CN106504535B - A kind of trip distribution modeling method of combination Gravity Models and Fratar models - Google Patents
A kind of trip distribution modeling method of combination Gravity Models and Fratar models Download PDFInfo
- Publication number
- CN106504535B CN106504535B CN201611087603.5A CN201611087603A CN106504535B CN 106504535 B CN106504535 B CN 106504535B CN 201611087603 A CN201611087603 A CN 201611087603A CN 106504535 B CN106504535 B CN 106504535B
- Authority
- CN
- China
- Prior art keywords
- cell
- models
- traffic
- volume
- trip
- 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
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
- 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
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of trip distribution modeling methods of combination Gravity Models and Fratar models, include the following steps：The generation for acquiring each cell first attracts the volume of traffic and present situation OD distributions；Secondly calibration without constraint Gravity Models parameter and predicts that the generation in each cell non-coming year attracts the volume of traffic；What then application had both been demarcated calculates non-coming year OD distributions without constraint Gravity Models；Fratar model runnings are finally applied once to obtain new prediction of non-coming year OD distributions；Convergence judgement is carried out to operation result and last time cycle result, the OD distributions for obtaining meeting convergence criterion are the non-coming year each minizone OD forecast of distribution final results.The distribution forecasting method combines the advantage of Gravity Models and Fratar models, both present situation trip distributed intelligence had been taken full advantage of, it can consider the variation of road network and the influence that land use generates people's trip again simultaneously, improve the accuracy of prediction result and the applicability of prediction model.
Description
Technical field
The present invention relates to a kind of trip distribution modeling methods being combined Gravity Models with Fratar models, belong to traffic
Demand and trip distribution modeling technical field.
Background technology
Make rational planning for too busy to get away accurate transport need analysis and the prediction of communication project.Transport need is analyzed and prediction is made
For the key technology of traffic programme, it is resolved that the accuracy held to future transportation development trend and reliability, to affect
The decision of traffic department and designer.In the level of urbanization higher and higher today, emerged largely newly-built city or
Urban planning new district (hereinafter referred to as Xincheng District), this just brings new problem and challenge to Urban Traffic Planning, especially exists
Transport need analysis and forecast period.Currently, carrying out transport need analysis in traffic programme with prediction mainly using biography
The procedural transport need analytical model of system, i.e. four stages of Trip generation forecast, traffic distribution, traffic modal splitting and traffic assignation
Prediction mode.For the second stage trip distribution modeling of Four-stage Method, many scholars propose different prediction models and
Method.
At present, in the trip distribution modeling of the Study on Highway Feasible Research using it is more be that present status method (also referred to as increases
Y-factor method Y), wherein Fratar methods are widely used due to fast convergence rate by planning governor.The basic assumption of Fratar methods
It is:Travel amount between traffic zone is unrelated with the variation of road network structure, or prediction the time in road network without big change.Thus
There are one unavoidable obvious shortcomings for Fratar methods, i.e.,:Only future transportation amount is realized with this sole indicator of growth rate, and
Not accounting for influences the factors of traffic distribution in network, thus in new mode of transportation, new road, new charge political affairs
Plan or new cell can not describe the variation of traffic distribution when generating.In addition, present status method, which goes on a journey to base year, is distributed precision
Dependence is larger, and the non-coming year trip distribution confidence level can not possibly be more than base year, and it is any appear in base year trip distribution in
Error will be amplified in calculating process.In contrast to this, " Gravity Models " method, or be " collective model " method, it is believed that area
Traffic distribution between area is influenced by all traffic impedances such as interzone distance, run time, expense, i.e., area and area it
Between trip distribution it is directly proportional to the attraction of trip with each area, and the traffic impedance between same district is inversely proportional, newly-built for some
The trip distribution modeling in city has higher applicability and accuracy.But gravity model method is distributed shadow based entirely on to trip
The considerations of factor of sound, lacks the analysis to the travel behaviour of people, does not make full use of present situation trip distributed data, prediction result can
Can and actual conditions there are certain deviations.
