CN114639239B - Improved gravity model traffic distribution prediction method - Google Patents
Improved gravity model traffic distribution prediction method Download PDFInfo
- Publication number
- CN114639239B CN114639239B CN202210172739.5A CN202210172739A CN114639239B CN 114639239 B CN114639239 B CN 114639239B CN 202210172739 A CN202210172739 A CN 202210172739A CN 114639239 B CN114639239 B CN 114639239B
- Authority
- CN
- China
- Prior art keywords
- traffic
- travel
- distribution
- cell
- land
- 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
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
-
- 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 provides an improved gravity model traffic travel distribution prediction method, which comprises the following steps: firstly, collecting relevant data of urban traffic travel demand distribution; secondly, dividing the traffic cells into different categories according to the acquired urban transportation travel demand distribution related data; then, carrying out model parameter calibration on demand distribution among different types of traffic cells by adopting an improved gravity model; and finally, forecasting the distribution of the urban traffic travel demands by using the calibrated gravity model. The invention not only fully inherits the advantages of the gravity model, but also improves the utilization degree of the distribution information of the current travel demand, considers the difference of the social and economic development level and the function positioning between different traffic districts, better accords with the actual situation, and can provide a reference basis for the planning and management of urban transportation.
Description
Technical Field
The invention relates to an improved gravity model traffic distribution prediction method considering traffic district categories, and belongs to the technical field of traffic demand and traffic distribution prediction.
Background
The urban traffic travel demand distribution prediction is one of key steps of a traffic planning four-stage method, and the main task is to convert the total traffic travel demand quantity obtained by the previous traffic generation prediction into a travel demand distribution matrix among traffic cells. The accuracy of urban traffic travel demand distribution prediction directly influences the precision of a traffic distribution process, and has very important significance for traffic planning research and decision analysis of urban traffic management departments.
At present, the research on traffic distribution models at home and abroad is numerous, but most of the research is limited to theoretical research and is difficult to meet the engineering practice requirements at the present stage. For most urban traffic planning and management, the growth coefficient method and the gravity model method are the most mature traffic distribution prediction models currently applied. The gravity model method is relatively more practical because the influence of the generation attraction amount and the traffic impedance of the traffic cell on the travel demand distribution is comprehensively considered. However, the conventional gravity model method treats all kinds of traffic cells equally, and neglects the difference of socioeconomic development level and functional positioning between different traffic cells. In fact, the traffic distribution volume is driven differently by the occurrence and attraction of traffic cells of different functional locations, for example, traffic cells of the residential and commercial or industrial type tend to have higher traffic travel demands due to the occupational relationship. On the other hand, the conventional gravity model method cannot consider the characteristic difference between the intra-area trip and the inter-area trip, and the current trip demand distribution rule is not sufficiently grasped, so that deviation often exists between the current situation and the expected situation in engineering practice application.
Disclosure of Invention
The purpose of the invention is as follows: in order to solve the defects and defects in the prior art, the invention provides the urban transportation travel demand distribution prediction method considering the traffic district category, which can improve the conventional gravity model, fully inherits the advantages of the gravity model, improves the utilization degree of the current travel demand distribution information, and better accords with the actual situation.
The technical scheme is as follows: in order to achieve the purpose, the invention adopts the technical scheme that: an improved gravity model traffic distribution prediction method comprises the following steps:
step 1), collecting relevant data of urban traffic travel demand distribution;
step 2), dividing the traffic subdistricts into different categories according to the collected relevant data of the urban traffic travel demand distribution;
step 3), carrying out model parameter calibration on demand distribution among different types of traffic cells by adopting an improved gravity model;
and 4) forecasting the distribution of urban transportation travel demands by using the calibrated gravity model.
