Intelligent traffic light coordination control method and system for traffic flow optimization

Abstract

The invention discloses an intelligent traffic light coordination control method and system for traffic flow optimization, and relates to the technical field of intelligent control. The method comprises the following steps: collecting traffic flow data of lanes in all directions in a target area in real time through heterogeneous sensor networks deployed at all intersections; identifying the traffic flow data to obtain tidal traffic flow features; performing dynamic intensity evaluation based on the tidal traffic flow characteristics to obtain a tidal direction intensity index; a multi-agent cooperative network is constructed, and a continuous intersection green light phase offset sequence is generated based on cooperative calculation of the multi-agent cooperative network; and when the tide direction intensity index is greater than a preset threshold value, inputting the continuous intersection green light phase offset sequence into a traffic signal lamp control system so as to start a tide green wave mode. The technical problems that in the prior art, traffic flow control is not flexible enough, and traffic lights cannot be intelligently adjusted according to the traffic flow condition are solved, and the technical effects of improving the road passing efficiency and reducing congestion are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control, and particularly to an intelligent traffic light co - control method and system for traffic flow optimization. Background Art

[0002] With the acceleration of urbanization, the urban traffic flow is constantly increasing. The traditional traffic signal control method seems inadequate in dealing with complex traffic flow patterns. Especially during peak hours, due to the uneven traffic flow, problems such as road congestion and unreasonable signal switching often occur, affecting traffic efficiency and increasing travel time and energy consumption. The traditional traffic light control system often switches signals based on fixed time intervals and cannot effectively respond to the dynamic changes in traffic flow, especially the tidal traffic phenomenon that occurs during morning and evening peak hours - that is, a large number of vehicles flow into the city center from the suburbs in the morning and flow in the opposite direction in the evening. This one - way peak traffic flow pattern not only exacerbates traffic congestion but also reduces the utilization efficiency of road resources, increasing commuting time and environmental pollution. Summary of the Invention

[0003] This application provides an intelligent traffic light co - control method and system for traffic flow optimization, which solves the technical problems in the prior art that the traffic flow control is not flexible enough and the traffic lights fail to make intelligent adjustments according to the traffic flow situation.

[0004] In the first aspect of this application, an intelligent traffic light co - control method for traffic flow optimization is provided. The method includes:

[0005] Real - time collecting the traffic flow data of each lane in each direction within the target area through a heterogeneous sensor network deployed at each intersection; identifying the traffic flow data to obtain tidal traffic flow characteristics, where the tidal traffic flow characteristics include the inbound traffic volume and outbound traffic volume, the degree of vehicle fleet aggregation, and the average vehicle speed of the vehicle fleet; performing dynamic intensity assessment based on the tidal traffic flow characteristics to obtain a tidal direction intensity index; constructing a multi - agent collaborative network, and collaboratively calculating and generating a sequence of green - light phase offsets for consecutive intersections based on the multi - agent collaborative network; when the tidal direction intensity index is greater than a preset threshold, inputting the sequence of green - light phase offsets for consecutive intersections into the traffic signal control system to activate the tidal green wave mode.

[0006] In the second aspect of this application, an intelligent traffic light co - control system for traffic flow optimization is provided. The system includes:

