CN113920739A - Traffic data driving framework based on information physical fusion system and construction method - Google Patents
Traffic data driving framework based on information physical fusion system and construction method Download PDFInfo
- Publication number
- CN113920739A CN113920739A CN202111269011.6A CN202111269011A CN113920739A CN 113920739 A CN113920739 A CN 113920739A CN 202111269011 A CN202111269011 A CN 202111269011A CN 113920739 A CN113920739 A CN 113920739A
- Authority
- CN
- China
- Prior art keywords
- data
- traffic
- vehicle
- road
- construction method
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/012—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from other sources than vehicle or roadside beacons, e.g. mobile networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/18—Network design, e.g. design based on topological or interconnect aspects of utility systems, piping, heating ventilation air conditioning [HVAC] or cabling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0133—Traffic data processing for classifying traffic situation
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Evolutionary Computation (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a traffic data driving framework based on an information physical fusion system and a construction method, wherein the construction method comprises the steps of urban road vehicle-mounted positioning equipment position acquisition, unmanned aerial vehicle video calculation, microscopic simulator simulation fusion and open source road network acquisition in a city-level range; a spatio-temporal data storage method; a data sharing and control scheme output method; sensor data are obtained through a network request mode by utilizing an http protocol and an Internet of things MQTT protocol, a road network resource file is obtained through a GraphML file protocol, real-time data of the unmanned aerial vehicle are obtained through a video stream access mode, and the collected data are preliminarily classified according to formatting; carrying out unified modeling on the multi-dimensional multilayer relation between the vehicle-road data; storing by using a distributed deployed database; the intelligent traffic travel algorithm is used for outputting a control scheme for optimizing the current traffic travel condition by data sharing and a data driving method, so that the traffic operation efficiency is improved.
Description
Technical Field
The invention belongs to the technical field of traffic data acquisition, analysis, storage and sharing, and particularly relates to a traffic data driving framework based on an information physical fusion system and a construction method.
Background
With the development of new infrastructure and the increasing perfection of digital city construction, the construction of smart cities becomes a new research hotspot. In the process of increasingly complete urban infrastructure, traffic plays a vital role in optimizing urban management and control and realizing facility data interconnection.
However, in the current research, the massive raw data generated by the infrastructure with the existing layout cannot be effectively used in solving the problem of intelligent transportation system construction. With the continuous generation of fragmented data, the structured storage of data also encounters great challenges, and in the data storage process, redundant data needs to be repeatedly cleaned and filtered to remove noise data, which causes unnecessary data processing cost. Data needed for solving common problems such as management and control decision and accident early warning in intelligent traffic are classified without unified standards, systems are independent of one another, and data fusion efficiency is low. On the other hand, a unique data engine system is lacked for solving the intelligent traffic problem in the information physical fusion system, the required data is subjected to low-delay and high-availability calculation, and the data is called for reliable deduction, so that the whole service flow from data calculation to data sharing is realized.
At present, the problem of traffic data fragmentation is solved by establishing a relational database method of each data type independently for storage; the results are simulated by separately collecting and processing data into a local historical data table, and calling the local historical data table to run some intelligent transportation algorithms.
Disclosure of Invention
The invention aims to provide a traffic data driving framework based on an information physical fusion system and a construction method thereof.
The specific technical scheme for realizing the purpose of the invention is as follows:
a construction method of a traffic data driving framework based on an information physical fusion system comprises the following specific steps:
s1: acquiring road data in an origin map database, constructing a road network model by taking intersections as nodes and roads between the intersections as connecting edges, numbering the intersections, and establishing relations by using source-target key values respectively;
s2: receiving GPS signals of vehicles of an operator in a city-level range, extracting activity data of the vehicles from the GPS signals through desensitization processing of a vehicle-mounted terminal service provider, wherein the data content comprises desensitized unique identification of the vehicles, acquisition time of each piece of data, longitude and latitude position information and direction angles of each vehicle; carrying out multi-dimensional multi-layer traffic data unified modeling on the vehicle identification and time relation in the extracted data and the road network relation in S1 according to the time sequence; taking the vehicle identification in the extracted data as a key, taking a time character string as a filtered, splicing the longitude and latitude subjected to GPS (global positioning system) deviation correction into a character string as a value, and storing the character string in a hash structure in a server Redis1 in a distributed deployed non-relational database cluster;
s3: unmanned aerial vehicle crossing monitoring module: a plurality of unmanned aerial vehicles are adopted to simultaneously acquire data at a plurality of traffic intersections in the city-level range, and the video stream transmitted back by the unmanned aerial vehicles is used for extracting the traffic flow of each traffic intersection at each moment by utilizing an image multi-target recognition and multi-target tracking algorithm and carrying out multi-source heterogeneous data unified modeling on the multi-dimensional multi-layer traffic data obtained in S2;
s4: storing the traffic flow of each traffic intersection at each moment of S3 in a server Redis2 in a distributed non-relational database cluster;
s5: storing the multi-source heterogeneous data model established in the S3 in a storage medium MySql;
s6: reading a time sequence in the storage medium MySql in S5, positioning longitude and latitude data of adjacent moments in a server Redis1 cache of S1 by using time and vehicle identification, calculating to obtain accurate speed data, and adding the accurate speed data into the storage medium MySql in S5 to realize distributed parallel calculation and storage of vehicle speed;
s7: reading road vehicle data stored in a storage medium MySql in S5 and traffic flow of a traffic intersection stored in a server Redis2 in S4, simulating real intersection traffic flow by using a microscopic simulator, and extracting activity data of a vehicle from a GPS signal to realize data fusion;
s8: data sharing is carried out on the result of the S7;
s9: inquiring congestion hot spot intersections;
s10: carrying out congestion dispersion on the congested intersections queried in the step S9 in a microscopic simulator by using an intelligent traffic algorithm, and storing dispersed vehicle running track data and calculated grid flow data in a server Redis3 in a distributed non-relational database cluster;
s11: the grid flow data in a server Redis3 in a non-relational database cluster is called, and a flow prediction algorithm is used for predicting whether congestion occurs in the future traffic in the current mode;
s12: if the overall waiting duration index in the predicted result is worse than the current overall waiting duration index, the data-driven method adjusts the parameters of the intelligent traffic algorithm, and returns to S11, otherwise, enters S13;
s13: and performing visualization deduction on the simulation data in the S12 in the three-dimensional scene.
