Smart city traffic optimization method and system based on 5G network

Abstract

The invention discloses a smart city traffic optimization method and system based on a 5G network, and particularly relates to the technical field of smart traffic, the smart city traffic optimization method based on the 5G network comprises the steps: deploying a 5G base station, and installing a sensor and traffic equipment on a road to collect traffic data; the traffic data comprises traffic flow data and a traffic signal state, rapidly transmitting the acquired traffic data to a cloud platform for storage by using a 5G network, preprocessing the acquired traffic data in the cloud platform, performing deep analysis through a machine learning algorithm to identify a traffic mode, and based on an analysis result, determining the traffic mode. The invention discloses a smart city traffic optimization system based on a 5G network, which is used for predicting a traffic flow demand, pre-judging an appearing congestion condition in advance and optimizing by adjusting a signal lamp period, and comprises a data acquisition module, a data analysis module and a traffic flow control module.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent transportation. More specifically, the present invention relates to a method and system for optimizing urban transportation based on a 5G network. Background Art

[0002] With the rapid development of information technology, the construction of smart cities has been accompanied by increasingly complex challenges in traffic management, which is an important part of urban management. With the increase in urban population and economic development, traditional traffic management methods are no longer able to cope with the growing traffic demand. Problems such as traffic congestion, frequent traffic accidents, and environmental pollution have become the core issues to be solved. Therefore, the proposal of intelligent transportation has become one of the effective ways to solve this problem.

[0003] As a new generation of communication technology, 5G technology has characteristics such as high speed, low latency, and large connection, providing important technical support for the optimization of smart city traffic systems. The low-latency feature of the 5G network makes real-time data transmission more efficient, while the large connection ability enables the collaborative work of intelligent devices. These advantages enable the intelligent transportation system based on the 5G network to achieve more accurate data collection and analysis, real-time monitoring and scheduling, thereby improving traffic flow, reducing the accident rate, and effectively reducing energy consumption and carbon emissions. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, embodiments of the present invention provide a method and system for optimizing urban transportation based on a 5G network to solve the problems raised in the above background art.

[0005] To achieve the above object, the present invention provides the following technical solution. A method for optimizing urban transportation based on a 5G network specifically includes the following steps: Step S1: Deploy 5G base stations and install sensors and traffic devices on the road to collect traffic data, where the traffic data includes traffic flow data and traffic signal status, and use the 5G network to quickly transmit the collected traffic data to the cloud platform for storage; Step S2: Preprocess the traffic data collected in Step S1 in the cloud platform and perform in-depth analysis through machine learning algorithms to identify traffic patterns; Step S3: Based on the results analyzed in Step S2, predict the traffic flow demand, anticipate congestion situations in advance, and optimize by adjusting the signal light cycle.

[0006] In a preferred embodiment, in step S1, by deploying 5G base stations and installing sensors and traffic devices on roads to collect traffic data, the traffic data includes traffic flow data and traffic signal status, and the collected traffic data is quickly transmitted to the cloud platform for storage through the 5G network. The specific steps are as follows: Step A1, Build network infrastructure: Deploy 5G base stations at transportation hubs, road intersections and high-traffic areas, and install traffic flow sensors and traffic signal monitoring devices on roads to obtain traffic flow data and traffic signal status, and connect all installed sensors and traffic devices to the 5G base station wirelessly; Step A2, Data transmission: Quickly upload the real-time collected traffic data to the cloud platform through the 5G network, and classify and store it according to the type of data collection to improve the efficiency of retrieval and query.

