Intelligent traffic light scheduling method and system combined with edge computing

Abstract

The application provides a kind of intelligent traffic light scheduling method and system combined with edge computing, it is related to traffic signal optimization scheduling field, method includes: monitoring and obtaining the traffic correlation data of target area in historical time zone;The red-green light scheduling optimization analysis of target area in preset time zone is carried out, and the first optimization scheduling strategy is generated, which includes a plurality of control schemes of a plurality of red-green lights in the target area;A plurality of control schemes are mapped and transmitted to a plurality of edge processing units of a plurality of red-green lights, and a plurality of red-green lights are dynamically scheduled.The purpose is to solve the problem that the traditional method is often based on fixed time period, cannot dynamically adjust according to real-time traffic flow, road conditions and weather factors, etc., leading to traffic congestion, waste of resources and other problems;By combining cloud and edge computing, the red-green light scheduling strategy is generated and optimized, which can dynamically adjust according to the real-time flow, road conditions and weather changes of each intersection, and optimize the operation efficiency of the whole traffic system.

Description

Technical Field

[0001] This invention relates to the field of traffic signal optimization and scheduling, and in particular to an intelligent traffic light scheduling method and system that combines edge computing. Background Technology

[0002] Traditional traffic light scheduling systems have played an important role in urban traffic management, but their inherent limitations have also led to many problems. Most existing traffic light scheduling systems operate based on fixed time periods, that is, they preset the traffic light cycles and signal durations for different time periods (such as morning rush hour, evening rush hour, nighttime, etc.). This scheduling method based on preset time periods does not take into account real-time factors such as actual traffic flow, road conditions, and weather. Therefore, it cannot flexibly respond to changes in different situations in complex traffic environments.

[0003] During peak traffic hours, traditional systems may experience traffic light cycles that are too long or too short, leading to traffic congestion or wasted resources. For example, on roads with high traffic volume, a green light that is too short may prevent vehicles from passing through completely, increasing queuing time. On roads with low traffic volume, a green light that is too long will waste time and energy, resulting in inefficient operation of the entire transportation system. In addition, climate change and weather factors (such as rain, snow, and strong winds) also affect traffic flow and driving behavior, but traditional dispatching systems fail to take these dynamic factors into account. Summary of the Invention

[0004] The purpose of this invention is to provide an intelligent traffic light scheduling method and system that combines edge computing, in order to solve the problems of traditional traffic light scheduling strategies, which are often based on fixed time periods and cannot be dynamically adjusted according to real-time traffic flow, road conditions, weather, and other factors, leading to traffic congestion and wasted resources. The invention includes:

[0005] In a first aspect, the present invention provides an intelligent traffic light scheduling method combining edge computing, comprising: monitoring and acquiring traffic association data of a target area within a historical time zone, and transmitting the traffic association data to a cloud central platform; performing traffic light scheduling optimization analysis of the target area within a preset time zone on the cloud central platform, generating a first optimized scheduling strategy, wherein the first optimized scheduling strategy includes several control schemes for several traffic lights within the target area; mapping and transmitting the several control schemes to edge processing units of several traffic lights, and performing dynamic scheduling of the several traffic lights within a preset time zone.

[0006] Preferably, the intelligent traffic light scheduling method combining edge computing further includes: monitoring and acquiring several traffic flow data and several road condition data of several streets in the target area within a historical time zone; monitoring and acquiring weather data of the target area within a historical time zone, and using the several traffic flow data, several road condition data and weather data as traffic-related data.

[0007] Preferably, the intelligent traffic light scheduling method combining edge computing further includes: obtaining several control parameter thresholds for several traffic lights within a target area, wherein the control parameter thresholds include red light duration thresholds and green light duration thresholds; randomly generating a first scheduling strategy based on several red light duration thresholds and several green light duration thresholds; predicting the red light waiting time of vehicles in the area according to several traffic flow data, several road condition data, weather data, and the first scheduling strategy, and outputting a first waiting time; continuing to randomly select scheduling strategies and iteratively predict waiting times until a predetermined number of iterations is reached, then the optimization converges, and the scheduling strategy corresponding to the shortest waiting time is output as the first optimized scheduling strategy.

