Smart city traffic jam identification and dispersion system based on big data

Abstract

The invention relates to the technical field of urban traffic management, in particular to a smart urban traffic jam identification and dispersion system based on big data. The system comprises an urban traffic congestion identification module, a traffic dispersion road section division module, a congestion dispersion road section simulation module, a signal lamp timing dispersion scheme generation module and a signal lamp timing dispersion scheme regulation and control module. The traffic congestion of each traffic road section in urban traffic is identified by combining a neural network technology, the traffic congestion of the traffic road section is efficiently and accurately identified, and the traffic dispersion conditions of each traffic road section under different signal lamp timing schemes are simulated by combining a simulation technology. And analyzing data such as the balance of each connecting road section and the dispersion effect of each traffic road section under the dispersion scheme, and selecting a signal lamp timing scheme with the best dispersion comprehensive effect to perform traffic congestion dispersion in combination with the actual predictability of the traffic road sections.

Description

Technical Field

[0001] The present invention relates to the technical field of urban traffic management, and more specifically, to a smart city traffic congestion identification and relief system based on big data. Background Art

[0002] With the acceleration of urbanization, urban traffic problems have become increasingly prominent, especially traffic congestion, which has become an important factor restricting urban development. At present, the rapid development of big data technology has provided a new opportunity to solve the problem of urban traffic congestion. By collecting and analyzing urban traffic data, real-time monitoring of traffic conditions can be achieved, providing a scientific basis for traffic management. However, the existing urban traffic management systems based on big data mostly remain at the level of data collection and display, lacking accurate identification of traffic congestion and effective means of diversion.

[0003] In terms of traffic diversion, existing diversion schemes often lack pertinence and flexibility. Traditional diversion methods usually rely on on-site command by traffic police or fixed signal light timing schemes, which are often ineffective when faced with sudden congestion or complex traffic conditions. Therefore, there is a need for an intelligent diversion system that can dynamically adjust the signal light timing scheme according to traffic congestion conditions.

[0004] In view of the above problems, the present invention proposes a smart city traffic congestion identification and relief system based on big data. Summary of the invention

[0005] In view of the shortcomings of the prior art, the purpose of the present invention is to provide a smart city traffic congestion identification and relief system based on big data.

[0006] To achieve the above object, the present invention provides the following technical solutions: A smart city traffic congestion identification and diversion system based on big data, including an urban traffic congestion identification module, a traffic diversion section division module, a congestion diversion section simulation module, a signal light timing diversion scheme generation module, and a signal light timing diversion scheme control module; The urban traffic congestion identification module: determines all traffic sections of urban traffic, determines the traffic congestion identification index of each traffic section in real time, and determines whether a congested section occurs based on the comparison result between the traffic congestion identification index and the traffic congestion identification boundary index; The traffic diversion road section division module: when a congested road section appears, the current time is marked as the congested time, and the target diversion road section is determined; The congestion relief section simulation module is used to construct a congestion relief section simulation model; The signal light timing and diversion scheme generation module: the congestion diversion section simulation model generates g signal light timing schemes, and determines the scheme diversion index of each signal light timing scheme; The signal light timing and diversion scheme control module selects a diversion signal light timing implementation scheme from the signal light timing scheme, and uses the diversion signal light timing implementation scheme to control the signal light timing.

[0007] Furthermore, the traffic congestion identification index of a traffic section is determined based on the following method: determine a traffic section, collect actual multi-dimensional traffic data of the traffic section in real time, obtain a traffic congestion identification model, input the actual multi-dimensional traffic data into the traffic congestion identification model, and the traffic congestion identification model outputs the traffic congestion identification index of the traffic section.

[0008] Furthermore, the traffic diversion radius is determined based on the traffic congestion identification index of the congested section, and the midpoint of the congested section is determined. A circle is drawn with the midpoint of the congested section as the center and the traffic diversion radius as the radius to obtain the traffic diversion range, and the remaining traffic sections within the traffic diversion range are marked as target diversion sections.