[0007] In a preferred embodiment, in step S2, the traffic data collected in step S1 is preprocessed in the cloud platform and deeply analyzed through machine learning algorithms to identify traffic patterns. The specific steps are as follows: Step B1, Feature extraction: Preprocess the received traffic data, remove duplicate and incomplete data records, fill in missing values, ensure data quality, and represent the traffic flow data and traffic signal status as and respectively, where represents a red light, represents a green light, represents a yellow light; Calculate the average traffic flow within the past n time points as: and obtain the peak traffic flow and the lowest traffic flow to extract statistical features, where represents the average traffic flow at time t, n is the time window size for calculating the average value, representing the number of past time periods, is the traffic flow data at time t - i, representing the traffic flow in the past n time points, and i represents the offset index in the time sliding window; Step B2, Build an LSTM model: Create a data set, where each row contains the traffic flow at the current time point t and the traffic signal status , as well as statistical features, the statistical features include the peak traffic flow , the lowest traffic flow and the average traffic flow , build an LSTM model using a deep learning framework, including an input layer, an LSTM layer, and an output layer, further including the following steps: Step B201, input layer: used to receive feature data, and the input is a vector containing traffic flow statistical features and traffic signal states ; Step B202, LSTM layer: used to capture long-term dependencies in the time series, and the output of the LSTM layer is: ; Step B203, output layer: used to predict future traffic flow, and the traffic flow at the future t+1 moment of the output layer is , where W is the weight matrix, b is the bias term, and the output is the predicted traffic flow, is the hidden state at the current moment, represents the hidden state at the previous moment and the current input data Based on this, the LSTM layer updates the hidden state; Step B3, after the model is trained, use a clustering algorithm to cluster the features to identify different traffic patterns, including traffic peak periods, trough periods, and normal periods, further including the following steps: Step B301, standardize the feature data obtained after the model is trained to ensure that all features have the same scale and combine them into a vector: , select k initial cluster centers for K-means clustering, denoted as , and perform the following steps: Step B302, for each data point , calculate its distance from each cluster center , and select the nearest cluster center: , and assign the data point to the cluster center with the minimum distance; Step B303, calculate the new center of each cluster, and its position is the mean of all data points within the cluster: , where is the number of data points in cluster , represents the set of all data points in cluster ; Step B304, repeat the above process of assigning and updating cluster centers until the cluster centers no longer change; after clustering is completed, each cluster represents a different traffic pattern. By analyzing the features of each cluster, identify the category of the traffic pattern. The traffic peak period is that the cluster center has a high average traffic flow and peak traffic flow, and Large, the traffic signal is characterized by long green and yellow light durations; during the low-traffic period, the traffic flow at the cluster center is low, and small, with a long red light time; during the normal period, the traffic flow is moderate, and the traffic flow fluctuation is small, and the traffic signal change rule is stable.

[0008] In a preferred embodiment, in step S3, based on the result analyzed in step S2, predict the traffic flow demand, anticipate the congestion situation in advance, and optimize it by adjusting the signal light cycle. The specific steps are as follows: Step C1, anticipate the congestion situation: Set the congestion threshold to , based on the LSTM model, predict the traffic flow demand at future time points to be , according to the prediction result and traffic pattern recognition, anticipate the congested area in advance. For each intersection j, when the predicted traffic flow is greater than the congestion threshold , and it is currently the peak period, record the status of this intersection as congested, denoted as ; when the predicted traffic flow is less than the congestion threshold R, record the status of this intersection as unobstructed, denoted as ; Step C2, optimize traffic signal control: According to the prediction result and congestion situation, optimize the traffic signal control strategy. The signal cycle of each intersection includes the green light cycle , the red light cycle and the yellow light cycle . Set the total signal cycle as: , improve the overall traffic flow by optimizing the green light cycle to maximize the passing capacity of the intersection. For each intersection, set the relationship between the passing capacity and the traffic flow, and maximize this capacity by adjusting the green light cycle. Set the objective function as , and the constraint conditions are that the total cycle and the green light cycle of each intersection do not exceed an upper limit value. The mathematical expression is: , where, is the green light cycle of the jth intersection, is the passing capacity corresponding to the traffic flow of the jth intersection, representing the maximum number of vehicles passing through this intersection, M is the total number of intersections, is the maximum signal cycle of the intersection, is the maximum green light cycle of the intersection.