[0008] Preferably, the intelligent traffic light scheduling method combining edge computing further includes: collecting multiple sample traffic flow sets, multiple sample road condition information sets, sample weather datasets, and sample scheduling strategy sets, and statistically analyzing the regional vehicle red light waiting time under different sample traffic flow, sample road condition information, sample weather data, and sample scheduling strategies to obtain a sample waiting time set; using the multiple sample traffic flow sets, multiple sample road condition information sets, sample weather datasets, and sample scheduling strategy sets as inputs, and using the sample waiting time set as supervision, training a BP neural network until convergence to obtain a waiting time predictor; inputting the multiple traffic flow sets, multiple road condition information sets, weather data, and a first scheduling strategy into the waiting time predictor to predict the regional vehicle red light waiting time and output a first waiting time.

[0009] Preferably, the intelligent traffic light scheduling method combining edge computing further includes: mapping and transmitting the plurality of control schemes to the edge processing units of the plurality of traffic lights; within the preset time zone, monitoring and acquiring a plurality of real-time road traffic flow sets of the roads associated with the plurality of traffic lights; and dynamically scheduling the plurality of traffic lights within the preset time zone according to the plurality of control schemes and the plurality of real-time road traffic flow sets.

[0010] Preferably, the intelligent traffic light scheduling method combining edge computing further includes: randomly selecting any traffic light from the plurality of traffic lights as the first traffic light, and obtaining a first control scheme and a first real-time road traffic flow set for the first traffic light; optimizing and correcting the first control scheme in real time according to the first real-time road traffic flow set, and outputting a first optimized control scheme; sequentially analyzing to obtain a plurality of optimized control schemes, and dynamically scheduling the plurality of traffic lights within a preset time zone according to the plurality of optimized control schemes.

[0011] Preferably, the intelligent traffic light scheduling method combining edge computing further includes: inputting the first real-time road traffic flow set into a traffic flow-correction coefficient lookup table, and outputting a first correction coefficient, wherein the traffic flow-correction coefficient lookup table is constructed based on the mapping of the sample traffic flow set and the sample correction coefficient set of the first traffic light, and the correction coefficient is the red light duration correction weight; and performing real-time optimization and correction of the first control scheme according to the first correction coefficient, and outputting a first optimized control scheme.

[0012] Secondly, the present invention also provides an intelligent traffic light scheduling system combining edge computing, used to execute an intelligent traffic light scheduling method combining edge computing as described in the first aspect, comprising: a traffic association data acquisition module, used to monitor and acquire traffic association data of a target area in a historical time zone, and to transmit the traffic association data to a cloud central platform; a traffic light scheduling optimization analysis module, used to perform traffic light scheduling optimization analysis of the target area in a preset time zone on the cloud central platform, and generate a first optimized scheduling strategy, wherein the first optimized scheduling strategy includes several control schemes for several traffic lights in the target area; and a traffic light dynamic control module, used to map and transmit the several control schemes to the edge processing units of several traffic lights, and to perform dynamic scheduling of the several traffic lights in a preset time zone.

[0013] The embodiments of the present invention include the following advantages: Traffic association data of the target area within a historical time zone is acquired through monitoring, and this traffic association data is communicatively transmitted to a cloud-based central platform. Then, on the cloud-based central platform, traffic light scheduling optimization analysis of the target area within a preset time zone is performed to generate a first optimized scheduling strategy. This first optimized scheduling strategy includes several control schemes for several traffic lights within the target area. Then, the several control schemes are mapped and transmitted to edge processing units of several traffic lights to perform dynamic scheduling of the traffic lights within a preset time zone. In other words, by combining cloud and edge computing, a traffic light scheduling strategy is generated and optimized, ensuring that the strategy is not only optimized based on global traffic flow but also dynamically adjusted according to real-time traffic flow, road conditions, and weather changes at each intersection, thereby optimizing the overall operational efficiency of the traffic system. Attached Figure Description

[0014] Figure 1 This is a flowchart illustrating the steps of an intelligent traffic light scheduling method incorporating edge computing according to the present invention.

[0015] Figure 2 This is a schematic diagram of the structure of an intelligent traffic light scheduling system that incorporates edge computing according to the present invention.

