Digital twin city traffic light control system based on the Internet of Things

Abstract

The present invention discloses a digital twin city traffic light control system based on the Internet of Things, which relates to the technical field of intelligent control, including an acquisition module, an analysis module and a control module, which calculate the rate of change of congestion, obtain a concentrated time period, calculate the weight of historical natural data, construct an interference function, calculate the interference duration and a new concentrated time period, establish a traffic model, compare the new rate of change of congestion with a threshold of the change in congestion, perform a first operation, and establish a first mapping relationship. The present invention optimizes the travel time allocation of traffic flow and dynamically adjusts the control strategy of traffic lights by real-time monitoring and analysis of traffic flow and congestion changes, and considering the influence of natural environmental factors. Through the analysis of historical traffic data and natural data, it is possible to predict future traffic conditions, make corresponding traffic signal adjustments and route planning in advance, and the application of Internet of Things technology enables the traffic light control system to achieve remote monitoring and centralized management.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control, and in particular to a digital twin city traffic light control system based on the Internet of Things. Background Art

[0002] In recent years, with the continuous optimization of artificial intelligence algorithms, the digital twin traffic command system has stronger self-learning and self-optimization capabilities, and can continuously improve decision-making capabilities based on real-time data and historical experience. With the development of technologies such as 5G and edge computing, traffic lights, surveillance cameras, road signs and other facilities will be highly integrated with the digital twin system to form an intelligent transportation network.

[0003] At present, a smart city traffic light control system and a control method thereof are disclosed in a Chinese invention patent with publication number CN114141021B. The method reasonably adjusts the display time of different signals of traffic lights according to the current traffic conditions at traffic intersections, thereby improving the command efficiency of traffic lights at traffic intersections, preventing traffic congestion at traffic intersections, and improving the quality of urban traffic. However, the relevant technology does not quantify and macro-regulate traffic congestion based on historical traffic conditions, lacks scientific data, does not compensate and eliminate interference caused by traffic according to different actual weather conditions, and lacks data accuracy and inclusiveness. Summary of the invention

[0004] The technical problem solved by the present invention is that the relevant technology does not quantify and macro-regulate traffic congestion based on historical traffic conditions, lacks scientific data, does not compensate and eliminate interference caused by traffic according to actual weather conditions, and lacks data accuracy and inclusiveness.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: A digital twin city traffic light control system based on the Internet of Things, comprising an acquisition module, an analysis module and a control module;

[0006] The acquisition module obtains historical traffic data and historical natural data of the target road section within the first historical time point;

[0007] The analysis module is used to calculate the congestion change rate based on historical traffic data, set congestion categories, perform cluster analysis on the congestion change rate based on the congestion categories, obtain the concentrated time period corresponding to each congestion category, obtain the historical natural data of each day in the first historical time period, obtain the concentrated time period corresponding to each day in the first historical time period, calculate the weight of the historical natural data, construct an interference function based on the weight, calculate the interference duration based on the interference function, and calculate a new concentrated time period based on the interference duration;

[0008] The control module models the target road section and its traffic data through the DTSE technology to obtain a traffic model, obtains a concentrated time period and a congestion change rate through the traffic model, obtains a new concentrated time period and a new congestion change rate through an interference function, sets a congestion change rate threshold, compares the new congestion change rate with the congestion change threshold, executes a first operation according to the comparison result, and establishes a first mapping relationship.

[0009] As a preferred solution of the digital twin city traffic light control system based on the Internet of Things described in the present invention, wherein: the historical traffic data includes historical time points, historical vehicle speeds, historical control signal phases, and control durations of historical control signals, and the historical vehicle speeds are represented as the average speeds of vehicles on the target road section at the corresponding historical time points;

[0010] The historical natural data include air visibility and ground friction;

[0011] The historical time points are represented as various time points continuously monitored within a first historical time period, and the first historical time period represents a historical time period with a period of one year.

