CN116611586A - Newly built road network flow prediction method and system based on double-layer heterogeneous network - Google Patents
Newly built road network flow prediction method and system based on double-layer heterogeneous network Download PDFInfo
- Publication number
- CN116611586A CN116611586A CN202310882561.8A CN202310882561A CN116611586A CN 116611586 A CN116611586 A CN 116611586A CN 202310882561 A CN202310882561 A CN 202310882561A CN 116611586 A CN116611586 A CN 116611586A
- Authority
- CN
- China
- Prior art keywords
- traffic
- network
- road section
- road
- double
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 239000011159 matrix material Substances 0.000 claims abstract description 63
- 238000004364 calculation method Methods 0.000 claims abstract description 16
- 239000010410 layer Substances 0.000 claims description 85
- 230000008878 coupling Effects 0.000 claims description 27
- 238000010168 coupling process Methods 0.000 claims description 27
- 238000005859 coupling reaction Methods 0.000 claims description 27
- 238000010276 construction Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 239000002355 dual-layer Substances 0.000 claims description 7
- 239000006185 dispersion Substances 0.000 claims description 6
- 238000004519 manufacturing process Methods 0.000 claims description 3
- 238000010998 test method Methods 0.000 claims description 3
- 238000011144 upstream manufacturing Methods 0.000 claims description 3
- 230000003993 interaction Effects 0.000 abstract description 4
- 230000007246 mechanism Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2337—Non-hierarchical techniques using fuzzy logic, i.e. fuzzy clustering
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- 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—Systems or methods specially adapted for 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
-
- 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
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention discloses a newly built road network flow prediction method and system based on a double-layer heterogeneous network, which belong to the technical field of traffic control and are used for solving the following technical problems: the existing new traffic volume prediction method does not fully utilize the traffic flow interaction mechanism between the expressway and the provincial road of the common country, and cannot solve the problem of flow estimation between the new expressway and the provincial road of the common country. The method comprises the following steps: constructing a double-layer heterogeneous highway network; dividing traffic cell units of a double-layer heterogeneous highway network based on toll station data; determining an initial OD distribution matrix based on traffic cell units according to toll station data; establishing a path generalized travel cost calculation model of the expressway and the common expressway, and carrying out iterative computation on an initial OD distribution matrix to obtain a current OD distribution matrix; and determining the traffic flow predicted value of the new road section according to the generalized travel cost of the new road section and the current OD distribution matrix.
Description
Technical Field
The invention relates to the technical field of traffic control, in particular to a new road network flow prediction method and system based on a double-layer heterogeneous network.
Background
In the society with rapidly increased economy and gradually improved efficiency, the time value concept of people is stronger and stronger, and the traffic conditions are coordinated with the development of the society. Therefore, the planning and construction of main transportation modes such as expressways, national roads, provinces and the like still can be the key development of the current and future transportation infrastructure.
In the planning of roads and road networks, the prediction of traffic is the basis of road planning. In recent years, newly built roads every year show increasing trends, and the accurate prediction of the traffic volume of the newly built roads is particularly important. The traffic prediction has important reference values for determining the construction time, the construction grade, the construction scale and the like of the new road, and is beneficial to improving the efficiency of the new road. However, since traffic flow detectors in common highways such as national roads and provinces are sparsely arranged, traffic flow data acquisition is difficult, and current newly-built traffic flow prediction methods are often used for predicting traffic flow of only newly-built highways, traffic flow of common national provinces cannot be accurately predicted, and the existing methods do not fully consider traffic flow interaction between highways and common national provinces and cannot solve the problem of traffic flow estimation of newly-built highways and newly-built common national provinces, so that it is highly desirable to reconstruct the highways and the common national provinces integrally, and research on the problem of traffic flow prediction of newly-built road sections suitable for the highways and the common national provinces.
Disclosure of Invention
The embodiment of the invention provides a newly built road network flow prediction method and a newly built road network flow prediction system based on a double-layer heterogeneous network, which are used for solving the following technical problems: the existing new traffic volume prediction method does not fully utilize the traffic flow interaction mechanism between the expressway and the provincial road of the common country, and cannot solve the problem of flow estimation between the new expressway and the provincial road of the common country.
The embodiment of the invention adopts the following technical scheme:
in one aspect, the embodiment of the invention provides a newly-built road network traffic prediction method based on a double-layer heterogeneous network, which comprises the following steps: constructing a double-layer heterogeneous highway network based on the highway network topology structure and the common highway network topology structure; determining historical daily traffic of each road section in the double-layer heterogeneous highway network; dividing traffic cell units of the double-layer heterogeneous highway network based on toll station data in the highway network; determining an initial OD distribution matrix based on traffic cell units according to the toll station data; establishing a generalized path travel cost calculation model of the expressway and the common highway according to the historical daily traffic of each road section, and carrying out iterative computation on the initial OD distribution matrix to obtain a current OD distribution matrix of the double-layer heterogeneous highway network; merging the newly built road section into the double-layer heterogeneous highway network, and defining generalized travel cost of the newly built road section; and determining a flow prediction value of the newly-built road section according to the generalized travel cost of the newly-built road section and the current OD distribution matrix.
