1: Randomly initialize the policy network and target network parameters;

[0181] A2: Use the target network to calculate the target value of the road traffic data of the intersection vehicle adjacent section, and update the target network parameters;

[0182] A3: Based on the calculated target value, the policy network parameters are updated using policy gradients based on the maximum policy entropy constraint, where the maximum policy entropy constraint calculation formula is:

[0183]

[0184] Among them, π(a|s) represents the probability that the strategy network takes the signal light control action a under the road traffic data state s of the intersection vehicle adjacent section; a~π(·|s) represents the sampling of the signal light control action according to the strategy network under the road traffic data state s of the intersection vehicle adjacent section;

[0185] A4: Continue to iterate steps A2 and A3 until the maximum number of iterations is reached.

[0186] Dynamically regulate traffic lights according to the calculated control strategy of the entire network to achieve congestion control on super-saturated roads

[0187] Embodiment 2:

[0188] like Figure 2 As shown, it is a functional module diagram of a supersaturated road congestion management and control system provided by an embodiment of the present invention, which can implement the supersaturated road congestion management and control method in Example 1.

[0189] The supersaturated road congestion management and control system 100 of the present invention can be installed in an electronic device. According to the functions to be implemented, the supersaturated road congestion management and control system can include a data acquisition module 101, a signal light optimization module 102 and a road congestion control module 103. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0190] The data collection module 101 is used to collect road traffic data, and perform congestion analysis on the collected road traffic data to identify congested road sections. The traffic data includes traffic volume, speed, location and time information;

[0191] The signal light optimization module 102 is used to optimize the signal lights at intersections near the congested road sections by combining the collected traffic data and the identified congested road sections, and dynamically adjust the signal duration and phase to achieve rapid relief of the congested road sections;

[0192] The road congestion control module 103 is used to combine the road network information and the traffic light control strategy at the intersection of the congested road section, dynamically control other traffic light control strategies of the road network through cascade analysis, dynamically control the vehicles on the entire network section, and dynamically control according to the calculated traffic light control strategy of the entire network to achieve super-saturated road congestion control.

[0193] In detail, each module in the supersaturated road congestion control and regulation system 100 in the embodiment of the present invention is used in the same manner as above. Figure 1 The technical means are the same as the super-saturated road congestion management and control method described in, and can produce the same technical effects, so I will not go into details here.

[0194] Embodiment 3:

[0195] like Figure 3 , is a schematic diagram of the structure of an electronic device for implementing a method for managing and regulating super-saturated road congestion provided by an embodiment of the present invention.

[0196] The electronic device 1 may include a processor 10 , a memory 11 , a communication interface 13 and a bus, and may also include a computer program stored in the memory 11 and executable on the processor 10 , such as a program 12 .

[0197] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. The memory 11 may be an internal storage unit of the electronic device 1 in some embodiments, such as a mobile hard disk of the electronic device 1. The memory 11 may also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Further, the memory 11 may also include both an internal storage unit of the electronic device 1 and an external storage device. The memory 11 may be used not only to store application software and various types of data installed in the electronic device 1, such as the code of the program 12, etc., but also to temporarily store data that has been output or is to be output.

[0198] The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips, etc. The processor 10 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules stored in the memory 11 (such as the program 12 for implementing supersaturated road congestion management and control), and calls data stored in the memory 11 to execute various functions of the electronic device 1 and process data.

[0199] The communication interface 13 may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices, and to achieve connection and communication between internal components of the electronic device.

[0200] The bus may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0201] Figure 3 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0202] For example, although not shown, the electronic device 1 may also include a power source (such as a battery) for supplying power to each component. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include any components such as one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, etc. The electronic device 1 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0203] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 1 and to display a visual user interface.

[0204] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for controlling and regulating supersaturated road congestion, characterized in that: The method comprises: S1: collecting road traffic data, and performing congestion analysis on the collected road traffic data to identify congested road sections, wherein the traffic data includes traffic flow, vehicle speed, location and time information; S2: Combined with the collected traffic data and the identified congested sections, the intelligent signal control algorithm is used to optimize the traffic lights at the intersections near the congested sections, dynamically adjust the signal duration and phase, and realize the rapid relief of congested sections; S3: Combine the road network information and the traffic light control strategy of the intersection of the congested road section, dynamically adjust the control strategy of other traffic lights in the road network through cascade analysis, and dynamically adjust the vehicles on the road section of the whole network to avoid congestion in the whole network and improve the traffic efficiency of the road section; S4: Dynamically adjust the traffic light control strategy of the entire network according to the calculated strategy to achieve congestion control on super-saturated roads.