[0012] As a preferred solution of the digital twin city traffic light control system based on the Internet of Things described in the present invention, the calculation logic of the congestion change rate includes:

[0013] Adjacent historical time points and corresponding historical vehicle speeds are obtained, the difference between adjacent historical time points is calculated and recorded as a first difference, the difference between the corresponding historical vehicle speeds is calculated and recorded as a second difference, the ratio of the second difference to the first difference is calculated, and the absolute value of the ratio is taken, and the absolute value of the ratio is taken as a positive value or a negative value, and the absolute value of the ratio after the positive or negative value is set as the congestion change rate, when the subsequent historical vehicle speed is greater than the previous historical vehicle speed, the absolute value of the ratio is taken as a positive value, and when the subsequent historical vehicle speed is less than the previous vehicle speed, the absolute value of the ratio is taken as a negative value.

[0014] As a preferred solution of the digital twin city traffic light control system based on the Internet of Things described in the present invention, wherein: the congestion category is represented by the category of the congestion degree of the target road section at the current moment relative to the previous moment, and the congestion categories include a first category, a second category, a third category and a fourth category. The first category and the second category are represented as a negative value of the congestion change rate, wherein the absolute value of the negative value of the first category is greater than the absolute value of the negative value of the second category, the third category is represented as a positive value of the congestion change rate and a congestion change amount with a value of 0, and the fourth category is represented as a positive value of the congestion change rate, and the positive value of the fourth category is greater than the positive value of the third category.

[0015] As a preferred solution of the digital twin city traffic light control system based on the Internet of Things described in the present invention, the classification logic of the concentration time corresponding to each congestion category includes:

[0016] The congestion change rate is cleaned, and the corresponding historical time points are converted into time periods at the hour level. The number of clusters is set to 4, and the congestion change rate is classified into various congestion categories. The labels of each congestion change rate are set with the congestion categories, and the labeled congestion change rate is input into the K-means algorithm to obtain the time period corresponding to each congestion category. The time period is expressed as A hours to B hours, where the value of A is less than B, and A and B are all distributed between 0 and 24. The time period corresponding to the fourth category is set as the concentrated time, and the concentrated time is expressed as the concentrated time of the historical day where the historical time point is located.

[0017] As a preferred solution of the digital twin city traffic light control system based on the Internet of Things described in the present invention, wherein: the air visibility and ground friction of each day in the first historical time period are obtained, and the concentrated time period corresponding to each day in the first historical time period is obtained;

[0018] The first value is set as the ideal air visibility, and the second value is set as the ideal ground friction. The concentrated time period corresponding to the ideal air visibility and the ideal ground friction is obtained, recorded as the ideal concentrated time period. The difference between the air visibility and ground friction of each day and the first value and the second value is calculated, recorded as the visibility difference and the friction difference. The difference between the corresponding concentrated time period and the ideal concentrated time period is calculated, recorded as the duration difference.

[0019] Calculate the weight of historical natural data, the calculation logic of the weight includes:

[0020] Multiple regression analysis was performed with visibility difference and friction difference as independent variables and duration difference as dependent variable to obtain the coefficient of visibility difference and the coefficient of friction difference. The coefficient of visibility difference and the coefficient of friction difference were set as the weight of air visibility and the weight of ground friction.

[0021] As a preferred solution of the digital twin city traffic light control system based on the Internet of Things described in the present invention, wherein: an interference function is constructed according to the weight, and the calculation expression of the interference function is:

[0022] ;

[0023] in, is the duration difference, Expressed as independent variables, For the The weights corresponding to the independent variables;

[0024] Input current natural data into the interference model, obtain the current duration difference, obtain the current day, obtain the concentrated time period corresponding to the current day, sum the current duration difference and the concentrated time period to obtain a first sum value, and set the first sum value as the new concentrated time period.