In one possible implementation, a dual-layer heterogeneous highway network is constructed based on a highway network topology structure and a common highway network topology structure, and specifically includes: constructing a highway road network topology structure by taking an intercommunication type three-dimensional intersection point in a highway as a node and taking a road section between two adjacent intercommunication type three-dimensional intersection points as an edge; the method comprises the steps of constructing a common road network topology structure by taking a plane intersection of a common road as a node and taking a road section between two adjacent plane intersections as an edge; and taking the expressway toll station as a coupling connection point of the expressway and the common highway, and carrying out coupling reconstruction on the expressway road network topological structure and the common road network topological structure based on the coupling connection point to obtain the double-layer heterogeneous highway network.
In a possible implementation manner, determining the historical daily traffic volume of each road section in the double-layer heterogeneous highway network specifically comprises: dividing a highway section into a main line basic section and a ramp section in the double-layer heterogeneous highway network; according to the high-speed toll station data, counting the historical daily traffic of the ramp road section; according to the high-speed portal data, counting the historical daily traffic of the basic road section of the main line; according toObtaining historical daily traffic of each common road section in the double-layer heterogeneous road network; wherein M is a lunar coefficient of the ordinary road section, D is a pericyclic coefficient of the ordinary road section, and AADT is an annual average daily traffic volume of the ordinary road section.
In a possible embodiment, the method further comprises: under the condition that a plurality of portals exist in the main line basic section, taking a historical daily traffic average value obtained by statistics of all the portals as a final historical daily traffic; in the case that a certain common highway section is not provided with an observation station, according toAnd respectively calculating the historical daily traffic of the upstream road section and the historical daily traffic of the downstream road section of the common road section, and taking the average value of the historical daily traffic and the historical daily traffic of the downstream road section as the historical daily traffic of the common road section.
In a possible implementation manner, the traffic cell units of the double-layer heterogeneous highway network are divided based on toll station data in the highway network, and specifically include: determining a characteristic index of each coupling connection point in the double-layer heterogeneous highway network; the characteristic indexes comprise the initial flow of the toll station, the arrival flow of the toll station, the unbalanced coefficient of the direction of the toll station, the convergence distribution coefficient of the main flow of the toll station and the dispersion distribution coefficient of the main flow of the toll station; wherein the toll station direction imbalance coefficient is the ratio of the toll station originating flow to the toll station arriving flow; the main flow convergence distribution coefficient of the toll station is the mean square error between the main flow reaching the toll station from other toll stations; the main flow dispersion distribution coefficient of the toll station is the mean square error between main flow arriving at other toll stations from the toll station; carrying out standardization processing and extremum standardization processing on the characteristic indexes; according to the processed characteristic index, determining the characteristic similarity between any two coupling connection points; according to the feature similarity between any two coupling connection points, constructing a fuzzy equivalence matrix by a transitive closure method; selecting different elements in the fuzzy equivalent matrix as classification threshold values to obtain different coupling connection point clustering results; and determining an optimal clustering result in the different coupling connection point clustering results by an F test method, and determining each clustering cluster in the optimal clustering result as a traffic cell unit.
In a possible implementation manner, determining an initial OD distribution matrix based on traffic cell units according to the toll station data specifically includes: according to the toll station data, obtaining an OD distribution matrix taking each toll station as a row and a column mark; OD merging is carried out on toll stations belonging to the same traffic cell unit, and an initial OD distribution matrix based on the traffic cell unit is obtained; the elements in the initial OD distribution matrix are: historical daily traffic between traffic cell units as travel occurrence sources and traffic cell units as travel attraction sources.
In a possible implementation manner, according to the historical daily traffic of each road section, a route generalized travel cost calculation model of the expressway and the common road is established, and the initial OD distribution matrix is calculated in an iterative manner to obtain a current OD distribution matrix of the double-layer heterogeneous road network, which specifically comprises: based on the historical daily traffic volume for each road segment,establishing a path generalized travel cost calculation model of the expressway and the common highway:the method comprises the steps of carrying out a first treatment on the surface of the Wherein r represents the r-th effective path from the traffic cell unit i to the traffic cell unit j; />The generalized travel cost of the route r is represented; h represents daily working time of people; d represents the daily workday of the people; GDP represents the local average production total; />Representing the total travel cost of the vehicle through the path r; />Representing a historical daily traffic volume of a road section a, a being an a-th road section in a path r; />Representing the traffic capacity of the road section a; />The free travel time of the road section a is represented; />A weight coefficient for the travel time value cost of the road user; />A weight coefficient for the cost of the travel economic value of the road user; r represents a set of all road segments on path R; according toObtaining the probability of selecting the r effective path when the traveler goes from the traffic cell unit i to the traffic cell unit j; wherein e is the base of the exponential function; distributing each OD distribution quantity in the initial OD distribution matrix to a plurality of effective paths to obtain traffic distribution quantity +_ after nth iteration of each effective path>Wherein n=1 is the initial condition, +.>Is the initial OD distribution; accumulating the traffic distribution amount after the nth iteration of all the effective paths passing through the road section a to obtain the traffic distribution amount after the nth iteration of the road section a>The method comprises the steps of carrying out a first treatment on the surface of the According to->Obtaining the expected traffic volume of a road section a between a traffic cell unit i and a traffic cell unit j; according to->Obtaining the expected traffic volume of the path r; wherein (1)>Representing the number of road segments; according to->Obtaining the OD distribution quantity +.after the nth iteration between the traffic cell unit i and the traffic cell unit j>The method comprises the steps of carrying out a first treatment on the surface of the Calculating a relative error between the traffic distribution amount after the nth iteration of the road section a and the historical daily traffic of the road section a; if the relative error is smaller than or equal to the convergence threshold, stopping iteration and outputting a current OD distribution matrix; if the relative error is greater than the convergence threshold, let n=n+1, and continue the iterative calculation until convergence.