[0016] Explanation of reference numerals in the attached figures:

[0017] Traffic-related data acquisition module 10, traffic light scheduling optimization and analysis module 20, and traffic light dynamic control module 30. Detailed Implementation

[0018] This invention provides an intelligent traffic light scheduling method and system that integrates edge computing. It addresses the problems of traditional traffic light scheduling strategies, which are often based on fixed time periods and cannot be dynamically adjusted according to real-time traffic flow, road conditions, and weather, leading to traffic congestion and resource waste. By combining cloud and edge computing, the invention generates and optimizes traffic light scheduling strategies, ensuring that the strategies are not only optimized based on global traffic flow but also dynamically adjusted according to real-time traffic flow, road conditions, and weather changes at each intersection, thereby optimizing the overall operational efficiency of the traffic system.

[0019] The technical solutions of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. It should be understood that the present invention is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention. It should also be noted that, for ease of description, only the parts related to the present invention are shown in the accompanying drawings, not all of them.

[0020] Example 1, please refer to the appendix. Figure 1 This invention provides an intelligent traffic light scheduling method incorporating edge computing, applied to an intelligent traffic light scheduling system incorporating edge computing, specifically including the following steps:

[0021] Step 101: Monitor and acquire traffic association data of the target area within the historical time zone, and transmit the traffic association data to the cloud central platform; Step 102: On the cloud central platform, perform traffic light scheduling optimization analysis of the target area within the preset time zone, and generate a first optimized scheduling strategy, wherein the first optimized scheduling strategy includes several control schemes for several traffic lights in the target area; Step 103: Map and transmit the several control schemes to the edge processing units of several traffic lights, and perform dynamic scheduling of the several traffic lights within the preset time zone.

[0022] Specifically, firstly, various monitoring devices (such as traffic sensors, cameras, and road flow meters) deployed in the target area are used to collect data related to traffic flow, road conditions, and weather. This data includes traffic flow (information such as vehicle flow and speed recorded by sensors or cameras), road condition information (such as factors affecting road conditions such as traffic congestion, accidents, and construction), and weather data (such as meteorological conditions that may affect traffic flow and driving behavior, such as rain, snow, and fog). The collected data is transmitted in real time to the cloud center platform as input data for traffic light scheduling optimization analysis.

[0023] Next, on the cloud-based central platform, traffic-related data from these historical time zones (such as historical traffic flow, weather, and road conditions) are used to perform traffic light scheduling optimization analysis. Through big data analysis and intelligent algorithms, the cloud generates several traffic light control schemes based on factors such as traffic flow, road conditions, and weather. Each scheme includes control parameters such as the signal cycle, duration, and sequence of each traffic light within that time zone, generating a preliminary traffic light scheduling strategy. This leads to the generation of a first optimized scheduling strategy, which includes several control schemes for several traffic lights within the target area.

[0024] The optimized traffic light scheduling and control scheme will be transmitted to the edge computing unit where each traffic light is located. Edge computing units, typically located at the intersection, are distributed computing nodes capable of processing scheduling schemes from the cloud locally. After receiving the control scheme transmitted from the cloud, each intersection's edge processing unit fine-tunes or dynamically adjusts the traffic light control scheme based on real-time traffic flow data (such as vehicle flow and speed information collected in real-time by sensors) to cope with emergencies or traffic changes. For example, if traffic flow suddenly increases at an intersection, the edge computing unit can extend the green light time and reduce red light waiting time.

[0025] The entire process realizes a distributed traffic light scheduling system. The cloud is responsible for global optimization analysis and formulating overall scheduling strategies, while the edge computing unit is responsible for local real-time scheduling adjustments at specific intersections. In this way, while ensuring global optimization, it is possible to quickly respond to changes in traffic flow, optimize traffic light control, improve traffic efficiency, and reduce congestion and resource waste.

[0026] Furthermore, step 101 of the present invention also includes:

[0027] The system monitors and acquires traffic flow data and road condition data for several streets within a historical time zone of the target area; it also monitors and acquires weather data for the target area within a historical time zone, and uses the traffic flow data, road condition data, and weather data as traffic-related data.

[0028] Specifically, monitoring involves acquiring traffic flow and road condition information for several streets within a target area over a historical time zone. Traffic flow data refers to the vehicle volume information for each street during a specific historical period. This data is typically collected using traffic monitoring equipment (such as geomagnetic sensors, cameras, and radar). Flow data includes information such as the number of vehicles passing through an intersection, vehicle speed, and lane occupancy. This data reflects the traffic density and flow status of each street at different times. For example, some streets may experience high traffic volume during the morning rush hour, while traffic volume is lower during off-peak hours. Road condition information refers to data reflecting road traffic conditions, mainly including: traffic congestion (e.g., whether certain road sections experience congestion at certain times), traffic accidents (some accidents or obstacles may affect the normal traffic capacity of road sections), and road construction (road construction areas usually affect traffic flow). This information is crucial for determining the traffic capacity of each street. Typically, road condition information is collected through traffic cameras, road surface sensors, or manual reporting.

