CN104766146A - Traffic demand forecasting method and system - Google Patents
Traffic demand forecasting method and system Download PDFInfo
- Publication number
- CN104766146A CN104766146A CN201510202393.9A CN201510202393A CN104766146A CN 104766146 A CN104766146 A CN 104766146A CN 201510202393 A CN201510202393 A CN 201510202393A CN 104766146 A CN104766146 A CN 104766146A
- Authority
- CN
- China
- Prior art keywords
- sample
- family
- activity pattern
- activity
- work
- 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.)
- Pending
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a traffic demand forecasting method and system. The method comprises the steps of obtaining the social economy characteristics and the land utilization characteristics of an forecast range and establishing a sample basic information database; allocating a piece of residence place information and a piece of employment place information for each sample; obtaining the activity mode, the activity place, the travel mode and the travel time of each sample, and determining the time-parting and mode-parting traffic transportation demands of different regions of the forecasting range according to the activity mode, the activity place, the travel mode and the travel time. According to the scheme, the social economy characteristics and the land utilization characteristics of the sample are used, the forecasting is conducted by combining the activity mode, the activity place, the travel mode and the travel time of each sample, the scientificity of traffic demand forecasting is improved, compared with a traditional four-stage method, the factors influencing the traffic demands can be better reflected, and the change conditions of the traffic demands under different circumstances can be better analyzed.
Description
Technical field
The present invention relates to traffic programme technical field, specifically a kind of needing forecasting method based on traffic behavior analysis and system.
Background technology
Along with the development in city, the scale in city constantly expands, and traffic becomes the mainstay supporting city operations.In the zones of different in city, due to the difference of inhabitation colony, trip mode and travel time etc., the transport need in each region has respective feature.In order to ensure that city is normally run, traffic department needs the feature reasonable distribution traffic resource for regional.
Traffic Demand Forecasting is the core of traffic programme, in order to carry out the planning such as urban road network and public transit system, needing to predict accurately transport need, determining the transport need amount between each traffic zone.At present, the travel demand forecast model that traffic programme field extensively adopts is traditional Four-stage Method, and the first stage is Trip generation forecast, and subordinate phase is traffic distribution, and the phase III is model split, and fourth stage is traffic assignation.But Four-stage Method has the following disadvantages, be first that its lacks explanation in behaviouristics, be difficult to explain behavioral mechanism, in addition, Four-stage Method causes time and space exists discontinuous, and is difficult to the impact analyzing Transportation Demand Management strategy.
A kind of Urban Traffic Planning emulation mode based on multiple agent motility model and system are also disclosed in Chinese patent literature CN201210256877, the method comprises first acquisition urban road information, generate road network information file, again according to the enquiry data obtained, generate initial transport need and initial day activity program, then day activity program is loaded on road network information file, next calculate each by the utility value of respondent and plan select probability, finally carry out iterative process, Output simulation result.But only considered motility model in the program, do not consider economic society and terrain characteristics, therefore the program is not comprehensive, the also transport need in unpredictable future.
Summary of the invention
For this reason, technical matters to be solved by this invention be to change Traffic Demand Forecasting of the prior art lacks behavioral mechanism basis and considers that influence factor does not cause comprehensively cannot the present situation of transport need in Accurate Prediction future, propose a kind of based on traffic behavior mechanism, the Forecast of Traffic Demand that contains major influence factors and system.
For solving the problems of the technologies described above, the invention provides a kind of new Forecast of Traffic Demand, comprising the steps:
Obtain social economy's characteristic and the Land_use change attribute of estimation range, set up sample basic information database;
For each sample distributes a residence information and employment ground information;
Obtain the activity pattern of each sample;
Obtain the activity venue of each sample;
Obtain the trip mode of each sample;
Obtain the travel time of each sample;
According to described activity pattern, activity venue, trip mode and travel time, determine in estimation range between zones of different at times, the traffic trip demand of point mode.
Preferably, described social economy characteristic comprises sex, age, income, vehicles recoverable amount.
Preferably, described Land_use change attribute comprises the living space of estimation range, commercial space, the size of population of industrial area and community and job quantity, apart from intown distance.