In a possible implementation manner, the new road section is merged into the double-layer heterogeneous road network, and the generalized travel cost of the new road section is defined, which specifically includes: adding the newly-built road section into the double-layer heterogeneous highway network according to the actual geographic position to obtain a new double-layer heterogeneous highway network; wide of the newly built road sectionThe trip cost is defined as:； wherein ,/>Representing the total travel cost of the vehicle passing through the newly-built road section b; />Indicating the free travel time of the newly created section b.
In a possible implementation manner, determining the flow prediction value of the new road section according to the generalized travel cost of the new road section and the current OD distribution matrix specifically includes: according to the generalized travel cost of the newly-built road section, the probability of each effective path is selected when the traveler moves from the traffic cell unit i to the traffic cell unit j again; distributing each OD distribution quantity in the current OD distribution matrix to a plurality of effective paths to obtain traffic distribution quantity of each effective path; and accumulating the traffic distribution amounts of all the effective paths passing through the new road section to obtain the traffic prediction value of the new road section.
On the other hand, the embodiment of the invention also provides a newly built road network flow prediction system based on a double-layer heterogeneous network, which comprises: the network construction module is used for constructing a double-layer heterogeneous highway network based on the highway network topological structure and the common highway network topological structure; the data processing module is used for determining the historical daily traffic volume of each road section in the double-layer heterogeneous highway network; dividing traffic cell units of the double-layer heterogeneous highway network based on toll station data in the highway network; determining an initial OD distribution matrix based on traffic cell units according to the toll station data; establishing a generalized path travel cost calculation model of the expressway and the common highway according to the historical daily traffic of each road section, and carrying out iterative computation on the initial OD distribution matrix to obtain a current OD distribution matrix of the double-layer heterogeneous highway network; merging the newly built road section into the double-layer heterogeneous highway network, and defining generalized travel cost of the newly built road section; and determining a flow prediction value of the newly-built road section according to the generalized travel cost of the newly-built road section and the current OD distribution matrix.
Compared with the prior art, the newly-built road network flow prediction method and system based on the double-layer heterogeneous network provided by the embodiment of the invention have the following beneficial effects:
according to the invention, a highway network and a common national provincial road network are coupled to construct a double-layer heterogeneous highway network, the double-layer heterogeneous highway network is divided into a plurality of traffic cell units through characteristic index data of highway toll stations, then an actual OD distribution matrix and an OD distribution prediction matrix of the whole double-layer heterogeneous highway network are calculated according to an initial OD distribution matrix and a route generalized travel cost calculation model, and further predicted traffic flow of a newly built road section is obtained according to a flow distribution algorithm. According to the invention, the expressway and the common national province are considered as a whole for research, so that the traffic flow interaction mechanism of the expressway and the common national province is fully exerted, the newly-built common national province flow reference value or the expressway flow reference value is conveniently calculated, and the flow reference value can provide accurate and effective data support for the construction grade, the construction scale and the like of the newly-built road. The traffic flow prediction method provided by the invention has strong applicability, solves the problems that traffic flow detectors in the province roads of the common country are sparsely arranged and traffic flow estimation is difficult to conveniently perform, and can also solve the traffic flow estimation problems of the new expressway and the new province roads of the common country.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present invention, and other drawings may be obtained according to the drawings without inventive effort to those skilled in the art. In the drawings:
fig. 1 is a flow chart of a new road network flow prediction method based on a dual-layer heterogeneous network, which is provided by the embodiment of the invention;
FIG. 2 is a schematic diagram of a dual-layer heterogeneous highway network according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a new road network traffic prediction system based on a dual-layer heterogeneous network according to an embodiment of the present invention.
Detailed Description
In order to make the technical solution of the present invention better understood by those skilled in the art, the technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present invention.
The embodiment of the invention provides a new road network flow prediction method based on a double-layer heterogeneous network, which specifically comprises the following steps of S101-S106 as shown in FIG. 1:
s101, constructing a double-layer heterogeneous highway network based on the highway network topological structure and the common highway network topological structure.
Specifically, an intercommunication type three-dimensional intersection point in the expressway is taken as a node, and a road section between two adjacent intercommunication type three-dimensional intersection points is taken as an edge, so that an expressway network topology structure is constructed.
And constructing a common road network topology structure by taking a plane intersection of a common road as a node and taking a road section between two adjacent plane intersections as an edge.
And taking the expressway toll station as a coupling connection point of the expressway and the common highway, and carrying out coupling reconstruction on the expressway network topology structure and the common highway network topology structure based on the coupling connection point to obtain the double-layer heterogeneous highway network.