Invention content
Goal of the invention：In order to overcome the deficiencies in the prior art, the present invention provide a kind of combination Gravity Models with
The trip distribution modeling method of Fratar models, the prediction technique can integrate the advantages of gravity model method is with Fratar models, both
Influence in view of road network variation and land use to trip distribution, and present situation trip distribution actual conditions are fully combined, simultaneously
Solve the problems, such as that Fratar method growth pattern is single, gravity model method Correlative Influence Factors are difficult to obtain, it can be to the non-coming year
Traffic distribution carries out reasonable prediction.
Technical solution：To achieve the above object, the technical solution adopted by the present invention is：
A kind of trip distribution modeling method of combination Gravity Models and Fratar models, includes the following steps：
The present situation that step 10) acquires each cell occurs to attract the volume of traffic, present situation OD distributions and relevant rudimentary data,
In, the trip occurrence quantity O for attracting the volume of traffic to include cell i occurs for the present situation of each celliWith the trip attraction amount D of cell jj,
I=1,2...n, j=1,2...n, n indicate cell number.
Step 20) calibration is without constraint Gravity Models, including step 201) is to step 204)：
Step 201) is determined without constraint Gravity Models form：Qij indicates the traffic between cell i, j
Amount, cijIndicate that the impedance between cell i, j, α, beta, gamma are without constraint Gravity Models parameter to be calibrated.
Step 202) is rightBoth sides take logarithm, obtain ln (qij)=ln alpha+beta l (OiDj)-γln(cij)。
Step 203) enables Y=ln (qij), a0=ln α, a1=β, a2=-γ, X1=ln (OiDj), X2=ln (cij), then Y
=a0+a1X1+a2X2, wherein a0, a1, a2For coefficient to be calibrated, X1, X2, Y is the vector comprising sample data set.
Step 204) occurs that the volume of traffic and present situation OD distributions is attracted to determine sample data set X by each cell present situation1, X2,
Y demarcates sample data using least square method, determines without constraint Gravity Models parameter.
Step 30) occurs to predict that the generation in each cell non-coming year attracts the volume of traffic, institute based on attracting the volume of traffic by present situation
The generation attraction volume of traffic for stating each cell non-coming year includes the trip occurrence quantity P in i-th of cell non-coming yeariNot with i-th of cell
The trip attraction amount A in the coming yeari。
The generation that step 30) is obtained each cell non-coming year by step 40) attracts the volume of traffic to substitute into the nothing demarcated in step 20)
Gravity Models is constrained, non-coming year OD distributions q is calculatedij。
Step 50)：It is distributed q with the OD that application in step 40) is obtained without constraint Gravity ModelsijAs initial OD, operation one
Secondary Fratar models obtain new prediction of non-coming year OD distributions qij 1, including step 501) is to step 503).
Step 501)：It is distributed q according to solving to obtain OD between cell i, j without constraint Gravity Modelsij, summarize to obtain each cell
Occur to attract the volume of traffic：
Step 502)：Calculate Fratar model related coefficients
Wherein, FOiIt indicates that convergence coefficient, F occurs using the trip of i-th of cell when Fratar modelsDjIndicate the trip of j-th of cell
Attract convergence coefficient, LijIndicate that regulation coefficient, L occur for the trip of i-th of celljiIndicate the trip attraction adjustment of j-th of cell
Coefficient.
Step 503)：Solve new non-coming year OD forecast of distribution qij 1=qij*FOi*FDj*(Lii+Ljj)/2。
Step 60)：Convergence judges：It is distributed q according to the OD that Fratar models one cycle obtains in step 50)ij 1, converge
The new prediction of the non-coming year of each cell must be arrived to occur to attract volume of traffic conduct
If each cell occurs to attract volume of traffic error within tolerance interval, i.e.,：
It is transferred to step 70), is otherwise enabledIt goes to step 40).
Step 70) prediction result meets the condition of convergence, and end loop, OD distributions at this time are the non-coming year each minizone
OD forecast of distribution results.