2. A method for controlling and regulating supersaturated road congestion according to claim 1, characterized in that: In step S1, collecting road traffic data, and performing congestion analysis on the collected road traffic data to identify congested road sections include: S11: Use navigation and positioning equipment and vehicle-mounted sensors to collect real-time road traffic data, including vehicle quantity, speed, location and time information; S12: Clean and process the collected raw data, remove outliers and noise, and standardize the data in time and space to ensure the consistency and comparability of the data; S13: Calculate a congestion index as a basis for identifying congested road sections, wherein the congestion index includes road vehicle density and road average vehicle speed, wherein the road vehicle density calculation formula is: in: N represents the number of vehicles passing through the road segment; L represents the length of the road segment to be analyzed; The formula for calculating the average road speed is: in: N represents the number of vehicles on the road segment; V i represents the speed of the i-th vehicle; S14: Based on the calculation result of the congestion index, if the road vehicle density is higher than a specified threshold and the road average vehicle speed is lower than a specified threshold, the current road section is identified as a congested section.

3. A method for controlling and regulating supersaturated road congestion according to claim 1, characterized in that: In step S2, based on the collected traffic data and the identified congested road sections, an intelligent signal control algorithm is used to optimize the traffic lights at intersections near the congested road sections, and dynamically adjust the signal duration and phase, including: S21: Constructing a congested road section coordinated control optimization objective function based on the collected traffic data and the identified congested road section. The objective function aims to minimize the total amount of traffic delays in the congested road section. The calculation formula is: in: J represents the objective function; M represents the number of traffic lights at the nearest intersection of the congested road section; D i represents the average traffic delay time of the i-th intersection; C i represents the number of vehicles passing through the i-th intersection; The average delay time D of vehicles at the i-th intersection i It is calculated by the waiting time model based on queuing theory, and the calculation formula is: in: L i represents the total number of vehicles near the congested section at the i-th intersection; λ i represents the average vehicle arrival rate at the i-th intersection. S22: Optimizing and solving the constructed congested road section coordinated control optimization objective function to obtain the optimal control duration and phase of the adjacent intersection signal lights of the congested road section, wherein the improved grey wolf algorithm is an implementation method of the optimization solution; S23: Control the traffic lights at the intersections adjacent to the congested road section according to the solved optimal control duration and phase of the intersection traffic lights, so as to quickly relieve the congested road section.

4. A method for controlling and regulating supersaturated road congestion according to claim 3, characterized in that: In the step S22, the constructed congested road section coordinated control optimization objective function is optimized to obtain the optimal control duration and phase of the adjacent intersection signal lights of the congested road section, including: S221: Randomly initialize a preset number of gray wolf individuals and parameters, each gray wolf individual represents a solution to the optimization objective function of the coordinated regulation of congested road sections, and the parameters include the population size and the maximum number of iterations; S222: Calculate the fitness value of each individual gray wolf, that is, the objective function value; S223: According to the fitness values ​​of the gray wolf individuals, the positions of the three gray wolves Alpha, Beta and Delta are updated, which represent the individual with the highest fitness, the individual with the second highest fitness and the individual with the third highest fitness in the population respectively; S224: According to the positions of Alpha, Beta and Delta gray wolves, update the positions of other gray wolves using the social behavior rules between gray wolves. The calculation formula is: X new =X old -A×P in: X new Indicates the updated position; X old Indicates the original position; A represents a random number in the range [0,2]; P represents the difference between the position of the Alpha, Beta or Delta gray wolf and the current position, and the calculation formula is: P=|C×X * -X| in: C represents a random coefficient, with a value range of [0,1], which is used to control the step length of the individual gray wolf's movement; X * represents the target position, and its value range is the position of the Alpha, Beta or Delta gray wolf, which is determined by random sampling; X indicates the current gray wolf position; S225: Calculate the fitness value of the updated gray wolf individual. S226: Determine whether the convergence condition is met, if not, return to step S223 to continue iteration, otherwise proceed to step S227, the convergence condition being the maximum number of iterations; S227: Output the optimal solution after convergence as the optimal control duration and phase of the intersection signal lights near the congested road section.