As a possible implementation mode, FIG. 2 is a schematic diagram of a double-layer heterogeneous highway network, as shown in FIG. 2, for highways, an inter-working type three-dimensional intersection is adoptedf 1 ，f 2 ，f 3 ，f 4 ) As nodes, road sections between two adjacent intercommunication type three-dimensional intersection points are edges, and a highway network is constructedN f The method comprises the steps of carrying out a first treatment on the surface of the For the province of the common country, the plane intersection is divided into two sectionsg 1 ，g 2 ，g 3 ，g 4 ，g 5 ) Mapping as nodes, and mapping road sections between two adjacent plane intersections as edges to construct a common national provincial road networkN g The method comprises the steps of carrying out a first treatment on the surface of the Finally, selecting a toll station of the expressway as a coupling connection point of the expressway network and the common national province road network, performing layer projection, coupling reconstruction and forming a double-layer heterogeneous trunk road network aiming at the existing road networkN S 。
In one embodiment, as shown in FIG. 2, in an expressway networkf 1 Mapped into a double-layer highway networks 6 In the national province networkg 1 Mapping into a two-layer highway networks 1 . Highway sectionf 1 f 2 Road section of national provinceg 1 g 2 Between and through toll stationss 10 And performing coupling connection. The latter nodes are coupled in the same way to obtain the final two-layer road network.
S102, determining the historical daily traffic volume of each road section in the double-layer heterogeneous highway network.
Specifically, in a two-layer heterogeneous road network, a highway section is divided into a main line basic section and a ramp section. And according to the high-speed toll station data, counting the historical daily traffic of the ramp road section. And according to the high-speed portal data, counting the historical daily traffic of the basic road section of the main line.
Further according toAnd obtaining the historical daily traffic DT of each common road section in the double-layer heterogeneous road network. Wherein M is the lunar coefficient of the ordinary road section, D is the pericyclic coefficient of the ordinary road section, and AADT is the annual average daily traffic volume of the ordinary road section.
Further, in the case that a plurality of portals exist in the main line basic section, taking a historical daily traffic average value obtained by statistics of all the portals as a final historical daily traffic. In the case that a certain common highway section is not provided with an observation station, according toThe historical daily traffic of the upstream road section and the historical daily traffic of the downstream road section of the common road section are calculated respectively, and the average value of the historical daily traffic and the historical daily traffic of the downstream road section is taken as the historical daily traffic of the common road section.
As a feasible implementation mode, all road sections in the double-layer heterogeneous highway network of the existing road network are divided by three types of nodes of an intercommunication three-dimensional intersection, a plane intersection and a toll station, the road sections are edges, the weight of the edges is historical daily traffic, and the unit is vehicles/day. The invention utilizes the data of the toll station or the gantry data to obtain the historical daily traffic of the expressway dividing road sections in the double-layer heterogeneous highway network, wherein the dividing road sections are divided into main line basic road sections and ramp road sections. Specifically, the daily traffic volume of the entrance/exit ramp section is statistically analyzed by the toll station data, the daily traffic volume of the main line basic section is statistically analyzed by the portal data, and the number of the portal of the main line basic section is usually one. When a plurality of portals exist in the main line basic section, taking a historical daily traffic average value obtained by statistics of all the portals as a final value. The above-mentioned daily traffic may be any daily traffic.
S103, dividing traffic cell units of the double-layer heterogeneous highway network based on toll station data in the highway network.
Specifically, determining a characteristic index of each coupling connection point in the double-layer heterogeneous highway network; the characteristic indexes comprise the originating flow of the toll station, the arriving flow of the toll station, the unbalanced coefficient of the direction of the toll station, the convergence distribution coefficient of the main flow of the toll station and the dispersion distribution coefficient of the main flow of the toll station. The direction imbalance coefficient of the toll station is the ratio of the origination flow of the toll station to the arrival flow of the toll station; the main flow convergence distribution coefficient of the toll station is the mean square error between the main flow reaching the toll station from other toll stations; the main flow dispersion distribution coefficient of the toll station is the mean square error between the main flow of vehicles reaching other toll stations from the toll station.
Further, the method for clustering and analyzing the toll station by adopting the fuzzy clustering method is used for determining the traffic cell unit and specifically comprises the following steps:
according toCarrying out standardization treatment on the characteristic indexes; in (1) the->Is a characteristic index->Representing the kth toll stationlThe index value. />Respectively represent all toll stationslMean and standard deviation of the term index.
Then according toPerforming extremum normalization processing on the normalized characteristic indexes; in (1) the-> and />Is all toll stationslMinimum and maximum values of the term index.
Further, according to the processed characteristic index, the characteristic similarity between any two coupling connection points is determined. Then constructing a fuzzy equivalence matrix by a transfer closure method according to the feature similarity between any two coupling connection points; and selecting different elements in the fuzzy equivalent matrix as classification threshold values to obtain different coupling connection point clustering results. And finally, determining an optimal clustering result in different coupling connection point clustering results by an F test method, and determining each clustering cluster in the optimal clustering result as a traffic cell unit.
In particular according toDetermining the toll stationk 1 Andk 2 feature similarity of (3). In (1) the-> and />Indicating toll stationk 1 Andk 2 average value of all characteristic indexes; /> and />Indicating toll stationk 1 Andk 2 normalized value of the u-th index.
S104, determining an initial OD distribution matrix based on the traffic cell unit according to the toll station data.
Specifically, according to the toll station data, an OD distribution matrix with each toll station as row and column identification is obtained, then the toll stations belonging to the same traffic cell unit are OD-combined to obtain an initial OD distribution matrix based on the traffic cell unit：
；
Matrix arrayThe elements in are->Is shown asThe historical daily traffic volume between the traffic cell unit i of the travel occurrence source and the traffic cell unit j as the travel attraction source, m representing the number of traffic cell units.