Step S1, constructing a road network model: the intersections of the city are taken as nodes in the network, and the roads between the intersections are taken as connecting edges of the network; and attaching the traffic flow information on the road to the node and the connecting edge as a weight.
Step S2, the GPS deviation rectifying process includes the following steps: collecting GPS signals of an operator vehicle, extracting longitude and latitude positions at each moment, calculating the similarity between a positioned track point and a corresponding position in a road network, then calculating the similarity of all matched road sections, taking a road section to be matched with the maximum result as a target road section, and modifying the longitude and latitude of the position point to the target road section to enable the position point to be matched with a map road of the WGS84 standard.
Step S2, the unified modeling of the multi-dimensional multi-layer traffic data is specifically as follows:
dividing the constructed road network model into a bus driving layer and a subway layer, taking a nearest intersection of a bus stop point as a bus layer node, taking a nearest intersection of a subway station as a subway layer node, storing the number of vehicles and the speed of the vehicles near the current position at different nodes, associating the same nodes of different layers through indexes, and marking hierarchical numbers, thereby constructing a multilayer network; different layers are connected through the nodes of the layer, the node information of the layer where the vehicle is located is confirmed through time and the position of the vehicle in the GPS signal, and the vehicle information of the corresponding nodes in other layers is inquired through the nodes.
Step S7, simulating the traffic flow at the real intersection and extracting the activity data of the vehicle from the GPS signal by using the microscopic simulator, so as to implement data fusion, specifically: the traffic control method comprises the steps of adopting a microscopic simulator SUMO, inputting the number and speed of vehicles extracted from GPS signals on a real road into the SUMO as parameters, automatically generating driving behaviors on the road by the SUMO according to the number of the input vehicles, inputting the traffic flow of the real intersection as queuing parameters of the intersection in the simulator, and fusing the traffic flow of the intersection and the traffic flow data of the road to generate a traffic control model in the simulator.
Step S11, the method calls grid traffic data in the server Redis3 in the non-relational database cluster, and performs prediction using a traffic prediction algorithm, specifically: carrying out 32-by-32 grid fine processing on the collected vehicle position data; for each (i, j), defining it as the grid corresponding to the ith row from top to bottom and the jth column from left to right in the map, then at time interval t, the traffic flow into the grid and the traffic flow out of the grid are respectively defined as:
Tris the traffic trajectory in P, gkRepresenting the longitude and latitude coordinates of the geographic space, gkE (i, j) indicates that the longitude and latitude are positioned in the grid (i, j); thereby forming mesh flow data; and then, carrying out grid flow prediction on the urban road by adopting a graph convolution space-time attention mechanism model and a space-time similarity attention neural network algorithm to obtain the traffic flow conditions of each grid at the future time.
Step S3, the unified modeling of the multi-source heterogeneous data is specifically as follows:
expressing query relations among all data tables in a network form, extracting a hash structure between equipment, time and position from activity data of a vehicle extracted from a GPS signal, and expressing acquisition time, unique identification of the vehicle, current position longitude and current position dimensional data by using a server Redis 1; extracting the traffic flow of each traffic intersection at every moment by using an image multi-target recognition and multi-target tracking algorithm through the video stream transmitted back by the unmanned aerial vehicle, and establishing an intersection-vehicle number-time relation data table; and creating external connection between each kind of data in the storage medium MySql to form a multi-source heterogeneous data model.