[0007] Data acquisition module: Real-time collect the traffic flow data of each lane in all directions within the target area through the heterogeneous sensor networks deployed at each intersection; Recognition module: Recognize the traffic flow data to obtain the characteristics of tidal traffic flow, where the characteristics of tidal traffic flow include the inbound traffic volume and outbound traffic volume, the degree of vehicle platoon aggregation, and the average vehicle speed of the platoon; Evaluation module: Conduct dynamic intensity evaluation based on the characteristics of tidal traffic flow to obtain the tidal direction intensity index; Calculation module: Construct a multi-agent collaborative network, and collaboratively calculate and generate a sequence of green light phase offsets for consecutive intersections based on the multi-agent collaborative network; Control module: When the tidal direction intensity index is greater than a preset threshold, input the sequence of green light phase offsets for consecutive intersections into the traffic signal control system to activate the tidal green wave mode.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] First, real-time collect the traffic flow data of each lane in all directions within the target area through the heterogeneous sensor networks deployed at each intersection. Next, recognize the traffic flow data to obtain the characteristics of tidal traffic flow, where the characteristics of tidal traffic flow include the inbound traffic volume and outbound traffic volume, the degree of vehicle platoon aggregation, and the average vehicle speed of the platoon. Further, conduct dynamic intensity evaluation based on the characteristics of tidal traffic flow to obtain the tidal direction intensity index. Then, construct a multi-agent collaborative network, and collaboratively calculate and generate a sequence of green light phase offsets for consecutive intersections based on the multi-agent collaborative network. Finally, when the tidal direction intensity index is greater than a preset threshold, input the sequence of green light phase offsets for consecutive intersections into the traffic signal control system to activate the tidal green wave mode. This solves the technical problems in the prior art that traffic flow control is not flexible enough and traffic signals cannot be intelligently adjusted according to the traffic flow situation, and achieves the technical effects of improving road traffic efficiency and reducing congestion. Description of the Drawings

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0011] Figure 1 It is a schematic flowchart of an intelligent traffic light cooperative control method for traffic flow optimization provided by an embodiment of this application;

[0012] Figure 2 It is a schematic structural diagram of an intelligent traffic light cooperative control system for traffic flow optimization provided by an embodiment of this application.

[0013] Description of the reference numerals: Data acquisition module 11, Recognition module 12, Evaluation module 13, Calculation module 14, Control module 15. Specific implementation manners

[0014] By providing an intelligent traffic light co - control method and system for traffic flow optimization, the present application solves the technical problems in the prior art that traffic flow control is not flexible enough and traffic lights cannot be intelligently adjusted according to the traffic flow situation.

[0015] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0016] It should be noted that the terms "include" and "have" are intended to cover non - exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units does not necessarily limit to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products, or devices.

[0017] Embodiment 1, as Figure 1 shown, the present application provides an intelligent traffic light co - control method for traffic flow optimization, wherein the method includes:

[0018] Real - time collection of traffic flow data of each lane in each direction within the target area through heterogeneous sensor networks deployed at each intersection.

[0019] By deploying heterogeneous sensor networks at each intersection within the target area, traffic flow data of each lane in each direction is collected in real - time. The heterogeneous sensor network is composed of various types of sensors, including but not limited to geomagnetic sensors, video surveillance devices, millimeter - wave radars, infrared sensors, etc. These sensors can monitor and collect traffic flow data from different dimensions in an all - round way. Specifically, the geomagnetic sensor senses the traffic flow by detecting the magnetic field change generated when a vehicle passes by, the video surveillance system obtains information such as traffic flow, vehicle speed, and vehicle queue density on the road in real - time through image recognition technology, the millimeter - wave radar can accurately measure the vehicle speed and work stably under bad weather conditions, and the infrared sensor is used to detect the presence and speed of vehicles, especially suitable for night or low - visibility environments. Through the collaborative work of these multiple sensors, the system can collect various traffic data, including traffic volume, vehicle speed, vehicle queue aggregation degree, traffic flow status, etc. in real - time on different road sections and lanes. These data provide accurate and real - time basic information for subsequent traffic flow analysis and signal light control, ensuring that the dynamic adjustment of traffic signal timing can reflect the current traffic conditions in real - time, thereby realizing more intelligent and efficient traffic flow optimization control.

[0020] Furthermore, traffic flow data of each lane in all directions within the target area is collected in real time through the heterogeneous sensor network deployed at each intersection. The method includes:

[0021] The heterogeneous sensor network includes geomagnetic detectors, video recognition units, and radar speed measurement devices; the geomagnetic detectors collect vehicle presence signals at a frequency of 10 Hz, the video recognition units extract license plate features at a frequency of 1 Hz, and the radar speed measurement devices obtain instantaneous vehicle speeds at a frequency of 5 Hz; the vehicle presence signals, the license plate features, and the instantaneous vehicle speeds are fused to generate traffic flow data.