[0009] This application also provides a smart city traffic optimization system based on the 5G network, which specifically includes a data collection module, a data analysis module, and a traffic flow control module; Data acquisition module: By deploying 5G base stations and installing sensors and traffic equipment on roads to collect traffic data, where the traffic data includes vehicle flow data and traffic signal status, and using the 5G network to quickly transmit the collected traffic data to the cloud platform for storage; Data analysis module: Preprocess the traffic data collected by the data acquisition module in the cloud platform and perform in-depth analysis through machine learning algorithms to identify traffic patterns; Traffic flow control module: Based on the results analyzed by the data analysis module, predict the traffic flow demand, anticipate congestion situations in advance, and optimize by adjusting the signal light cycle.

[0010] The beneficial effects of the present invention are as follows: By deploying 5G base stations and installing sensors and traffic equipment on roads to collect traffic data, where the traffic data includes vehicle flow data and traffic signal status, using the 5G network to quickly transmit the collected traffic data to the cloud platform for storage, preprocessing the collected traffic data in the cloud platform, performing in-depth analysis through machine learning algorithms to identify traffic patterns, based on the analyzed results, predicting the traffic flow demand, anticipating congestion situations in advance, and optimizing by adjusting the signal light cycle. The present invention utilizes the high-speed and low-latency characteristics of the 5G network to be able to transmit large-scale traffic data to the cloud platform for storage and processing in a short time, improving data transmission efficiency and reliability. Based on the prediction results of the traffic flow demand, it can adjust the signal light cycle in advance, optimize the distribution and switching of traffic signals, effectively relieve traffic congestion, and improve traffic fluency. Description of the Drawings

[0011] Figure 1 is the method flowchart of the present invention; Figure 2 is the structural block diagram of the present invention. Detailed Embodiments

[0012] 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 the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0013] In the description of the present application, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the described features. In the description of the present application, "a plurality" means two or more unless otherwise specifically defined.

[0014] In the description of the present application, the term "for example" is used to mean "serving as an example, illustration, or explanation". Any embodiment described as "for example" in the present application is not necessarily construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the present invention. In the following description, details are set forth for purposes of explanation. It should be understood that those of ordinary skill in the art can recognize that the present invention can be implemented without the use of these specific details. In other instances, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but rather to be in line with the broadest scope consistent with the principles and features disclosed in the present application.

[0015] Embodiment 1 This embodiment provides a method for optimizing smart city transportation based on a 5G network as shown in Figure 1 Figure [not provided], and specifically includes the following steps: Step S1: Deploy 5G base stations and install sensors and traffic devices on the road to collect traffic data, where the traffic data includes traffic flow data and traffic signal status, and use the 5G network to quickly transmit the collected traffic data to the cloud platform for storage; Step S2: Preprocess the traffic data collected in Step S1 in the cloud platform, and perform in-depth analysis through machine learning algorithms to identify traffic patterns; Step S3: Based on the results analyzed in Step S2, predict the traffic flow demand, anticipate congestion situations in advance, and optimize by adjusting the signal light cycle.

[0016] Preferably, in Step S1, by deploying 5G base stations and installing sensors and traffic devices on the road to collect traffic data, where the traffic data includes traffic flow data and traffic signal status, and using the 5G network to quickly transmit the collected traffic data to the cloud platform for storage, the specific steps are as follows: Step A1: Build network infrastructure: Deploy 5G base stations at transportation hubs, road intersections, and high-traffic areas, and install traffic flow sensors and traffic signal monitoring devices on roads to obtain traffic flow data and traffic signal status. Connect all installed sensors and traffic devices wirelessly to the 5G base station to ensure efficient communication between the devices and the network; Step A2: Data transmission: Rapidly upload the real-time collected traffic data to the cloud platform through the 5G network, and classify and store it according to the type of data collection to improve the efficiency of retrieval and query.