[0025] As a preferred solution of the digital twin city traffic light control system based on the Internet of Things described in the present invention, the modeling logic of the traffic model includes:

[0026] Obtain the historical time points, historical vehicle speeds, historical control signal phases, and control durations of the historical control signals of the target road section, perform missing value processing and outlier processing on the historical time points, historical vehicle speeds, historical control signal phases, and control durations of the historical control signals, divide the target road section into cells of a first length, wherein the length of the cell is greater than the length of the vehicle, and the cell can only accommodate one vehicle, obtain the cellized historical vehicle positions, and use the historical vehicle positions, historical vehicle speeds, and historical control signal phases as variables to extract the position matrix, speed matrix, and phase matrix, respectively;

[0027] Set the sampling time step. When there is a vehicle within the sampling time step, set the element corresponding to the position matrix to 1. Otherwise, set the element corresponding to the position matrix to 0. Normalize the historical vehicle speed so that the historical vehicle speed is distributed between 0 and 1. Assign the normalized historical vehicle speed to the element in the speed matrix. When the historical control signal phase is green, set the elements in the phase matrix corresponding to all cells on the target section to 1. Otherwise, set the elements in the phase matrix corresponding to all cells on the target section to 0.

[0028] The position matrix, speed matrix and phase matrix are encoded through DTSE encoding, and a deep learning model is selected. The encoded matrices are used as the input of the model, and the corresponding concentrated time period and the corresponding congestion change rate are used as output to construct a traffic model.

[0029] As a preferred solution of the digital twin city traffic light control system based on the Internet of Things described in the present invention, wherein: the corresponding historical control signal phase and the corresponding historical control signal control duration are input into the traffic model to obtain the concentrated time period and the congestion change rate, the corresponding historical natural data are obtained, and the new concentrated time period and the new congestion change rate are obtained through the interference function;

[0030] Setting the third value as the congestion change rate threshold, comparing the absolute value of the new congestion change rate with the congestion change amount threshold, and performing a first operation according to the comparison result, wherein the first operation includes changing the control duration of the control signal and sending a completion signal;

[0031] When the absolute value of the new congestion change rate is greater than or equal to the congestion change rate threshold, the first operation is set to change the control duration of the control signal, and the change includes continuous reduction or continuous increase until the absolute value of the new congestion change rate is less than the congestion change rate threshold, then stop changing the control duration of the control signal and send a completion signal; when the absolute value of the new congestion change rate is less than the congestion change rate threshold, the first operation is set to send a completion signal.

[0032] As a preferred solution of the digital twin city traffic light control system based on the Internet of Things described in the present invention, wherein: a first mapping relationship is established, and the first mapping relationship is expressed as a mapping relationship between natural data, a new concentrated time period of any day and the control duration of the control signal, and by inputting natural data and a new concentrated time period of any day, the corresponding control duration of the control signal is obtained.

[0033] The beneficial effects of the present invention are as follows: by real-time monitoring and analysis of changes in traffic flow and congestion, and by considering the influence of natural environmental factors, the system can intelligently adjust the timing plan of traffic lights, optimize the travel time allocation of traffic flow, and dynamically adjust the control strategy of traffic lights according to information such as traffic flow, as well as natural data such as weather conditions. By analyzing historical traffic data and natural data, the system can predict future traffic conditions and make corresponding traffic signal adjustments and route planning in advance. The application of Internet of Things technology enables remote monitoring and centralized management of traffic light control systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 A schematic diagram of the basic flow of a digital twin city traffic light control system based on the Internet of Things provided for one embodiment of the present invention. DETAILED DESCRIPTION

[0035] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0036] Example, see Figure 1 , as an embodiment of the present invention, provides a digital twin city traffic light control system based on the Internet of Things, including a collection module, an analysis module and a control module;

[0037] The acquisition module obtains historical traffic data and historical natural data of the target road section within the first historical time point;

[0038] The analysis module is used to calculate the congestion change rate based on historical traffic data, set congestion categories, perform cluster analysis on the congestion change rate based on the congestion categories, obtain the concentrated time period corresponding to each congestion category, obtain the historical natural data of each day in the first historical time period, obtain the concentrated time period corresponding to each day in the first historical time period, calculate the weight of the historical natural data, construct an interference function based on the weight, calculate the interference duration based on the interference function, and calculate a new concentrated time period based on the interference duration;

[0039] The control module models the target road section and its traffic data through the DTSE technology to obtain a traffic model, obtains a concentrated time period and a congestion change rate through the traffic model, obtains a new concentrated time period and a new congestion change rate through an interference function, sets a congestion change rate threshold, compares the new congestion change rate with the congestion change threshold, executes a first operation according to the comparison result, and establishes a first mapping relationship.