[0022] Preferably, the heterogeneous sensor network is composed of multiple different types of sensors, mainly including geomagnetic detectors, video recognition units, and radar speed measurement devices. Each sensor collects data at different frequencies and in different ways to comprehensively and accurately obtain traffic flow information. Specifically, the geomagnetic detectors collect vehicle presence signals at a frequency of 10 Hz, that is, by detecting the magnetic field changes generated when vehicles pass under the road surface, to determine in real time whether a vehicle has passed through the lane; the video recognition units extract license plate features at a frequency of 1 Hz, and through high-definition cameras and image processing algorithms, conduct real-time video monitoring of all passing vehicles on the lane, identify license plate information, and track the driving trajectories of each vehicle; the radar speed measurement devices obtain instantaneous vehicle speeds at a frequency of 5 Hz, and accurately measure the real-time driving speed of each vehicle through radar technology. The vehicle presence signals, license plate features, instantaneous vehicle speeds, and other data collected by the above sensors will undergo data fusion processing to generate comprehensive traffic flow data. These data can comprehensively reflect the traffic conditions of each lane within the target area, including multi-dimensional information such as traffic volume, vehicle speed, vehicle type, and lane occupancy, thereby providing accurate basic data support for subsequent traffic flow analysis, signal light optimization control, and traffic flow management.

[0023] Identify the traffic flow data to obtain tidal traffic flow characteristics, where the tidal traffic flow characteristics include inbound traffic volume, outbound traffic volume, fleet aggregation degree, and fleet average speed.

[0024] The collected traffic flow data is further identified and analyzed to extract tidal traffic flow characteristics, specifically including key indicators such as inbound traffic volume, outbound traffic volume, fleet aggregation degree, and fleet average speed. The tidal traffic flow characteristics reflect the fluctuation laws of traffic flow at different times and in different directions, and can effectively reveal the dynamic changes of urban traffic.

[0025] The inbound traffic volume refers to the number of vehicles entering the urban area within a specific time period. This indicator usually increases significantly during the morning rush hour and can reflect the inflow pressure on the central urban area. Through the analysis of traffic flow data, the system can accurately identify the number of inbound vehicles and quantify the changes in this traffic volume.

[0026] The outbound traffic volume refers to the number of vehicles leaving the urban area within a certain period of time. Usually during the evening rush hour, the outbound traffic volume will increase. This indicator helps to understand the outflow trend of traffic flow and predict possible congestion or traffic bottlenecks. By identifying and extracting the data of the outbound traffic volume, the system can grasp the traffic conditions in the outbound direction in real time.

[0027] The vehicle platoon concentration reflects the density of vehicles on a certain road section or lane. When the traffic flow density is too high, the vehicle platoon concentration increases, which may lead to traffic congestion or slow driving. By real-time monitoring of the traffic flow density, the system can calculate the vehicle platoon concentration, evaluate the traffic load on a certain section of the road or lane, and predict potential congestion risks in advance.

[0028] The average speed of the vehicle platoon refers to the average value of the overall driving speed of vehicles within a certain period of time. A lower speed usually indicates that the traffic flow is not smooth, which may be caused by traffic congestion or traffic control. By real-time analysis of the speed data, the system can monitor the driving speed of the vehicle platoon, and timely detect and respond to low-speed driving or congestion phenomena.

[0029] Furthermore, the traffic flow data is identified to obtain the characteristics of the tidal traffic flow. The method includes:

[0030] The traffic flow data includes vehicle identification information, vehicle speed information, and vehicle queue information; based on the vehicle identification information, the number of vehicles passing through per unit time in each direction is counted to obtain the inbound traffic volume and the outbound traffic volume; based on the vehicle speed information, the average speed during a predetermined period is calculated to obtain the average speed of the vehicle platoon; based on the vehicle queue information, the number of vehicles within a unit distance is calculated to obtain the vehicle platoon concentration; the inbound traffic volume, the outbound traffic volume, the vehicle platoon concentration, and the average speed of the vehicle platoon are added to the characteristics of the tidal traffic flow.