[0017] Preferably, in step S2, the traffic data collected in step S1 is preprocessed in the cloud platform and deeply analyzed through machine learning algorithms to identify traffic patterns. The specific steps are as follows: Step B1: Feature extraction: Preprocess the received traffic data, remove duplicate and incomplete data records, fill in missing values to ensure data quality, and represent the traffic flow data and traffic signal status as and , where represents a red light, represents a green light, represents a yellow light; Calculate the average traffic flow within the past n time points as: , and obtain the peak traffic flow and the lowest traffic flow to extract statistical features, where represents the average traffic flow at time t, n is the time window size for calculating the average value, representing the number of past time periods, is the traffic flow data at time t−i, representing the traffic flow in the past n time points, and i represents the offset index in the time sliding window; Step B2: Build an LSTM model: Create a data set, where each row contains the traffic flow at the current time point t and the traffic signal status , as well as statistical features, where the statistical features include the peak traffic flow , the lowest traffic flow and the average traffic flow . Use the extracted statistical features as the input feature vector X, and the target output is the traffic flow at the future time point t+1, represented as . Build an LSTM model using a deep learning framework, including an input layer, an LSTM layer, and an output layer, and further including the following steps: Step B201: Input layer: Used to receive feature data, and the input is a vector containing traffic flow statistical features and traffic signal status; Step B202, LSTM layer: used to capture long-term dependencies in the time series. The output of the LSTM layer is: ; Step B203, output layer: used to predict future traffic flow. The traffic flow at the future time t+1 of the output layer is , where W is the weight matrix, b is the bias term, and the output is the predicted traffic flow, is the hidden state at the current moment, represents that based on the hidden state at the previous moment and the current input data , the LSTM layer updates the hidden state; Step B3, after the model is trained, use a clustering algorithm to cluster the features to identify different traffic patterns, including traffic peak periods, trough periods, and normal periods, which further includes the following steps: Step B301, standardize the feature data obtained after the model is trained to ensure that all features have the same scale and combine them into a vector: , select k initial cluster centers for K-means clustering, denoted as , and perform the following steps: Step B302, for each data point , calculate its distance from each cluster center , and select the nearest cluster center: , and assign the data point to the cluster center with the minimum distance; Step B303, calculate the new center of each cluster, and its position is the mean of all data points within the cluster: , where is the number of data points in cluster , represents all data point sets within cluster ; Step B304, repeat the above process of assigning and updating the cluster centers until the cluster centers no longer change; after clustering is completed, each cluster represents a different traffic pattern. By analyzing the features of each cluster, identify the category of the traffic pattern. The traffic peak period is that the cluster center has a high average traffic flow and peak traffic flow, and is large, and the traffic signal is characterized by longer green and yellow light durations; the trough period is that the traffic flow at the cluster center is low, and is small, and the red light time is long; the normal period is that the traffic flow is moderate, and the traffic flow fluctuation is small, and the traffic signal change rule is stable.

[0018] Preferably, in step S3, based on the results analyzed in step S2, predict the traffic flow demand, anticipate the congestion situation in advance, and optimize it by adjusting the signal light cycle. The specific steps are as follows: Step C1. Anticipate the congestion situation: Set the congestion threshold to , and based on the LSTM model, predict the traffic flow demand at future time points to be . According to the prediction results and traffic pattern recognition, anticipate the congested areas in advance. For each intersection j, when the predicted traffic volume is greater than the congestion threshold , and it is currently the peak period, record the status of this intersection as congested, denoted as ; when the predicted traffic volume is less than the congestion threshold R, record the status of this intersection as unobstructed, denoted as ; Step C2. Optimize traffic signal control: According to the prediction results and congestion situation, optimize the traffic signal control strategy. The signal cycle of each intersection includes the green light cycle , the red light cycle and the yellow light cycle . Set the total signal cycle as: . Improve the overall traffic flow by optimizing the green light cycle to maximize the traffic capacity of the intersection. For each intersection, set the relationship between the traffic capacity and the traffic volume, and maximize this capacity by adjusting the green light cycle. Set the objective function as , and the constraint conditions are that the total cycle and the green light cycle of each intersection do not exceed an upper limit value. The mathematical expression is: , where is the green light cycle of the jth intersection, is the traffic capacity corresponding to the traffic volume of the jth intersection, representing the maximum number of vehicles passing through this intersection, M is the total number of intersections, is the maximum signal cycle of the intersection, is the maximum green light cycle of the intersection.