[0029] Monitoring and acquiring weather data for the target area within historical time zones involves identifying meteorological factors that influence traffic flow and road conditions. For example, precipitation (such as rain, snow, and frost) can make roads slippery and reduce visibility, thus affecting driver speed and traffic volume. This data, collected from multiple sources (traffic flow, road conditions, and weather), collectively constitutes traffic-related data. This data combination comprehensively reflects the traffic conditions of the target area and the impact of external factors on traffic flow.

[0030] Furthermore, step 102 of the present invention also includes:

[0031] Obtain several control parameter thresholds for several traffic lights within the target area, including red light duration thresholds and green light duration thresholds; randomly generate a first scheduling strategy based on the several red light duration thresholds and several green light duration thresholds; predict the red light waiting time of vehicles in the area based on the several traffic flow data, several road condition data, weather data, and the first scheduling strategy, and output the first waiting time; continue to randomly select scheduling strategies and iteratively predict waiting times until a predetermined number of iterations is reached, then the optimization converges, and the scheduling strategy corresponding to the shortest waiting time is output as the first optimized scheduling strategy.

[0032] Specifically, several control parameter thresholds for traffic lights within the target area are obtained. These control parameter thresholds include red light duration thresholds and green light duration thresholds. The red light duration threshold specifies the maximum duration of the red light signal, with an upper limit for the red light duration at each intersection to ensure sufficient time for traffic in each direction. The green light duration threshold specifies the maximum duration of the green light signal, controlling the length of time vehicles in each direction can travel. Obtaining these control parameter thresholds is to set a reasonable time range when generating subsequent scheduling strategies, avoiding excessively long or short traffic light control times.

[0033] Next, based on multiple red light duration thresholds and green light duration thresholds, any red light duration and any green light duration within these thresholds are randomly selected as the first control scheme for the first traffic light. This results in multiple first control schemes for several traffic lights, constructing a first scheduling strategy. This scheduling strategy includes the duration and control cycle of each traffic light. Then, on the cloud platform, the system predicts the waiting time of vehicles in the area during red light periods based on traffic flow, road condition information, weather data, and the first scheduling strategy. The prediction of waiting time is crucial because it directly affects traffic flow and the average queuing time of vehicles. Through comprehensive analysis of this data, the first waiting time is predicted, which is the average waiting time of vehicles during red light periods based on the first scheduling strategy.

[0034] Further, by randomly selecting new scheduling strategies and predicting new waiting times, iterative predictions are performed until a preset number of iterations is reached. In each iteration, the scheduling strategy is fine-tuned, adjusting the traffic light durations based on the results of the previous iteration to reduce waiting times. Each adjustment is based on predicted waiting time data, ensuring that the scheduling strategy can more effectively reduce vehicle waiting time at red lights. After several iterations, the scheduling strategy is gradually optimized, and finally, the system selects the scheduling strategy corresponding to the shortest waiting time as the final scheduling scheme, i.e., the first optimized scheduling strategy.

[0035] This process implements a traffic light scheduling strategy generation method based on random generation and iterative optimization. By introducing factors such as traffic flow, road conditions, and weather, the system can continuously optimize the control duration and signal cycle of traffic lights, and finally output an optimal traffic light scheduling strategy, thereby minimizing vehicle waiting time and improving overall traffic efficiency.

[0036] Furthermore, the present invention also includes the following steps:

[0037] Multiple sample traffic flow sets, multiple sample road condition information sets, sample weather datasets, and sample scheduling strategy sets are collected. The regional vehicle red light waiting times under different sample traffic flow, road condition information, weather data, and scheduling strategies are statistically analyzed to obtain a sample waiting time set. Using the multiple sample traffic flow sets, multiple sample road condition information sets, sample weather datasets, and sample scheduling strategy sets as input, and using the sample waiting time set as supervision, a backpropagation neural network is trained until convergence to obtain a waiting time predictor. The multiple traffic flow sets, multiple road condition information sets, weather data, and a first scheduling strategy are input into the waiting time predictor to predict the regional vehicle red light waiting times, and the first waiting time is output.