[0031] Based on vehicle identification information, count the number of vehicles passing through in each direction per unit time. Through license plate recognition or other vehicle detection technologies, the system can accurately identify the passing situation of each vehicle, and calculate the traffic flow in each direction according to the timestamp information of the vehicle, so as to obtain the inbound traffic flow and outbound traffic flow, and then reveal the number of vehicles entering and leaving the city and their traffic flow fluctuations during different time periods, reflecting the typical tidal traffic phenomenon. Based on vehicle speed information, the system calculates the average vehicle speed within a predetermined time period. This information reflects the overall driving speed of the vehicle fleet. A lower vehicle speed may mean that the traffic flow is blocked and there is a risk of congestion. By calculating the change in vehicle speed within a unit time period, the system can obtain the average vehicle speed of the vehicle fleet, which helps to further evaluate the traffic smoothness and congestion status and monitor the smoothness of traffic in real time. Based on vehicle queue information, the system calculates the number of vehicles per unit distance to obtain the traffic flow density on the lane, that is, the degree of vehicle fleet aggregation. The degree of vehicle fleet aggregation reflects the concentration of vehicles on the lane. When the aggregation degree is high, it usually indicates that the traffic mobility of this section is poor and there may be congestion. As one of the characteristics of tidal traffic, the degree of vehicle fleet aggregation can help the traffic management system identify traffic bottlenecks or congestion points in time. Integrate the key data such as the inbound traffic flow, outbound traffic flow, degree of vehicle fleet aggregation, and average vehicle speed of the vehicle fleet to form a complete tidal traffic feature.

[0032] Conduct a dynamic intensity assessment based on the tidal traffic characteristics to obtain the tidal direction intensity index.

[0033] Based on the extracted tidal traffic characteristics, further conduct a dynamic intensity assessment to obtain the tidal direction intensity index. The tidal direction intensity index is used to measure the traffic flow intensity in each direction within the target area during different time periods, and provides data support for subsequent traffic signal optimization and flow scheduling.

[0034] Furthermore, conduct a dynamic intensity assessment based on the tidal traffic characteristics to obtain the tidal direction intensity index. The method includes:

[0035] Tidal direction intensity index: I(t) = ω1I1(t) + ω2I2(t) + ω3I3(t), where I(t) is the tidal direction intensity index at time t, I1(t) is the traffic flow intensity at time t, I2(t) is the vehicle fleet aggregation intensity at time t, I3(t) is the vehicle speed intensity at time t, and ω1, ω2, ω3 are the weight factors of the traffic flow intensity, vehicle fleet aggregation intensity, and vehicle speed intensity.

[0036] Using the tidal direction intensity index calculation formula, multiple traffic flow characteristics are weighted and combined to obtain the tidal direction intensity index, which reflects the traffic flow intensity in a certain direction at a certain moment. Among them, I(t) is the tidal direction intensity index at time t, I1(t) is the traffic flow intensity at time t, I2(t) is the platoon concentration intensity at time t, I3(t) is the vehicle speed intensity at time t, and ω1, ω2, ω3 are the weight factors of the traffic flow intensity, platoon concentration intensity, and vehicle speed intensity. Through the above calculation formula, the system can comprehensively evaluate the tidal direction intensity at a certain moment and reflect the traffic pressure and flow conditions in that direction. The tidal direction intensity index is a dynamically changing quantity and is updated in real time as the traffic flow changes.

[0037] Furthermore, based on the tidal traffic flow characteristics, a dynamic intensity evaluation is performed to obtain the tidal direction intensity index. The method includes:

[0038] Q1(t) is the inbound traffic flow at time t, and Q2(t) is the outbound traffic flow at time t; Among them, D(t) is the platoon concentration at time t, and D max is the maximum platoon density; Among them, V(t) is the average platoon speed at time t, and V max is the maximum vehicle speed.