Further, the data related to the urban transportation travel demand distribution collected in step 1) includes characteristic data of transportation cells, land use data and population structure data in the transportation cells, a current transportation travel demand distribution matrix and a travel impedance matrix between the transportation cells, and an occurrence amount, an attraction amount and a travel impedance matrix of each transportation cell in the coming year, which are specifically as follows:
step 1.1), collecting traffic cell characteristic data, including traffic cell division range, traffic cell area and work post total amount;
step 1.2), collecting land use data in the traffic district, wherein the land use data comprises the total building area and the development intensity of different land types (public management and public service facility land, commercial service facility land, green land and square land, construction land, industrial land, residential land, road and traffic facility land, public facility land and logistics storage land) in the traffic district;
step 1.3), collecting population structure data in the traffic district, wherein the population structure data comprises population total amount, sex ratio, age distribution and unemployment population ratio in the traffic district;
preferably, in step 2), the traffic cells are divided into different categories according to the collected data related to urban transportation travel demand distribution, which is as follows:
step 2.1), determining classification characteristics according to the research range and the collected data related to the urban transportation travel demand distribution;
and 2.2) adopting a GMM (Gaussian mixture model) clustering algorithm to divide the traffic cells into four categories (a residential leading traffic cell, a commercial leading traffic cell, an industrial leading traffic cell and a comprehensive traffic cell) according to the classification characteristics.
Further, the improved gravity model in step 3) is:
wherein, T ij Distribution quantity of travel demands from a traffic cell i to a traffic cell j; o is i ，D j Respectively of traffic cell iThe amount of occurrence and the amount of attraction for traffic cell j; c ij Impedance from traffic cell i to traffic cell j; k is a radical of a ，k b ，k c ，α 1 ，α 2 ，α 3 ，β 1 ，β 2 ，β 3 ，γ 1 ，γ 2 ，γ 3 For the model parameters, calibrating the model parameters by adopting different traffic cell category samples; k is a radical of formula a ，k b ，k c The driving strength of the traffic distribution quantity of the occurrence quantity and the attraction quantity of the traffic districts positioned by different functions can be reflected, the impedance from the traffic district i to the traffic district j is the traffic trip impedance between the corresponding traffic district i and the traffic district j, the generalized trip cost of the trip time and/or the trip cost is used for representing the occurrence quantity O i I.e. the total quantity of travel demands, the attraction D, from traffic cell i to all other traffic cells j I.e. the total amount of travel demand from all other traffic cells to traffic cell j.
Further, in step 4), the distribution prediction of urban transportation travel demand is performed by using the calibrated gravity model, and the method specifically includes:
step 4.1), judging the types of the traffic cell i and the traffic cell j;
step 4.2), substituting the occurrence amount and the attraction amount of each traffic cell and the travel impedance matrix into a calibrated improved gravity model in the next year to obtain the travel demand distribution amount from the traffic cell i to the traffic cell j in the next year;
and 4.3) repeating the steps 4.1 and 4.2 until the travel demand distribution quantity among all traffic districts is obtained, and further obtaining an urban traffic travel demand distribution matrix in the next year.
Has the advantages that: compared with the prior art, the technical scheme of the invention has the following beneficial technical effects:
the technical scheme of the invention fully inherits the advantages of the gravity model, improves the utilization degree of the current travel demand distribution information, considers the difference between the social and economic development level and the function positioning among different traffic districts, better accords with the actual situation, and has better prediction effect on the prediction of the urban traffic travel demand distribution.
Drawings
FIG. 1 is a block flow diagram of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples for the purpose of facilitating understanding and implementation of the invention by those skilled in the art, and it is to be understood that the implementation examples described herein are only for the purpose of illustration and explanation and are not to be construed as limiting the invention.
It should be noted that the traffic cell described in the present invention is a general term, and is well known to those skilled in the art, that is, in urban traffic planning, an urban traffic network is divided into a plurality of traffic sub-areas according to a certain principle, and these functional sub-areas are referred to as traffic cells.
In the embodiment, relevant data of urban transportation travel demands within a certain regional downtown area range are collected, wherein the data comprises the area of a traffic cell, the total population, the proportion of a lost-business population, the proportion of an elderly or children population, the area of a commercial service facility, the area of a residential site, the area of a road and a traffic facility and the area of an industrial site, the data are shown in table 1 and are used as classification features, all traffic cells are classified into four categories, namely a residential leading traffic cell, a commercial leading traffic cell, an industrial leading traffic cell and a comprehensive traffic cell, and the classification results are shown in table 2.
TABLE 1 relevant data of urban transportation travel demand
Table 2 traffic cell category division results
| Traffic cell categories | Traffic cell numbering |
| Residence leading type traffic district | 2，4，7，31，……，41，49，50 |
| Business-oriented traffic cell | 5，6，8，13，……，34，43，46 |
| Industry-oriented traffic district | 1，9，16，17，……，42，44，47 |
| Comprehensive traffic district | 3，10，11，12，……，40，45，48 |
The present embodiment collects and obtains a current transportation demand distribution matrix and a transportation impedance matrix between transportation cells, and the occurrence amount and the attraction amount of each transportation cell in the next year are shown in tables 3 and 4, and the transportation impedance in the next year is the same as the current situation.