Preferably：Relevant rudimentary data include cell population, area, land use, locational factor number in the step 10)
According to.
Preferably：The generation in each cell non-coming year is predicted in the step 30) based on the present situation generation attraction volume of traffic
It includes original unit's method, growth rate method, cross classification, function method to attract the method for the volume of traffic.
Advantageous effect：The present invention compared with prior art, has the advantages that：
1) the advantages of inheriting Gravity Models can consider many factors such as road network variation, land use for cell
The influence of the attraction volume of traffic occurs.There is higher standard simultaneously for the Traffic Demand Forecasting in newly-built city or urban planning new district
True property and applicability.
2) the advantages of merger Fratar model of growth, obtainable present situation cell trip distribution letter is made full use of
Breath controls the deviation between non-coming year trip forecast of distribution result and practical trip distribution, ensures prediction knot to a certain extent
The confidence level of fruit.
It 3), still can be initial first with Gravity Models when present situation OD distributions are difficult to obtain or base year distributed intelligence lacks
Change prediction year OD, Fratar models is recycled gradually to adjust prediction result.
Description of the drawings
Fig. 1 is the flow diagram of the present invention.
Specific implementation mode
In the following with reference to the drawings and specific embodiments, the present invention is furture elucidated, it should be understood that these examples are merely to illustrate this
It invents rather than limits the scope of the invention, after having read the present invention, those skilled in the art are various to the present invention's
The modification of equivalent form falls within the application range as defined in the appended claims.
A kind of trip distribution modeling method of combination Gravity Models and Fratar models, as shown in Figure 1, including following step
Suddenly：
The present situation that step 10) acquires each cell occurs to attract volume of traffic Oi, Dj, present situation OD is distributed and relevant rudimentary data,
Wherein, the acquisition of relevant rudimentary data includes：Include on what traffic zone generation attraction volume of traffic generation directly or indirectly influenced
The acquisition of cell population, area, land use, position related data.
Step 20) calibration is without constraint Gravity Models, including step 201) is to step 204)：
Step 201) is determined without constraint Gravity Models form：Wherein, i=1,2...n, j=1,
2...n, n indicates cell number, qijIndicate the volume of traffic between cell i, j, cijIndicate the impedance between cell i, j, OiIt indicates
The trip occurrence quantity of cell i, DjIndicate that the trip attraction amount of cell j, α, beta, gamma are without constraint Gravity Models parameter to be calibrated.
Step 202) is rightBoth sides take logarithm, obtain ln (qij)=ln alpha+beta l (OiDj)-γln(cij)
Step 203) enables Y=ln (qij), a0=ln α, a1=β, a2=-γ, X1=ln (OiDj), X2=ln (cij), then Y
=a0+a1X1+a2X2, wherein a0, a1, a2For coefficient to be calibrated, X1, X2, Y is the vector comprising sample data set.
Step 204) occurs that the volume of traffic and present situation OD distributions is attracted to determine sample data set X by each cell present situation1, X2,
Y demarcates sample data using least square method, determines without constraint Gravity Models parameter.
Step 30) occurs to predict the generation attraction volume of traffic in each cell non-coming year based on attracting the volume of traffic by present situation, and i-th
The generation of a cell attracts the volume of traffic to be denoted as P respectivelyi、Ai.Wherein, the generation in the cell non-coming year attracts Traffic volume forecasting method packet
Include original unit's method, growth rate method, cross classification, function method etc..
Step 40) applying step 20) in demarcate without constraint Gravity Models, substituting into non-coming year occurs to attract volume of traffic Pi、
Ai, non-coming year OD distributions are calculated.