[0009] Furthermore, the traffic diversion radius is determined based on the traffic congestion identification index of the congested road section: Obtaining the traffic congestion identification index of the congested road section , set the traffic congestion recognition coefficient to Vm, through Determine the traffic diversion radius.

[0010] Furthermore, the scheme diversion index of the signal light timing scheme is determined based on the following method: after the implementation of the signal light timing scheme in the congestion diversion section simulation model begins, The duration determines the comprehensive balance index of the congestion relief section simulation model. After the implementation of the congestion relief section simulation model, the signal light timing plan determines the actual simulation difference index of each traffic section in the congestion relief section simulation model. , and mark the total implementation time of the signal light timing plan as , and simultaneously determine the section equilibrium optimization index of the congestion relief section simulation model ,pass Calculate the traffic light timing scheme's plan guidance index .

[0011] Furthermore, the actual simulation difference index of the traffic section is determined based on the following method: performing time and value calculation on the congestion moment and the total implementation time of the signal timing plan to obtain the congestion end time, determining a traffic section, determining the traffic congestion identification index of the traffic section after the implementation of the congestion relief section simulation model, and marking the traffic congestion identification index as the simulated traffic congestion index, obtaining the traffic congestion identification index of the traffic section at the end time of congestion in the previous n days, summing and averaging the traffic congestion identification indexes at the end time of congestion in the previous n days to obtain the actual traffic congestion index, performing absolute difference calculation on the simulated traffic congestion index and the actual traffic congestion index to obtain the actual simulation difference index of the traffic section.

[0012] Furthermore, the section balance optimization index of the congestion relief section simulation model is determined based on the following method: collecting the comprehensive balance indexes of all sections of the congestion relief section simulation model, summing up the average of all the comprehensive balance indexes of the sections, and calculating the average section comprehensive balance index , sort the comprehensive balance indexes of all sections according to the order of the determined time, compare the comprehensive balance index of the next adjacent section after sorting with the comprehensive balance index of the previous section, and when the comprehensive balance index of the next section is greater than the comprehensive balance index of the previous section, increase the number of diversion progress by one, and mark the number of diversion progress as ,pass Determine the section equilibrium optimization index of the congestion relief section simulation model .

[0013] Furthermore, the comprehensive balance index of the congestion relief section simulation model is determined based on the following method: The traffic congestion identification index of each traffic section in the congestion relief section simulation model is determined by the duration, every two traffic sections with connection relationship in the congestion relief section simulation model are counted as a connection section group, the connection balance index of each connection section group is obtained, the connection balance index of all the connection section groups is summed and averaged, and the comprehensive balance index of the section of the congestion relief section simulation model is calculated.

[0014] Furthermore, the connection balance index of the connection section group is determined based on the following method: the traffic congestion identification index of two traffic sections in the connection section group is calculated by absolute difference, and the traffic congestion difference index is calculated. , the traffic congestion identification index of the two traffic sections in the connecting section group is calculated and the calculated value is ,pass Determine the connection balance index of the connection segment group , where c1 is the first coefficient and c2 is the second coefficient.

[0015] Furthermore, the actual multi-dimensional traffic data and expected multi-dimensional traffic data of the congested sections are collected, and the actual multi-dimensional traffic data of all target relief sections are collected simultaneously. The actual multi-dimensional traffic data and the expected multi-dimensional traffic data of the congested sections as well as the actual multi-dimensional traffic data of the target relief sections are input into the congestion relief section simulation model, and the congestion relief section simulation model generates g signal light timing plans.

[0016] Compared with the prior art, the present invention has the following beneficial effects: Through the urban traffic congestion identification module, the traffic diversion section division module, and the congestion diversion section simulation module, the traffic congestion of each traffic section in the urban traffic is identified in combination with the neural network technology, ensuring efficient and accurate identification of the congestion of the traffic section. After the congested section is found, the traffic diversion range is quickly locked according to the actual situation of the congested section, and the corresponding target diversion section is determined to facilitate the determination and implementation of the subsequent diversion plan. Through the signal light timing diversion plan generation module and the signal light timing diversion plan control module, combined with the simulation technology, the traffic diversion situation of each traffic section under different signal light timing plans is simulated, and the balance of each connecting section under the diversion plan, the diversion effect of each traffic section and other data are analyzed. In combination with the actual predictability of the traffic section, the signal light timing plan with the best comprehensive diversion effect is selected to divert the traffic congestion, effectively ensuring the normal operation of urban traffic and improving the intelligent management level of urban traffic. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a module block diagram of the smart city traffic congestion identification and diversion system based on big data; Figure 2 It is the system operation flow chart; Figure 3 A flow chart for determining the target diversion section; Figure 4 The flowchart for determining the traffic congestion identification index is shown in FIG. DETAILED DESCRIPTION