The server Redis1, the server Redis2, the server Redis3 and the storage medium MySql are distributed; the storage medium MySql is used as a relational database, and the server Redis1, the server Redis2 and the server Redis3 are used as non-relational databases, are distributed in a mode of respectively starting different ports, and the process of realizing distributed data consistency is as follows: real-time data are stored in each server Redis firstly, are synchronized in a storage medium MySql after being inquired, and the double-write consistency of the database under the distributed mode is ensured by utilizing the principle of deleting cache firstly and then updating the database; a distributed lock is designed by using a storage medium and a server to ensure that read-write inconsistency abnormity occurs in the data storage medium and the server in a concurrent scene; the inaccurate uploading problem of the speed data of the vehicle is solved by reading the time sequence in the storage medium MySql, quickly inquiring the position of the vehicle in the hash table in the server Reids1, and then calculating the speed of the adjacent time and synchronizing the speed to the storage medium MySql.
The data sharing in step S8 specifically includes: and for the road vehicle simulation behavior generated after data fusion in the microscopic simulator, sending the road vehicle simulation behavior to a program call for inquiring the congested hot spot intersection in a http protocol mode aiming at a Get/Post network request mode of a user.
Step S10, the congestion evacuation with the intelligent traffic algorithm specifically includes: the intelligent traffic algorithm is a webster algorithm, congestion evacuation is carried out by inquiring congestion vehicle data of intersections, overall waiting time delay is reduced by adopting the webster algorithm, running track data of the evacuated vehicles are obtained, grid flow data are processed, and simulated vehicle running data and grid flow data are obtained.
A traffic data driving framework based on an information physical fusion system is constructed by the method.
The beneficial effects of the invention at least comprise:
(1) the invention designs a traffic data system based on data fusion, and provides a frame for solving the traffic trip pain point problem based on the data system. Matching an open source road network based on privately deployed vehicle positioning equipment and unmanned aerial vehicle monitoring equipment; then modeling the multi-source heterogeneous data returned by the acquisition system; building a distributed data storage medium in a server by utilizing relational and non-relational databases; and fusing a data processing algorithm in the data calling process to generate gridding flow data. The idea of classification and required processing method for data sources in the construction process of the traffic database system is provided.
(2) The invention solves the problem of traffic jam based on the data-driven thought, and obtains a jam leading scheme. The method comprises the steps of analyzing multi-scale attributes such as node centrality, betweenness centers and community structures of a traffic network by using a complex network theory, carrying out congestion dredging by using a control algorithm aiming at areas with traffic congestion, predicting urban flow after dredging by using a graph convolution space-time attention mechanism, and ensuring the efficiency of traffic travel by using the obtained overall waiting delay index change.
Drawings
FIG. 1 is a flow chart of a construction method of the present invention;
FIG. 2 is a schematic of the data storage of the present invention;
FIG. 3 is a multi-dimensional multi-level data unified modeling diagram of the present invention;
FIG. 4 is a schematic diagram of the unified modeling of multi-source heterogeneous data according to the present invention;
FIG. 5 is a diagram illustrating a statistical number of vehicles query result according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a result of calculating video data of an unmanned aerial vehicle according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of a traffic simulator data deduction according to an embodiment of the present invention;
fig. 8 is a schematic diagram illustrating traffic control deduction in a three-dimensional scene according to an embodiment of the present invention;
fig. 9 is a diagram illustrating a result of optimizing the overall waiting duration of traffic grooming according to the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in detail with reference to the accompanying drawings and embodiments.
Referring to fig. 1, the open source road network obtaining method of the present invention comprises: introducing an open source road network library into the data system, configuring a script for automatically processing road network information, when a user inputs a city name, automatically generating road topology data of the city through the script, taking intersections as nodes, taking roads between the intersections as connecting edges to construct a road network model, numbering the intersections, and establishing a relationship by using source-target key value pairs respectively.
The operator vehicle GPS signal data processing method of the invention is: and through desensitization processing of a vehicle-mounted terminal service provider, activity data of the vehicle are extracted from the GPS signals, and the data content comprises a desensitized unique vehicle identifier, the acquisition time of each piece of data, longitude and latitude position information and a direction angle of each vehicle.
The invention discloses a real-time monitoring data acquisition method of an unmanned aerial vehicle, which comprises the following steps: a plurality of unmanned aerial vehicles are adopted to simultaneously acquire data at a plurality of traffic intersections within the city-level range, and the traffic flow of each traffic intersection at each moment is extracted by utilizing an image multi-target recognition and multi-target tracking algorithm through the video stream returned by the unmanned aerial vehicles.
Referring to fig. 3, the unified modeling method for multidimensional multi-layer data of the present invention comprises: dividing the constructed road network model into a bus driving layer and a subway layer, taking a nearest intersection of a bus stop point as a bus layer node, taking a nearest intersection of a subway station as a subway layer node, storing the number of vehicles and the speed of the vehicles near the current position at different nodes, associating the same nodes of different layers through indexes, and marking hierarchical numbers, thereby constructing a multilayer network; different layers are connected through the nodes of the layer, the node information of the layer where the vehicle is located is confirmed through time and the position of the vehicle in the GPS signal, and the vehicle information of the corresponding nodes in other layers is inquired through the nodes.