S105, establishing a generalized path travel cost calculation model of the expressway and the common highway according to the historical daily traffic volume of each road section, and carrying out iterative computation on the initial OD distribution matrix to obtain the current OD distribution matrix of the double-layer heterogeneous highway network.
Specifically, according to the historical daily traffic of each road section, a route generalized travel cost calculation model of the expressway and the common road is established:；
wherein r represents the r-th effective path from the traffic cell unit i to the traffic cell unit j;the generalized travel cost of the route r is represented; h represents daily working time of people; d represents the daily workday of the people; GDP represents the local average production total; />Representing the total travel cost of the vehicle through the path r; />Representing a historical daily traffic volume of a road section a, a being an a-th road section in a path r; />Representing the traffic capacity of the road section a; />The free travel time of the road section a is represented; />A weight coefficient for the travel time value cost of the road user; />For making roadA weight coefficient of the cost of the trip economic value of the user; r represents the set of all road segments on path R.
Further, there are multiple effective paths between any OD pairs, according toObtaining the probability of selecting the r effective path when the traveler goes from the traffic cell unit i to the traffic cell unit j; where e is the base of the exponential function.
Further, each OD distribution amount in the initial OD distribution matrix is distributed to a plurality of effective paths to obtain traffic distribution amount after nth iteration of each effective pathWherein n=1 is the initial condition, +.>Is the initial OD profile.
Accumulating the traffic distribution amount after the nth iteration of all the effective paths passing through the road section a to obtain the traffic distribution amount after the nth iteration of the road section a。
Further, the traffic allocation amount of the road segment a is revised according toThe expected traffic volume of the road section a between the traffic cell unit i and the traffic cell unit j is obtained.
Further according toObtaining the expected traffic volume of the path r; wherein (1)>Representing the number of road segments.
Further according toObtaining OD distribution quantity +.after nth iteration between traffic cell unit i and traffic cell unit j>。
Further, calculating a relative error between the traffic distribution amount after the nth iteration of the road section a and the historical daily traffic volume of the road section a; if the relative error is smaller than or equal to the convergence threshold, stopping iteration and outputting a current OD distribution matrix; if the relative error is greater than the convergence threshold, let n=n+1, and continue the iterative calculation until convergence.
S106, merging the new road section into a double-layer heterogeneous road network, and defining generalized travel cost of the new road section; and determining a flow prediction value of the newly-built road section according to the generalized trip cost of the newly-built road section and the current OD distribution matrix.
Specifically, according to the actual geographic position, adding the newly-built road section into the double-layer heterogeneous highway network to obtain the new double-layer heterogeneous highway network.
In one embodiment, a two-layer highway network as in FIG. 2N s As shown, if nodeS 10 And nodeS 3 When a new road is planned or a common road is established, the new road is added to the double-layer road network according to the positions of two endpoints of the new roadN s And obtaining a new double-layer highway network. Meanwhile, the newly-built highway is determined to be connected or the nearest high-speed toll station is determined, and the newly-built highway is divided into traffic cell units where the high-speed toll station is located.
Further, the generalized travel cost of the newly built road section is defined as:； wherein ,/>Representing the total travel cost of the vehicle passing through the newly-built road section b; />Representing the self-created section bFrom the time of flight.
Further, according to the generalized travel cost of the newly-built road sectionT b When recalculating the probability of selecting each effective path when the traveler goes from traffic cell unit i to traffic cell unit j, i.e.. And then, according to the probability, distributing each OD distribution quantity in the current OD distribution matrix to a plurality of effective paths to obtain the traffic distribution quantity of each effective path.
Further, traffic distribution amounts of all effective paths passing through the new road section b are accumulated, and a flow prediction value of the new road section b is obtained.
In addition, the embodiment of the invention also provides a newly built road network flow prediction system based on a double-layer heterogeneous network, as shown in fig. 3, the system comprises:
a network construction module 310, configured to construct a dual-layer heterogeneous highway network based on the highway network topology structure and the common highway network topology structure;
a data processing module 320, configured to determine a historical daily traffic volume of each road section in the dual-layer heterogeneous highway network; dividing traffic cell units of the double-layer heterogeneous highway network based on toll station data in the highway network; determining an initial OD distribution matrix based on traffic cell units according to the toll station data; establishing a generalized path travel cost calculation model of the expressway and the common highway according to the historical daily traffic of each road section, and carrying out iterative computation on the initial OD distribution matrix to obtain a current OD distribution matrix of the double-layer heterogeneous highway network; merging the newly built road section into the double-layer heterogeneous highway network, and defining generalized travel cost of the newly built road section; and determining a flow prediction value of the newly-built road section according to the generalized travel cost of the newly-built road section and the current OD distribution matrix.
As a possible implementation, the system further includes a data acquisition module 330 for acquiring toll station data, portal data of the expressway, and observation station data of the general highway, etc.
The embodiments of the present invention are described in a progressive manner, and the same and similar parts of the embodiments are all referred to each other, and each embodiment is mainly described in the differences from the other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.