[0039] The traffic flow intensity measures the relative intensity of the inbound and outbound traffic flows and reflects the imbalance degree of the inbound and outbound traffic flows. Q1(t) is the inbound traffic flow at time t, and Q2(t) is the outbound traffic flow at time t. The platoon concentration intensity reflects the density of vehicles at a specific moment and can represent the traffic density on a certain road section or lane. D(t) is the platoon concentration at time t, and D max is the maximum platoon density. The vehicle speed intensity measures the speed of the platoon and reflects the traffic smoothness. V(t) is the average platoon speed at time t, and V max is the maximum vehicle speed.

[0040] Construct a multi-agent collaborative network, and based on the multi-agent collaborative network, collaboratively calculate and generate a sequence of green light phase offsets for consecutive intersections.

[0041] By constructing a multi-agent collaborative network and using the collaborative computing ability of the network, a sequence of green light phase offsets for consecutive intersections is generated, thereby realizing intelligent traffic flow optimization.

[0042] Furthermore, to construct a multi-agent collaborative network, the method includes:

[0043] The traffic control unit at each intersection in the target area is used as an intelligent agent node, and the intelligent agent node is used to receive real-time traffic data; multiple intelligent agent nodes are added to the multi-agent collaborative network.

[0044] The traffic control unit at each intersection in the target area is regarded as an independent agent node. Each agent node corresponds to the traffic light control system of an intersection and is responsible for receiving real-time traffic data from various sensors (such as geomagnetic detectors, video recognition units, radar speed measuring devices, etc.), including information such as vehicle flow, vehicle speed, and fleet concentration. By acquiring and processing these traffic data in real time, the agent node can dynamically evaluate the traffic conditions at the intersection and respond according to changes in traffic flow. Next, multiple agent nodes are added to a multi-agent collaborative network, which is a network structure formed by multiple agent nodes through communication and collaboration. In this network, each agent node can share traffic flow data, exchange information, and make coordinated decisions based on shared data. Each agent node not only makes decisions based on the traffic conditions at its own intersection, but also receives real-time information from agents at other intersections, and performs global optimization through information exchange and collaboration. The agent node at each intersection can make decisions based on local traffic data, and at the same time, with the help of information from other agent nodes in the network, achieve cross-intersection coordinated regulation. Through collaborative computing, the entire system can dynamically adjust the timing of traffic lights based on real-time data such as tidal traffic characteristics and traffic flow changes at each intersection, optimize traffic flow, avoid traffic bottlenecks, and improve the overall efficiency of traffic in the area.

[0045] Furthermore, the multi-agent collaborative network collaboratively calculates and generates a sequence of green light phase offsets at consecutive intersections based on shared real-time traffic data. The method includes:

[0046] Through a multi-agent collaborative network, real-time traffic data of each intersection in a target area is obtained; based on the real-time traffic data, the green light phase offset of each intersection is calculated; and a green light phase sequence of continuous intersections is generated according to the green light phase offset.

[0047] First, through the multi-agent collaborative network, the traffic control unit at each intersection in the target area acts as an agent node to receive and upload local traffic data in real time. Each agent node obtains real-time information about vehicles through sensors, including data such as traffic flow, speed, and fleet concentration, and shares this data with agent nodes at other intersections through the collaborative network. Each agent node can not only obtain the traffic conditions of the local intersection, but also receive real-time traffic information from surrounding intersections, forming a dynamic information flow network to help achieve global optimization. Next, based on the above real-time traffic data, each agent node calculates the green light phase offset of the intersection where it is located, which indicates the degree of deviation between the current green light phase of the intersection and the preset signal light timing. The agent node dynamically adjusts the duration of the green light by analyzing tidal traffic characteristics such as traffic flow, speed, and fleet concentration. When the traffic flow at a certain intersection is large and congested, the system may extend the green light duration of the intersection; if the traffic flow at a certain intersection is small, the system will shorten the green light time, thereby optimizing the cycle of traffic signals and avoiding unnecessary waiting time. After calculating the green light phase offset at each intersection, the system further generates a green light phase sequence for consecutive intersections. This sequence coordinates the green light signals at each intersection in chronological order, so that the green light signals between adjacent intersections can be adjusted synchronously, thereby forming a green wave effect and ensuring that vehicles can pass smoothly between a series of consecutive intersections. Through precise green light timing, the parking and waiting caused by asynchronous traffic signals are reduced, thereby effectively improving the overall efficiency of traffic flow and reducing traffic congestion. Finally, the generated green light phase offset sequence will be input into the traffic light control system in real time to adjust the timing of traffic lights.