TABLE 3 distribution matrix of current traffic travel demand and future annual occurrence and attraction
Note: the element values in the current traffic trip demand distribution matrix are the current trip demand between corresponding ODs; the future occurrence is the total amount of the future travel demands from the traffic district O to all the traffic districts; the future attraction is the total amount of future travel demand from all traffic cells to traffic cell D.
TABLE 4 Current State traffic travel impedance matrix
| O\D | 1 | 2 | 3 | …… | 48 | 49 | 50 |
| 1 | 1540 | 3614 | 2943 | …… | 6920 | 3628 | 8621 |
| 2 | 3641 | 2608 | 4256 | …… | 5621 | 3529 | 2931 |
| 3 | 6251 | 5529 | 1315 | …… | 2261 | 4812 | 3691 |
| …… | …… | …… | …… | …… | …… | …… | …… |
| 48 | 6920 | 3628 | 8621 | …… | 2193 | 3621 | 4862 |
| 49 | 6920 | 3628 | 8621 | …… | 6248 | 2360 | 3621 |
| 50 | 6920 | 3628 | 8621 | …… | 4862 | 4962 | 2355 |
Note: the element values in the current traffic trip impedance matrix are the current traffic trip impedance between the corresponding ODs, and are expressed by generalized trip costs including trip time and/or trip costs.
And calibrating parameters of the improved gravity model according to the data to obtain:
it should be understood that the above-mentioned embodiments are merely illustrative of the technical idea of the present invention, and that a person skilled in the art may make several improvements and modifications without departing from the principle of the present invention, and that these improvements and modifications should also be regarded as the protection scope of the present invention.
Claims (3)
1. An improved gravity model traffic travel distribution prediction method is characterized by comprising the following steps:
step 1), collecting relevant data of urban traffic travel demand distribution;
step 2), dividing the traffic cells into different categories according to the collected urban transportation travel demand distribution related data;
step 3), carrying out model parameter calibration on demand distribution among different types of traffic cells by adopting an improved gravity model;
step 4), forecasting the distribution of urban traffic travel demands by using the calibrated gravity model;
the improved gravity model in the step 3) is as follows:
wherein, T ij Distribution quantity of travel demands from a traffic cell i to a traffic cell j; o is i ，D j Respectively the occurrence amount of the traffic cell i and the attraction amount of the traffic cell j; c ij Impedance from traffic cell i to traffic cell j; k is a radical of a ，k b ，k c ，α 1 ，α 2 ，α 3 ，β 1 ，β 2 ，β 3 ，γ 1 ，γ 2 ，γ 3 For the model parameters, calibrating the model parameters by adopting different traffic cell category samples; the impedance from the traffic cell i to the traffic cell j is the traffic travel impedance between the corresponding traffic cell i and the traffic cell j, and is expressed by the travel time and/or the generalized travel cost of the travel cost, and the occurrence O i I.e. the total quantity of travel demands, the attraction D, from traffic cell i to all other traffic cells j The total amount of travel demands from all other traffic cells to the traffic cell j;
in the step 4), the distribution of urban transportation travel demands is predicted by using the calibrated gravity model, and the method specifically comprises the following steps:
step 4.1), judging the types of the traffic cell i and the traffic cell j;
step 4.2), substituting the occurrence amount and the attraction amount of each traffic cell and the travel impedance matrix into a calibrated improved gravity model in the next year to obtain the travel demand distribution amount from the traffic cell i to the traffic cell j in the next year;
and 4.3), repeating the steps 4.1 and 4.2 until the travel demand distribution quantity among all traffic districts is obtained, and further obtaining the urban traffic travel demand distribution matrix in the next year.
2. The improved gravity model traffic distribution prediction method according to claim 1, wherein the data related to the distribution of urban transportation travel demands collected in step 1) comprises: the traffic community characteristic data, the land use data and the population structure data in the traffic community, the current traffic trip demand distribution matrix and the trip impedance matrix between the traffic communities and the occurrence and the attraction and the trip impedance matrix of the traffic communities in the next year are as follows:
step 1.1), collecting traffic cell characteristic data, including traffic cell division range, traffic cell area and work post total amount;
step 1.2), collecting land use data in the traffic district, wherein the land use data comprises the total building area and development strength of different land types in the traffic district, and the land types comprise: public management and public service facility land, commercial service facility land, green land and square land, construction land, industrial land, residential land, road and transportation facility land, public facility land and logistics storage land;
and step 1.3), collecting population structure data in the traffic cell, wherein the population structure data comprises the total population amount, the sex ratio, the age distribution and the unemployed population ratio in the traffic cell.