The foregoing describes certain embodiments of the present invention. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The foregoing is merely exemplary of the present invention and is not intended to limit the present invention. Various modifications and changes may be made to the embodiments of the invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. The newly built road network flow prediction method based on the double-layer heterogeneous network is characterized by comprising the following steps:
constructing a double-layer heterogeneous highway network based on the highway network topology structure and the common highway network topology structure;
determining historical daily traffic of each road section in the double-layer heterogeneous highway network;
dividing traffic cell units of the double-layer heterogeneous highway network based on toll station data in the highway network;
determining an initial OD distribution matrix based on traffic cell units according to the toll station data;
establishing a generalized path travel cost calculation model of the expressway and the common highway according to the historical daily traffic of each road section, and carrying out iterative computation on the initial OD distribution matrix to obtain a current OD distribution matrix of the double-layer heterogeneous highway network;
merging the newly built road section into the double-layer heterogeneous highway network, and defining generalized travel cost of the newly built road section;
and determining a flow prediction value of the newly-built road section according to the generalized travel cost of the newly-built road section and the current OD distribution matrix.
2. The method for predicting the traffic of the newly built road network based on the double-layer heterogeneous network according to claim 1, wherein the method for predicting the traffic of the newly built road network based on the highway road network topology structure and the common highway road network topology structure comprises the following steps:
constructing a highway road network topology structure by taking an intercommunication type three-dimensional intersection point in a highway as a node and taking a road section between two adjacent intercommunication type three-dimensional intersection points as an edge;
the method comprises the steps of constructing a common road network topology structure by taking a plane intersection of a common road as a node and taking a road section between two adjacent plane intersections as an edge;
and taking the expressway toll station as a coupling connection point of the expressway and the common highway, and carrying out coupling reconstruction on the expressway road network topological structure and the common road network topological structure based on the coupling connection point to obtain the double-layer heterogeneous highway network.
3. The method for predicting new road network traffic based on the double-layer heterogeneous network according to claim 1, wherein determining the historical daily traffic of each road section in the double-layer heterogeneous road network specifically comprises:
dividing a highway section into a main line basic section and a ramp section in the double-layer heterogeneous highway network;
according to the high-speed toll station data, counting the historical daily traffic of the ramp road section;
according to the high-speed portal data, counting the historical daily traffic of the basic road section of the main line;
according toObtaining historical daily traffic of each common road section in the double-layer heterogeneous road network; wherein M is a lunar coefficient of the ordinary road section, D is a pericyclic coefficient of the ordinary road section, and AADT is an annual average daily traffic volume of the ordinary road section.
4. The method for predicting new road network traffic based on dual-layer heterogeneous network as recited in claim 3, further comprising:
under the condition that a plurality of portals exist in the main line basic section, taking a historical daily traffic average value obtained by statistics of all the portals as a final historical daily traffic;
in the case that a certain common highway section is not provided with an observation station, according toAnd respectively calculating the historical daily traffic of the upstream road section and the historical daily traffic of the downstream road section of the common road section, and taking the average value of the historical daily traffic and the historical daily traffic of the downstream road section as the historical daily traffic of the common road section.
5. The newly-built road network traffic prediction method based on the double-layer heterogeneous network according to claim 1, wherein the traffic cell units of the double-layer heterogeneous road network are divided based on toll station data in the highway road network, specifically comprising:
determining a characteristic index of each coupling connection point in the double-layer heterogeneous highway network; the characteristic indexes comprise the initial flow of the toll station, the arrival flow of the toll station, the unbalanced coefficient of the direction of the toll station, the convergence distribution coefficient of the main flow of the toll station and the dispersion distribution coefficient of the main flow of the toll station;
wherein the toll station direction imbalance coefficient is the ratio of the toll station originating flow to the toll station arriving flow; the main flow convergence distribution coefficient of the toll station is the mean square error between the main flow reaching the toll station from other toll stations; the main flow dispersion distribution coefficient of the toll station is the mean square error between main flow arriving at other toll stations from the toll station;
carrying out standardization processing and extremum standardization processing on the characteristic indexes;
according to the processed characteristic index, determining the characteristic similarity between any two coupling connection points;
according to the feature similarity between any two coupling connection points, constructing a fuzzy equivalence matrix by a transitive closure method; selecting different elements in the fuzzy equivalent matrix as classification threshold values to obtain different coupling connection point clustering results;
and determining an optimal clustering result in the different coupling connection point clustering results by an F test method, and determining each clustering cluster in the optimal clustering result as a traffic cell unit.
6. The method for predicting new road network traffic based on double-layer heterogeneous network according to claim 1, wherein determining an initial OD distribution matrix based on traffic cell unit according to the toll station data comprises:
according to the toll station data, obtaining an OD distribution matrix taking each toll station as a row and a column mark;
OD merging is carried out on toll stations belonging to the same traffic cell unit, and an initial OD distribution matrix based on the traffic cell unit is obtained;
the elements in the initial OD distribution matrix are: historical daily traffic between traffic cell units as travel occurrence sources and traffic cell units as travel attraction sources.