[0040] By real-time monitoring and analysis of traffic flow and congestion changes, as well as consideration of the impact of natural environmental factors, the present invention enables the system to intelligently adjust the timing of traffic lights, optimize the travel time allocation of traffic flow, and dynamically adjust the control strategy of traffic lights based on information such as traffic flow, as well as natural data such as weather conditions. By analyzing historical traffic data and natural data, the system can predict future traffic conditions and make corresponding traffic signal adjustments and route planning in advance. The application of Internet of Things technology enables remote monitoring and centralized management of traffic light control systems.

[0041] The historical traffic data includes historical time points, historical vehicle speeds, historical control signal phases, and control durations of historical control signals, wherein the historical vehicle speeds are expressed as the average speeds of vehicles on the target road section at the corresponding historical time points;

[0042] The historical natural data include air visibility and ground friction;

[0043] The historical time points are represented as various time points continuously monitored within a first historical time period, and the first historical time period represents a historical time period with a period of one year.

[0044] In specific implementation, based on historical vehicle speed data, the changes in vehicle speed in different time periods are understood, and combined with historical control signal phase and control duration information, the phase and duration of traffic lights can be accurately adjusted. For example, in periods when the average vehicle speed is higher, the green light duration can be appropriately extended to reduce the number of vehicle stops and waiting time, thereby improving the traffic efficiency at intersections. When the vehicle speed is lower, the green light duration can be reasonably shortened to avoid vehicle backlogs at intersections and reduce the occurrence of traffic congestion. By analyzing historical natural data on air visibility and ground friction, the system can adaptively adjust traffic signals according to weather changes. On foggy or rainy days with low visibility, the system will increase the duration of red lights and reduce vehicle speeds to improve driving safety. On icy and snowy weather with reduced ground friction, the system will adjust the phase difference of signal lights to ensure that vehicles have sufficient safety distance when turning or braking, reducing the risk of traffic accidents. A traffic flow prediction model is established using historical traffic data over a one-year period to predict traffic flow trends in different time periods in the future. Based on the prediction results, the intelligent traffic information release system provides drivers with traffic flow information and recommended routes in advance, guides vehicles to divert reasonably, avoids traffic congestion in a certain direction or section, and achieves a balanced distribution of traffic flow.

[0045] The calculation logic of the congestion degree change rate includes:

[0046] Adjacent historical time points and corresponding historical vehicle speeds are obtained, the difference between adjacent historical time points is calculated and recorded as a first difference, the difference between the corresponding historical vehicle speeds is calculated and recorded as a second difference, the ratio of the second difference to the first difference is calculated, and the absolute value of the ratio is taken, and the absolute value of the ratio is taken as a positive value or a negative value, and the absolute value of the ratio after the positive or negative value is set as the congestion change rate, when the subsequent historical vehicle speed is greater than the previous historical vehicle speed, the absolute value of the ratio is taken as a positive value, and when the subsequent historical vehicle speed is less than the previous vehicle speed, the absolute value of the ratio is taken as a negative value.

[0047] In specific implementation, the positive and negative values ​​of the congestion change rate can dynamically reflect the upward or downward trend of traffic flow speed. When the speed of the next historical vehicle is greater than the previous one, the congestion change rate is positive, indicating that the traffic flow speed is accelerating and the traffic state may be changing from congestion to smooth traffic; conversely, when the speed of the next historical vehicle is less than the previous one, the congestion change rate is negative, indicating that the traffic flow speed is slowing down and the traffic state may be changing from smooth traffic to congestion. Capturing this dynamic change helps to grasp the traffic situation in a timely manner and provide real-time information for traffic management and dispatching.