[0038] Specifically, firstly, multiple sample traffic flow sets, sample road condition information sets, sample weather datasets, and sample dispatching strategy sets are collected. The regional vehicle red light waiting times under different sample traffic flow, road condition, weather, and dispatching strategies are statistically analyzed to obtain a sample waiting time set. Next, a waiting time predictor is constructed based on a backpropagation (BP) neural network. Using the aforementioned sample traffic flow sets, road condition information sets, weather datasets, and dispatching strategy sets as input, and the sample waiting time set as supervision, the waiting time predictor is trained under supervised conditions. First, the input data is passed through the neural network, and the network output is calculated. Then, the neural network output is compared with the actual sample waiting times to calculate the error. Next, the network weights and biases are adjusted based on the error to minimize the output error. Finally, through multiple iterations of training, the network converges, meaning the error is reduced to an acceptable level. Through training, the BP neural network learns the relationship between traffic flow, road conditions, weather, dispatching strategies, and waiting times. Ultimately, this network model (i.e., the waiting time predictor) can predict new input data.

[0039] Finally, the aforementioned traffic flow data, road condition information, weather data, and the first scheduling strategy are input into the waiting time predictor to predict the regional vehicle red light waiting time and output the first waiting time. By training a BP neural network, the system can establish a relationship model between traffic light scheduling and waiting time based on historical sample data of traffic flow, road conditions, weather, and scheduling strategies. After training, the system can predict the waiting time of vehicles at red lights under specific conditions. This prediction result can help the system continuously optimize the traffic light scheduling strategy, reduce waiting time, and improve traffic flow.

[0040] Furthermore, step 103 of the present invention also includes:

[0041] The control schemes are mapped and transmitted to the edge processing units of several traffic lights; within the preset time zone, several real-time road traffic sets of the roads associated with the traffic lights are obtained by fixed-point monitoring; and the traffic lights are dynamically scheduled within the preset time zone according to the control schemes and the real-time road traffic sets.

[0042] Specifically, the optimal or preliminary traffic light control strategy generated in the cloud (including the duration, cycle, and switching method of red and green lights) needs to be transmitted to the edge processing units at the actual intersections. These edge processing units are local devices distributed across various intersections, capable of processing data and performing calculations and control locally. They typically have real-time control capabilities for parameters such as traffic flow and signal light duration. Next, within the preset time zone, several real-time road flow sets for the roads associated with several traffic lights are acquired through fixed-point monitoring. The edge processing unit for each traffic light periodically monitors the real-time traffic flow data of its associated roads. This data is generally collected through traffic sensors, video surveillance, geomagnetic sensors, radar, or other devices. These datasets may include information such as the number of vehicles, vehicle speed, and traffic density at each intersection or street during the current time period. Then, by combining the control scheme (the cloud-optimized traffic light scheduling strategy) with real-time road flow data (e.g., an increase or decrease in traffic flow at a certain intersection), the edge processing unit dynamically adjusts each traffic light signal. Its main goal is to optimize the timing of traffic light switching in real time and reduce traffic congestion.

[0043] By transmitting the optimized traffic light control strategy to the edge processing unit at the intersection and combining it with real-time traffic flow data, the duration and cycle of traffic light signals are adjusted in real time, thereby reducing traffic congestion and improving road traffic efficiency. In this way, the system can quickly respond to changes in traffic conditions and achieve more flexible and intelligent traffic signal control.

[0044] Furthermore, the present invention also includes the following steps:

[0045] Randomly select any traffic light from the plurality of traffic lights as the first traffic light, and obtain the first control scheme and the first real-time road traffic flow set of the first traffic light; optimize and correct the first control scheme in real time according to the first real-time road traffic flow set, and output the first optimized control scheme; analyze and obtain a plurality of optimized control schemes in sequence, and dynamically schedule the plurality of traffic lights within a preset time zone according to the plurality of optimized control schemes.