Preferably, described activity pattern comprises " family-work-family ", " family-work-family-work-family ", " family-work-other-family ", " family-work-other-work-family ", " family-other-family ".
Preferably, the step of the activity pattern of each sample of described acquisition, comprising:
Calculate the utility value of each specimen needle to each activity pattern, computing formula is:
wherein, Vj is the utility value of this sample for activity pattern j, and i is sample number, and n is total sample number; Aij is the parameter item demarcated, and Xi is the variable-value of sample;
Calculate the probable value of each activity pattern of each samples selection, computing formula is:
M is the quantity of activity pattern;
The selection result of the activity pattern of each sample is obtained according to described probable value.
Preferably, described trip mode comprises car, public transport, bicycle, walking.
Preferably, the described travel time comprise morning peak before, morning peak, daytime, evening peak, after evening peak.
A kind of Traffic Demand Forecasting system, comprising:
Basic information database sets up unit, obtains social economy's characteristic and the Land_use change attribute of estimation range, sets up sample basic information database;
Selected cell, for each sample distributes a residence information and employment ground information;
Activity pattern forecast model unit, obtains the activity pattern of each sample;
Activity venue forecast model unit, obtains the activity venue of each sample;
Trip mode forecast model unit, obtains the trip mode of each sample;
Travel time prediction model unit, obtains the travel time of each sample;
Output unit, according to described activity pattern, activity venue, trip mode and travel time, determine in estimation range between zones of different at times, the traffic trip demand of point mode.
Preferably, described activity pattern forecast model unit comprises:
The utility value computing module of activity pattern, calculate the utility value of each specimen needle to each activity pattern, computing formula is:
wherein, Vj is the utility value of this sample for activity pattern j, and i is sample number, and n is total sample number; Aij is the parameter item demarcated, and Xi is the variable-value of sample;
The probable value computing module of activity pattern, calculates the probable value of each activity pattern of each samples selection, and computing formula is:
m is the quantity of activity pattern;
Result computing module, obtains the selection result of the activity pattern of each sample according to described probable value.
According to claim 8 or claim 9, system, is characterized in that, described activity pattern comprises " family-work-family ", " family-work-family-work-family ", " family-work-other-family ", " family-work-other-work-family ", " family-other-family ".
Technique scheme of the present invention has the following advantages compared to existing technology:
(1) Forecast of Traffic Demand in the present invention and system, make use of social economy's characteristic of sample, Land_use change attribute, predict in conjunction with the activity pattern of each sample, activity venue and trip mode and travel time, transport need is all be derived from movable Derived Demand, understand the basic source that activity pattern could understand transport need, improve the science of Traffic Demand Forecasting, compared to traditional Four-stage Method, more can reflect the factor affecting transport need, better can analyze the situation of change of transport need under different sight.
Accompanying drawing explanation
In order to make content of the present invention be more likely to be clearly understood, below according to a particular embodiment of the invention and by reference to the accompanying drawings, the present invention is further detailed explanation, wherein
Fig. 1 is the process flow diagram of the Forecast of Traffic Demand of the embodiment of the present invention 1;
Fig. 2 is the process flow diagram that the activity pattern of the embodiment of the present invention 1 is selected;
Fig. 3 is the process flow diagram that the activity venue of the embodiment of the present invention 1 is selected.
Embodiment
In order to make those skilled in the art person understand content of the present invention better, below in conjunction with drawings and Examples, technical scheme provided by the present invention is described in further detail.
embodiment 1:
A kind of novel traffic needing forecasting method provided in the present embodiment, overall flow figure as shown in Figure 1, comprises the steps:
S1: the social economy's characteristic and the Land_use change attribute that obtain estimation range, sets up sample basic information database.Be specially:
First the sample social economy characteristic of traffic zone aspect and Land_use change attribute in input prediction area.Wherein, social economy's characteristic comprise sex, the age (be divided into 0-18 year, 18-35 year, 35-60 year, more than 60 years old four classes), monthly income (be divided into 0-5000 unit, 5000-10000 is first, 10000-20000 is first, more than 20000 yuan four classes), car is possessed, bicycle is possessed statistics percent profile; Land_use change attribute comprises the living space of community, commercial space, the All population capacities of industrial area and community and job quantity, apart from intown distance.Based on these economic society data, utilize the way of Monte Carlo simulation at random to sample assignment, Monte-Carlo Simulation Method is a kind of analogy method of the prior art, based on a probability model, according to the process that this model is described, by the result of simulated experiment, as the approximate solution of problem.Such as statistics obtains M-F 52% and 49%, the some samples of corresponding stochastic generation, and according to this number percent assignment, thus each sample is to the value that should have this number of variables, forms sample basic information database.