[0048] The congestion category is expressed as a category of the congestion level of the target road section at the current moment relative to the previous moment, and the congestion categories include a first category, a second category, a third category and a fourth category. The first category and the second category are expressed as a negative value of the congestion change rate, wherein the absolute value of the negative value of the first category is greater than the absolute value of the negative value of the second category. The third category is expressed as a positive value of the congestion change rate and a congestion change amount of 0. The fourth category is expressed as a positive value of the congestion change rate, and the positive value of the fourth category is greater than the positive value of the third category.

[0049] In specific implementation, the system can dynamically adjust the timing of traffic lights according to different categories of congestion change rates. For example, when traffic congestion intensifies (the first category), the system extends the green light duration in the congested direction and shortens the green light duration in other directions to ease congestion pressure; and when traffic congestion is relieved (the third or fourth category), the system appropriately adjusts the phase difference and duration of the traffic lights to improve the traffic efficiency of the intersection, and predicts future traffic congestion trends based on historical data and real-time monitoring data, combined with the classification of congestion change rates. For example, when the congestion change rates at multiple consecutive time points belong to the first category, the system predicts that traffic congestion will further intensify and prepares countermeasures in advance.

[0050] The classification logic of the concentration time corresponding to each congestion category includes:

[0051] The congestion change rate is cleaned, and the corresponding historical time points are converted into time periods at the hour level. The number of clusters is set to 4, and the congestion change rate is classified into various congestion categories. The labels of each congestion change rate are set with the congestion categories, and the labeled congestion change rate is input into the K-means algorithm to obtain the time period corresponding to each congestion category. The time period is expressed as A hours to B hours, where the value of A is less than B, and A and B are all distributed between 0 and 24. The time period corresponding to the fourth category is set as the concentrated time, and the concentrated time is expressed as the concentrated time of the historical day where the historical time point is located.

[0052] In specific implementation, by classifying the rate of change of congestion and determining the concentrated time period, the traffic management department can formulate traffic management strategies more targetedly. For example, in the concentrated time period corresponding to the fourth category, the traffic flow is large, and the green light duration of the traffic lights is increased to improve the traffic efficiency of the intersection. According to the concentrated time period corresponding to each congestion category, the control scheme of the traffic lights is dynamically adjusted. In the time period with a high rate of change of congestion, the green light duration in the congested direction is appropriately extended; in the time period with a low rate of change of congestion, the signal light duration is reasonably allocated to ensure smooth traffic flow in all directions.

[0053] Obtain the air visibility and ground friction of each day in the first historical time period, and obtain the concentrated time period corresponding to each day in the first historical time period;

[0054] The first value is set as the ideal air visibility, and the second value is set as the ideal ground friction. The concentrated time period corresponding to the ideal air visibility and the ideal ground friction is obtained, recorded as the ideal concentrated time period. The difference between the air visibility and ground friction of each day and the first value and the second value is calculated, recorded as the visibility difference and the friction difference. The difference between the corresponding concentrated time period and the ideal concentrated time period is calculated, recorded as the duration difference.

[0055] Calculate the weight of historical natural data, the calculation logic of the weight includes:

[0056] Multiple regression analysis was performed with visibility difference and friction difference as independent variables and duration difference as dependent variable to obtain the coefficient of visibility difference and the coefficient of friction difference. The coefficient of visibility difference and the coefficient of friction difference were set as the weight of air visibility and the weight of ground friction.

[0057] An interference function is constructed according to the weights, and the calculation expression of the interference function is:

[0058] ;

[0059] in, is the duration difference, Expressed as independent variables, For the The weights corresponding to the independent variables;

[0060] Input current natural data into the interference model, obtain the current duration difference, obtain the current day, obtain the concentrated time period corresponding to the current day, sum the current duration difference and the concentrated time period to obtain a first sum value, and set the first sum value as the new concentrated time period.