[0019] Embodiment 2 This embodiment provides a smart city traffic optimization system based on a 5G network, which specifically includes a data collection module, a data analysis module, and a traffic flow control module; Data collection module: Deploy 5G base stations and install sensors and traffic equipment on the road to collect traffic data. The traffic data includes traffic volume data and traffic signal status, and use the 5G network to quickly transmit the collected traffic data to the cloud platform for storage; Data Analysis Module: Preprocesses the traffic data collected by the Data Collection Module in the cloud platform, and performs in-depth analysis through machine learning algorithms to identify traffic patterns; Traffic Flow Control Module: Based on the results analyzed by the Data Analysis Module, predicts traffic flow demands, anticipates congestion situations in advance, and optimizes them by adjusting the signal light cycle.

[0020] It should be noted that in the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0021] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program code.

[0022] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for realizing the functions specified in Figure 1 one or more of the processes or multiple processes and / or blocks Figure 1 one or more of the blocks or multiple blocks.

[0023] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means realizes the functions specified in Figure 1 one or more of the processes or multiple processes and / or blocks Figure 1 one or more of the blocks or multiple blocks.

[0024] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide means for realizing the functions specified in Figure 1steps of one or more processes and / or blocks Figure 1 steps of functions specified in one or more blocks.

[0025] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications to these embodiments once they know the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications falling within the scope of the present invention.

[0026] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A smart city traffic optimization method based on 5G network, characterized in that: The specific steps include: Step S1: Deploy 5G base stations and install sensors and traffic equipment on the road to collect traffic data, including traffic flow data and traffic signal status, and use the 5G network to quickly transmit the collected traffic data to the cloud platform for storage; Step S2: pre-process the traffic data collected in step S1 in the cloud platform, and perform in-depth analysis through machine learning algorithms to identify traffic patterns. The specific steps are as follows: Step B1, feature extraction: pre-process the received traffic data, remove duplicate and incomplete data records, fill in missing values, ensure data quality, and represent the traffic flow data and traffic signal status as and ,in, Indicates a red light. Indicates green light, Indicates a yellow light; the average value of the traffic flow at the past n time points is calculated as: , and obtain the peak traffic flow and the minimum traffic flow to extract statistical features, where represents the average traffic flow at time t, n is the time window size used to calculate the average value, and represents the number of time periods in the past. is the traffic flow data at time t−i, representing the traffic flow at the past n time points, and i represents the offset index in the time sliding window; Step B2: Build an LSTM model: Create a dataset where each row contains the traffic volume at the current time point t and traffic signal status , and statistical features, including peak traffic flow , minimum traffic volume and average traffic volume , using the extracted statistical features as the input feature vector X, the target output is the traffic flow at the future time point t+1, expressed as , use the deep learning framework to build the LSTM model, including the input layer, LSTM layer and output layer; Step B3: After the model is trained, the features are clustered using a clustering algorithm to identify different traffic patterns, including peak, valley, and normal traffic periods; In the step B2, the LSTM model is constructed using a deep learning framework, including an input layer, an LSTM layer and an output layer, and further includes the following steps: Step B201, input layer: used to receive feature data, the input is a vector containing traffic flow statistics and traffic signal status ; Step B202, LSTM layer: used to capture long-term dependencies in time series. The output of the LSTM layer is: ; Step B203, output layer: used to predict future traffic flow. The traffic flow at the output layer at time t+1 in the future is , where W is the weight matrix, b is the bias term, and the output For the predicted traffic flow, is the hidden state at the current moment, Represents the hidden state at the previous moment and the current input data Based on , the LSTM layer updates the hidden state; In step B3, after the model is trained, a clustering algorithm is used to cluster the features to identify different traffic modes, including peak traffic periods, valley traffic periods, and normal traffic periods, further comprising the following steps: Step B301: Standardize the feature data obtained after model training to ensure that all features have the same scale and combine them into a vector: , select k initial cluster centers for K-means clustering, denoted as , perform the following steps: Step B302: For each data point , calculate its relationship with each cluster center , select the nearest cluster center: , the data points Assigned to the cluster center with the smallest distance; Step B303: Calculate the new center of each cluster , whose position is the mean of all data points in the cluster: ,in, It is a cluster The number of data points in Representation Cluster The set of all data points in ; Step B304, repeat the above process of assigning and updating cluster centers until the cluster centers no longer change; after clustering is completed, each cluster represents a different traffic mode, and the category of the traffic mode is identified by analyzing the characteristics of each cluster; Step S3: Based on the analysis results of step S2, predict the traffic flow demand, predict the congestion in advance, and optimize it by adjusting the traffic light cycle.