Referring to fig. 4, the unified modeling method for multi-source heterogeneous data of the present invention comprises: expressing query relations among all data tables in a network form, extracting a hash structure between equipment, time and position from activity data of a vehicle extracted from a GPS signal, and expressing acquisition time, unique identification of the vehicle, current position longitude and current position dimensional data by using a server Redis 1; extracting the traffic flow of each traffic intersection at every moment by using an image multi-target recognition and multi-target tracking algorithm through the video stream transmitted back by the unmanned aerial vehicle, and establishing an intersection-vehicle number-time relation data table; and creating external connection between each kind of data in the storage medium MySql to form a multi-source heterogeneous data model.
The data fusion method of the microscopic simulator comprises the following steps: adopting SUMO as a microscopic simulator; the number and speed of vehicles extracted from GPS signals on a real road are used as parameters to be input into a microscopic simulator SUMO, the microscopic simulator SUMO automatically generates driving behaviors on the road according to the input number of the vehicles, the traffic flow of the real intersection is used as queuing parameters of the intersection in the simulator to be input, and the traffic flow data of the intersection and the traffic flow data of the road are fused to generate a traffic control model in the simulator.
The data gridding processing method comprises the following steps: and carrying out 32-by-32 gridding fine processing on the collected vehicle position data. For each (i, j), defining it as the grid corresponding to the ith row from top to bottom and the jth column from left to right in the map, then at time interval t, the traffic flow into the grid and the traffic flow out of the grid are respectively defined as:
Tris the traffic trajectory in P, gkRepresenting the longitude and latitude coordinates of the geographic space, gkE (i, j) indicates that the latitude and longitude lies within the grid (i, j).
Referring to fig. 2, the distributed deployment method of the server and the storage medium of the present invention includes: the server Redis1, the server Redis2, the server Redis3 and the storage medium MySql are distributed; the storage medium MySql is used as a relational database and is distributed in a mode of respectively starting different ports by taking a storage medium server Redis1, a storage medium server Redis2 and a storage medium server Redis3 as non-relational databases, and the process of realizing the consistency of distributed data is as follows: real-time data is stored in each Redis firstly, is synchronized in MySql after being inquired, and the double-write consistency of the database under the distributed mode is ensured by utilizing the principle of deleting cache firstly and then updating the database; a storage medium server is used for designing a distributed lock to ensure that read-write inconsistency abnormity occurs in a data storage medium in a concurrent scene; the inaccurate uploading problem of the speed data of the vehicle is solved by reading the time sequence in MySql, quickly inquiring the position of the vehicle in a hash table in Reids1, and then calculating the speed of the adjacent time and synchronizing the speed to the storage medium MySql.
The data sharing method comprises the following steps: and for the road vehicle simulation behavior generated after data fusion in the microscopic simulator, sending the road vehicle simulation behavior to a program call for inquiring the congested hot spot intersection in a http protocol mode aiming at a Get/Post network request mode of a user.
The congestion dispersion method used by the invention comprises the following steps: the webster algorithm is used as an intelligent traffic algorithm, congestion dredging is carried out by inquiring congestion vehicle data of intersections, overall waiting time delay is reduced by adopting the intelligent traffic algorithm webster, running track data of the dredged vehicles are obtained, grid flow data are processed, and simulated vehicle running data and grid flow data are obtained.
Examples
The effectiveness of the traffic data driving framework based on the cyber-physical system and the construction method thereof in optimizing traffic traveling is demonstrated through a real urban traffic scene of Wuxi city in Jiangsu province of China.
The track data of all vehicles in a day in the Wuxi city are transmitted, the driving framework can quickly calculate the average speed of the vehicles at all times according to the longitude and latitude data, count the average speed of the road and the number of the vehicles in the district and store the average speed and the number in the district in a database system, and the driving framework is utilized to quickly inquire to obtain the congestion condition of each district and visually present the congestion condition, as shown in FIG. 5. 5 a-5 d are 8:30,9:00,18:00 and 18:30 respectively, the color depth of the vehicle distribution of each tin-free area indicates the number of vehicles in the district, and the darker the color indicates the number of vehicles in the district.
Through observation, the congestion change situation is obvious in the peak of the beam creek in the morning and at night every day, so that the congestion mode in the area is focused and the congestion situation is dredged. And analyzing by sharing the video data of the unmanned aerial vehicle in the area. And according to the frame rate of the video returned by the unmanned aerial vehicle, cutting the video in the congestion time period by frames by using a video cutting algorithm, as shown in fig. 6. Fig. 6b is a certain frame of picture cut out in fig. 6a, and fig. 6c is a block of traffic data of the city designed by the invention, which is obtained by using an overhead vehicle detection algorithm to obtain the number of different types of vehicles in each frame of picture and the total number of all types of vehicles, and the number of vehicles in all frames is counted and the dead weight is removed to obtain the jammed vehicle data of the intersection at the peak time.