S2: for each sample distributes a residence information and employment ground information.
Residence and the place of working addressing of resident is obtained subsequently by statistics, this results in family and the work unit of resident, here Monte Carlo simulation is carried out equally according to the resident population of community and working population, a residence and employment ground is distributed, as the basis of next step travel demand forecast model to each sample.
Next the activity pattern of each sample, activity venue, trip mode, travel time is obtained successively, specific as follows:
S3: the activity pattern obtaining each sample, activity pattern comprises " family-work-family " (hwh, pattern 1), " family-work-family-work-family " (hwhwh. pattern 2), " family-work-other-family " (hwh+, mode 3), " family-work-other-work-family " (hw+wh. pattern 4), " family-other-family " (hoh, pattern 5), the process flow diagram that activity pattern is selected is as shown in Figure 2.
S3-1: first, calculate the utility value of each specimen needle to often kind of activity pattern (five kinds of patterns) according to following formula, computing formula is:
Wherein, V
jfor this sample is for the utility value of activity pattern j, utility value has reacted individual preference, and in general, utility value is larger, selects the probability of this selection limb also larger.
X
ifor the variable-value of sample, i.e. social economy's characteristic (such as sex, age, income, automobile pollution etc.) of sample and the Land_use change characteristic (such as the proportion of inhabitation, business, industrial land) of related cell.I=1 ..., n, n are the sum of sample, and for each sample i, one number of variables value is from the sample basic information database of first stage.
A
ijfor the parameter item demarcated, parameter item has reacted the weight of each variable in effectiveness item, and parameter item should be demarcated and obtain before demand forecast.First traffic trip investigation is implemented, a certain amount of sample is extracted out from the total population of city, its movable and travel behaviour of investigation records, thus obtain the Land_use change characteristic of the sampling movable trip information of resident, social economy's characteristic and related cell, then according to enquiry data, set up Logit model and demarcate.Logit model is the model I extensively used in Discrete Choice Model, and be also model most widely used at present, do not repeat them here, those skilled in the art can implement the program according to the ABC of this area under the prompting of this step.Logit model calibration is very proven technique in travel mode choice, and concrete demarcation mode can see " Transport Planning Theory and method " (Lu Huapu writes), the 7th chapter, P164-174.
S3-2: subsequently, calculates the probable value of each activity pattern of samples selection, is calculated by following formula:
Wherein, j be activity pattern numbering (one in five kinds of activity patterns, j=1 ..., 5),
be the summation that five kinds of activity patterns calculate.
According to this probable value, use Monte Carlo simulation, simulation obtains the activity pattern selection result of each sample.Monte Carlo is conventional Method of Stochastic, and for each sample, he has certain select probability to each preference pattern, and some model selection probability are comparatively large, and what have is less; For example the select probability of its five kinds of patterns is respectively 0.2,0.3,0.3,0.1,0.1, so produces the random number between 0 to 1 during simulation at random, if this number is less than 0.2, assert its preference pattern one; If this random number is between 0.2 to 0.5 (0.2+0.3), its preference pattern two; Between 0.5 to 0.8, its preference pattern three; Between 0.8 to 0.9, preference pattern four, between 0.9 to 1, preference pattern five.So operate each sample, namely simulation obtains the model selection result of each sample.
As
namely the select probability of activity pattern 1 is represented.
namely the select probability of activity pattern 2 is represented;
namely the select probability of activity pattern 3 is represented;
namely the select probability of activity pattern 4 is represented;
namely the select probability of activity pattern 5 is represented;
If sample Xi ∈ is (0, P
1], then preference pattern 1; If Xi ∈ is (P
1, P
1+ P
2], then preference pattern 2; If Xi ∈ is (P
1+ P
2, P
1+ P
2+ P
3], then preference pattern 3; If Xi ∈ is (P
1+ P
2+ P
3, P
1+ P
2+ P
3+ P
4], then preference pattern 4; If Xi ∈ is (P
1+ P
2+ P
3+ P
4, 1], then preference pattern 5.