3. The improved gravity model traffic distribution prediction method according to claim 2, wherein in step 2), traffic cells are divided into different categories according to the collected data related to the urban transportation travel demand distribution, specifically as follows:
step 2.1), determining classification characteristics according to the research range and the collected data related to the urban transportation travel demand distribution;
step 2.2), according to the classification characteristics, a clustering algorithm is adopted to divide the traffic subdistrict into four categories: residential, commercial, industrial, and integrated traffic cells.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210172739.5A CN114639239B (en) | 2022-02-24 | 2022-02-24 | Improved gravity model traffic distribution prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210172739.5A CN114639239B (en) | 2022-02-24 | 2022-02-24 | Improved gravity model traffic distribution prediction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114639239A CN114639239A (en) | 2022-06-17 |
| CN114639239B true CN114639239B (en) | 2023-04-18 |
Family
ID=81947898
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210172739.5A Active CN114639239B (en) | 2022-02-24 | 2022-02-24 | Improved gravity model traffic distribution prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114639239B (en) |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105070042B (en) * | 2015-07-22 | 2017-10-10 | 济南市市政工程设计研究院（集团）有限责任公司 | A kind of modeling method of traffic forecast |
| CN106504535B (en) * | 2016-11-30 | 2018-10-12 | 东南大学 | A kind of trip distribution modeling method of combination Gravity Models and Fratar models |
| CN112133090A (en) * | 2020-08-14 | 2020-12-25 | 南京瑞栖智能交通技术产业研究院有限公司 | Multi-mode traffic distribution model construction method based on mobile phone signaling data |
-
2022
- 2022-02-24 CN CN202210172739.5A patent/CN114639239B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN114639239A (en) | 2022-06-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Schneider et al. | Modern grid initiative distribution taxonomy final report | |
| CN106600063B (en) | Space load prediction method based on fuzzy rough set theory and spatio-temporal information | |
| Voulis et al. | Understanding spatio-temporal electricity demand at different urban scales: A data-driven approach | |
| Yang et al. | Efficient local AADT estimation via SCAD variable selection based on regression models | |
| CN113611105B (en) | Urban traffic travel demand total quantity prediction method | |
| CN107292484A (en) | The recognition methods of urban redevelopment soil and system based on city space big data | |
| Caceres et al. | Estimating traffic flow profiles according to a relative attractiveness factor | |
| Liu et al. | A Bayesian approach to residential property valuation based on built environment and house characteristics | |
| CN115099542A (en) | Cross-city commuting trip generation and distribution prediction method, electronic device and storage medium | |
| CN105005942A (en) | Method for selecting differentiated construction mode of smart distribution grid | |
| CN115798189A (en) | Traffic congestion index evaluation method | |
| CN113888210A (en) | Engineering cost estimation method | |
| CN114639239B (en) | Improved gravity model traffic distribution prediction method | |
| CN113537596A (en) | Short-time passenger flow prediction method for new line station of urban rail transit | |
| Yang et al. | New efficient regression method for local AADT estimation via SCAD variable selection | |
| CN110020799B (en) | Urban management grid resource allocation based on space-time reference | |
| CN102663230A (en) | Method for land resource evaluation factor level classification based on genetic algorithm | |
| CN106022546B (en) | Load prediction method based on residential community load growth cycle | |
| Zhang et al. | Regional impact and spillover effect of public infrastructure investment: An empirical study in the Yangtze River Delta, China | |
| CN110942260B (en) | College traffic safety evaluation method based on Bayesian maximum entropy | |
| CN113393079A (en) | Traffic zone dividing method based on public traffic data | |
| CN113744525A (en) | Traffic distribution prediction method based on feature extraction and deep learning | |
| CN112633991A (en) | Rental index analysis method and device | |
| Hu et al. | Planning support in estimating green housing opportunities for different socioeconomic groups in Nanjing, China | |
| Li et al. | Identifying urban form typologies in seoul with mixture model based clustering |
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 |