[0018] Reference Figures 1 to 4 The smart city traffic congestion identification and diversion system based on big data includes an urban traffic congestion identification module, a traffic diversion section division module, a congestion diversion section simulation module, a signal light timing diversion plan generation module, and a signal light timing diversion plan control module.

[0019] Urban traffic congestion identification module: determine all traffic sections of urban traffic, determine the traffic congestion identification index of each traffic section in real time, set the traffic congestion identification boundary index (the traffic congestion identification boundary index is a preset index used for comparison with the traffic congestion identification index), and when the traffic congestion identification index of a traffic section is greater than the traffic congestion identification boundary index, mark the traffic section as a congested section.

[0020] The traffic congestion identification index of a traffic section is determined based on the following method: determine a traffic section, collect the actual multi-dimensional traffic data of the traffic section in real time (the actual multi-dimensional traffic data includes the actual intersection queue length, actual traffic flow data, the actual section average speed, and the actual section occupancy rate), obtain a traffic congestion identification model, input the actual multi-dimensional traffic data into the traffic congestion identification model, and the traffic congestion identification model outputs the traffic congestion identification index of the traffic section.

[0021] The traffic congestion recognition model is obtained based on the following method: construct a neural network model, collect i actual multi-dimensional traffic data, train the neural network model through the actual multi-dimensional traffic data, assign a traffic congestion recognition index to each training data, and the index range of the traffic congestion recognition index is (10.0~100.0). The larger the traffic congestion recognition index is, the more congested the corresponding traffic section is. The training data is divided into a training set, a validation set, and a test set, with a ratio of 70%:15%:15%. The training set is used to train the model, and the parameters of the model are continuously adjusted to minimize the value of the loss function. During the training process, the validation set is used to monitor the performance of the model to avoid overfitting, and the trained model is evaluated using the test set. Finally, the traffic congestion recognition model is obtained.

[0022] Traffic diversion section division module: When a congested section appears, the current moment is marked as the congested moment, the traffic diversion radius is determined based on the traffic congestion identification index of the congested section, and the midpoint of the congested section is determined. A circle is drawn with the midpoint of the congested section as the center and the traffic diversion radius as the radius to obtain the traffic diversion range, and the remaining traffic sections within the traffic diversion range are marked as target diversion sections (if only part of a traffic section is within the traffic diversion range, the traffic section will not be marked as a target diversion section).

[0023] Determine the traffic diversion radius based on the traffic congestion identification index of the congested road section: Obtain the traffic congestion identification index of the congested road section , set the traffic congestion identification coefficient to Vm, m=1, 2, ..., M, V1<V2<...<VM-1<VM, each traffic congestion identification coefficient corresponds to a traffic congestion identification index within a range, and the index range of the traffic congestion identification index includes (0, ],( , ], …, ( , ], when the traffic congestion identification index of the congested road section ∈(0, ], the traffic congestion recognition coefficient is V1, through Determine the traffic diversion radius.

[0024] The midpoint of the congested road section is determined based on the following method: the geographic coordinates (usually longitude and latitude) of the two end points of the congested road section are obtained from the Geographic Information System (GIS) or related map data. Assume that the coordinates of the two end points of the congested road section are and , according to the midpoint coordinate calculation formula, calculate the midpoint M coordinate of the congested road section, , ,in, It is the midpoint coordinate of the congested road section.