2. According to a 5G network-based smart city traffic optimization method according to claim 1, it is characterized in that: In step S1, 5G base stations are deployed, and sensors and traffic equipment are installed on the road to collect traffic data, which includes traffic flow data and traffic signal status. The collected traffic data is quickly transmitted to the cloud platform for storage using the 5G network. The specific steps are as follows: Step A1: Build network infrastructure: Deploy 5G base stations at transportation hubs, road intersections and high-traffic areas, and install traffic flow sensors and traffic signal monitoring equipment on the roads to obtain traffic flow data and traffic signal status. Connect all installed sensors and traffic equipment to the 5G base stations wirelessly to ensure efficient communication between the equipment and the network. Step A2, data transmission: The real-time collected traffic data is quickly uploaded to the cloud platform through the 5G network, and classified and stored according to the type of data collected to increase the efficiency of retrieval and query.

3. According to a 5G network-based smart city traffic optimization method according to claim 1, it is characterized in that: In step S3, based on the analysis result of step S2, traffic flow demand is predicted, congestion is predicted in advance, and optimization is performed by adjusting the signal light cycle. The specific steps are as follows: Step C1: Predict congestion: Set the congestion threshold to , the traffic flow demand predicted at a future time point based on the LSTM model is , based on the prediction results and traffic pattern recognition, the congested areas are predicted in advance. For each intersection j, when the traffic flow is predicted Greater than the congestion threshold , and it is currently peak time, the state of the intersection is recorded as congested, which is represented by When predicting traffic flow If it is less than the congestion threshold R, the state of the intersection is recorded as unblocked, which is expressed as ; Step C2, traffic signal control optimization: According to the prediction results and congestion conditions, optimize the traffic signal control strategy. The signal cycle of each intersection includes the green light cycle , Red light cycle Yellow light cycle , set the total signal period to: , by optimizing the green light cycle To improve the overall traffic flow and maximize the traffic capacity of the intersection, for each intersection, set the relationship between traffic capacity and traffic flow, and maximize this capacity by adjusting the green light cycle. Set the objective function as , the constraint is the total cycle of each intersection and green light cycle Does not exceed an upper limit value, the mathematical expression is: , in, is the green light cycle at the jth intersection, is the traffic capacity corresponding to the traffic flow at the jth intersection, indicating the maximum number of vehicles passing through the intersection, M is the total number of intersections, is the maximum signal period at the intersection, is the maximum green light cycle at the intersection.

4. A smart city traffic optimization system based on 5G network is applied to a smart city traffic optimization method based on 5G network as described in any one of claims 1-3, characterized in that: It includes data collection module, data analysis module, and traffic flow control module; Data collection module: By deploying 5G base stations and installing sensors and traffic equipment on the road, traffic data is collected, including traffic flow data and traffic signal status. The collected traffic data is quickly transmitted to the cloud platform for storage using the 5G network; Data analysis module: pre-processes the traffic data collected by the data collection module in the cloud platform and conducts in-depth analysis through machine learning algorithms to identify traffic patterns; Traffic flow control module: Based on the analysis results of the data analysis module, predict traffic flow demand, predict congestion in advance, and optimize by adjusting the traffic light cycle.

Images