[0048] When the tidal direction intensity index is greater than a preset threshold, the continuous intersection green light phase offset sequence is input into a traffic signal light control system to start a tidal green wave mode.

[0049] When the tidal direction intensity index is greater than the preset threshold, it means that the traffic flow in that direction is too large, and there is a potential traffic bottleneck or congestion problem, and it is necessary to optimize the flow by adjusting the timing of traffic lights.

[0050] When the tidal direction intensity index exceeds the preset threshold, the system triggers the startup process of the tidal green wave mode. Specifically, through a multi-agent collaborative network, the system calculates a sequence of green light phase offsets for consecutive intersections based on the current traffic flow state and tidal traffic flow characteristics. This sequence adjusts the signal phases of adjacent intersections to ensure that vehicles can pass through multiple intersections continuously without having to stop frequently, thus achieving the green wave effect, reducing traffic pressure, and improving road traffic efficiency. After the tidal green wave mode is activated, the green light signals at all intersections are adjusted according to the optimized phase sequence to ensure smooth traffic flow between multiple intersections and avoid traffic bottlenecks. Under the tidal green wave mode, vehicles can pass through multiple intersections continuously within a certain speed range, thereby maximizing the road traffic capacity, reducing traffic congestion, and enhancing the intelligent level of traffic management.

[0051] In summary, the embodiments of the present application have at least the following technical effects:

[0052] First, heterogeneous sensor networks deployed at each intersection are used to collect real-time traffic flow data on lanes in all directions within the target area. Then, the traffic flow data is identified to obtain tidal traffic flow characteristics, which include inbound traffic volume, outbound traffic volume, fleet aggregation degree, and average fleet speed. Further, a dynamic intensity assessment is performed based on the tidal traffic flow characteristics to obtain the tidal direction intensity index. Then, a multi-agent collaborative network is constructed, and a sequence of green light phase offsets for consecutive intersections is generated through collaborative calculation based on the multi-agent collaborative network. Finally, when the tidal direction intensity index is greater than the preset threshold, the sequence of green light phase offsets for consecutive intersections is input into the traffic signal control system to activate the tidal green wave mode. This solves the technical problems in the prior art that traffic flow control is not flexible enough and traffic signals cannot be intelligently adjusted according to traffic flow conditions, and achieves the technical effects of improving road traffic efficiency and reducing congestion.

[0053] Embodiment 2, based on the same inventive concept as the intelligent traffic light cooperative control method for traffic flow optimization in the foregoing embodiment, as Figure 2 shown, the present application provides an intelligent traffic light cooperative control system for traffic flow optimization, wherein the system includes:

[0054] Data acquisition module 11: Real-time collect the traffic flow data of each lane in all directions within the target area through the heterogeneous sensor networks deployed at each intersection; Identification module 12: Identify the traffic flow data to obtain the tidal traffic flow characteristics, where the tidal traffic flow characteristics include the inbound traffic volume and outbound traffic volume, the degree of vehicle fleet aggregation, and the average vehicle speed of the vehicle fleet; Evaluation module 13: Perform dynamic intensity evaluation based on the tidal traffic flow characteristics to obtain the tidal direction intensity index; Calculation module 14: Construct a multi-agent collaborative network and collaboratively calculate and generate a sequence of green light phase offsets for consecutive intersections based on the multi-agent collaborative network; Control module 15: When the tidal direction intensity index is greater than a preset threshold, input the sequence of green light phase offsets for consecutive intersections into the traffic signal control system to activate the tidal green wave mode.