[0025] Congestion relief section simulation module: Based on the topological structure information and basic parameters of the congested sections and target relief sections, a congestion relief section simulation model is constructed, and the actual multi-dimensional traffic data and expected multi-dimensional traffic data of the congested sections are collected (the expected multi-dimensional traffic data include the expected intersection queue length, expected traffic flow data, expected section average vehicle speed, expected section occupancy rate, and the expected multi-dimensional traffic data of each traffic section are pre-set data for determining that the traffic is not congested). The actual multi-dimensional traffic data of all target relief sections are simultaneously collected, and the actual multi-dimensional traffic data of the congested sections, the expected multi-dimensional traffic data, and the actual multi-dimensional traffic data of the target relief sections are input into the congestion relief section simulation model.

[0026] The congestion relief section simulation model is constructed based on the following method: select traffic simulation software (the traffic simulation software can be VISSIM or PARAMICS), collect the topological structure information of congested sections and target relief sections in urban traffic, the topological structure information includes the connection relationship between congested sections and target relief sections, intersection types (such as cross intersections, T-shaped intersections, etc.), collect basic parameters of congested sections and target relief sections, the basic parameters include road length, number of lanes, lane width, speed limit, and create a congestion relief section simulation model based on the topological structure information and basic parameters of congested sections and target relief sections.

[0027] Signal light timing and diversion scheme generation module: The congestion diversion section simulation model generates g signal light timing schemes (the signal light timing scheme controls the signal light timing of each traffic section in the congestion diversion section simulation model. By controlling the traffic light timing, the actual multi-dimensional traffic data of the congested section can be adjusted to the expected multi-dimensional traffic data), and determines the diversion index of each signal light timing scheme.

[0028] The scheme diversion index of the signal light timing scheme is determined based on the following method: after the implementation of the congestion diversion section simulation model of the signal light timing scheme begins, The duration determines the comprehensive balance index of the congestion relief section simulation model. After the implementation of the congestion relief section simulation model, the signal light timing plan determines the actual simulation difference index of each traffic section in the congestion relief section simulation model. , and mark the total implementation time of the signal light timing plan as , and simultaneously determine the section equilibrium optimization index of the congestion relief section simulation model ,pass Calculate the traffic light timing scheme's plan guidance index , where c3 is the third coefficient, and the value of c3 is 1.08.

[0029] The actual simulation difference index of the traffic section is determined in the following way: the congestion moment and the total implementation time of the signal light timing plan are calculated by time and value to obtain the congestion end time (for example, the congestion moment is 8:30 in the morning, the total implementation time of the signal light timing plan is 40 minutes, and the congestion end time is 8:30 plus 40 minutes, that is, 9:10). A traffic section is determined, and the traffic congestion identification index of the traffic section after the congestion relief section simulation model is implemented is determined, and the traffic congestion identification index is marked as the simulated traffic congestion index. The traffic congestion identification index of the traffic section before (in actual circumstances) is obtained. The traffic congestion identification index at the end of the congestion of the past n days is calculated by summing up the average of the traffic congestion identification indexes at the end of the congestion of n days to obtain the actual traffic congestion index, and the absolute difference between the simulated traffic congestion index and the actual traffic congestion index is calculated to obtain the actual simulation difference index of the traffic section (the smaller the actual simulation difference index is, the more similar the traffic congestion situation of the traffic section at the same time today is to the previous one, which can ensure the predictability of the traffic section, that is, the traffic section will not have abnormal situations, avoiding increasing the uncertainty and anxiety of drivers traveling on the traffic section).

[0030] The section balance optimization index of the congestion relief section simulation model is determined based on the following method: collect the comprehensive balance indexes of all sections of the congestion relief section simulation model, calculate the sum of the comprehensive balance indexes of all sections, and calculate the average section comprehensive balance index , sort the comprehensive balance indexes of all sections according to the order of the determined time, compare the comprehensive balance index of the next adjacent section after sorting with the comprehensive balance index of the previous section, and when the comprehensive balance index of the next section is greater than the comprehensive balance index of the previous section, increase the number of diversion progress by one (when the comprehensive balance index of the next section is less than or equal to the comprehensive balance index of the previous section, no further processing is performed), and mark the number of diversion progress as ,pass Determine the section equilibrium optimization index of the congestion relief section simulation model .