[0046] Specifically, firstly, any traffic light among the several traffic lights is randomly selected as the first traffic light, and a first control scheme and a first real-time road traffic flow set for the first traffic light are obtained. Next, the first control scheme is optimized and corrected in real-time based on the first real-time road traffic flow set; that is, the duration of the traffic light is fine-tuned according to the current traffic conditions to maximize traffic flow. For example, if the traffic flow in a certain direction is high, the system may extend the green light duration for that direction; if the traffic flow in a certain direction is low, the system may reduce the green light duration or quickly switch to other directions, outputting the first optimized control scheme. Then, the control schemes of all other traffic lights are analyzed one by one, using the same optimization algorithm to optimize each traffic light based on real-time traffic flow and road conditions. Several optimized control schemes are obtained sequentially, and an optimized control scheme is generated for each traffic light. The optimized schemes for different intersections may differ, adjusting the signal cycle according to their respective traffic flow, road conditions, and environmental conditions. Finally, the traffic lights are dynamically scheduled within a preset time zone according to the several optimized control schemes.

[0047] Furthermore, the present invention also includes the following steps:

[0048] The first real-time road traffic flow set is input into the traffic flow-correction coefficient lookup table, and the first correction coefficient is output. The traffic flow-correction coefficient lookup table is constructed based on the mapping between the sample traffic flow set and the sample correction coefficient set of the first traffic light, and the correction coefficient is the red light duration correction weight. The first control scheme is optimized and corrected in real time according to the first correction coefficient, and the first optimized control scheme is output.

[0049] Specifically, firstly, real-time road traffic flow data for the segment where the first traffic light is located is acquired. This data may include vehicle flow, speed, and traffic density, reflecting the current traffic conditions of the segment. Next, the first real-time road traffic flow set is input into a flow-correction coefficient lookup table. This table is a pre-built mapping table that associates different traffic flow data (such as vehicle flow and speed) with corresponding correction coefficients. Each traffic flow condition corresponds to a correction coefficient, which represents the correction weight for the red light duration. The correction coefficient reflects the impact of traffic flow changes on traffic light scheduling. When traffic flow increases, the system may need to increase the red light duration to reduce congestion. The larger the correction coefficient, the greater the adjustment range of the red light duration. The purpose of the correction coefficient is to dynamically adjust the red light duration according to traffic flow changes to optimize traffic control. By inputting the real-time road traffic flow set, the first correction coefficient matching the current traffic flow is found from the flow-correction coefficient lookup table. This coefficient determines the adjustment range of the red light duration for the current time period.

[0050] Then, the first control scheme is optimized and corrected in real time based on the first correction coefficient. If the traffic flow is large, the system will extend the red light duration to avoid vehicle congestion; if the traffic flow is small, the red light duration may be reduced to shorten the waiting time, and the first optimized control scheme will be output.

[0051] In summary, the intelligent traffic light scheduling method combining edge computing provided by this invention has the following technical effects:

[0052] Traffic correlation data of the target area within historical time zones is acquired through monitoring and transmitted to a cloud-based central platform. Then, on the cloud-based central platform, traffic light scheduling optimization analysis of the target area within a preset time zone is performed to generate a first optimized scheduling strategy. This first optimized scheduling strategy includes several control schemes for several traffic lights within the target area. These control schemes are then mapped and transmitted to edge processing units of several traffic lights to dynamically schedule them within the preset time zone. In other words, by combining cloud and edge computing, a traffic light scheduling strategy is generated and optimized, ensuring that the strategy is not only optimized based on global traffic flow but also dynamically adjusted according to real-time traffic flow, road conditions, and weather changes at each intersection, thereby optimizing the overall operational efficiency of the traffic system.

[0053] Example 2: Based on the same inventive concept as the intelligent traffic light scheduling method combining edge computing in the foregoing examples, this invention also provides an intelligent traffic light scheduling system combining edge computing. Please refer to the appendix. Figure 2 The system includes: a traffic-related data acquisition module 10, used to monitor and acquire traffic-related data of a target area within a historical time zone, and to transmit the traffic-related data to a cloud-based central platform; a traffic light scheduling optimization analysis module 20, used to perform traffic light scheduling optimization analysis of a target area within a preset time zone on the cloud-based central platform, and generate a first optimized scheduling strategy, wherein the first optimized scheduling strategy includes several control schemes for several traffic lights within the target area; and a traffic light dynamic control module 30, used to map and transmit the several control schemes to the edge processing units of several traffic lights, and to perform dynamic scheduling of the several traffic lights within a preset time zone.