Fig. 7a shows a tin-free topology, fig. 7b shows a mapping scenario in the micro simulator SUMO, and fig. 7c shows a data fusion result of the present invention, which transmits actual congestion vehicle data to a certain intersection in the micro simulator SUMO.
The invention utilizes the three-dimensional modeling technology to carry out simulation deduction on the vehicle running behavior without using the intelligent traffic algorithm and after using the intelligent traffic algorithm, as shown in figure 8. Fig. 8a is an aerial view of a three-dimensional model of city-road-vehicle driving behavior of the present invention, fig. 8b is a local area after a lens is zoomed in, it can be seen that there is a large difference in congestion modes (left and right) at the intersection, fig. 8c is a microscopic simulation of the intersection, the left image is a road congestion situation where a congestion leading strategy is not adopted at the start of the simulation, it can be seen that at the intersection where vehicles are gathered more, the situation of vehicle waiting at the intersection gradually occurs in the conventional traffic mode. The right diagram is the traffic pattern after the intelligent traffic algorithm webster is adopted, i.e. vehicles are arranged as far away from the convergence intersection as possible when the congestion is not yet fully developed. Fig. 8d shows that as the number of iterations increases, the degree of road junction congestion increases without any strategy (left), and the road with the congestion leading strategy is more smooth (right).
The traffic data driving framework based on the cyber-physical system and the construction method thereof adopt an intelligent traffic algorithm webster to adjust the road junction timing scheme, and optimize the timing scheme parameters of the model by using the data driving idea to continuously perform iterative adjustment. Fig. 9a and 9b are the results of the overall waiting time duration of the road after the use of the intelligent transportation algorithm webster (square) in the morning and evening rush hour and the use of the intelligent transportation algorithm webster (star) in the present invention, respectively. In the iterative process of optimizing the parameter of the webster timing scheme of the intelligent traffic algorithm by using data driving, the overall waiting time of the road is always lower than that without any strategy.
In the embodiment, traffic problems in specific cities are managed and deduced by adopting the traffic data driving framework based on the information physical fusion system, so that waiting time in a trip can be effectively improved.
The foregoing is illustrative and explanatory only and is not intended to be exhaustive or to limit the invention to the precise embodiments described, and various modifications, additions, and substitutions may be made by those skilled in the art without departing from the scope of the invention as defined in the following claims.
Claims (11)
1. A construction method of a traffic data driving framework based on an information physical fusion system is characterized by comprising the following steps: the method comprises the following specific steps:
s1: acquiring road data in an origin map database, constructing a road network model by taking intersections as nodes and roads between the intersections as connecting edges, numbering the intersections, and establishing relations by using source-target key values respectively;
s2: receiving GPS signals of vehicles of an operator in a city-level range, extracting activity data of the vehicles from the GPS signals through desensitization processing of a vehicle-mounted terminal service provider, wherein the data content comprises desensitized unique identification of the vehicles, acquisition time of each piece of data, longitude and latitude position information and direction angles of each vehicle; carrying out multi-dimensional multi-layer traffic data unified modeling on the vehicle identification and time relation in the extracted data and the road network relation in S1 according to the time sequence; taking the vehicle identification in the extracted data as a key, taking a time character string as a filtered, splicing the longitude and latitude subjected to GPS (global positioning system) deviation correction into a character string as a value, and storing the character string in a hash structure in a server Redis1 in a distributed deployed non-relational database cluster;
s3: unmanned aerial vehicle crossing monitoring module: a plurality of unmanned aerial vehicles are adopted to simultaneously acquire data at a plurality of traffic intersections in the city-level range, and the video stream transmitted back by the unmanned aerial vehicles is used for extracting the traffic flow of each traffic intersection at each moment by utilizing an image multi-target recognition and multi-target tracking algorithm and carrying out multi-source heterogeneous data unified modeling on the multi-dimensional multi-layer traffic data obtained in S2;
s4: storing the traffic flow of each traffic intersection at each moment of S3 in a server Redis2 in a distributed non-relational database cluster;
s5: storing the multi-source heterogeneous data model established in the S3 in a storage medium MySql;
s6: reading a time sequence in the storage medium MySql in S5, positioning longitude and latitude data of adjacent moments in a server Redis1 cache of S1 by using time and vehicle identification, calculating to obtain accurate speed data, and adding the accurate speed data into the storage medium MySql in S5 to realize distributed parallel calculation and storage of vehicle speed;
s7: reading road vehicle data stored in a storage medium MySql in S5 and traffic flow of a traffic intersection stored in a server Redis2 in S4, simulating real intersection traffic flow by using a microscopic simulator, and extracting activity data of a vehicle from a GPS signal to realize data fusion;
s8: data sharing is carried out on the result of the S7;
s9: inquiring congestion hot spot intersections;
s10: carrying out congestion dispersion on the congested intersections queried in the step S9 in a microscopic simulator by using an intelligent traffic algorithm, and storing dispersed vehicle running track data and calculated grid flow data in a server Redis3 in a distributed non-relational database cluster;
s11: the grid flow data in a server Redis3 in a non-relational database cluster is called, and a flow prediction algorithm is used for predicting whether congestion occurs in the future traffic in the current mode;
s12: if the overall waiting duration index in the predicted result is worse than the current overall waiting duration index, the data-driven method adjusts the parameters of the intelligent traffic algorithm, and returns to S11, otherwise, enters S13;
s13: and performing visualization deduction on the simulation data in the S12 in the three-dimensional scene.