S4: the activity venue obtaining each sample.As shown in Figure 3, the realization flow figure of activity venue is shown.
In the present embodiment, four kinds of situations are divided into determine its activity venue:
1) " family-work-family " i.e. hwh, " family-work-family-work-family " i.e. hwhwh
Activity venue is place of working.
2) " family-work-other-work-family " i.e. hw+wh
An activity venue is place of working, also needs to determine that work comes and goes destination;
3) " family-work-other-family " i.e. hwh+
Only consider an inoperative trip, wherein β 1 is for parked in working process, and β 2, for parked in process of coming off duty, needs to determine parked some position;
Wherein: β 1=0.3; β 2=0.7.
4) " family-other-family " i.e. hoh
The place of other activities need be determined.
For needing the trip determining activity venue, still using similar formula to determine utility value and the select probability of each possibility community, place, then using the way of Monte Carlo simulation to determine its activity venue.
S5: the trip mode obtaining each sample, described trip mode comprises car, public transport, bicycle, walking.The method obtaining the trip mode of each sample and the class of algorithms obtaining activity pattern are seemingly.
Such as in Passenger Traveling Choice, limb is selected just to include four kinds of mode of transportation (walkings, bicycle, public transport, car), concerning each sample, first the utility value of each selection limb is calculated, account form and formula (1) similar, variable-value is identical, unlike parameter value A
ijneeding to demarcate according to sample survey results before, is different from the calibrating parameters of activity pattern.
Scaling method is demarcated identical with activity pattern.It is emphasized that this calibration result, although scaling method is identical, the coefficient demarcated out is different, can not simply directly take the calibration coefficient of motility model to use.
After obtaining the utility value of sample for each mode of transportation, calculate select probability according to formula (2).
After obtaining the select probability of each mode of transportation, the method for Monte Carlo simulation described before use determines the selection result of each sample.
Identical with activity pattern, the probable value of often kind of mode is drawn by following formula
only selection limb here only has 4 kinds (car, public transport, bicycle, walkings), and the selection limb in activity pattern model has 5 kinds.
After obtaining the select probability of often kind of mode of transportation, analog sample actual selection result activity pattern model class equally and before seemingly, adopts Monte Carlo simulation.Concrete example is with consistent above.For example the select probability of four kinds of modes of transportation is respectively 0.2 (walking), 0.3 (bicycle), 0.3 (car), 0.2 (public transport), so produce the random number between 0 to 1 during simulation at random, if this number is less than 0.2, assert that it selects walking trip; If this random number is between 0.2 to 0.5 (0.2+0.3), it selects cycling trip; Between 0.5 to 0.8, it selects car trip; Between 0.8 to 1, select transit trip.So operate each sample, namely simulation obtains the model selection result of each sample.
S6: the travel time obtaining each sample, the described travel time comprise morning peak before, morning peak, daytime, evening peak, after evening peak.The method obtaining the travel time of each sample is also similar with the method for acquisition activity pattern, trip mode.
The determination of travel time is similar with mode before, selects limb to include five kinds of travel times: " before morning peak (before 7:00) ", " morning peak (7:00 to 9:00) ", " daytime (9:00 to 17:00) ", " evening peak (17:00 to 19:00) ", " after evening peak (after 19:00) ".Calculation process is consistent with above-mentioned, parameter value A
ijneed to demarcate according to sample survey results before.Scaling method and activity pattern model, trip mode model class seemingly, are not repeating at this.
Above-mentioned S3-S6 order is carried out, then obtain activity pattern, activity venue, trip mode and travel time.
S7: according to described activity pattern, activity venue, trip mode and travel time, determine in estimation range between zones of different at times, the traffic trip demand of point mode.
Last according to cell level, samples selection result set meter is got up, obtains the OD table of minizone point mode at times, can be used for traffic assignation and traffic programme.