[0054] Furthermore, the intelligent traffic light scheduling system combined with edge computing is also used to: monitor and acquire traffic flow and road condition information of several streets in the target area within a historical time zone; monitor and acquire weather data of the target area within a historical time zone, and use the traffic flow, road condition information and weather data as traffic-related data.

[0055] Furthermore, the intelligent traffic light scheduling system combined with edge computing is also used to: obtain several control parameter thresholds for several traffic lights in a target area, wherein the control parameter thresholds include red light duration thresholds and green light duration thresholds; randomly generate a first scheduling strategy based on several red light duration thresholds and several green light duration thresholds; predict the red light waiting time of vehicles in the area according to several traffic flow data, several road condition information, weather data and the first scheduling strategy, and output the first waiting time; continue to randomly select scheduling strategies and waiting time for iterative prediction until a predetermined number of iterations is reached, then the optimization converges, and the scheduling strategy corresponding to the shortest waiting time is output as the first optimized scheduling strategy.

[0056] Furthermore, the intelligent traffic light scheduling system combined with edge computing is also used to: collect multiple sample traffic flow sets, multiple sample road condition information sets, sample weather datasets, and sample scheduling strategy sets, and statistically analyze the regional vehicle red light waiting time under different sample traffic flow, sample road condition information, sample weather data, and sample scheduling strategies to obtain a sample waiting time set; using the multiple sample traffic flow sets, multiple sample road condition information sets, sample weather datasets, and sample scheduling strategy sets as inputs, and using the sample waiting time set as supervision, train a BP neural network until convergence to obtain a waiting time predictor; input the multiple traffic flow sets, multiple road condition information sets, weather data, and the first scheduling strategy into the waiting time predictor to predict the regional vehicle red light waiting time and output the first waiting time.

[0057] Furthermore, the intelligent traffic light scheduling system combined with edge computing is also used to: map and transmit the several control schemes to the edge processing units of several traffic lights; within the preset time zone, monitor and obtain several real-time road traffic sets of the roads associated with the several traffic lights; and dynamically schedule the several traffic lights within the preset time zone according to the several control schemes and the several real-time road traffic sets.

[0058] Furthermore, the intelligent traffic light scheduling system combined with edge computing is also used for: randomly selecting any traffic light from the plurality of traffic lights as the first traffic light, and obtaining a first control scheme and a first real-time road traffic flow set for the first traffic light; optimizing and correcting the first control scheme in real time according to the first real-time road traffic flow set, and outputting a first optimized control scheme; sequentially analyzing to obtain a plurality of optimized control schemes, and dynamically scheduling the plurality of traffic lights within a preset time zone according to the plurality of optimized control schemes.

[0059] Furthermore, the intelligent traffic light scheduling system combined with edge computing is also used to: input the first real-time road traffic flow set into a traffic flow-correction coefficient lookup table, and output a first correction coefficient, wherein the traffic flow-correction coefficient lookup table is constructed based on the mapping of the sample traffic flow set and the sample correction coefficient set of the first traffic light, and the correction coefficient is the red light duration correction weight; optimize and correct the first control scheme in real time according to the first correction coefficient, and output a first optimized control scheme.

[0060] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. The intelligent traffic light scheduling method and specific examples combining edge computing described in Embodiment 1 are also applicable to the intelligent traffic light scheduling system combining edge computing in this embodiment. Through the foregoing detailed description of the intelligent traffic light scheduling method combining edge computing, those skilled in the art can clearly understand the intelligent traffic light scheduling system combining edge computing in this embodiment; therefore, for the sake of brevity, it will not be described in detail here. As for the system disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple, and relevant details can be found in the method section.

[0061] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0062] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of this invention and its equivalents, this invention also intends to include these modifications and variations.