[0061] In specific implementation, by calculating the weights of air visibility and ground friction, the impact of these natural factors on traffic congestion can be more accurately assessed. When making traffic forecasts, changes in natural conditions can be better considered, the accuracy of forecast results can be improved, and after understanding the impact of air visibility and ground friction on traffic congestion, traffic management departments can formulate traffic management strategies more targeted. For example, in weather conditions with low visibility or poor ground friction, measures can be taken in advance, such as adjusting the timing of traffic lights and issuing traffic warning information, to alleviate traffic congestion. The calculation of weights provides a scientific basis for traffic decision-making. When formulating traffic planning and management plans, the impact of natural factors such as air visibility and ground friction is comprehensively considered to make decisions more scientific and reasonable.

[0062] The modeling logic of the traffic model includes:

[0063] Obtain the historical time points, historical vehicle speeds, historical control signal phases, and control durations of the historical control signals of the target road section, perform missing value processing and outlier processing on the historical time points, historical vehicle speeds, historical control signal phases, and control durations of the historical control signals, divide the target road section into cells of a first length, wherein the length of the cell is greater than the length of the vehicle, and the cell can only accommodate one vehicle, obtain the cellized historical vehicle positions, and use the historical vehicle positions, historical vehicle speeds, and historical control signal phases as variables to extract the position matrix, speed matrix, and phase matrix, respectively;

[0064] Set the sampling time step. When there is a vehicle within the sampling time step, set the element corresponding to the position matrix to 1. Otherwise, set the element corresponding to the position matrix to 0. Normalize the historical vehicle speed so that the historical vehicle speed is distributed between 0 and 1. Assign the normalized historical vehicle speed to the element in the speed matrix. When the historical control signal phase is green, set the elements in the phase matrix corresponding to all cells on the target section to 1. Otherwise, set the elements in the phase matrix corresponding to all cells on the target section to 0.

[0065] The position matrix, speed matrix and phase matrix are encoded through DTSE encoding, and a deep learning model is selected. The encoded matrices are used as the input of the model, and the corresponding concentrated time period and the corresponding congestion change rate are used as output to construct a traffic model.

[0066] Inputting the corresponding historical control signal phase and the corresponding historical control signal control duration into the traffic model, obtaining the concentrated time period and the congestion change rate, acquiring the corresponding historical natural data, and obtaining a new concentrated time period and a new congestion change rate through an interference function;

[0067] Setting the third value as the congestion change rate threshold, comparing the absolute value of the new congestion change rate with the congestion change amount threshold, and performing a first operation according to the comparison result, wherein the first operation includes changing the control duration of the control signal and sending a completion signal;

[0068] When the absolute value of the new congestion change rate is greater than or equal to the congestion change rate threshold, the first operation is set to change the control duration of the control signal, and the change includes continuous reduction or continuous increase until the absolute value of the new congestion change rate is less than the congestion change rate threshold, then stop changing the control duration of the control signal and send a completion signal; when the absolute value of the new congestion change rate is less than the congestion change rate threshold, the first operation is set to send a completion signal.

[0069] In specific implementation, the deep learning model can analyze and learn the encoded traffic data, capture the complex relationship between multiple factors such as traffic flow, vehicle speed, and signal control, and thus improve the accuracy of traffic forecasts. The model can provide optimization suggestions for traffic signal control based on the predicted concentrated time period and congestion change rate. For example, in the concentrated time period when the traffic congestion is predicted to be high and lasting for a long time, the green light duration is extended to improve the traffic efficiency of the intersection.

[0070] A first mapping relationship is established, wherein the first mapping relationship is represented as a mapping relationship between natural data, a new concentrated time period of any day and a control duration of a control signal, and the corresponding control duration of the control signal is obtained by inputting natural data and a new concentrated time period of any day.

[0071] In a specific implementation, by establishing the first mapping relationship, the traffic signal control system automatically adjusts the control duration of the traffic light according to real-time natural data and traffic conditions without manual intervention, thereby realizing intelligent traffic signal control.