Step 50)：It is distributed using application in step 40) as initial OD, application without the OD that constraint Gravity Models obtains
Fratar models carry out primary convergence and obtain new prediction of non-coming year OD distributions, including step 501) is to step 503)：
Step 501)：It is distributed q according to solving to obtain OD between cell i, j without constraint Gravity Modelsij, summarized respectively according to OD tables
Cell occurs to attract the volume of traffic：
Step 502)：Calculate Fratar Parameters in Mathematical Model：
Step 503)：Solve new non-coming year OD forecast of distribution qij 1=qij*FOi*FDj*(Lii+Ljj)/2。
Step 60)：Convergence judges：It is distributed q according to the OD that Fratar models one cycle obtains in step 50)ij 1, converge
The new prediction of the non-coming year of each cell must be arrived to occur to attract volume of traffic conduct
If each cell occurs to attract volume of traffic error within tolerance interval, i.e.,：
It is transferred to step 70), is otherwise enabledIt goes to step 40).
Step 70) prediction result meets the condition of convergence, and end loop, OD distributions at this time are the non-coming year each minizone
OD forecast of distribution results.
The present invention provides a kind of trip distribution modeling method of combination Gravity Models and Fratar models, which can
The advantages of comprehensive gravity model method is with Fratar models had both considered the influence of road network variation and land use to trip distribution,
Present situation trip distribution actual conditions are fully combined again, while solving that Fratar method growth pattern is single, gravity model method phase
It closes influence factor and obtains accuracy problem, reasonable prediction is carried out to the traffic distribution in the non-coming year.
The present invention has fully considered the actual conditions being likely to occur during trip distribution modeling, by gravity model method with
Fratar growth rate methods are combined, and are reasonably predicted not under the premise of utmostly utilizing present situation trip distribution to can get information
Coming year trip distribution.The method of the present invention uses Gravity Models to carry out initialization prediction to the distribution of the following year traffic first, passes through
Fratar models gradually restrain initial predicted result, recycle above-mentioned two step until meeting the final condition of convergence.The present invention's
Method does not have substantial modifications to the basic principle of existing forecast of distribution model, but it combines Gravity Models and Fratar models
Advantage, not only taken full advantage of present situation trip distributed intelligence, and but also can consider that the variation of road network and land use went out people
The influence that row generates, improves the accuracy of prediction result and the applicability of prediction model.Therefore the present invention's is highly practical, can
Suitable for the traffic distribution of New and old community and Traffic Demand Forecasting, to have important practical significance.
A specific embodiment is given below.
By taking the trip forecast of distribution of 3, Jiangsu Province city traffic zone as an example, illustrate the practicability of the inventive method with
Advantage.
The present situation that step 10) acquires each cell occurs to attract the volume of traffic P, A, present situation OD distributions and relevant rudimentary data,
It counts between each cell and Intra-cell present situation running time, prediction future travel time.
1 present situation OD distribution tables of table
2 present situation running time of table
The 3 future travel time of table
Step 20) calibration is without constraint Gravity Models：
Step 201) is determined without constraint Gravity Models form：
Step 202) is rightBoth sides take logarithm, obtain ln (qij)=ln alpha+beta ln (OiDj)-γln(cij)。
Step 203) enables Y=ln (qij), a0=ln α, a1=β, a2=-γ, X1=ln (OiDj), X2=ln (cij), then Y
=a0+a1X1+a2X2, wherein a0, a1, a2For coefficient to be calibrated, cijTake between cell with Intra-cell running time, X1, X2, Y is
Include the vector of sample data set.
Step 204) occurs that the volume of traffic and present situation OD distributions is attracted to determine sample data set X by each cell present situation1, X2,
Y demarcates sample data using least square method, determines without constraint Gravity Models parameter.
4 Gravity Models of table demarcates sample data
Solve linear equation in two unknowns parameter a0=-2.084, a1=1.173, a2=-1.455, further solve Gravity Models
Parameter alpha=0.124, β=1.173, γ=1.455, that is, the Gravity Models demarcated are：
Step 30) occurs to predict the generation attraction volume of traffic in each cell non-coming year based on attracting the volume of traffic by present situation, and i-th
The generation of a cell attracts the volume of traffic to be denoted as P respectivelyi、Ai。
The 5 non-coming year of table occurs to attract the volume of traffic
Step 40) applying step 20) in demarcate without constraint Gravity Models, substituting into non-coming year occurs to attract volume of traffic Pi、
Ai, non-coming year OD distributions are calculated.