[0031] The comprehensive balance index of the congestion relief section simulation model is determined based on the following method: The traffic congestion identification index of each traffic section in the congestion relief section simulation model is determined by the duration, every two traffic sections with connection relationship in the congestion relief section simulation model are counted as a connection section group, the connection balance index of each connection section group is obtained, the connection balance index of all the connection section groups is summed and averaged, and the comprehensive balance index of the section of the congestion relief section simulation model is calculated.

[0032] The connection balance index of the connection section group is determined based on the following method: the traffic congestion identification index of two traffic sections in the connection section group is calculated by absolute difference calculation to obtain the traffic congestion gap index. , the traffic congestion identification index of the two traffic sections in the connecting section group is calculated and the calculated value is ,pass Determine the connection balance index of the connection segment group , where c1 is the first coefficient, c2 is the second coefficient, the value of c1 is 0.63, and the value of c2 is 0.28.

[0033] Traffic light timing and diversion scheme control module: select the traffic light timing scheme with the largest scheme diversion index value as the diversion signal light timing implementation scheme, and use the diversion signal light timing implementation scheme to control the traffic light timing.

[0034] Through the urban traffic congestion identification module, the traffic diversion section division module, and the congestion diversion section simulation module, the traffic congestion of each traffic section in the urban traffic is identified in combination with the neural network technology, ensuring efficient and accurate identification of the congestion of the traffic section. After the congested section is found, the traffic diversion range is quickly locked according to the actual situation of the congested section, and the corresponding target diversion section is determined to facilitate the determination and implementation of the subsequent diversion plan. Through the signal light timing diversion plan generation module and the signal light timing diversion plan control module, combined with the simulation technology, the traffic diversion situation of each traffic section under different signal light timing plans is simulated, and the balance of each connecting section under the diversion plan, the diversion effect of each traffic section and other data are analyzed. In combination with the actual predictability of the traffic section, the signal light timing plan with the best comprehensive diversion effect is selected to divert the traffic congestion, effectively ensuring the normal operation of urban traffic and improving the intelligent management level of urban traffic.

[0035] The above formulas are all dimensionless and numerical calculations are performed, and the preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0036] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0037] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0038] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0039] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0040] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0041] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0042] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A smart city traffic congestion identification and diversion system based on big data, characterized by: It includes urban traffic congestion identification module, traffic diversion section division module, congestion diversion section simulation module, signal light timing diversion plan generation module, and signal light timing diversion plan control module; The urban traffic congestion identification module: determines all traffic sections of urban traffic, determines the traffic congestion identification index of each traffic section in real time, and determines whether a congested section occurs based on the comparison result between the traffic congestion identification index and the traffic congestion identification boundary index; The traffic diversion road section division module: when a congested road section appears, the current time is marked as the congested time, and the target diversion road section is determined; The congestion relief section simulation module is used to construct a congestion relief section simulation model; The signal light timing and diversion scheme generation module: the congestion diversion section simulation model generates g signal light timing schemes, and determines the scheme diversion index of each signal light timing scheme; The signal light timing and diversion scheme control module selects a diversion signal light timing implementation scheme from the signal light timing scheme, and uses the diversion signal light timing implementation scheme to control the signal light timing.

2. The smart city traffic congestion identification and diversion system based on big data according to claim 1 is characterized in that: The traffic congestion identification index of a traffic section is determined based on the following method: determine a traffic section, collect actual multi-dimensional traffic data of the traffic section in real time, obtain a traffic congestion identification model, input the actual multi-dimensional traffic data into the traffic congestion identification model, and the traffic congestion identification model outputs the traffic congestion identification index of the traffic section.

3. The smart city traffic congestion identification and diversion system based on big data according to claim 1 is characterized in that: The traffic diversion radius is determined based on the traffic congestion identification index of the congested section, and the midpoint of the congested section is determined. A circle is drawn with the midpoint of the congested section as the center and the traffic diversion radius as the radius to obtain the traffic diversion range. The remaining traffic sections within the traffic diversion range are marked as target diversion sections.