[0055] Further, the data acquisition module 11 is used to execute the following method:

[0056] The heterogeneous sensor network includes a geomagnetic detector, a video recognition unit, and a radar speed measurement device; The geomagnetic detector collects vehicle presence signals at a frequency of 10 Hz, the video recognition unit extracts license plate features at a frequency of 1 Hz, and the radar speed measurement device obtains the instantaneous vehicle speed at a frequency of 5 Hz; Fuse the vehicle presence signals, the license plate features, and the instantaneous vehicle speed to generate traffic flow data.

[0057] Further, the identification module 12 is used to execute the following method:

[0058] The traffic flow data includes vehicle identification information, vehicle speed information, and vehicle queue information; Based on the vehicle identification information, count the number of vehicles passing through per unit time in each direction to obtain the inbound traffic volume and outbound traffic volume; Based on the vehicle speed information, calculate the average vehicle speed over a predetermined time period to obtain the average vehicle speed of the vehicle fleet; Based on the vehicle queue information, calculate the number of vehicles within a unit distance to obtain the degree of vehicle fleet aggregation; Add the inbound traffic volume, outbound traffic volume, degree of vehicle fleet aggregation, and average vehicle speed of the vehicle fleet to the tidal traffic flow characteristics.

[0059] Further, the evaluation module 13 is used to execute the following method:

[0060] Tidal direction intensity index: I(t) = ω1I1(t) + ω2I2(t) + ω3I3(t), where I(t) is the tidal direction intensity index at time t, I1(t) is the traffic flow intensity at time t, I2(t) is the vehicle fleet aggregation intensity at time t, I3(t) is the vehicle speed intensity at time t, and ω1, ω2, ω3 are the weight factors of the traffic flow intensity, vehicle fleet aggregation intensity, and vehicle speed intensity.

[0061] Further, the evaluation module 13 is used to execute the following method:

[0062] Q1(t) is the traffic flow into the city at time t, and Q2(t) is the traffic flow out of the city at time t; where D(t) is the degree of vehicle aggregation at time t, and D max is the maximum vehicle density; where V(t) is the average vehicle speed of the vehicle fleet at time t, and V max is the maximum vehicle speed.

[0063] Furthermore, the calculation module 14 is used to execute the following method:

[0064] Regarding each traffic control unit at each intersection within the target area as an agent node, the agent node is used to receive real-time traffic data; adding multiple agent nodes to a multi-agent cooperation network.

[0065] Furthermore, the calculation module 14 is used to execute the following method:

[0066] Through the multi-agent cooperation network, obtain the real-time traffic data at each intersection within the target area; based on the real-time traffic data, calculate the green light phase offset at each intersection; generate a green light phase sequence for consecutive intersections according to the green light phase offset.

[0067] It should be noted that the above sequence of embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above describes specific embodiments of this specification. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0068] The above are only the preferred embodiments of the present application and are not used to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included within the protection scope of the present application.

[0069] This specification and the drawings are only exemplary descriptions of the present application and are considered to have covered any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. An intelligent traffic light coordination control method for traffic flow optimization, characterized in that: The method comprises: The heterogeneous sensor network deployed at each intersection collects the traffic data of lanes in each direction in the target area in real time; Identify the traffic flow data to obtain tidal traffic flow characteristics, wherein the tidal traffic flow characteristics include inbound and outbound traffic flow, fleet concentration, and average fleet speed; Dynamic strength evaluation is performed based on tidal traffic characteristics to obtain the tidal direction strength index; Constructing a multi-agent collaborative network, and generating a sequence of green light phase offsets at consecutive intersections based on collaborative calculations of the multi-agent collaborative network; When the tidal direction intensity index is greater than a preset threshold, the continuous intersection green light phase offset sequence is input into a traffic signal light control system to start a tidal green wave mode.