Claims

1. A smart traffic light scheduling method combining edge computing, characterized in that the method include: The system monitors and acquires traffic-related data for the target area within historical time zones, and then transmits this traffic-related data to the cloud central platform. On the cloud-based central platform, traffic light scheduling optimization analysis is performed in the target area within a preset time zone to generate a first optimized scheduling strategy, wherein the first optimized scheduling strategy includes several control schemes for several traffic lights in the target area. The aforementioned control schemes are mapped and transmitted to the edge processing units of several traffic lights to perform dynamic scheduling of the traffic lights within a preset time zone. Monitoring and acquiring traffic correlation data for the target area within historical time zones, including: The system monitors and obtains traffic flow and road condition information for several streets within a historical time zone in the target area. Monitor and acquire weather data for the target area within historical time zones, and use the aforementioned traffic flow, road condition information, and weather data as traffic-related data; On the cloud-based central platform, traffic light scheduling optimization analysis is performed in the target area within a preset time zone to generate a first optimized scheduling strategy, including: Obtain several control parameter thresholds for several traffic lights within the target area, including red light duration thresholds and green light duration thresholds; The first scheduling strategy is randomly generated based on several red light duration thresholds and several green light duration thresholds; Based on the aforementioned traffic flow data, road condition information, weather data, and the first scheduling strategy, the regional vehicle red light waiting time is predicted, and the first waiting time is output. Continue to randomly select scheduling strategies and waiting time for iterative prediction until the predetermined number of iterations is reached. Then the optimization converges, and the scheduling strategy corresponding to the shortest waiting time is output as the first optimized scheduling strategy. Based on the aforementioned traffic flow data, road condition information, weather data, and the first scheduling strategy, the regional vehicle red light waiting time is predicted, and the first waiting time is output, including: Multiple sample traffic flow sets, multiple sample road condition information sets, sample weather datasets, and sample scheduling strategy sets are collected. The regional vehicle red light waiting time under different sample traffic flow, sample road condition information, sample weather data, and sample scheduling strategies is statistically analyzed to obtain a sample waiting time set. Using the multiple sample traffic flow sets, multiple sample road condition information sets, sample weather datasets, and sample scheduling strategy sets as inputs, and using the sample waiting time set as supervision, a BP neural network is trained until convergence is obtained to acquire a waiting time predictor. The waiting time predictor is input into the traffic flow data, road condition data, weather data, and the first scheduling strategy to predict the red light waiting time of vehicles in the area and output the first waiting time.

2. The intelligent traffic light scheduling method combining edge computing according to claim 1, characterized in that, The aforementioned control schemes are mapped and transmitted to the edge processing units of several traffic lights, and dynamic scheduling of the traffic lights within a preset time zone is performed, including: The aforementioned control schemes are mapped and transmitted to the edge processing units of several traffic lights; Within the preset time zone, fixed-point monitoring acquires several real-time road traffic flow sets for roads associated with several traffic lights; Based on the aforementioned control schemes and real-time road traffic flow sets, dynamic scheduling of several traffic lights is performed within a preset time zone.

3. The intelligent traffic light scheduling method combining edge computing according to claim 2, characterized in that, Based on the aforementioned control schemes and real-time road traffic flow sets, dynamic scheduling of several traffic lights within a preset time zone is performed, including: Randomly select any traffic light from the plurality of traffic lights as the first traffic light, and obtain the first control scheme and the first real-time road traffic flow set of the first traffic light; The first control scheme is optimized and corrected in real time based on the first real-time road traffic flow set, and the first optimized control scheme is output. Several optimized control schemes were obtained through sequential analysis, and dynamic scheduling of several traffic lights within a preset time zone was carried out according to the several optimized control schemes.

4. The intelligent traffic light scheduling method combining edge computing according to claim 3, characterized in that, The first control scheme is optimized and corrected in real time based on the first real-time road traffic flow set, and the first optimized control scheme is output, including: The first real-time road traffic flow set is input into the traffic flow-correction coefficient lookup table, and the first correction coefficient is output. The traffic flow-correction coefficient lookup table is constructed based on the mapping of the sample traffic flow set and the sample correction coefficient set of the first traffic light, and the correction coefficient is the red light duration correction weight. The first control scheme is optimized and corrected in real time based on the first correction coefficient, and the first optimized control scheme is output.

5. An intelligent traffic light scheduling system incorporating edge computing, characterized in that: The steps for implementing the intelligent traffic light scheduling method combining edge computing as described in any one of claims 1 to 4 include: The traffic-related data acquisition module is used to monitor and acquire traffic-related data of the target area in historical time zones, and to transmit the traffic-related data to the cloud center platform. The traffic light scheduling optimization analysis module is used to perform traffic light scheduling optimization analysis in a target area within a preset time zone on a cloud central platform, and generate a first optimized scheduling strategy, wherein the first optimized scheduling strategy includes several control schemes for several traffic lights in the target area. The traffic light dynamic control module is used to map and transmit the several control schemes to the edge processing units of several traffic lights, and to perform dynamic scheduling of the several traffic lights within a preset time zone.

Images