7. The method for predicting the traffic of a newly built road network based on a double-layer heterogeneous network according to claim 1, wherein the method is characterized by establishing a route generalized travel cost calculation model of an expressway and a common road according to the historical daily traffic of each road section, and performing iterative computation on the initial OD distribution matrix to obtain a current OD distribution matrix of the double-layer heterogeneous road network, and specifically comprises the following steps:
according to the historical daily traffic of each road section, a route generalized travel cost calculation model of the expressway and the common road is established:；
wherein r represents the r-th effective path from the traffic cell unit i to the traffic cell unit j;the generalized travel cost of the route r is represented; h represents daily working time of people; d represents the daily workday of the people; GDP represents the local average production total;representing the total travel cost of the vehicle through the path r; />Representing a historical daily traffic volume of a road section a, a being an a-th road section in a path r; />Representing the traffic capacity of the road section a; />The free travel time of the road section a is represented; />A weight coefficient for the travel time value cost of the road user; />A weight coefficient for the cost of the travel economic value of the road user; r represents a set of all road segments on path R;
according toObtaining the traffic of the travelerWhen the cell unit i goes to the traffic cell unit j, selecting the probability of the (r) th effective path; wherein e is the base of the exponential function;
distributing each OD distribution quantity in the initial OD distribution matrix to a plurality of effective paths to obtain traffic distribution quantity after nth iteration of each effective pathWherein n=1 is the initial condition, +.>Is the initial OD distribution;
accumulating the traffic distribution amount after the nth iteration of all the effective paths passing through the road section a to obtain the traffic distribution amount after the nth iteration of the road section a；
According toObtaining the expected traffic volume of a road section a between a traffic cell unit i and a traffic cell unit j;
according toObtaining the expected traffic volume of the path r; wherein (1)>Representing the number of road segments;
according toObtaining the OD distribution quantity +.after the nth iteration between the traffic cell unit i and the traffic cell unit j>；
Calculating a relative error between the traffic distribution amount after the nth iteration of the road section a and the historical daily traffic of the road section a;
if the relative error is smaller than or equal to the convergence threshold, stopping iteration and outputting a current OD distribution matrix; if the relative error is greater than the convergence threshold, let n=n+1, and continue the iterative calculation until convergence.
8. The method for predicting the traffic of a newly built road network based on a double-layer heterogeneous network according to claim 1, wherein the newly built road section is merged into the double-layer heterogeneous road network and the generalized travel cost of the newly built road section is defined, specifically comprising:
adding the newly-built road section into the double-layer heterogeneous highway network according to the actual geographic position to obtain a new double-layer heterogeneous highway network;
the generalized travel cost of the newly-built road section is defined as:；
wherein ,representing the total travel cost of the vehicle passing through the newly-built road section b; />Indicating the free travel time of the newly created section b.
9. The method for predicting the traffic of the newly-built road network based on the double-layer heterogeneous network according to claim 1, wherein the method for predicting the traffic of the newly-built road network according to the generalized travel cost of the newly-built road network and the current OD distribution matrix comprises the following steps:
according to the generalized travel cost of the newly-built road section, the probability of each effective path is selected when the traveler moves from the traffic cell unit i to the traffic cell unit j again;
distributing each OD distribution quantity in the current OD distribution matrix to a plurality of effective paths to obtain traffic distribution quantity of each effective path;
and accumulating the traffic distribution amounts of all the effective paths passing through the new road section to obtain the traffic prediction value of the new road section.
10. A newly built road network flow prediction system based on a double-layer heterogeneous network, the system comprising:
the network construction module is used for constructing a double-layer heterogeneous highway network based on the highway network topological structure and the common highway network topological structure;
the data processing module is used for determining the historical daily traffic volume of each road section in the double-layer heterogeneous highway network; dividing traffic cell units of the double-layer heterogeneous highway network based on toll station data in the highway network; determining an initial OD distribution matrix based on traffic cell units according to the toll station data; establishing a generalized path travel cost calculation model of the expressway and the common highway according to the historical daily traffic of each road section, and carrying out iterative computation on the initial OD distribution matrix to obtain a current OD distribution matrix of the double-layer heterogeneous highway network; merging the newly built road section into the double-layer heterogeneous highway network, and defining generalized travel cost of the newly built road section; and determining a flow prediction value of the newly-built road section according to the generalized travel cost of the newly-built road section and the current OD distribution matrix.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310882561.8A CN116611586B (en) | 2023-07-19 | 2023-07-19 | Newly built road network flow prediction method and system based on double-layer heterogeneous network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310882561.8A CN116611586B (en) | 2023-07-19 | 2023-07-19 | Newly built road network flow prediction method and system based on double-layer heterogeneous network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116611586A true CN116611586A (en) | 2023-08-18 |