2. The intelligent traffic light coordination control method for traffic flow optimization according to claim 1, characterized in that: The vehicle flow data of lanes in each direction in the target area are collected in real time through a heterogeneous sensor network deployed at each intersection. The method includes: The heterogeneous sensor network includes a geomagnetic detector, a video recognition unit and a radar speed measurement device; The geomagnetic detector collects vehicle presence signals at a frequency of 10 Hz, the video recognition unit extracts license plate features at a frequency of 1 Hz, and the radar speed measuring device obtains instantaneous vehicle speed at a frequency of 5 Hz; The vehicle presence signal, the license plate feature and the instantaneous vehicle speed are fused and processed to generate traffic flow data.

3. The intelligent traffic light coordination control method for traffic flow optimization according to claim 1, characterized in that: Identifying the traffic flow data to obtain tidal traffic characteristics, the method comprising: The vehicle flow data includes vehicle identification information, vehicle speed information, and vehicle queue information; Based on the vehicle identification information, the number of vehicles passing through in each direction per unit time is counted to obtain the inbound and outbound vehicle flows; Based on the vehicle speed information, calculating the average vehicle speed in a predetermined time period to obtain the average vehicle speed of the fleet; Based on the vehicle queue information, the number of vehicles within a unit distance is calculated to obtain a fleet concentration degree; The in-city traffic flow, out-city traffic flow, convoy concentration and convoy average speed are added to the tidal traffic flow characteristics.

4. The intelligent traffic light coordination control method for traffic flow optimization according to claim 1, characterized in that: Based on the tidal traffic characteristics, dynamic strength evaluation is performed to obtain a tidal direction strength index, the method comprising: Tidal direction intensity index: I(t)=ω1I1(t)+ω2I2(t)+ω3I3(t), where I(t) is the tidal direction intensity index at time t, I1(t) is the traffic flow intensity at time t, I2(t) is the fleet concentration intensity at time t, I3(t) is the vehicle speed intensity at time t, ω1, ω2, ω3 are the weight factors of traffic flow intensity, fleet concentration intensity, and vehicle speed intensity.

5. The intelligent traffic light coordination control method for traffic flow optimization as claimed in claim 4, characterized in that: Based on the tidal traffic characteristics, dynamic strength evaluation is performed to obtain a tidal direction strength index, the method comprising: Q1(t) is the traffic flow into the city at time t, and Q2(t) is the traffic flow out of the city at time t; Among them, D(t) is the fleet aggregation degree at time t, D max is the maximum fleet density; Among them, V(t) is the average speed of the fleet at time t, V max is the maximum vehicle speed.

6. The intelligent traffic light coordination control method for traffic flow optimization according to claim 1, characterized in that: Constructing a multi-agent collaborative network, the method comprising: The traffic control unit at each intersection in the target area is used as an intelligent agent node, and the intelligent agent node is used to receive real-time traffic data; Add multiple agent nodes to the multi-agent collaborative network.

7. The intelligent traffic light coordination control method for traffic flow optimization as claimed in claim 6, characterized in that: The multi-agent collaborative network collaboratively calculates and generates a sequence of green light phase offsets at consecutive intersections based on shared real-time traffic data. The method comprises: Obtain real-time traffic data at each intersection in the target area through a multi-agent collaborative network; Based on the real-time traffic data, calculating the green light phase offset of each intersection; A green light phase sequence of continuous intersections is generated according to the green light phase offset.

8. An intelligent traffic light coordination system for traffic flow optimization, characterized in that: An intelligent traffic light coordination control method for implementing traffic flow optimization according to any one of claims 1 to 7, the system comprising: Data collection module: collects traffic data of lanes in all directions in the target area in real time through heterogeneous sensor networks deployed at each intersection; Identification module: Identify the traffic flow data to obtain tidal traffic flow characteristics, wherein the tidal traffic flow characteristics include inbound and outbound traffic flow, fleet concentration and fleet average speed; Evaluation module: Perform dynamic strength evaluation based on tidal traffic characteristics to obtain tidal direction strength index; Calculation module: constructing a multi-agent collaborative network, and generating a sequence of green light phase offsets of continuous intersections based on collaborative calculation of the multi-agent collaborative network; Control module: When the tidal direction intensity index is greater than a preset threshold, the continuous intersection green light phase offset sequence is input into the traffic signal light control system to start the tidal green wave mode.

Images