6 non-coming year OD distribution tables of table
Step 50)：To apply the OD distribution tables obtained without constraint Gravity Models as initial OD, application in step 40)
Fratar models carry out primary convergence and obtain new prediction of non-coming year OD distributions, including step 501) is to step 502)：
Step 501)：It is distributed q according to solving to obtain OD between cell i, j without constraint Gravity Modelsij, summarized respectively according to OD tables
Cell occurs to attract the volume of traffic：
7 Gravity Models of table occurs to attract the volume of traffic with the non-coming year under actual prediction
Step 502)：It asks
Table 7Fratar Parameters in Mathematical Model
Step 503)：The non-coming year OD forecast of distribution q to look for noveltyij 1=qij*FOi*FDj*(Lii+Ljj)/2。
8 non-coming year OD distribution tables of table
Step 60)：Convergence judges：
It is distributed q according to the OD that Fratar models one cycle obtains in step 50)ij 1, summarize to obtain each cell new future
Year prediction occurs to attract volume of traffic conduct
Table 9 predicts that the non-coming year occurs to attract traffic counts
Each cell occurs that the volume of traffic is attracted to recycle result ratio with last time after judging this cycleWhether satisfaction can
Receive range：
Cyclic error counts table 10 twice
The condition of convergence is unsatisfactory for, therefore is enabledIt goes to step 40).
After carrying out 8 cycles to step 40) to step 60), obtain：
11 non-coming year OD distribution tables of table
Cyclic error counts table 12 twice
The condition of convergence meets, i.e.,：
It is transferred to step 70).
Step 70) end loop, OD distributions at this time are the non-coming year each minizone OD forecast of distribution final results.
13 non-coming year OD distribution tables of table
The above is only a preferred embodiment of the present invention, it should be pointed out that：For the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (3)
1. a kind of trip distribution modeling method of combination Gravity Models and Fratar models, which is characterized in that include the following steps：
The present situation that step 10) acquires each cell occurs to attract the volume of traffic, present situation OD distributions and relevant rudimentary data, wherein institute
The trip occurrence quantity O for attracting the volume of traffic to include cell i occurs for the present situation for stating each celliWith the trip attraction amount D of cell jj, i=1,
2...n, j=1,2...n, n indicate cell number；
Step 20) calibration is without constraint Gravity Models, including step 201) is to step 204)：
Step 201) is determined without constraint Gravity Models form：qijIndicate the volume of traffic between cell i, j, cij
Indicate that the impedance between cell i, j, α, beta, gamma are without constraint Gravity Models parameter to be calibrated；
Step 202) is rightBoth sides take logarithm, obtain ln (qij)=ln alpha+beta ln (OiDj)-γln(cij)；
Step 203) enables Y=ln (qij), a0=ln α, a1=β, a2=-γ, X1=ln (OiDj), X2=ln (cij), then Y=a0+
a1X1+a2X2, wherein a0, a1, a2For coefficient to be calibrated, X1, X2, Y is the vector comprising sample data set；
Step 204) occurs that the volume of traffic and present situation OD distributions is attracted to determine sample data set X by each cell present situation1, X2, Y, use
Least square method demarcates sample data, determines without constraint Gravity Models parameter；
Step 30) occurs to predict that the generation in each cell non-coming year attracts the volume of traffic based on attracting the volume of traffic by present situation, described each
It includes the trip occurrence quantity P in i-th of cell non-coming year that the generation in the cell non-coming year, which attracts the volume of traffic,iWith i-th of cell non-coming year
Trip attraction amount Ai；
Step 40) by step 30) obtain each cell non-coming year generation attract the volume of traffic substitute into step 20) in demarcate without constraint
Non- coming year OD distributions q is calculated in Gravity Modelsij；
Step 50)：It is distributed q with the OD that application in step 40) is obtained without constraint Gravity ModelsijAs initial OD, operation is primary
