CN118609370A - A traffic diversion and control method based on cloud computing - Google Patents

Abstract

The present invention discloses a traffic diversion and control method based on cloud computing, which relates to the field of resource allocation and comprises the following steps: setting a traffic diversion and management platform, acquiring basic road data, constructing a road traffic image, acquiring traffic data information of each road section and its acquisition time; based on the traffic data information, generating a fluctuation cycle corresponding to each road section; acquiring the congestion level of each road section according to the acquired traffic data information, generating a traffic event image; judging whether there is a correlation between each road section and other road sections according to the preset congestion level of each road section in the traffic event image; generating a corresponding diversion plan according to the traffic data information currently acquired of the road section, and generating a corresponding auxiliary diversion plan according to the traffic data information of other road sections with correlation; regulating the traffic lights and lanes of the corresponding road section according to the acquired diversion plan and the auxiliary diversion plan, and completing traffic data control; the present invention improves the efficiency of traffic diversion.

Description

A traffic diversion and control method based on cloud computing

Technical Field

The present invention relates to the field of power grid management, and in particular to a vehicle flow diversion and control method based on cloud computing.

Background Art

With the development of society and the improvement of people's living standards, people's travel methods are constantly changing. With the continuous increase in vehicles, traffic management is becoming more and more important. In order to strengthen urban traffic management, maintain good road traffic order, and ensure the safety and smooth travel of the masses, we need to solve the problem. Therefore, it is necessary to conduct traffic diversion and control according to the traffic flow on the road;

A traffic diversion system for traffic accidents and its control method with publication number CN109537489B discloses a traffic diversion system for traffic accidents, including a bottom plate; a box, the bottom of the box is fixed to the top of the bottom plate; a telescopic slot, the bottom of the telescopic slot is fixed to the top of the box, and a sliding plate is slidably connected between the two sides of the inner wall of the telescopic slot. The present invention relates to the technical field of traffic control equipment. The traffic diversion system for traffic accidents and its control method have multiple control functions to avoid the waste of time caused by the different number of vehicles on different roads. The rotation of the signboard will provide road guidance to avoid vehicles changing lanes at will and cutting in, thereby improving the triggerability of traffic accidents. Moreover, through the setting of a display screen and a speaker, information display and sound prompts can be performed, thereby improving the convenience of road diversion. It has multiple road diversion functions to facilitate the understanding of drivers in different positions, improve the smoothness of vehicle driving, and avoid road congestion.

A method and system for optimizing urban traffic congestion with publication number CN116959275A discloses a method and system for optimizing urban traffic congestion, which relates to the field of traffic management technology. The method includes obtaining a detection road image and marking the detection road; determining the detection lane area according to the lane matching relationship; obtaining the length of the vehicle queue in the detection lane area; judging whether the length of the vehicle queue is greater than the congestion reference length; if greater, defining the lane as a congestion lane, and determining the associated lane corresponding to the congestion lane according to the intersection matching relationship, and defining the vehicle queue length of the associated lane as the associated length; determining the reference duration corresponding to the associated length according to the duration matching relationship; determining the associated demand duration according to all the reference durations, and determining the congestion relief duration according to the signal light cycle duration and the associated demand duration, and controlling the signal light corresponding to the congestion lane to pass with a green light according to the congestion relief duration. The application has the effect of facilitating the handling of traffic congestion.

However, only directing traffic on congested sections of road has problems such as low traffic diversion efficiency. In addition, the congested traffic is diverted according to the adjacent sections of the road without judging the congestion of the corresponding sections and incorporating them into the diversion process, which also affects the diversion efficiency to a certain extent. Therefore, how to improve the efficiency of the traffic diversion process is a problem we need to solve. To this end, a traffic diversion control method based on cloud computing is provided.

Summary of the invention

In order to solve the above technical problems, the purpose of the present invention is to provide a traffic diversion and control method based on cloud computing.

The purpose of the present invention can be achieved by the following technical solution: A traffic diversion and control method based on cloud computing, comprising the following steps:

Step S1: Setting up a traffic flow management platform, obtaining basic road data in the area, constructing a road traffic image based on the basic road data, setting up data monitoring nodes, obtaining traffic flow data information corresponding to each road section in the road traffic image, and marking its collection time;

Step S2: Obtain historical traffic flow data information, determine the congestion level corresponding to each road section, generate the corresponding volatility cycle according to the congestion level of the historical data information, and store it;

Step S3: obtaining the congestion level corresponding to each road section in the road traffic image at the current moment according to the obtained traffic flow data information, and performing visualization processing on the congestion level to generate a traffic event image;

Step S4: preset the traffic diversion priority according to the congestion level, obtain the road section with high traffic diversion priority in the traffic event image, preset the basic diversion radius, obtain the congestion level of other road sections within the basic diversion radius and the volatility cycle therein, and judge whether there is a correlation relationship between it and the road section according to its congestion level at the current moment and the predicted congestion level at the next moment within the volatility cycle according to its congestion level and the predicted congestion level;

Step S5: Analyze and process the traffic flow data information currently obtained on the road section, generate a corresponding traffic diversion plan according to the processing result, and generate auxiliary traffic diversion plans for other road sections that are associated with the road section according to their corresponding traffic flow data information;

Step S6: Traffic lights and lanes of corresponding road sections are regulated according to the obtained traffic diversion plan and auxiliary traffic diversion plan to complete traffic flow data control.

Furthermore, the process of constructing a road traffic image and collecting traffic flow data information includes:

A traffic diversion management platform is provided, wherein a platform external window is provided, the platform external window acquires a corresponding road distribution image based on satellite image data, and is used for staff to input basic road data; the basic road data is the name of the corresponding road section, lane type information, fork information, road section position relationship and vehicle comprehensive interval; a road traffic image is constructed based on the road distribution image and the basic road data;

A data monitoring node is set according to the road traffic image. A corresponding data acquisition terminal is set in the data monitoring node. The data acquisition terminal is used to obtain traffic data information of the corresponding road section. The traffic data information includes vehicle flow data and vehicle density data. The vehicle flow data includes lane flow data corresponding to each lane in the road section; the vehicle density data includes lane density data corresponding to each lane in the road section.

Furthermore, the process of obtaining the volatility period of each road section includes:

The traffic diversion management platform stores historical traffic data information corresponding to each road section in the road traffic image, obtains historical traffic data information, sets corresponding weight factors according to the importance of historical vehicle flow data and historical vehicle density data to road congestion, and obtains vehicle comprehensive data based on the relationship between the historical vehicle flow data and the corresponding weight factors, and obtains the collection time;

Obtaining a vehicle comprehensive section preset with a congestion level corresponding to the corresponding road information in the road traffic image; the congestion levels include no congestion, light congestion, moderate congestion and severe congestion in order from light to heavy severity; comparing and analyzing the obtained vehicle comprehensive data with the vehicle comprehensive section, and determining the congestion level according to the vehicle comprehensive section to which it belongs;

The corresponding spectrum curve is set for the obtained vehicle comprehensive data according to the collection time, and the spectrum features are extracted from the spectrum curve according to the spectrum analysis algorithm. The periodic fluctuation is obtained according to the obtained spectrum features, and the congestion level of the vehicle comprehensive data corresponding to each unit time in the periodic fluctuation is marked to generate the fluctuation period of the corresponding road section and store it.

Furthermore, the process of generating the traffic event image includes:

Obtain the obtained traffic flow data information for analysis and processing, obtain the corresponding vehicle comprehensive data, compare and analyze the vehicle comprehensive data obtained in each road section information with the corresponding vehicle comprehensive interval, obtain the congestion level in each road section information, and mark its collection time;

Obtain road traffic images, visualize the road traffic images according to the congestion levels corresponding to the information of each road section within the current acquisition time, and generate traffic event images; and update the obtained traffic event images in real time according to the acquisition time.

Furthermore, the process of obtaining the correlation between the road sections includes:

The traffic diversion management platform sets traffic diversion priorities according to the congestion level and severity from light to heavy, obtains a traffic event image, obtains a road section with a high priority according to the traffic diversion priority, obtains the congestion level of the road section, presets a basic diversion radius according to the congestion level, and obtains the congestion level and volatility period corresponding to other road sections within the basic diversion radius in the traffic event image with the road section as the center;

Mark the congestion levels corresponding to other road sections, obtain the unit time of the volatility cycle to which each other road section belongs according to the volatility cycle of each other road section and the current collection time, and obtain the congestion level corresponding to the next unit time of the volatility cycle according to the current unit time, and record it as the predicted congestion level; mark the predicted congestion level corresponding to other road sections; obtain the location of the corresponding road section and other road sections within the basic diversion radius in the traffic event image and the number of forks between them, and mark the number of forks corresponding to other road sections;

The congestion levels, predicted congestion levels and number of forks corresponding to other road sections within the basic diversion radius are processed respectively, and the correlation data corresponding to different data information between each road section is obtained based on the big data algorithm. The obtained correlation data is multiplied by the congestion level, predicted congestion level and number of forks respectively and the sum is obtained to obtain comprehensive correlation data; a correlation threshold is preset, and when the comprehensive correlation data is greater than or equal to the correlation threshold, it is indicated that there is correlation between the two road sections; when the comprehensive correlation data is less than the correlation threshold, there is no correlation between the two road sections;

Other associated road segments are temporarily stored according to their comprehensive associated data.

Furthermore, the process of obtaining the diversion plan corresponding to the road section includes:

Obtain the vehicle flow data and vehicle density data collected on the corresponding road section, obtain the lane type corresponding to the lane flow data and lane density data, process the lane flow data and lane density data according to the lane type, obtain the corresponding average lane flow and average density data according to the lane type, obtain the average vehicle comprehensive data of the corresponding lane type, compare and analyze the average vehicle comprehensive data corresponding to different lane types, obtain the difference data, set the difference threshold according to the minimum average vehicle comprehensive data, compare and analyze the difference data with the difference threshold, and when the difference data is greater than the difference threshold, set lane flexible diversion for the road section; when the difference data is less than or equal to the difference threshold, do not set lane flexible diversion for the road section;

The traffic flow diversion management platform is preset with a traffic light control adjustment curve of average vehicle comprehensive data on travel time, and the average vehicle comprehensive data of the corresponding lane type in the road section is mapped to the traffic light control adjustment curve to obtain the travel time and set the traffic light for flexible diversion;

The flexible lane diversion and traffic light diversion obtained for the corresponding road section are used to generate a diversion plan.

Furthermore, the process of setting an auxiliary guidance scheme according to the correlation result includes:

Acquire other road sections associated with it, and acquire the current traffic flow data information of the other road sections associated with it and the position relationship between them; the position relationship includes a traffic flow import relationship and a traffic flow export relationship;

When the position relationship between other road sections and the corresponding road sections is a traffic flow import relationship, the average vehicle comprehensive of the road section is obtained and mapped to the traffic light control adjustment curve to obtain its travel time; the slow travel time coefficient is set according to the current congestion level of the road section, and the travel time of the road section is analyzed and processed according to the obtained slow travel time coefficient to obtain the auxiliary travel time of the road section;

When the position relationship between other road sections and the corresponding road sections is a traffic flow derived relationship, the travel time is obtained, and a speed-up travel time coefficient is set according to the current congestion level of the road section; the travel time of the road section is analyzed and processed according to the obtained speed-up travel time coefficient to obtain the auxiliary travel time of the road section;

An auxiliary traffic diversion plan is generated according to the auxiliary travel time corresponding to other road sections that are associated with the corresponding road section.

Furthermore, the process of traffic diversion and control includes:

The traffic lights and lane control signals of the corresponding road sections are regulated according to the obtained traffic diversion plan and auxiliary traffic diversion plan, and the traffic lights corresponding to each road section are adjusted according to the generated passing time and auxiliary passing time to complete the traffic diversion and control.

Compared with the prior art, the present invention has the following beneficial effects:

By setting a volatility cycle for each road section, the predicted congestion level in the corresponding time, the congestion level at the current time and the number of intersections between each road section are obtained according to the volatility cycle, and the correlation data between each road section is obtained. It is judged whether the corresponding road sections are correlated based on the correlation data. When the corresponding road section needs to be diverted, it can be assisted in diverting according to the road sections that are mutually correlated with it, thereby improving the efficiency of the traffic diversion process of the corresponding road section to a certain extent; in addition, a corresponding volatility cycle is set for each road section, and its congestion level in different unit time is predicted. According to the prediction results, it is possible to not only judge whether there is an abnormality in the traffic data information in the section, but also take preventive measures in advance.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a schematic diagram of a method for directing and controlling traffic flow based on cloud computing according to an embodiment of the present application.

DETAILED DESCRIPTION

As shown in FIG1 , a method for controlling traffic flow diversion based on cloud computing includes the following steps:

Step S1: Setting up a traffic flow management platform, obtaining basic road data in the area, constructing a road traffic image based on the basic road data, setting up data monitoring nodes, obtaining traffic flow data information corresponding to each road section in the road traffic image, and marking its collection time;

Step S2: Obtain historical traffic flow data information, determine the congestion level corresponding to each road section, generate the corresponding volatility cycle according to the congestion level of the historical data information, and store it;

Step S3: obtaining the congestion level corresponding to each road section in the road traffic image at the current moment according to the obtained traffic flow data information, and performing visualization processing on the congestion level to generate a traffic event image;

Step S4: preset the traffic diversion priority according to the congestion level, obtain the road section with high traffic diversion priority in the traffic event image, preset the basic diversion radius, obtain the congestion level of other road sections within the basic diversion radius and the volatility cycle therein, and judge whether there is a correlation relationship between it and the road section according to its congestion level at the current moment and the predicted congestion level at the next moment within the volatility cycle according to its congestion level and the predicted congestion level;

Step S5: Analyze and process the traffic flow data information currently obtained on the road section, generate a corresponding traffic diversion plan according to the processing result, and generate auxiliary traffic diversion plans for other road sections that are associated with the road section according to their corresponding traffic flow data information;

Step S6: Traffic lights and lanes of corresponding road sections are regulated according to the obtained traffic diversion plan and auxiliary traffic diversion plan to complete traffic flow data control.

It should be further explained that, in the specific implementation process, the process of setting up a traffic diversion management platform, obtaining basic road data and basic commercial data in the area, the traffic diversion management platform constructing a road traffic image based on the basic road data, and marking the corresponding basic road data in the road traffic image includes:

A traffic diversion management platform is provided, the traffic diversion management platform is used to analyze and control urban roads that need traffic diversion, wherein an external platform window is provided, the external platform window is used for the traffic diversion management platform to obtain corresponding road distribution images based on satellite image data, and basic road data is input by staff in the traffic diversion management platform; the basic road data includes the name of the road section, lane type information, fork information, road section position relationship and vehicle comprehensive interval;

Analyze and process the road distribution image and the corresponding basic road data obtained in the platform external window, match the corresponding basic road data with each road in the road distribution image, mark the road distribution image according to the matching results, and construct the corresponding road traffic image;

The traffic diversion management platform obtains the constructed road traffic image, analyzes and processes it, divides the road according to the intersections in the road traffic image, obtains the corresponding road section information, and sets corresponding marks according to the road name and the division result.

The process of setting a flow monitoring node according to the road traffic image, wherein the flow monitoring node is used to obtain vehicle flow data and vehicle density data at its corresponding position, and marking and storing the data information obtained in each flow monitoring node includes:

Acquire a road traffic image, and acquire corresponding road section information therein according to the road traffic image, and set a data monitoring node according to the set road section information; the data monitoring node is provided with a flow monitoring terminal and a density monitoring terminal; the data monitoring node acquires lane information therein according to the road section information in the road traffic image, and sets corresponding monitoring areas respectively according to the lane information;

The flow monitoring terminal is preset with a flow monitoring area corresponding to each lane information, and video data in the flow monitoring area is obtained; a flow unit time is preset, video frame processing is performed on the obtained video data according to the flow unit time, feature extraction is performed on the video frame within each flow unit time, vehicle image data is obtained, the number of vehicles in the vehicle image data within each lane flow monitoring area within the flow unit time is obtained, lane flow data is obtained, lane flow data corresponding to each lane information in the road section information is obtained, and addition operation is performed on them to obtain vehicle flow data in the road section information.

The density monitoring terminal is preset with density monitoring areas corresponding to each lane information, and video data in the density monitoring area is obtained; a density unit time is preset, and video frame processing is performed on the obtained video data according to the density unit time, and the number of vehicles in the vehicle image data in each lane density monitoring area in each density unit time is obtained to obtain lane density data, and the lane flow data corresponding to each lane information in the road section information is obtained, and encryption operation is performed on it to obtain the vehicle density data in the road section information;

Marking the lane types corresponding to the obtained lane flow data and lane density data;

The vehicle flow data in each road section information and the corresponding lane flow data therein and the vehicle density data in each road section information and the lane density data of the corresponding lane therein are stored, and their collection time is marked according to the flow unit time and the density unit time respectively;

It should be further explained that, in the specific implementation process, the monitoring areas corresponding to the flow monitoring area and the density monitoring area are different, and the collection methods corresponding to the video data are also different.

Acquire historical data information, analyze and process the historical data information, determine the congestion level of the historical data information corresponding to each road section information, and generate the volatility cycle corresponding to each road section information according to the congestion level of the historical data information; the specific implementation process includes:

Acquire historical data information of each road section information, wherein the historical data information includes historical vehicle flow data, historical vehicle density data of the road section information and their corresponding collection time; set corresponding weight factors according to the importance of the historical vehicle flow data and the historical vehicle density data to road congestion, and obtain vehicle comprehensive data by the relationship between the historical vehicle flow data and the corresponding weight factors;

The road traffic image set in the traffic diversion management platform is preset with vehicle flow intervals, vehicle density intervals and vehicle comprehensive intervals of congestion levels corresponding to the corresponding road information, and the congestion levels include no congestion, mild congestion, moderate congestion and severe congestion;

Compare and analyze the obtained vehicle comprehensive data with the vehicle comprehensive interval; determine the vehicle comprehensive interval to which the corresponding vehicle comprehensive data in the corresponding road section information belongs, and determine the congestion level according to the vehicle comprehensive interval to which it belongs;

Analyze and process the historical data information corresponding to each road section information, compare and analyze the vehicle flow data and vehicle density data obtained in the corresponding unit time with the vehicle flow intervals and vehicle density intervals corresponding to different congestion levels, and obtain the congestion level; when the congestion levels corresponding to the intervals to which the vehicle flow data and vehicle density data belong are not equal, mark the historical data information as abnormal; mark and process the road sections with abnormalities in the traffic diversion management platform to avoid unexpected situations;

The congestion level and the corresponding vehicle comprehensive data of the historical data information in each road section that has been compared and analyzed in the corresponding unit time are obtained; the frequency spectrum curve corresponding to the corresponding vehicle comprehensive data in the unit time is set, and the frequency spectrum characteristics of the frequency spectrum curve are extracted according to the frequency spectrum analysis algorithm. It is determined whether there is periodic fluctuation according to the obtained frequency spectrum characteristics. If there is periodic fluctuation, the corresponding fluctuation period is set according to its periodic fluctuation; if there is no periodic fluctuation, the corresponding frequency spectrum curve is extended and repeated analysis is performed until its fluctuation period is obtained;

It should be further explained that, in the specific implementation process, the traffic diversion management platform stores and marks the volatility cycle corresponding to each road section information in the road traffic image; in addition, the traffic diversion management platform updates and corrects the volatility cycle corresponding to each road section information based on the update processing of historical data information, and correlates the corrected volatility cycle with the each road section information in the road traffic image.

The obtained vehicle flow data and vehicle density data are analyzed and processed to obtain the congestion level of the current corresponding road section information, and the congestion level of each road section information in the obtained road traffic image is visualized to obtain a traffic event image. The specific implementation process includes:

Obtaining weight factors corresponding to vehicle flow data and vehicle density data set in the vehicle flow management platform, and analyzing and processing the corresponding vehicle flow data and vehicle density data according to the obtained weight factors to obtain comprehensive vehicle data;

Obtain the vehicle comprehensive interval of the corresponding congestion level of the corresponding road section information stored in the platform; compare and analyze the vehicle comprehensive data obtained in each road section information with its corresponding vehicle comprehensive interval, obtain the congestion level of each road section information, and mark it according to the collection time of vehicle flow data and vehicle density data;

Obtain a road traffic image, and perform visualization processing according to the congestion level corresponding to each road section information within the current acquisition time, wherein the congestion level includes no congestion, light congestion, moderate congestion and severe congestion; when the congestion level is no congestion, the corresponding road section information is marked in green; when the congestion level is light congestion, the corresponding road section information is marked in blue; when the congestion level is moderate congestion, the corresponding road section information is marked in orange; when the congestion level is severe congestion, the corresponding road section information is marked in red; and generate a traffic event image according to the marking result of the corresponding road section information in the road traffic image;

The generated traffic situation image is updated in real time according to the obtained vehicle flow data and vehicle density data.

The traffic diversion management platform sets traffic diversion priorities according to the congestion level and severity from light to heavy, obtains a traffic event image, obtains a road section with a high priority according to the traffic diversion priority, obtains the congestion level of the road section, presets a basic diversion radius according to the congestion level, and obtains the congestion level and volatility period corresponding to other road sections within the basic diversion radius in the traffic event image with the road section as the center;

Mark the congestion levels corresponding to other road sections, obtain the unit time of the volatility cycle to which each other road section belongs according to the volatility cycle of each other road section and the current collection time, and obtain the congestion level corresponding to the next unit time of the volatility cycle according to the current unit time, and record it as the predicted congestion level; mark the predicted congestion level corresponding to other road sections; obtain the location of the corresponding road section and other road sections within the basic diversion radius in the traffic event image and the number of forks between them, and mark the number of forks corresponding to other road sections;

The congestion levels, predicted congestion levels and number of forks corresponding to other road sections within the basic diversion radius are processed respectively, and the correlation data corresponding to different data information between each road section is obtained based on the big data algorithm. The obtained correlation data is multiplied by the congestion level, predicted congestion level and number of forks respectively and the sum is obtained to obtain comprehensive correlation data; a correlation threshold is preset, and when the comprehensive correlation data is greater than or equal to the correlation threshold, it is indicated that there is correlation between the two road sections; when the comprehensive correlation data is less than the correlation threshold, there is no correlation between the two road sections;

Other associated road segments are temporarily stored according to their comprehensive associated data.

Obtain the vehicle flow data and vehicle density data collected on the corresponding road section, obtain the lane type corresponding to the lane flow data and lane density data, process the lane flow data and lane density data according to the lane type, obtain the corresponding average lane flow and average density data according to the lane type, obtain the average vehicle comprehensive data of the corresponding lane type, compare and analyze the average vehicle comprehensive data corresponding to different lane types, obtain the difference data, set the difference threshold according to the minimum average vehicle comprehensive data, compare and analyze the difference data with the difference threshold, and when the difference data is greater than the difference threshold, set lane flexible diversion for the road section; when the difference data is less than or equal to the difference threshold, do not set lane flexible diversion for the road section;

The traffic flow diversion management platform is preset with a traffic light control adjustment curve of average vehicle comprehensive data on travel time, and the average vehicle comprehensive data of the corresponding lane type in the road section is mapped to the traffic light control adjustment curve to obtain the travel time and set the traffic light for flexible diversion;

Generate a traffic flow plan based on the lane flexible traffic flow and traffic light flexible traffic flow obtained on the corresponding road section;

It should be further explained that, in the specific implementation process, flexible lanes are set in the corresponding road sections, and the flexible lanes are used to set corresponding lane types according to needs. The lane types include left-turn lanes, through lanes and right-turn lanes.

Acquire other road sections associated with it, and acquire the current traffic flow data information of the other road sections associated with it and the position relationship between them; the position relationship includes a traffic flow import relationship and a traffic flow export relationship;

When the position relationship between other road sections and the corresponding road sections is a traffic flow import relationship, the average vehicle comprehensive of the road section is obtained and mapped to the traffic light control adjustment curve to obtain its travel time; the slow travel time coefficient is set according to the current congestion level of the road section, and the travel time of the road section is analyzed and processed according to the obtained slow travel time coefficient to obtain the auxiliary travel time of the road section;

When the position relationship between other road sections and the corresponding road sections is a traffic flow derived relationship, the travel time is obtained, and a speed-up travel time coefficient is set according to the current congestion level of the road section; the travel time of the road section is analyzed and processed according to the obtained speed-up travel time coefficient to obtain the auxiliary travel time of the road section;

Generate an auxiliary traffic diversion plan according to the auxiliary travel time corresponding to other road sections associated with the corresponding road section;

It should be further explained that, during the specific implementation process, the coefficient information set in the platform is obtained through analysis and training based on the historical traffic data information of each road section using digital twin technology.

The traffic lights and lane control signals of the corresponding road sections are regulated according to the obtained traffic diversion plan and auxiliary traffic diversion plan, and the traffic lights corresponding to each road section are adjusted according to the generated passing time and auxiliary passing time to complete the traffic diversion and control.

The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims (8)

1. The traffic flow dredging control method based on cloud computing is characterized by comprising the following steps of:

Step S1: setting a traffic flow dredging management platform, acquiring basic road data in an area, constructing a road traffic image according to the basic road data, setting a data monitoring node, acquiring traffic flow data information corresponding to each road section in the road traffic image, and marking the acquisition time of the traffic flow data information;

step S2: acquiring historical traffic flow data information, judging the congestion level corresponding to each road section, generating a corresponding fluctuation period according to the congestion level to which the historical traffic flow data information belongs, and storing the fluctuation period;

Step S3: according to the obtained traffic flow data information, obtaining the congestion level corresponding to each road section at the current moment in the road traffic image, and carrying out visual processing on the congestion level to generate a traffic situation image;

Step S4: presetting traffic flow dredging priority according to the congestion level, acquiring a road section with high traffic flow dredging priority in a traffic situation image, presetting a basic dredging radius, acquiring the congestion level of other road sections within the basic dredging radius range and the fluctuation period in the road section, judging whether the road section has a relevance relation with the road section according to the congestion level at the current moment and the predicted congestion level at the next moment in the fluctuation period;

Step S5: analyzing and processing the current acquired traffic flow data information of the road section, generating a corresponding dispersion scheme according to the processing result, and generating an auxiliary dispersion scheme according to the corresponding traffic flow data information of other road sections with association relation with the road section;

step S6: and regulating and controlling traffic lights and lanes of the corresponding road sections according to the obtained dredging scheme and the auxiliary dredging scheme, and completing traffic flow data management and control.

2. The traffic flow grooming control method based on cloud computing as claimed in claim 1, wherein the process of constructing road traffic images and collecting traffic flow data information comprises the following steps:

Setting a traffic flow dredging management platform, wherein a platform external window is arranged, and the platform external window is used for acquiring corresponding road distribution images based on satellite image data and inputting basic road data by staff; the basic road data are the name of the corresponding road section, the lane type information, the intersection information, the road section position relation and the vehicle comprehensive section; constructing a road traffic image based on the road distribution image and the basic road data;

Setting a data monitoring node according to a road traffic image, wherein a corresponding data acquisition terminal is arranged in the data monitoring node, the data acquisition terminal is used for acquiring traffic flow data information of a corresponding road section, the traffic flow data information comprises vehicle flow data and vehicle density data, and the vehicle flow data comprises lane flow data corresponding to each lane in the road section; the vehicle density data comprises lane density data corresponding to each lane in the road section.

3. The traffic grooming control method based on cloud computing according to claim 2, wherein the process of obtaining the volatility period of each road segment comprises:

The traffic flow dredging management platform stores historical traffic flow data information corresponding to each road section in the road traffic image, acquires the historical traffic flow data information, sets corresponding weight factors according to the importance degree of the historical traffic flow data and the historical traffic density data on road congestion, acquires vehicle comprehensive data according to the relation between the historical traffic flow data and the corresponding weight factors, and acquires acquisition time of the vehicle comprehensive data;

Acquiring a vehicle comprehensive interval preset with a congestion level corresponding to the corresponding road information in a road traffic image; the congestion level sequentially comprises non-congestion, light congestion, medium congestion and serious congestion according to the severity from light to heavy; comparing and analyzing the obtained vehicle comprehensive data with a vehicle comprehensive interval, and judging the congestion level of the vehicle comprehensive interval according to the vehicle comprehensive interval to which the vehicle comprehensive data belongs;

Setting a corresponding spectrum curve according to the acquired vehicle comprehensive data, extracting spectrum characteristics of the spectrum curve according to a spectrum analysis algorithm, acquiring periodic fluctuation of the spectrum curve according to the acquired spectrum characteristics, marking the congestion level of the vehicle comprehensive data corresponding to each unit time in the periodic fluctuation, generating a fluctuation period of a corresponding road section, and storing the fluctuation period.

4. A traffic flow grooming control method based on cloud computing as claimed in claim 3, wherein the process of generating traffic situation images comprises:

The method comprises the steps of obtaining vehicle flow data information, analyzing and processing the obtained vehicle flow data information, obtaining vehicle comprehensive data corresponding to the vehicle flow data information, comparing and analyzing the obtained vehicle comprehensive data in each road section information with a corresponding vehicle comprehensive section, obtaining congestion levels belonging to each road section information, and marking the collection time of the congestion levels;

Acquiring a road traffic image, and performing visual processing on the road traffic image according to the congestion level corresponding to each road section information in the current acquisition time to generate a traffic situation image; and updating the obtained traffic situation image in real time according to the acquisition time.

5. The traffic grooming control method based on cloud computing as claimed in claim 4, wherein the process of obtaining the association between the road segments comprises:

The traffic flow dispersion management platform is internally provided with traffic flow dispersion priority from light to heavy according to the severity of the traffic flow dispersion priority, a traffic situation image is obtained, a road section with high priority is obtained according to the traffic flow dispersion priority, the congestion level of the road section is obtained, a basic dispersion radius is preset according to the congestion level, and the road section is taken as the center to obtain the congestion level and the fluctuation period corresponding to other road sections in the basic dispersion radius range in the traffic situation image;

Marking the congestion level corresponding to other road sections, acquiring the unit time of the fluctuation period of each other road section according to the fluctuation period of each other road section and the acquisition time of the current moment, acquiring the congestion level corresponding to the next unit time of the fluctuation period according to the current unit time, and marking the congestion level as the predicted congestion level; marking the predicted congestion level corresponding to other road sections; acquiring positions of corresponding road sections and other road sections in a basic dredging radius range in the traffic situation image and the number of the intersections of intervals between the road sections, and marking the number of the intersections corresponding to the other road sections;

processing the congestion level, the predicted congestion level and the number of intersections corresponding to other road sections within the basic dredging radius range respectively, acquiring correlation data corresponding to different data information among the road sections based on a big data algorithm, multiplying the acquired correlation data by the congestion level, the predicted congestion level and the number of intersections respectively, and acquiring the sum of the correlation data to acquire comprehensive correlation data; presetting an association threshold, and when the comprehensive association data is greater than or equal to the association threshold, associating the two road sections on the surface; when the comprehensive association data is smaller than the association threshold value, no association exists between the two road sections; and temporarily storing other road sections with relevance according to the comprehensive relevance data.

6. The traffic flow grooming control method based on cloud computing according to claim 5, wherein the process of obtaining the grooming scheme corresponding to the road section comprises:

Acquiring vehicle flow data and vehicle density data acquired by a corresponding road section, acquiring lane types corresponding to the lane flow data and the lane density data, processing the lane flow data and the lane density data according to the lane types, acquiring average vehicle comprehensive data corresponding to the lane types according to the lane types, comparing and analyzing the average vehicle comprehensive data corresponding to different lane types to acquire difference data, setting a difference threshold according to the minimum average vehicle comprehensive data, comparing and analyzing the difference data with the difference threshold, and setting a lane for the road section to flexibly dredge when the difference data is larger than the difference threshold; when the difference value data is smaller than or equal to the difference value threshold value, the road section is not provided with the lane flexible guiding;

The traffic light control and regulation curve of the average vehicle comprehensive data about the traffic time is preset in the traffic flow dredging management platform, the average vehicle comprehensive data of the corresponding lane type in the road section is mapped into the traffic light control and regulation curve, the traffic time is acquired, and the traffic light is set to be flexibly dredged;

and flexibly guiding the lanes and the traffic lights obtained by the corresponding road sections to generate a guiding scheme.

7. The traffic grooming control method based on cloud computing as claimed in claim 6, wherein the process of setting the auxiliary grooming scheme according to the correlation result comprises:

Acquiring other road sections with relevance, and acquiring traffic flow data information at the current moment and the position relation between the traffic flow data information and the other road sections with relevance; the position relationship comprises a traffic flow import relationship and a traffic flow export relationship;

when the position relationship between other road sections and the corresponding road sections is a traffic flow guiding relationship, acquiring average vehicle synthesis of the road sections, mapping the average vehicle synthesis to a traffic light control and regulation curve, and acquiring the passing time of the traffic light control and regulation curve; setting a slow transit time coefficient according to the current congestion level of the road section, and analyzing and processing the transit time of the road section according to the obtained slow transit time coefficient to obtain the auxiliary transit time of the road section;

when the position relation between other road sections and the corresponding road sections is a traffic flow guiding relation, acquiring the passing time of the road sections, and setting a traffic time accelerating coefficient according to the current congestion level of the road sections; analyzing and processing the traffic time of the road section according to the obtained accelerated traffic time coefficient to obtain the auxiliary traffic time of the road section;

and generating an auxiliary dispersion scheme according to the auxiliary transit time corresponding to the other road sections with the relevance of the corresponding road sections.

8. The cloud computing-based traffic grooming control method as recited in claim 7, wherein the traffic grooming control process comprises:

And regulating and controlling traffic lights and lane control signals of corresponding road sections according to the obtained dredging scheme and auxiliary dredging scheme, regulating the traffic lights corresponding to each road section according to the generated passing time and auxiliary passing time, and completing traffic flow dredging and controlling.