2. The construction method of the traffic data driven framework based on the cyber-physical system according to claim 1, wherein the construction method comprises the following steps: step S1, constructing a road network model: the intersections of the city are taken as nodes in the network, and the roads between the intersections are taken as connecting edges of the network; and attaching the traffic flow information on the road to the node and the connecting edge as a weight.
3. The construction method of the traffic data driven framework based on the cyber-physical system according to claim 1, wherein the construction method comprises the following steps: step S2, the GPS deviation rectifying process includes the following steps: collecting GPS signals of an operator vehicle, extracting longitude and latitude positions at each moment, calculating the similarity between a positioned track point and a corresponding position in a road network, then calculating the similarity of all matched road sections, taking a road section to be matched with the maximum result as a target road section, and modifying the longitude and latitude of the position point to the target road section to enable the position point to be matched with a map road of the WGS84 standard.
4. The construction method of the traffic data driven framework based on the cyber-physical system according to claim 1, wherein the construction method comprises the following steps: step S2, the unified modeling of the multi-dimensional multi-layer traffic data is specifically as follows:
dividing the constructed road network model into a bus driving layer and a subway layer, taking a nearest intersection of a bus stop point as a bus layer node, taking a nearest intersection of a subway station as a subway layer node, storing the number of vehicles and the speed of the vehicles near the current position at different nodes, associating the same nodes of different layers through indexes, and marking hierarchical numbers, thereby constructing a multilayer network; different layers are connected through the nodes of the layer, the node information of the layer where the vehicle is located is confirmed through time and the position of the vehicle in the GPS signal, and the vehicle information of the corresponding nodes in other layers is inquired through the nodes.
5. The construction method of the traffic data driven framework based on the cyber-physical system according to claim 1, wherein the construction method comprises the following steps: step S7, simulating the traffic flow at the real intersection and extracting the activity data of the vehicle from the GPS signal by using the microscopic simulator, so as to implement data fusion, specifically: the traffic control method comprises the steps of adopting a microscopic simulator SUMO, inputting the number and speed of vehicles extracted from GPS signals on a real road into the SUMO as parameters, automatically generating driving behaviors on the road by the SUMO according to the number of the input vehicles, inputting the traffic flow of the real intersection as queuing parameters of the intersection in the simulator, and fusing the traffic flow of the intersection and the traffic flow data of the road to generate a traffic control model in the simulator.
6. The construction method of the traffic data driven framework based on the cyber-physical system according to claim 1, wherein the construction method comprises the following steps: step S11, the method calls grid traffic data in the server Redis3 in the non-relational database cluster, and performs prediction using a traffic prediction algorithm, specifically: carrying out 32-by-32 grid fine processing on the collected vehicle position data; for each (i, j), defining it as the grid corresponding to the ith row from top to bottom and the jth column from left to right in the map, then at time interval t, the traffic flow into the grid and the traffic flow out of the grid are respectively defined as:
Tris the traffic trajectory in P, gkRepresenting the longitude and latitude coordinates of the geographic space, gkE (i, j) indicates that the longitude and latitude are positioned in the grid (i, j); thereby forming mesh flow data; and then, carrying out grid flow prediction on the urban road by adopting a graph convolution space-time attention mechanism model and a space-time similarity attention neural network algorithm to obtain the traffic flow conditions of each grid at the future time.
7. The construction method of the traffic data driven framework based on the cyber-physical system according to claim 1, wherein the construction method comprises the following steps: step S3, the unified modeling of the multi-source heterogeneous data is specifically as follows:
expressing query relations among all data tables in a network form, extracting a hash structure between equipment, time and position from activity data of a vehicle extracted from a GPS signal, and expressing acquisition time, unique identification of the vehicle, current position longitude and current position dimensional data by using a server Redis 1; extracting the traffic flow of each traffic intersection at every moment by using an image multi-target recognition and multi-target tracking algorithm through the video stream transmitted back by the unmanned aerial vehicle, and establishing an intersection-vehicle number-time relation data table; and creating external connection between each kind of data in the storage medium MySql to form a multi-source heterogeneous data model.