Fratar models obtain new prediction of non-coming year OD distributions qij 1, including step 501) is to step 503)；
Step 501)：It is distributed q according to solving to obtain OD between cell i, j without constraint Gravity Modelsij, summarize to obtain each cell generation
Attract the volume of traffic：
Step 502)：Calculate Fratar model related coefficients Wherein, FOiIt indicates that convergence coefficient, F occurs using the trip of i-th of cell when Fratar modelsDjIndicate jth
The trip attraction convergence coefficient of a cell, LijIndicate that regulation coefficient, L occur for the trip of i-th of celljiIndicate j-th cell
Trip attraction regulation coefficient；
Step 503)：Solve new non-coming year OD forecast of distribution qij 1=qij*FOi*FDj*(Lii+Ljj)/2；
Step 60)：Convergence judges：It is distributed q according to the OD that Fratar models one cycle obtains in step 50)ij 1, summarize
The non-coming year prediction new to each cell occurs to attract volume of traffic conduct
If each cell occurs to attract volume of traffic error within tolerance interval, i.e.,：
It is transferred to step 70), is otherwise enabledIt goes to step 40)；
Step 70) prediction result meets the condition of convergence, and end loop, OD distributions at this time are each minizone OD distributions of the non-coming year
Prediction result.
2. the trip distribution modeling method of combination Gravity Models according to claim 1 and Fratar models, feature exist
In：Relevant rudimentary data include cell population, area, land use, locational factor data in the step 10).
3. the trip distribution modeling method of combination Gravity Models according to claim 1 and Fratar models, feature exist
In：Predict that the generation in each cell non-coming year attracts the volume of traffic based on the present situation generation attraction volume of traffic in the step 30)
Method includes original unit's method, growth rate method, cross classification, function method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611087603.5A CN106504535B (en) | 2016-11-30 | 2016-11-30 | A kind of trip distribution modeling method of combination Gravity Models and Fratar models |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611087603.5A CN106504535B (en) | 2016-11-30 | 2016-11-30 | A kind of trip distribution modeling method of combination Gravity Models and Fratar models |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106504535A CN106504535A (en) | 2017-03-15 |
| CN106504535B true CN106504535B (en) | 2018-10-12 |
Family
ID=58329476
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611087603.5A Active CN106504535B (en) | 2016-11-30 | 2016-11-30 | A kind of trip distribution modeling method of combination Gravity Models and Fratar models |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106504535B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107294794A (en) * | 2017-07-31 | 2017-10-24 | 国网辽宁省电力有限公司 | A kind of large-scale ip communication service matrix estimation method and system |
| CN108269399B (en) * | 2018-01-24 | 2020-12-25 | 哈尔滨工业大学 | High-speed rail passenger flow demand prediction method based on road network passenger flow OD reverse thrust technology |
| CN108615360B (en) * | 2018-05-08 | 2022-02-11 | 东南大学 | Traffic demand day-to-day evolution prediction method based on neural network |
| CN109035112B (en) * | 2018-08-02 | 2021-01-26 | 东南大学 | City construction and updating mode determining method and system based on multi-source data fusion |
| CN112613662B (en) * | 2020-12-23 | 2023-11-17 | 北京恒达时讯科技股份有限公司 | Highway traffic analysis method, device, electronic equipment and storage medium |
| CN114639239B (en) * | 2022-02-24 | 2023-04-18 | 东南大学 | Improved gravity model traffic distribution prediction method |
| CN114694378B (en) * | 2022-03-21 | 2023-02-14 | 东南大学 | Two-stage traffic distribution prediction method |
| CN115100849B (en) * | 2022-05-24 | 2023-04-18 | 东南大学 | Combined traffic distribution analysis method for comprehensive traffic system |
| CN115099542B (en) * | 2022-08-26 | 2023-02-03 | 深圳市城市交通规划设计研究中心股份有限公司 | Cross-city commuting trip generation and distribution prediction method, electronic device and storage medium |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7221287B2 (en) * | 2002-03-05 | 2007-05-22 | Triangle Software Llc | Three-dimensional traffic report |