[0072] By real-time monitoring and analysis of traffic flow and congestion changes, as well as consideration of the impact of natural environmental factors, the present invention enables the system to intelligently adjust the timing of traffic lights, optimize the travel time allocation of traffic flow, and dynamically adjust the control strategy of traffic lights based on information such as traffic flow, as well as natural data such as weather conditions. By analyzing historical traffic data and natural data, the system can predict future traffic conditions and make corresponding traffic signal adjustments and route planning in advance. The application of Internet of Things technology enables remote monitoring and centralized management of traffic light control systems.

[0073] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program codes. Wherein, the storage medium is implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0074] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions of the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention should be included in the scope of the claims of the present invention.

Claims

1. The digital twin city traffic light control system based on the Internet of Things is characterized by: It includes an acquisition module, an analysis module and a control module; The acquisition module acquires historical traffic data and historical natural data of the target road section within the first historical time point period, wherein the historical traffic data includes historical time points, historical vehicle speeds, historical control signal phases, and control durations of historical control signals, wherein the historical vehicle speeds are represented as average speeds of vehicles on the target road section at corresponding historical time points, and the historical natural data include air visibility and ground friction, wherein the historical time points are represented as various time points continuously monitored within the first historical time period, and wherein the first historical time period represents a historical time period with a period of one year; The analysis module is used to calculate the congestion change rate based on historical traffic data, set congestion categories, perform cluster analysis on the congestion change rate based on the congestion categories, obtain the concentrated time period corresponding to each congestion category, obtain the historical natural data of each day in the first historical time period, obtain the concentrated time period corresponding to each day in the first historical time period, calculate the weight of the historical natural data, construct an interference function based on the weight, calculate the interference duration based on the interference function, and calculate a new concentrated time period based on the interference duration; The control module models the target road section and its traffic data through the DTSE technology to obtain a traffic model, inputs the corresponding historical control signal phase and the corresponding historical control signal control duration into the traffic model, obtains the concentrated time period and the congestion change rate, obtains the corresponding historical natural data, obtains a new concentrated time period and a new congestion change rate through the interference function, sets the third value as the congestion change rate threshold, compares the absolute value of the new congestion change rate with the congestion change threshold, and performs a first operation according to the comparison result, wherein the first operation includes changing the control duration of the control signal and sending a completion signal, and when the absolute value of the new congestion change rate When it is greater than or equal to the congestion change rate threshold, the first operation is set to change the control duration of the control signal, and the change includes continuous reduction or continuous increase until the absolute value of the new congestion change rate is less than the congestion change rate threshold, then stop changing the control duration of the control signal and send a completion signal. When the absolute value of the new congestion change rate is less than the congestion change rate threshold, the first operation is set to send a completion signal and establish a first mapping relationship. The first mapping relationship is represented by a mapping relationship between natural data, a new concentrated time period of any day, and the control duration of the control signal. By inputting natural data and a concentrated time period of any day, the corresponding control duration of the control signal is obtained.

2. The digital twin city traffic light control system based on the Internet of Things as claimed in claim 1, characterized in that: The calculation logic of the congestion degree change rate includes: Adjacent historical time points and corresponding historical vehicle speeds are obtained, the difference between adjacent historical time points is calculated and recorded as a first difference, the difference between the corresponding historical vehicle speeds is calculated and recorded as a second difference, the ratio of the second difference to the first difference is calculated, and the absolute value of the ratio is taken, and the absolute value of the ratio is taken as a positive value or a negative value, and the absolute value of the ratio after the positive or negative value is set as the congestion change rate, when the subsequent historical vehicle speed is greater than the previous historical vehicle speed, the absolute value of the ratio is taken as a positive value, and when the subsequent historical vehicle speed is less than the previous vehicle speed, the absolute value of the ratio is taken as a negative value.