| CN116611586B CN116611586B (en) | 2023-10-31 |
Family
ID=87678615
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310882561.8A Active CN116611586B (en) | 2023-07-19 | 2023-07-19 | Newly built road network flow prediction method and system based on double-layer heterogeneous network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116611586B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117116062A (en) * | 2023-10-23 | 2023-11-24 | 山东高速股份有限公司 | Expressway traffic prediction method and system under construction occupation condition |
| CN117612379A (en) * | 2024-01-24 | 2024-02-27 | 山东华夏高科信息股份有限公司 | Intelligent traffic flow prediction method and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104269051A (en) * | 2014-10-17 | 2015-01-07 | 成都四为电子信息股份有限公司 | Expressway monitoring and management system |
| CN105096614A (en) * | 2015-09-23 | 2015-11-25 | 南京遒涯信息技术有限公司 | Newly established crossing traffic flow prediction method based on generating type deep belief network |
| CN110245423A (en) * | 2019-06-14 | 2019-09-17 | 重庆大学 | Discharge relation analysis method between a kind of freeway toll station |
| WO2022143549A1 (en) * | 2020-12-31 | 2022-07-07 | 北京千方科技股份有限公司 | Expressway road condition monitoring method and apparatus based on toll collection data |
| CN115455534A (en) * | 2022-09-05 | 2022-12-09 | 广州市交通运输研究院有限公司 | Method and system for evaluating adaptability of network layout structure of expressway |
| CN116030617A (en) * | 2021-10-22 | 2023-04-28 | 交通运输部规划研究院 | Method and device for predicting traffic flow based on road OD data |
| CN116403410A (en) * | 2023-06-06 | 2023-07-07 | 中南大学 | Highway mixed path induction model construction method considering congestion traffic sources |
-
2023
- 2023-07-19 CN CN202310882561.8A patent/CN116611586B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104269051A (en) * | 2014-10-17 | 2015-01-07 | 成都四为电子信息股份有限公司 | Expressway monitoring and management system |
| CN105096614A (en) * | 2015-09-23 | 2015-11-25 | 南京遒涯信息技术有限公司 | Newly established crossing traffic flow prediction method based on generating type deep belief network |
| CN110245423A (en) * | 2019-06-14 | 2019-09-17 | 重庆大学 | Discharge relation analysis method between a kind of freeway toll station |
| WO2022143549A1 (en) * | 2020-12-31 | 2022-07-07 | 北京千方科技股份有限公司 | Expressway road condition monitoring method and apparatus based on toll collection data |
| CN116030617A (en) * | 2021-10-22 | 2023-04-28 | 交通运输部规划研究院 | Method and device for predicting traffic flow based on road OD data |
| CN115455534A (en) * | 2022-09-05 | 2022-12-09 | 广州市交通运输研究院有限公司 | Method and system for evaluating adaptability of network layout structure of expressway |
| CN116403410A (en) * | 2023-06-06 | 2023-07-07 | 中南大学 | Highway mixed path induction model construction method considering congestion traffic sources |
Non-Patent Citations (2)
| Title |
|---|
| 邱永鸿;: "高速公路城区段交通量组合预测方法研究", 城市道桥与防洪, no. 05 * |
| 陈海华;谭国贤;黄子敬;林培群;: "基于出口流水数据的高速公路节假日日OD交通量分布预测", 广西大学学报(自然科学版), no. 01 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117116062A (en) * | 2023-10-23 | 2023-11-24 | 山东高速股份有限公司 | Expressway traffic prediction method and system under construction occupation condition |
| CN117116062B (en) * | 2023-10-23 | 2024-01-09 | 山东高速股份有限公司 | Expressway traffic prediction method and system under construction occupation condition |
| CN117612379A (en) * | 2024-01-24 | 2024-02-27 | 山东华夏高科信息股份有限公司 | Intelligent traffic flow prediction method and system |
| CN117612379B (en) * | 2024-01-24 | 2024-03-29 | 山东华夏高科信息股份有限公司 | Intelligent traffic flow prediction method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116611586B (en) | 2023-10-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116611586B (en) | Newly built road network flow prediction method and system based on double-layer heterogeneous network | |
| CN110298500B (en) | Urban traffic track data set generation method based on taxi data and urban road network | |
| CN107241512B (en) | Intercity Transportation trip mode judgment method and equipment based on data in mobile phone | |
| CN109686091B (en) | Traffic flow filling algorithm based on multi-source data fusion | |
| CN111653088A (en) | Vehicle driving quantity prediction model construction method, prediction method and system | |
| CN102521965B (en) | Effect evaluation method of traffic demand management measures based on identification data of license plates | |
| CN104464344B (en) | A kind of vehicle running path Forecasting Methodology and system | |
| Kianfar et al. | Optimizing freeway traffic sensor locations by clustering global-positioning-system-derived speed patterns | |
| CN104809112A (en) | Method for comprehensively evaluating urban public transportation development level based on multiple data | |
| WO2022227303A1 (en) | Information processing method and apparatus, computer device, and storage medium | |
| CN112784000B (en) | Passenger searching method based on taxi track data | |
| CN104282142B (en) | Bus station arrangement method based on taxi GPS data | |
| Kim | Spatial contiguity-constrained hierarchical clustering for traffic prediction in bike sharing systems | |
| CN109544967A (en) | A kind of public transport network running state monitoring method based on low frequency AVL data | |
| CN116504050A (en) | Special event city partitioning method based on multi-mode public transport trip data | |
| CN111723871B (en) | Estimation method for real-time carriage full load rate of bus | |
| CN112309118B (en) | Vehicle trajectory calculation method based on space-time similarity | |
| CN111008730B (en) | Crowd concentration prediction model construction method and device based on urban space structure | |
| CN114078322A (en) | Bus running state evaluation method, device, equipment and storage medium | |
| CN111191817A (en) | Bus network topology division method based on transfer passenger flow | |
| CN115146840A (en) | Data-driven rail transit new line access passenger flow prediction method | |
| CN115909750A (en) | Accident multi-occurrence identification method, device, equipment and storage medium | |
| Wong et al. | Estimation of origin‐destination matrices for a multimodal public transit network | |
| CN113536493A (en) | Effective path generation method based on clustering reverse thrust and section passenger flow estimation method | |
| CN110120154B (en) | Traffic road condition prediction method using detector data under large-scale road network |
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 |