For example, have a ground to divide into 3 traffic zones (1,2,3), respectively there are 2 people each community, so one has 6 people;
Sample 1,2 inhabits community 1,3,4 and inhabits community 2,5,6 and inhabit community 3;
Sample 1,4 works in community 2,2,5 and works in community 3,3,6 without work;
Everyone activity pattern, activity venue, trip mode, travel time utilize said method to calculate, as shown in the table:
Next, be exactly the information collected from this table needed for meter;
If need total OD table, so first choose all row (every a line representative is once gone on a journey) that departure place in summary table is 1, obtain following table:
| Activity pattern | Trip sequence number | Departure place | Destination | Trip mode | Travel time | |
| Sample 1 | hwh | 1 | 1 | 2 | Car | Morning peak |
| Sample 2 | hwh+ | 1 | 1 | 3 | Public transport | Morning peak |
| Sample 6 | hoh | 2 | 1 | 3 | Car | Evening peak |
Add up destination, can obtain community 1 has 1 trip to community 2, have 2 trips to community 3 again; Equally the trip that departure place is community 2,3 is added up, finally obtains OD table following (being classified as departure place, behavior destination):
So far, obtain total traffic trip OD to show.
If need the OD of point mode to show, the OD table of such as car, can first extract the content that mode of transportation is car, and then a point community as above operates to summary table, can obtain the OD table of car.
If need the OD of point time to show, the OD table of such as evening peak, can first extract to summary table the content that line time is evening peak equally, then carry out statistical study.
Forecast of Traffic Demand in the present embodiment and system, make use of social economy's characteristic of sample, Land_use change attribute, predict in conjunction with the activity pattern of each sample, activity venue and trip mode and travel time, transport need is all be derived from movable Derived Demand, understand the basic source that activity pattern could understand transport need, improve the science of Traffic Demand Forecasting, compared to traditional Four-stage Method, more can reflect the factor affecting transport need, better can analyze the situation of change of transport need under different sight
embodiment 2:
The application example that one concrete is provided in the present embodiment.
For Shangdi-Qinghe area traffic demand forecast, Shangdi-area, Qinghe is divided into 15 internal zones and 3 outside great Qu altogether.
First, input social economy's performance data of each traffic zone, comprise age, population, income dis tribution, and the Land_use change characteristic of each traffic zone, through place of working, residence preference pattern, obtain community, the residence ID of each sample, community, place of working ID.
Subsequently through the travel demand forecast model system of four layers, adopt the method in embodiment 1, obtain the activity pattern of each sample, activity venue, trip mode, travel time.
For activity pattern, obtain the activity pattern of Shangdi-Qinghe Area Inhabitants, as shown in table 1:
Table 1 Shangdi-Qinghe Area Inhabitants activity pattern analysis result
About trip mode, prediction obtains the share rate in Shangdi-area, Qinghe, as shown in table 2:
Table 2 Shangdi-Qinghe Area Inhabitants travel mode split rate analysis result
| Trip mode | Car | Public transport | Subway | Bicycle | Walking |
| Share rate | 31％ | 20％ | 16％ | 18％ | 15％ |
Finally by the mode of collection meter, obtain the OD table of point mode at times between each traffic zone.For morning peak on working day (7:00-9:00), traffic zone 1 is as shown in table 3 to the car transportation demand between each community:
Table 3 Shangdi-Qinghe district work day morning peak car transportation demand (for traffic zone 1)
| Object community | 01 | 02 | 03 | 04 | 05 | 06 | 07 | 08 | 09 |
| Transport need | 239 | 31 | 109 | 68 | 17 | 18 | 27 | 24 | 17 |
| Object community | 10 | 11 | 12 | 13 | 14 | 15 | 16 | 17 | 18 |
| Transport need | 30 | 18 | 18 | 18 | 19 | 24 | 14 | 98 | 3 |
Sample, just obtains the car transportation demand of this regional traffic community 1, in like manner can also obtain the transport need of public transport, bicycle, subway etc., is convenient to traffic department and makes rational planning for traffic resource.
embodiment 3:
A kind of Traffic Demand Forecasting system is provided in the present embodiment, comprises:
Basic information database sets up unit, obtains social economy's characteristic and the Land_use change attribute of estimation range, sets up sample basic information database;
Selected cell, for each sample distributes a residence information and employment ground information;
Activity pattern forecast model unit, obtains the activity pattern of each sample;
Activity venue forecast model unit, obtains the activity venue of each sample;
Trip mode forecast model unit, obtains the trip mode of each sample;
Travel time prediction model unit, obtains the travel time of each sample;
Output unit, according to described activity pattern, activity venue, trip mode and travel time, determine in estimation range between zones of different at times, the traffic trip demand of point mode.