3. The digital twin city traffic light control system based on the Internet of Things as claimed in claim 1, characterized in that: The congestion category is expressed as a category of the congestion level of the target road section at the current moment relative to the previous moment, and the congestion categories include a first category, a second category, a third category and a fourth category. The first category and the second category are expressed as a negative value of the congestion change rate, wherein the absolute value of the negative value of the first category is greater than the absolute value of the negative value of the second category. The third category is expressed as a positive value of the congestion change rate and a congestion change amount of 0. The fourth category is expressed as a positive value of the congestion change rate, and the positive value of the fourth category is greater than the positive value of the third category.

4. The digital twin city traffic light control system based on the Internet of Things as claimed in claim 1, characterized in that: The classification logic of the concentration time corresponding to each congestion category includes: The congestion change rate is cleaned, and the corresponding historical time points are converted into time periods at the hour level. The number of clusters is set to 4, and the congestion change rate is classified into various congestion categories. The labels of each congestion change rate are set with the congestion categories, and the labeled congestion change rate is input into the K-means algorithm to obtain the time period corresponding to each congestion category. The time period is expressed as A hours to B hours, where the value of A is less than B, and A and B are all distributed between 0 and 24. The time period corresponding to the fourth category is set as the concentrated time, and the concentrated time is expressed as the concentrated time of the historical day where the historical time point is located.

5. The digital twin city traffic light control system based on the Internet of Things as claimed in claim 1, characterized in that: Obtain the air visibility and ground friction of each day in the first historical time period, and obtain the concentrated time period corresponding to each day in the first historical time period; The first value is set as the ideal air visibility, and the second value is set as the ideal ground friction. The concentrated time period corresponding to the ideal air visibility and the ideal ground friction is obtained, recorded as the ideal concentrated time period. The difference between the air visibility and ground friction of each day and the first value and the second value is calculated, recorded as the visibility difference and the friction difference. The difference between the corresponding concentrated time period and the ideal concentrated time period is calculated, recorded as the duration difference. The weight of historical natural data is calculated, and the calculation logic of the weight includes: Multiple regression analysis was performed with visibility difference and friction difference as independent variables and duration difference as dependent variable to obtain the coefficient of visibility difference and the coefficient of friction difference. The coefficient of visibility difference and the coefficient of friction difference were set as the weight of air visibility and the weight of ground friction.

6. The digital twin city traffic light control system based on the Internet of Things as claimed in claim 5, characterized in that: An interference function is constructed according to the weights, and the calculation expression of the interference function is: ； in, is the duration difference, Expressed as independent variables, For the The weights corresponding to the independent variables; Input current natural data into the interference model, obtain the current duration difference, obtain the current day, obtain the concentrated time period corresponding to the current day, sum the current duration difference and the concentrated time period to obtain a first sum value, and set the first sum value as the new concentrated time period.

7. The digital twin city traffic light control system based on the Internet of Things as claimed in claim 1, characterized in that: The modeling logic of the traffic model includes: Obtain the historical time points, historical vehicle speeds, historical control signal phases, and control durations of the historical control signals of the target road section, perform missing value processing and outlier processing on the historical time points, historical vehicle speeds, historical control signal phases, and control durations of the historical control signals, divide the target road section into cells of a first length, wherein the length of the cell is greater than the length of the vehicle, and the cell can only accommodate one vehicle, obtain the cellized historical vehicle positions, and use the historical vehicle positions, historical vehicle speeds, and historical control signal phases as variables to extract the position matrix, speed matrix, and phase matrix, respectively; Set the sampling time step. When there is a vehicle within the sampling time step, set the element corresponding to the position matrix to 1. Otherwise, set the element corresponding to the position matrix to 0. Normalize the historical vehicle speed so that the historical vehicle speed is distributed between 0 and 1. Assign the normalized historical vehicle speed to the element in the speed matrix. When the historical control signal phase is green, set the elements in the phase matrix corresponding to all cells on the target section to 1. Otherwise, set the elements in the phase matrix corresponding to all cells on the target section to 0. The position matrix, speed matrix and phase matrix are encoded through DTSE encoding, and a deep learning model is selected. The encoded matrices are used as the input of the model, and the corresponding concentrated time period and the corresponding congestion change rate are used as output to construct a traffic model.

Images