5. A method for controlling and regulating supersaturated road congestion according to claim 1, characterized in that: In the step S3, other signal light control strategies of the road network are dynamically regulated through cascade analysis to dynamically regulate vehicles on the entire network, including: S31: establishing a road network topology structure in combination with the road network information, wherein the road network topology structure includes intersections, road segments, and connection relationships between them, and constructing a directed graph by taking each intersection as a node and the road segment as an edge; S32: Calculate the traffic flow impact range of each intersection, and calculate the impact of each intersection on its adjacent intersections. The calculation formula is: Among them: Impact ij It indicates the influence degree of intersection i on intersection j; F i represents the traffic flow of the road section near intersection i; d ij represents the distance from intersection i to intersection j; C j represents the road capacity of intersection j; S33: sorting the calculated influence of the adjacent intersections of the congested road section on the remaining intersections in reverse order, and dynamically regulating the traffic lights of the remaining intersections in reverse order, wherein deep reinforcement learning is an implementation method of the dynamic regulation.

6. A method for controlling and regulating supersaturated road congestion according to claim 5, characterized in that: In the step S33, the remaining intersection signal lights are dynamically controlled in reverse order, including: S331: Use a deep neural network to establish a traffic light control model, the model uses the road traffic data of the intersection vehicle adjacent section as input, uses the traffic light control strategy as output, and uses a multi-objective evaluation function as a reward function. The reward function includes a minimum vehicle delay target and a smooth traffic flow target. The minimum delay target calculation formula is: r delay ＝-β·D in: β represents the penalty coefficient, which controls the severity of the delay; D represents the average vehicle delay time at the intersection; The calculation formula for smooth traffic flow target is: r smooth =γ·smoothness in: γ represents the reward coefficient, which controls the intensity of the reward for smooth traffic flow; Smoothness is an indicator of the smoothness of traffic flow through the intersection, which is calculated by the average of the average speed of the adjacent road sections; S332: Optimize and solve the constructed traffic light control model to obtain the optimal model parameters, and instantiate the model according to the optimal model parameters to dynamically control the traffic lights at other intersections, wherein the improved SAC is the implementation method of the optimization solution.

7. A method for controlling and regulating supersaturated road congestion according to claim 6, characterized in that: The step of optimizing and solving the constructed traffic light control model to obtain the optimal model parameters includes: The SAC based on maximizing policy entropy is the main implementation method of the improved SAC, and the specific process includes: A1: Randomly initialize the policy network and target network parameters; A2: Use the target network to calculate the target value of the road traffic data of the intersection vehicle adjacent section, and update the target network parameters; A3: Based on the calculated target value, the policy network parameters are updated using policy gradients based on the maximum policy entropy constraint, where the maximum policy entropy constraint calculation formula is: Among them, π(a|s) represents the probability that the strategy network takes the signal light control action a under the road traffic data state s of the intersection vehicle adjacent section; a~π(·|s) represents the sampling of the signal light control action according to the strategy network under the road traffic data state s of the intersection vehicle adjacent section; A4: Continue to iterate steps A2 and A3 until the maximum number of iterations is reached.

8. A supersaturated road congestion management and control system, characterized in that: The system comprises: The data collection module is used to collect road traffic data, and conduct congestion analysis on the collected road traffic data to identify congested road sections. The traffic data includes traffic volume, speed, location and time information; The traffic light optimization module is used to combine the collected traffic data and the identified congested sections, and use the intelligent signal control algorithm to optimize the traffic lights at the intersections near the congested sections, dynamically adjust the signal duration and phase, and realize the rapid relief of congested sections; A road congestion control module is used to combine road network information and traffic light control strategies at intersections of congested sections, dynamically control other traffic light control strategies of the road network through cascade analysis, dynamically control vehicles on sections of the entire network, and dynamically control vehicles according to the calculated traffic light control strategies of the entire network to achieve super-saturated road congestion control, so as to realize a super-saturated road congestion management and control method as described in any one of claims 1-7.

Images