8. The construction method of the traffic data driven framework based on the cyber-physical system according to claim 1, wherein the construction method comprises the following steps: the server Redis1, the server Redis2, the server Redis3 and the storage medium MySql are distributed; the storage medium MySql is used as a relational database, and the server Redis1, the server Redis2 and the server Redis3 are used as non-relational databases, are distributed in a mode of respectively starting different ports, and the process of realizing distributed data consistency is as follows: real-time data are stored in each server Redis firstly, are synchronized in a storage medium MySql after being inquired, and the double-write consistency of the database under the distributed mode is ensured by utilizing the principle of deleting cache firstly and then updating the database; a distributed lock is designed by using a storage medium and a server to ensure that read-write inconsistency abnormity occurs in the data storage medium and the server in a concurrent scene; the inaccurate uploading problem of the speed data of the vehicle is solved by reading the time sequence in the storage medium MySql, quickly inquiring the position of the vehicle in the hash table in the server Reids1, and then calculating the speed of the adjacent time and synchronizing the speed to the storage medium MySql.
9. The construction method of the traffic data driven framework based on the cyber-physical system according to claim 1, wherein the construction method comprises the following steps: the data sharing in step S8 specifically includes: and for the road vehicle simulation behavior generated after data fusion in the microscopic simulator, sending the road vehicle simulation behavior to a program call for inquiring the congested hot spot intersection in a http protocol mode aiming at a Get/Post network request mode of a user.
10. The construction method of the traffic data driven framework based on the cyber-physical system according to claim 1, wherein the construction method comprises the following steps: step S10, the congestion evacuation with the intelligent traffic algorithm specifically includes: the intelligent traffic algorithm is a webster algorithm, congestion evacuation is carried out by inquiring congestion vehicle data of intersections, overall waiting time delay is reduced by adopting the webster algorithm, running track data of the evacuated vehicles are obtained, grid flow data are processed, and simulated vehicle running data and grid flow data are obtained.
11. A traffic data driven framework based on an cyber-physical fusion system constructed by the method of claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111269011.6A CN113920739B (en) | 2021-10-29 | 2021-10-29 | Traffic data driving frame based on information physical fusion system and construction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111269011.6A CN113920739B (en) | 2021-10-29 | 2021-10-29 | Traffic data driving frame based on information physical fusion system and construction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113920739A true CN113920739A (en) | 2022-01-11 |
| CN113920739B CN113920739B (en) | 2023-05-23 |
Family
ID=79243353
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111269011.6A Active CN113920739B (en) | 2021-10-29 | 2021-10-29 | Traffic data driving frame based on information physical fusion system and construction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113920739B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114093171A (en) * | 2022-01-21 | 2022-02-25 | 杭州海康威视数字技术股份有限公司 | Traffic running state monitoring method and device based on multi-source data fusion |
| CN114418468A (en) * | 2022-03-29 | 2022-04-29 | 成都秦川物联网科技股份有限公司 | Smart city traffic scheduling strategy control method and Internet of things system |
| CN114627650A (en) * | 2022-05-11 | 2022-06-14 | 深圳市城市交通规划设计研究中心股份有限公司 | Urban public transport priority simulation deduction system, method, electronic equipment and storage medium |
| CN115083168A (en) * | 2022-08-23 | 2022-09-20 | 河北博士林科技开发有限公司 | Multi-level traffic simulation network construction method based on multi-source data |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102110364A (en) * | 2009-12-28 | 2011-06-29 | 日电（中国）有限公司 | Traffic information processing method and traffic information processing device based on intersections and sections |
| CN106897417A (en) * | 2017-02-22 | 2017-06-27 | 东南大学 | A kind of construction method of the city space holographic map based on the fusion of multi-source big data |
| WO2018122585A1 (en) * | 2016-12-30 | 2018-07-05 | 同济大学 | Method for urban road traffic incident detecting based on floating-car data |
| CN108335482A (en) * | 2017-01-20 | 2018-07-27 | 亚信蓝涛（江苏）数据科技有限公司 | A kind of urban transportation Situation Awareness method and method for visualizing |
| CN109410576A (en) * | 2018-11-08 | 2019-03-01 | 深圳北斗应用技术研究院有限公司 | Road condition analyzing method, apparatus, storage medium and the system of multisource data fusion |
| CN110570651A (en) * | 2019-07-15 | 2019-12-13 | 浙江工业大学 | Road network traffic situation prediction method and system based on deep learning |
| CN110874391A (en) * | 2019-09-29 | 2020-03-10 | 北京旋极伏羲科技有限公司 | Data fusion and display method based on urban space three-dimensional grid model |
-
2021