4. The smart city traffic congestion identification and diversion system based on big data according to claim 3 is characterized in that: Determine the traffic diversion radius based on the traffic congestion identification index of the congested road section: Obtain the traffic congestion identification index of the congested road section , set the traffic congestion recognition coefficient to Vm, through Determine the traffic diversion radius.

5. The smart city traffic congestion identification and diversion system based on big data according to claim 1 is characterized in that: The scheme diversion index of the signal light timing scheme is determined based on the following method: after the implementation of the congestion diversion section simulation model of the signal light timing scheme begins, The duration determines the comprehensive balance index of the congestion relief section simulation model. After the implementation of the congestion relief section simulation model, the signal light timing plan determines the actual simulation difference index of each traffic section in the congestion relief section simulation model. , and mark the total implementation time of the signal light timing plan as , and simultaneously determine the section equilibrium optimization index of the congestion relief section simulation model ,pass Calculate the traffic light timing scheme's plan guidance index .

6. The smart city traffic congestion identification and diversion system based on big data according to claim 5 is characterized in that: The actual simulation difference index of a traffic section is determined based on the following method: performing time and value calculation on the congestion moment and the total implementation time of the signal light timing plan to obtain the congestion end time, determining a traffic section, determining the traffic congestion identification index of the traffic section after the implementation of the congestion relief section simulation model, and marking the traffic congestion identification index as the simulated traffic congestion index, obtaining the traffic congestion identification index of the traffic section at the end time of congestion in the previous n days, summing and averaging the traffic congestion identification indexes at the end time of congestion in the previous n days to obtain the actual traffic congestion index, performing absolute difference calculation on the simulated traffic congestion index and the actual traffic congestion index to obtain the actual simulation difference index of the traffic section.

7. The smart city traffic congestion identification and diversion system based on big data according to claim 5 is characterized in that: The section balance optimization index of the congestion relief section simulation model is determined based on the following method: collect the comprehensive balance indexes of all sections of the congestion relief section simulation model, calculate the sum of the comprehensive balance indexes of all sections, and calculate the average section comprehensive balance index , sort the comprehensive balance indexes of all sections according to the order of the determined time, compare the comprehensive balance index of the next adjacent section after sorting with the comprehensive balance index of the previous section, and when the comprehensive balance index of the next section is greater than the comprehensive balance index of the previous section, increase the number of diversion progress by one, and mark the number of diversion progress as ,pass Determine the section equilibrium optimization index of the congestion relief section simulation model .

8. The smart city traffic congestion identification and diversion system based on big data according to claim 5 is characterized in that: The comprehensive balance index of the congestion relief section simulation model is determined based on the following method: The traffic congestion identification index of each traffic section in the congestion relief section simulation model is determined by the duration, every two traffic sections with connection relationship in the congestion relief section simulation model are counted as a connection section group, the connection balance index of each connection section group is obtained, the connection balance index of all the connection section groups is summed and averaged, and the comprehensive balance index of the section of the congestion relief section simulation model is calculated.

9. The smart city traffic congestion identification and diversion system based on big data according to claim 8 is characterized in that: The connection balance index of the connection section group is determined based on the following method: the traffic congestion identification index of two traffic sections in the connection section group is calculated by absolute difference calculation to obtain the traffic congestion gap index. , the traffic congestion identification index of the two traffic sections in the connecting section group is calculated and the calculated value is ,pass Determine the connection balance index of the connection segment group , where c1 is the first coefficient and c2 is the second coefficient.

10. The smart city traffic congestion identification and diversion system based on big data according to claim 1 is characterized in that: The actual multi-dimensional traffic data and expected multi-dimensional traffic data of the congested sections are collected, and the actual multi-dimensional traffic data of all target diversion sections are collected simultaneously. The actual multi-dimensional traffic data and expected multi-dimensional traffic data of the congested sections and the actual multi-dimensional traffic data of the target diversion sections are input into the congestion diversion section simulation model, and the congestion diversion section simulation model generates g signal light timing plans.

Images