| CN101261768B (en) * | 2007-03-23 | 2010-06-09 | 天津市国腾公路咨询监理有限公司 | Traffic survey data collection and analysis application system for road network and its working method |
| CN101436345B (en) * | 2008-12-19 | 2010-08-18 | 天津市市政工程设计研究院 | System for forecasting harbor district road traffic requirement based on TransCAD macroscopic artificial platform |
| CN102024206A (en) * | 2010-12-20 | 2011-04-20 | 江苏省交通科学研究院股份有限公司 | Method for predicting suburban rail transit passenger flow |
| CN102609781A (en) * | 2011-12-15 | 2012-07-25 | 东南大学 | Road traffic predication system and method based on OD (Origin Destination) updating |
| US9171461B1 (en) * | 2013-03-07 | 2015-10-27 | Steve Dabell | Method and apparatus for providing estimated patrol properties and historic patrol records |
| CN104183119B (en) * | 2014-08-19 | 2016-08-24 | 中山大学 | Based on the anti-arithmetic for real-time traffic flow distribution forecasting method pushed away of section OD |
| CN104899443B (en) * | 2015-06-05 | 2018-03-06 | 陆化普 | For assessing the method and system of current trip requirements and the following trip requirements of prediction |
-
2016
- 2016-11-30 CN CN201611087603.5A patent/CN106504535B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN106504535A (en) | 2017-03-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106504535B (en) | A kind of trip distribution modeling method of combination Gravity Models and Fratar models | |
| CN106781489B (en) | A kind of road network trend prediction method based on recurrent neural network | |
| Li et al. | Prediction for tourism flow based on LSTM neural network | |
| Flötteröd et al. | Behavioral calibration and analysis of a large-scale travel microsimulation | |
| CN110176141B (en) | Traffic cell division method and system based on POI and traffic characteristics | |
| CN108416690A (en) | Load Forecasting based on depth LSTM neural networks | |
| CN103530704A (en) | Predicating system and method for air dynamic traffic volume in terminal airspace | |
| CN103208034B (en) | A kind of track traffic for passenger flow forecast of distribution model is set up and Forecasting Methodology | |
| CN103632212A (en) | System and method for predicating time-varying user dynamic equilibrium network-evolved passenger flow | |
| CN112054943B (en) | Traffic prediction method for mobile network base station | |
| CN109814066A (en) | RSSI indoor positioning distance measuring method, indoor positioning platform based on neural network learning | |
| CN108182484A (en) | Spatial Load Forecasting method based on gridding technology and BP neural network | |
| CN109800916A (en) | The modeling method of vehicle flowrate is driven into a kind of Expressway Service | |
| CN109785618A (en) | Short-term traffic flow prediction method based on combinational logic | |
| CN108597227A (en) | Road traffic flow forecasting method under freeway toll station | |
| Barceló et al. | Robustness and computational efficiency of Kalman filter estimator of time-dependent origin–destination matrices: Exploiting traffic measurements from information and communications technologies | |
| CN109191845A (en) | A kind of public transit vehicle arrival time prediction technique | |
| CN105225541A (en) | Based on the method for Trajectory Prediction in short-term that blank pipe historical data is excavated | |
| CN109508826A (en) | The schedulable capacity prediction methods of electric car cluster of decision tree are promoted based on gradient | |
| CN109345296A (en) | Common people's Travel Demand Forecasting method, apparatus and terminal | |
| CN108615360A (en) | Transport need based on neural network Evolution Forecast method day by day | |
| Yu et al. | Speed‐Density Model of Interrupted Traffic Flow Based on Coil Data | |
| CN109544062A (en) | A kind of Fast Packet vanning information processing system and method suitable for Air Logistics | |
| CN109255948A (en) | A kind of divided lane wagon flow scale prediction method based on Kalman filtering | |
| CN108830414A (en) | A kind of load forecasting method of electric car commercialization charging zone |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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 |