- 2021-10-29 CN CN202111269011.6A patent/CN113920739B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102110364A (en) * | 2009-12-28 | 2011-06-29 | 日电（中国）有限公司 | Traffic information processing method and traffic information processing device based on intersections and sections |
| WO2018122585A1 (en) * | 2016-12-30 | 2018-07-05 | 同济大学 | Method for urban road traffic incident detecting based on floating-car data |
| CN108335482A (en) * | 2017-01-20 | 2018-07-27 | 亚信蓝涛（江苏）数据科技有限公司 | A kind of urban transportation Situation Awareness method and method for visualizing |
| CN106897417A (en) * | 2017-02-22 | 2017-06-27 | 东南大学 | A kind of construction method of the city space holographic map based on the fusion of multi-source big data |
| CN109410576A (en) * | 2018-11-08 | 2019-03-01 | 深圳北斗应用技术研究院有限公司 | Road condition analyzing method, apparatus, storage medium and the system of multisource data fusion |
| CN110570651A (en) * | 2019-07-15 | 2019-12-13 | 浙江工业大学 | Road network traffic situation prediction method and system based on deep learning |
| CN110874391A (en) * | 2019-09-29 | 2020-03-10 | 北京旋极伏羲科技有限公司 | Data fusion and display method based on urban space three-dimensional grid model |
Non-Patent Citations (8)
| Title |
|---|
| 《张涛》: "公路勘察设计多源数据融合方法研究" * |
| 张纯: "基于数据融合的城市轨道交通 规划理论研究 ——BIM与GIS一体化研究综述" * |
| 曹晶;李清泉;: "城市路网中浮动车数据和线圈数据的融合", 交通与计算机 * |
| 李文雄;王建伟;: "城市快速路网本体交通数据集成及其应用", 长安大学学报(自然科学版) * |
| 杨超: "城市道路网络演变模型", 《同济大学学报（自然科学版）》 * |
| 聂玉强: "城市主干路网交通信息多源数据融合系统研究" * |
| 蒋斌: "基于 DenseNet 的复杂交通场景语义分割方法" * |
| 贾琳;: "城市交通大数据智能计算平台与应用", 数字通信世界 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114093171A (en) * | 2022-01-21 | 2022-02-25 | 杭州海康威视数字技术股份有限公司 | Traffic running state monitoring method and device based on multi-source data fusion |
| CN114093171B (en) * | 2022-01-21 | 2022-05-06 | 杭州海康威视数字技术股份有限公司 | Traffic running state monitoring method and device based on multi-source data fusion |
| CN114418468A (en) * | 2022-03-29 | 2022-04-29 | 成都秦川物联网科技股份有限公司 | Smart city traffic scheduling strategy control method and Internet of things system |
| CN114418468B (en) * | 2022-03-29 | 2022-07-05 | 成都秦川物联网科技股份有限公司 | Smart city traffic scheduling strategy control method and Internet of things system |
| US11587436B1 (en) | 2022-03-29 | 2023-02-21 | Chengdu Qinchuan Iot Technology Co., Ltd. | Methods for controlling traffic scheduling strategies in smart cities and Internet of Things (IoT) systems thereof |
| CN114627650A (en) * | 2022-05-11 | 2022-06-14 | 深圳市城市交通规划设计研究中心股份有限公司 | Urban public transport priority simulation deduction system, method, electronic equipment and storage medium |
| CN115083168A (en) * | 2022-08-23 | 2022-09-20 | 河北博士林科技开发有限公司 | Multi-level traffic simulation network construction method based on multi-source data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113920739B (en) | 2023-05-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113920739A (en) | Traffic data driving framework based on information physical fusion system and construction method | |
| CN106297291B (en) | Urban expressway traffic information acquisition system | |
| WO2020034903A1 (en) | Smart navigation method and system based on topological map | |
| CN110531770B (en) | RRT path planning method and system based on improvement | |
| CN113283581B (en) | Multi-fusion graph network collaborative multi-channel attention model and application method thereof | |
| KR102377637B1 (en) | Hybride Traffic Signal Control System and Method thereof | |
| CN116824859B (en) | Intelligent traffic big data analysis system based on Internet of things | |
| CN112163446A (en) | Obstacle detection method and device, electronic equipment and storage medium | |
| CN111526324B (en) | Monitoring system and method | |
| CN114328780B (en) | Hexagonal lattice-based smart city geographic information updating method, equipment and medium | |
| CN113380028B (en) | Intelligent travel traffic data fusion method and device | |
| WO2021237768A1 (en) | Data-driven-based system for implementing automatic iteration of prediction model | |
| CN112862171A (en) | Flight arrival time prediction method based on space-time neural network | |
| CN113868492A (en) | Visual OD (origin-destination) analysis method based on electric police and checkpoint data and application | |
| CN114443784A (en) | Local dynamic map implementation method based on high-precision map | |
| CN114578848A (en) | Unmanned aerial vehicle routing inspection path planning method based on discrete point density and global planning | |
| CN114780864B (en) | Human-object-space interaction model construction method based on knowledge graph | |
| CN114120631B (en) | Method and device for constructing dynamic high-precision map and traffic cloud control platform | |
| Sinha et al. | Sustainable time series model for vehicular traffic trends prediction in metropolitan network | |
| CN115841762A (en) | Unmanned vehicle control method, unmanned vehicle control system and unmanned vehicle | |
| Shein et al. | Discovery of loose group companion from trajectory data streams | |
| Yang et al. | Distributed data-driven engine framework facing CPS brain-inspired intelligent transportation | |
| CN115376055B (en) | Vehicle tracking method for urban road digital twin scene | |
| CN117725662B (en) | Engineering construction simulation method and system based on municipal engineering | |
| Liu | High precision map crowdsource update technology and SLAM technology-Application in autonomous driving |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |