CN112820108B - Self-learning road network traffic state analysis and prediction method - Google Patents
Self-learning road network traffic state analysis and prediction method Download PDFInfo
- Publication number
- CN112820108B CN112820108B CN202110036476.0A CN202110036476A CN112820108B CN 112820108 B CN112820108 B CN 112820108B CN 202110036476 A CN202110036476 A CN 202110036476A CN 112820108 B CN112820108 B CN 112820108B
- Authority
- CN
- China
- Prior art keywords
- road network
- traffic
- intersection
- data
- vehicle
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000004458 analytical method Methods 0.000 title claims abstract description 20
- 238000011144 upstream manufacturing Methods 0.000 claims abstract description 43
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000012544 monitoring process Methods 0.000 claims description 5
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000002596 correlated effect Effects 0.000 claims 1
- 238000011156 evaluation Methods 0.000 abstract description 2
- 238000005457 optimization Methods 0.000 abstract description 2
- 238000007619 statistical method Methods 0.000 abstract description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 229920006395 saturated elastomer Polymers 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
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
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- 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
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Chemical & Material Sciences (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Analytical Chemistry (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Entrepreneurship & Innovation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Bioinformatics & Computational Biology (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a self-learning road network traffic state analysis and prediction method, which comprises the following steps: (1) constructing an urban road network model, configuring basic data and establishing an urban road network topological structure; (2) acquiring real-time vehicle passing information and calculating vehicle passing data; (3) grouping and managing vehicle passing data again, and analyzing the road section traffic running state between the upstream and downstream intersections; (4) analyzing the current urban road network traffic state, and calculating various road network traffic indexes; (5) and predicting the traffic state of the urban road network in the future, and carrying out statistical learning based on historical traffic data to automatically optimize a prediction model. The invention realizes the analysis and evaluation of the whole traffic running state of the road network level, can predict the running state of the future road network, provides effective data for traffic priority control and optimization, and simultaneously, continuously corrects the parameter index in the prediction model by a statistical method based on the characteristic of continuous evolution of the urban traffic state, thereby improving the accuracy of the prediction result.
Description
Technical Field
The invention relates to the technical field of intelligent traffic, in particular to a self-learning road network traffic state analysis and prediction method.
Background
Along with the rapid development of social economy, the quantity of motor vehicles kept in China is rapidly increased, and the urban traffic pressure is higher and higher, so that increasingly serious traffic jam and traffic safety problems are brought. Meanwhile, technologies such as big data, artificial intelligence and 5G communication are gradually mature and begin to be popularized in a large range, a new solution is provided for the traffic industry, and the main development trend is towards solving traffic problems by applying an informatization means.
The urban road network traffic state is important basic data of traffic management work, scientific and reasonable organization and control of road traffic can be realized according to an accurate traffic state analysis result, limited road resources are fully utilized, and road traffic efficiency is improved. Common traffic detection means mainly comprise coils, geomagnetism, microwaves, videos and the like, and with the wide-range popularization and application of a digital video sensing technology in the traffic field, vehicle traffic information extracted from video images becomes the most valuable data in the traffic state analysis and prediction process.
At present, a traffic state analysis method based on vehicle traffic information mainly performs cluster statistics on original data according to road sections, does not fully consider traffic influence of upstream and downstream intersections, and cannot accurately evaluate urban traffic from a road network level. Meanwhile, the prior art is used for summarizing and analyzing the traffic state which occurs already, has certain hysteresis, and cannot meet the requirement of traffic control on future prediction data. Urban traffic is a constantly changing process, some traffic parameters in an analysis and prediction model need to be constantly corrected to adapt to the changing trend of the urban traffic, and the prior art can only adjust the urban traffic in a manual observation mode and cannot automatically analyze and evolve through traffic state data.
Disclosure of Invention
The purpose of the invention is as follows: the invention aims to provide a self-learning road network traffic state analysis and prediction method capable of realizing monitoring, analysis and prediction of the traffic operation situation of the whole road network.
The technical scheme is as follows: the invention relates to a self-learning road network traffic state analysis and prediction method, which comprises the following steps:
(1) constructing an urban road network model, configuring basic data of road sections, intersections and lanes, and establishing an urban road network topological structure;
(2) acquiring real-time vehicle passing information, and calculating vehicle passing data according to the upstream and downstream relations of the intersection;
(3) grouping and managing vehicle passing data again, and analyzing the road section traffic running state between the upstream and downstream intersections;
(4) analyzing the whole traffic state of the current urban road network, and calculating indexes such as road network load-bearing traffic flow, traffic operation indexes and the like;
(5) and predicting the whole traffic state of the future urban road network, performing statistical learning based on historical traffic data, and automatically optimizing a prediction model.
Preferably, the step (1) of constructing an urban road network model, configuring basic data of road sections, intersections and lanes, and establishing an urban road network topological structure comprises the following specific steps:
(11) configuring all intersections in the urban road network range, wherein the attributes of intersection objects include but are not limited to codes, names, types and geographic coordinates;
(12) configuring all road sections in the range of the urban road network, wherein the attributes of the section objects include but are not limited to codes, names, types, front intersection codes, directions of the located intersections, speed limits, the number of lanes, lengths and geographic coordinates;
(13) configuring all intersection entrance direction lanes in an urban road network range, wherein the attributes of lane objects include but are not limited to intersection codes, intersection directions, lane numbers, lane widths, lane types, detector types and detector numbers;
(14) and (3) establishing a topological structure of the urban road network and configuring the upstream and downstream relations of the intersection. The topological structure comprises crossing codes, crossing directions, upstream crossing codes, upstream crossing distances, turning directions, left-turning directions, straight directions, right-turning directions and free flow rates;
preferably, the step (2) acquires real-time vehicle passing information, and calculates vehicle passing data according to the upstream and downstream relationship of the intersection, and the specific steps are as follows:
(21) the method comprises the steps of (1) butting vehicle monitoring systems such as an intersection electric police, an ETC (electronic toll collection), an RFID (radio frequency identification device) and the like, acquiring real-time vehicle passing information, matching the real-time vehicle passing information with lane data in a road network model, and obtaining lane passing data after data association;
(22) according to the intersection codes and the intersection direction information in the lane vehicle-passing data, traversing the road network topological structure to find the upstream intersection code information.
(23) And searching the passing information of the vehicle at the upstream crossing according to the code of the upstream crossing and the number plate of the vehicle, combining the passing information of the vehicle at the current crossing and the vehicle at the upstream crossing, and calculating the vehicle passing data.
Preferably, in the step (3), the vehicle traffic data is managed in groups again, and the road section traffic running state between the upstream and downstream intersections is analyzed, specifically including the steps of:
(31) the vehicle passing data are grouped according to crossing codes, crossing directions and current lane types, sequencing is carried out according to the passing time of the current crossing, and vehicles passing through a crossing stop line in the same signal lamp period are extracted as a vehicle passing data set { v }1,…,vn}。
(32) The passing time t of each vehicle in the vehicle passing data set is extracted, and a passing time queue { t is established according to the sequence from small to large1,…,tn}；
(33) Calculating the median transit time t0.5；
When the length n of the transit time queue is odd, t0.5＝t(n+1)/2
When the transit time queue length n is even,
(34) calculating the average delay time taAverage delay time ratio α;
the average delay time calculation formula is as follows:
the average delay time ratio calculation formula is as follows: α ═ ta÷t0.5)×100％
(35) And analyzing the traffic state of the road sections between the adjacent intersections according to the traffic flow and the average delay time, wherein the corresponding judgment rule is as shown in the following table.
Preferably, the step (4) of analyzing the overall traffic state of the current urban road network and calculating indexes such as road network load-bearing traffic flow and traffic operation index includes the following specific steps:
(41) summarizing the vehicle traffic data of the latest p minutes in the road network into a data queue, wherein the traffic data with the same number plate number only retains the latest elapsed time, and the data volume in the queue is the traffic flow borne by the current road network;
(42) calculating a road network traffic operation index c according to the vehicle travel time, the free flow time and the traffic flow of the road section, wherein the calculation formula is as follows;
(43) and analyzing the whole traffic state of the urban road network according to the road network traffic operation index c, wherein the corresponding judgment rule is as shown in the table below.
| Traffic running index c | [0，1.6) | [1.6,2.7) | [2.7，4.2) | [4.2 |
| Road network traffic status | Clear | Light congestion | Congestion | Severe congestion |
Preferably, the whole traffic state of the urban road network in the future p minutes is predicted in the step (5), statistical learning is carried out based on historical traffic data, and a prediction model is automatically optimized.
The urban road network traffic state has obvious time correlation, and the characteristic value and the growth trend of the traffic state at the same time point are very consistent in a continuous period of time. Therefore, the time characteristics of the historical data of the road network traffic operation indexes are extracted, and a reference sequence of the road network traffic state can be established as the basis of the prediction model. And correcting the traffic state prediction index of p minutes in the future by combining the traffic state in the reference sequence with the current traffic volume.
The method comprises the following specific steps:
(51) according to the urban road network traffic operation index sequence of the current day { c1，…，ckAnd a reference sequence { cb }1，…，cbnPredicting the traffic operation index c of the urban road network in the next statistical period (p minutes)k+1。
(52) Extracting traffic operation indexes of the current time point i of the last 90 days from the road network traffic operation index historical data set, and arranging { c) according to the sequence from small to bigi1,…,cijCalculating a traffic operation index reference value cb of the current time point ii；
When the number j of data samples is odd, k is (j +1)/2, cbi＝cik
When the number j of data samples is even, m is j/2,
cbi＝(cim+cin)/2
(53) automatic updating traffic operation index reference sequence { cb1,…,cbnIn cbiFor the next prediction analysis.
Has the advantages that: compared with the prior art, the invention has the following advantages: 1. by constructing an urban road network model, the analysis and evaluation of the whole traffic running state of a road network layer are realized; 2. a statistical learning model is established based on historical traffic operation data, the future road network operation state can be predicted, and effective data is provided for traffic priority control and optimization; 3. in order to meet the characteristic of continuous evolution of urban traffic states, parameter indexes in the prediction model are continuously corrected through a statistical method, and the accuracy of a prediction result is improved.
Drawings
FIG. 1 is a flow chart of the steps of the present invention.
Detailed Description
The technical scheme of the invention is further explained by combining the attached drawings.
As shown in fig. 1, the self-learning road network traffic state analyzing and predicting method of the present invention comprises the following steps:
(1) constructing an urban road network model, configuring basic data of road sections, intersections and lanes, and establishing an urban road network topological structure;
(2) acquiring real-time vehicle passing information, and calculating vehicle passing data according to the upstream and downstream relations of the intersection;
(3) grouping and managing vehicle passing data again, and analyzing the road section traffic running state between the upstream and downstream intersections;
(4) analyzing the whole traffic state of the current urban road network, and calculating indexes such as road network load-bearing traffic flow, traffic operation indexes and the like;
(5) and predicting the whole traffic state of the future urban road network, performing statistical learning based on historical traffic data, and automatically optimizing a prediction model.
The method comprises the following steps of (1) constructing an urban road network model, configuring basic data of road sections, intersections and lanes, and establishing an urban road network topological structure, wherein the method specifically comprises the following steps:
(11) configuring all intersections in the urban road network range, wherein the attributes of intersection objects include but are not limited to codes, names, types and geographic coordinates;
the intersections are intersections between roads, are key nodes for running and controlling the traffic flow of the roads, and can be divided into important intersections, secondary intersections and general intersections according to the traffic flow characteristics.
(12) Configuring all road sections in the range of the urban road network, wherein the attributes of the section objects include but are not limited to codes, names, types, front intersection codes, directions of the located intersections, speed limits, the number of lanes, lengths and geographic coordinates;
the road sections are configured according to the driving direction of the motor vehicle, such as a road passing in both directions from south to north, and are configured into two road section objects from south to north and from north to south according to the driving direction. Each road segment starts from the stop line of the upstream intersection and ends at the stop line of the adjacent downstream intersection.
The front intersection is the first intersection reached when the vehicle travels along the road section driving direction, and the coding value of the intersection is taken as the front intersection coding value of the road section.
(13) Configuring all intersection entrance direction lanes in an urban road network range, wherein the attributes of lane objects include but are not limited to intersection codes, intersection directions, lane numbers, lane widths, lane types, detector types and detector numbers;
the direction of the intersection is the direction of the position of the lane relative to the position of the center point of the intersection. The lane types comprise turning around, left turning, straight going, right turning, left straight right, left turning, turning around and straight going.
(14) And (3) establishing a topological structure of the urban road network and configuring the upstream and downstream relations of the intersection. The topological structure comprises crossing codes, crossing directions, upstream crossing codes, upstream crossing distances, turning directions, left-turning directions, straight directions, right-turning directions and free flow rates;
the value of the free flow rate is the highest speed limit value of the road.
The step (2) of obtaining real-time vehicle passing information and calculating vehicle passing data according to the upstream and downstream relations of the intersection comprises the following specific steps:
(21) the method comprises the steps of (1) butting vehicle monitoring systems such as an intersection electric police, an ETC (electronic toll collection), an RFID (radio frequency identification device) and the like, acquiring real-time vehicle passing information, matching the real-time vehicle passing information with lane data in a road network model, and obtaining lane passing data after data association;
the lane passing data includes contents such as vehicle number plate, vehicle type, passing time, crossing code, crossing direction, lane number and the like.
(22) According to the intersection codes and the intersection direction information in the lane vehicle-passing data, traversing the road network topological structure to find the upstream intersection code information.
(23) And searching the passing information of the vehicle at the upstream intersection according to the code of the upstream intersection and the number plate of the vehicle, combining the passing information of the vehicle at the current intersection and the upstream intersection, and calculating the vehicle passing data.
The vehicle passing data comprises a vehicle number plate, a vehicle type, a current intersection code, a current intersection direction, current intersection passing time, a current lane number, a current lane type, an upstream intersection code, an upstream intersection direction, an upstream lane number, upstream intersection passing time, an upstream intersection distance and passing time;
the transit time calculation formula is as follows: t is tpass＝tend-tstart
Wherein,
tpass: vehicle transit time in seconds
tend: the unit of the current intersection passing time point is second
tstart: the time point of the upstream crossing is passed in seconds
In the step (3), vehicle traffic data is managed in groups again, and the road section traffic running state between the upstream and downstream intersections is analyzed, and the specific steps are as follows:
(31) the vehicle passing data are grouped according to crossing codes, crossing directions and current lane types, sequencing is carried out according to the passing time of the current crossing, and vehicles passing through a crossing stop line in the same signal lamp period are extracted as a vehicle passing data set { v }1,…,vn}。
(32) Extracting the passing time t of each vehicle in the vehicle passing data set, and establishing a passing time queue { t) according to the sequence from small to large1,…,tn}；
(33) Calculating the median transit time t0.5；
When n is an odd number, t0.5＝t(n+1)/2
When n is an even number, the number of n,
wherein,
t0.5: median of transit time of all vehicles in the queue, in seconds
n: the number of data in the queue is one
(34) Calculating the average delay time taAverage delay time ratio α;
the average delay time calculation formula is as follows:
wherein,
ta: average delay time in seconds
t0.5: median transit time in seconds
d: the road network topological relation data is concentrated with the distance of the upstream intersection in meters
s: free flow rate in kilometers per hour of road section
The average delay time ratio calculation formula is as follows: α ═ ta÷t0.5)×100％
Wherein,
α: average delay time ratio
ta: average delay time in seconds
t0.5: median transit time in seconds
(35) And analyzing the traffic state of the road sections between the adjacent intersections according to the traffic flow and the average delay time, wherein the corresponding judgment rule is as shown in the following table.
The unit of traffic flow is (vehicle/lane), and the unit of delay time is (second).
When each lane continuously passes less than 8 vehicles, the traffic flow is in an unsaturated state, the intersection delay time is mainly caused by the waiting time of a red light at the time, but if the delay time exceeds 270s, the abnormal events such as irregular driving or traffic accidents occur on the road section, the driving of the vehicles on the changed road section is influenced, and the longer time delay is caused.
When each lane continuously passes more than 8 vehicles, the traffic flow is in a half-saturated and saturated state, at this time, the intersection delay time comprises red light waiting time and delay time caused by vehicle queuing, and the traffic state can be judged according to different delay time lengths.
The step (4) of analyzing the whole traffic state of the current urban road network and calculating indexes such as road network load-bearing traffic flow, traffic operation indexes and the like comprises the following specific steps:
(41) summarizing the vehicle traffic data of the latest p minutes in the road network into a data queue, wherein the traffic data with the same number plate number only retains the latest elapsed time, and the data volume in the queue is the traffic flow borne by the current road network;
(42) calculating a road network traffic operation index c according to the vehicle travel time, the free flow time and the traffic flow of the road section, wherein the calculation formula is as follows;
wherein,
c: road network traffic operation index
ti: median vehicle travel time in seconds for the last p minutes of road segment i
ni: the latest p minutes of traffic flow of the road section i, the unit is a vehicle
di: distance between the upstream and downstream intersections of the road section i in meters
si: free flow rate in kilometers per hour for section i
(43) And analyzing the whole traffic state of the urban road network according to the road network traffic operation index c, wherein the corresponding judgment rule is as shown in the table below.
| Traffic running index c | [0,1.6) | [1.6，2.7) | [2.7，4.2) | [4.2 |
| Road network traffic status | Clear | Light congestion | Congestion | Severe congestion |
And (5) predicting the whole traffic state of the urban road network in the future p minutes, performing statistical learning based on historical traffic data, and automatically optimizing a prediction model.
The urban road network traffic state has obvious time correlation, and the characteristic value and the growth trend of the traffic state at the same time point are very consistent in a continuous period of time. Therefore, the time characteristics of the historical data of the road network traffic operation indexes are extracted, and a reference sequence of the road network traffic state can be established as the basis of the prediction model. And correcting the traffic state prediction index of p minutes in the future by combining the traffic state in the reference sequence with the current traffic volume.
The method comprises the following specific steps:
(51) according to the urban road network traffic operation index sequence of the current day { c1，…，ckAnd a reference sequence { cb }1,…，cbnPredicting the traffic operation of city road network in the next statistical period (p minutes)Index ck+1。
The calculation formula is as follows:
ck+1＝cbk+1+(ck-cbk)×0.5+(ck-1-cbk-1)×0.3+(ck-2-cbk-2)×0.2
wherein,
ck+1: traffic operation index of next cycle
cbk+1: traffic running index of next period in reference sequence
ck: traffic operation index at current time point
cbk: traffic operation index of current time point in reference sequence
(52) Extracting traffic operation indexes corresponding to the current time point of the last 90 days from the road network traffic operation index historical data set, and arranging the { c in the order from small to bigi1,…,cijAnd calculating a traffic operation index reference value cb of the current time pointi；
When the number j of data samples is odd, k is (j +1)/2, cbi＝cik
When the number j of data samples is even, m is j/2,
cbi＝(cim+cin)/2
wherein,
j: number of data samples
i: traffic operation index subscript corresponding to current time point
k: queue data sequence number when j is odd
m: queue data sequence number 1 when j is even number
n: queue data sequence number 2 when j is even
cbi: recalculated current time point traffic operation index reference value
(53) Automatic updating traffic operation index reference sequence { cb1,…,cbnIn cbiValue of (1) forAnd (4) carrying out primary prediction analysis.
Claims (6)
1. A self-learning road network traffic state analysis and prediction method is characterized by comprising the following steps:
(1) constructing an urban road network model, configuring basic data of road sections, intersections and lanes, and establishing an urban road network topological structure;
(2) acquiring real-time vehicle passing information, and calculating vehicle passing data according to the upstream and downstream relations of the intersection;
(3) grouping and managing vehicle passing data again, and analyzing the road section traffic running state between the upstream and downstream intersections;
(31) the vehicle passing data are grouped according to crossing codes, crossing directions and current lane types, sequencing is carried out according to the passing time of the current crossing, and vehicles passing through a crossing stop line in the same signal lamp period are extracted as a vehicle passing data set { v }1,…,vn}；
(32) The passing time t of each vehicle in the vehicle passing data set is extracted, and a passing time queue { t is established according to the sequence from small to large1,…,tn}；
(33) Calculating the median transit time t0.5；
When the length n of the transit time queue is odd, t0.5＝t(n+1)/2
When the transit time queue length n is even,
(34) calculating the average delay time taAverage delay time ratio α;
the average delay time calculation formula is as follows:
the average delay time ratio calculation formula is as follows: α ═ ta÷t0.5)×100％
(35) Analyzing the traffic state of the road sections between adjacent intersections according to the traffic flow and the average delay time;
(4) analyzing the whole traffic state of the current urban road network, and calculating various indexes including road network load-bearing traffic flow and traffic operation indexes;
(41) summarizing the vehicle traffic data of the latest p minutes in the road network into a data queue, wherein the traffic data with the same number plate number only retains the latest elapsed time, and the data volume in the queue is the traffic flow borne by the current road network;
(42) calculating a road network traffic operation index c according to the vehicle travel time, the free flow time and the traffic flow of the road section, wherein the calculation formula is as follows;
wherein,
c: road network traffic operation index;
ti: the median of the vehicle travel time of the last p minutes of the road segment i, the unit being second;
ni: the traffic flow of the section i in the last p minutes is in units of vehicles;
di: the distance between the upstream intersection and the downstream intersection of the road section i is measured in meters;
si: the free flow rate of the road section i is kilometer per hour;
(43) analyzing the whole traffic state of the urban road network according to the road network traffic operation index c;
(5) predicting the whole traffic state of a future urban road network, performing statistical learning based on historical traffic data, and automatically optimizing a prediction model;
(51) according to the urban road network traffic operation index sequence of the current day { c1,…,ckAnd a reference sequence { cb }1,…,cbnPredicting traffic operation index c of urban road network in next statistical periodk+1；
(52) Extracting traffic operation indexes of the current time point i of the last 90 days from the road network traffic operation index historical data set, and arranging the traffic operation indexes in a descending orderColumn { ci1,…,cijCalculating a traffic operation index reference value cb of the current time point ii；
When the number j of data samples is odd, k is (j +1)/2, cbi＝cik
When the number j of data samples is even, m is j/2,
cbi＝(cim+cin)/2
(53) automatic updating traffic operation index reference sequence { cb1,…,cbnIn cbiFor the next predictive analysis.
2. The self-learning road network traffic status analyzing and predicting method according to claim 1, wherein said step (1) comprises the steps of:
(11) configuring all intersections in the urban road network range, wherein the attributes of intersection objects comprise codes, names, types and geographic coordinates;
(12) configuring attributes of all road sections in the urban road network range;
(13) configuring the attributes of all intersection inlet direction lanes in the urban road network range;
(14) and (3) establishing a topological structure of the urban road network and configuring the upstream and downstream relations of the intersection.
3. The self-learning road network traffic status analysis and prediction method of claim 2, characterized in that: the attributes of the road section comprise codes, names, types, front intersection codes, the direction of the intersection, speed limit, the number of lanes, length and geographic coordinates.
4. The self-learning road network traffic status analysis and prediction method of claim 2, characterized in that: the attributes of the lanes comprise intersection codes, intersection directions, lane numbers, lane widths, lane types, detector types and detector numbers.
5. The self-learning road network traffic status analysis and prediction method of claim 2, characterized in that: the topological structure comprises intersection codes, intersection directions, upstream intersection codes, upstream intersection distances, turning directions, left-turning directions, straight directions, right-turning directions and free flow rates.
6. The self-learning road network traffic status analyzing and predicting method according to claim 1, wherein said step (2) comprises the steps of:
(21) the method comprises the steps that a vehicle monitoring system is connected, wherein the vehicle monitoring system comprises an intersection electric police, an ETC and an RFID, real-time vehicle passing information is obtained, the vehicle passing information is matched with lane data in a road network model, and the lane passing data is obtained after the data are correlated;
(22) traversing a road network topological structure to find upstream intersection code information according to intersection codes and intersection direction information in the lane vehicle-passing data;
(23) and searching the passing information of the vehicle at the upstream intersection according to the code of the upstream intersection and the number plate of the vehicle, combining the passing information of the vehicle at the current intersection and the upstream intersection, and calculating the vehicle passing data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110036476.0A CN112820108B (en) | 2021-01-12 | 2021-01-12 | Self-learning road network traffic state analysis and prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110036476.0A CN112820108B (en) | 2021-01-12 | 2021-01-12 | Self-learning road network traffic state analysis and prediction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112820108A CN112820108A (en) | 2021-05-18 |
| CN112820108B true CN112820108B (en) | 2022-05-24 |
Family
ID=75868888
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110036476.0A Active CN112820108B (en) | 2021-01-12 | 2021-01-12 | Self-learning road network traffic state analysis and prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112820108B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113793500B (en) * | 2021-09-14 | 2022-07-26 | 上海天壤智能科技有限公司 | Method and system for constructing computable road network of urban traffic road |
| CN113936454B (en) * | 2021-09-22 | 2023-02-21 | 上海宝康电子控制工程有限公司 | Information processing method and system based on track fusion |
| CN113870570B (en) * | 2021-12-02 | 2022-02-18 | 湖南省交通科学研究院有限公司 | ETC-based road network operation state method, system and storage medium |
| CN114419907B (en) * | 2021-12-29 | 2023-10-27 | 联通智网科技股份有限公司 | Method, device, terminal equipment and medium for judging accident multiple road sections |
| CN114822016B (en) * | 2022-03-11 | 2023-07-25 | 上海工程技术大学 | Road section uniform speed estimation system based on GPS data flow |
| CN114822019A (en) * | 2022-03-31 | 2022-07-29 | 阿里巴巴（中国）有限公司 | Traffic information processing method and device |
| CN114842647B (en) * | 2022-05-10 | 2023-06-13 | 华人运通(上海)自动驾驶科技有限公司 | Method, product and system for providing electronic horizon service for intersection |
| CN114611337B (en) * | 2022-05-11 | 2022-09-23 | 深圳市城市交通规划设计研究中心股份有限公司 | Distributed traffic simulation method and device and storage medium |
| CN115050179B (en) * | 2022-05-26 | 2023-10-27 | 昆明理工大学 | Intersection traffic prediction and method for predicting intersection traffic behavior and static state on path of intersection traffic |
| CN117409569A (en) * | 2023-08-21 | 2024-01-16 | 广东飞翔云计算有限公司 | Intelligent traffic system and method based on big data |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN106816009B (en) * | 2017-02-28 | 2019-06-21 | 广东省交通运输档案信息管理中心 | Highway real-time traffic congestion road conditions detection method and its system |
| CN108629974B (en) * | 2018-05-17 | 2020-09-08 | 电子科技大学 | Traffic operation index establishing method considering urban road traffic network characteristics |
| CN110807919A (en) * | 2019-10-22 | 2020-02-18 | 浙江大学 | Urban road network traffic operation situation evaluation method based on vehicle passing data |
| CN111145546B (en) * | 2019-12-27 | 2021-02-12 | 银江股份有限公司 | Urban global traffic situation analysis method |
-
2021
- 2021-01-12 CN CN202110036476.0A patent/CN112820108B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112820108A (en) | 2021-05-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112820108B (en) | Self-learning road network traffic state analysis and prediction method | |
| WO2019047905A1 (en) | Road traffic analysis system, method and apparatus | |
| CN108629973A (en) | Road section traffic volume congestion index computational methods based on fixed test equipment | |
| CN102708698B (en) | Vehicle optimal-path navigation method based on vehicle internet | |
| CN108734955B (en) | Method and device for predicting road condition state | |
| CN102855760B (en) | On-line queuing length detection method based on floating vehicle data | |
| CN103996289B (en) | A kind of flow-speeds match model and Travel Time Estimation Method and system | |
| CN111008223B (en) | Regional traffic jam correlation calculation method based on space-time correlation rule | |
| CN108053645A (en) | A kind of signalized intersections cycle flow estimation method based on track data | |
| CN110491158B (en) | Bus arrival time prediction method and system based on multi-metadata fusion | |
| CN104217605A (en) | Bus arrival time estimation method and device | |
| CN112767683B (en) | Path induction method based on feedback mechanism | |
| CN102087788A (en) | Method for estimating traffic state parameter based on confidence of speed of float car | |
| CN109272168A (en) | Urban rail transit passenger flow change trend prediction method | |
| CN109215350A (en) | A kind of short-term traffic status prediction method based on RFID electronic license plate data | |
| CN114202120A (en) | Urban traffic travel time prediction method aiming at multi-source heterogeneous data | |
| CN110889444B (en) | Driving track feature classification method based on convolutional neural network | |
| CN112926768B (en) | Ground road lane-level traffic flow prediction method based on space-time attention mechanism | |
| CN106910350B (en) | A method of finding signalized crossing group critical path | |
| CN109489679B (en) | Arrival time calculation method in navigation path | |
| CN107527501A (en) | The building method of travel time data and the method for predicting the motorway journeys time between a kind of highway station | |
| CN109615865B (en) | OD data increment based iterative road section traffic flow estimation method | |
| CN114708746A (en) | Traffic signal prompting method and system for smart city | |
| CN115601983A (en) | Method, device, equipment and storage medium for determining cycle duration of traffic signal lamp | |
| CN113362605A (en) | Distributed traffic flow optimization system and method based on potential homogeneous region identification |
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 |