Wherein, described activity pattern forecast model unit comprises:
The utility value computing module of activity pattern, calculate the utility value of each specimen needle to each activity pattern, computing formula is:
wherein, V
jfor this sample is for the utility value of activity pattern j, i is sample number, and n is total sample number; A
ijfor the parameter item demarcated, Xi is the variable-value of sample;
The probable value computing module of activity pattern, calculates the probable value of each activity pattern of each samples selection, and computing formula is:
m is the quantity of activity pattern;
Result computing module, obtains the selection result of the activity pattern of each sample according to described probable value.
Originally be in embodiment, described activity pattern comprise " family-work-family ", " family-work-family-work-family ", " family-work-other-family ", " family-work-other-work-family ", " family-other-family ".Described social economy characteristic comprises sex, age, income, vehicles recoverable amount.Described Land_use change attribute comprises the living space of estimation range, commercial space, the size of population of industrial area and community and job quantity, apart from intown distance.Described trip mode comprises car, public transport, bicycle, walking.The described travel time comprise morning peak before, morning peak, daytime, evening peak, after evening peak.
Traffic Demand Forecasting system in the present invention improves the science of Traffic Demand Forecasting, better can analyze the situation of change of transport need under different sight.
Obviously, above-described embodiment is only for clearly example being described, and the restriction not to embodiment.For those of ordinary skill in the field, can also make other changes in different forms on the basis of the above description.Here exhaustive without the need to also giving all embodiments.And thus the apparent change of extending out or variation be still among the protection domain of the invention.
Those skilled in the art should understand, embodiments of the invention can be provided as method, system or computer program.Therefore, the present invention can adopt the form of complete hardware embodiment, completely software implementation or the embodiment in conjunction with software and hardware aspect.And the present invention can adopt in one or more form wherein including the upper computer program implemented of computer-usable storage medium (including but not limited to magnetic disk memory, CD-ROM, optical memory etc.) of computer usable program code.
The present invention describes with reference to according to the process flow diagram of the method for the embodiment of the present invention, equipment (system) and computer program and/or block scheme.Should understand can by the combination of the flow process in each flow process in computer program instructions realization flow figure and/or block scheme and/or square frame and process flow diagram and/or block scheme and/or square frame.These computer program instructions can being provided to the processor of multi-purpose computer, special purpose computer, Embedded Processor or other programmable data processing device to produce a machine, making the instruction performed by the processor of computing machine or other programmable data processing device produce device for realizing the function of specifying in process flow diagram flow process or multiple flow process and/or block scheme square frame or multiple square frame.
These computer program instructions also can be stored in can in the computer-readable memory that works in a specific way of vectoring computer or other programmable data processing device, the instruction making to be stored in this computer-readable memory produces the manufacture comprising command device, and this command device realizes the function of specifying in process flow diagram flow process or multiple flow process and/or block scheme square frame or multiple square frame.
These computer program instructions also can be loaded in computing machine or other programmable data processing device, make on computing machine or other programmable devices, to perform sequence of operations step to produce computer implemented process, thus the instruction performed on computing machine or other programmable devices is provided for the step realizing the function of specifying in process flow diagram flow process or multiple flow process and/or block scheme square frame or multiple square frame.
Although describe the preferred embodiments of the present invention, those skilled in the art once obtain the basic creative concept of cicada, then can make other change and amendment to these embodiments.So claims are intended to be interpreted as comprising preferred embodiment and falling into all changes and the amendment of the scope of the invention.
Claims (10)
1. a Forecast of Traffic Demand, is characterized in that, comprises the steps:
Obtain social economy's characteristic and the Land_use change attribute of estimation range, set up sample basic information database;
For each sample distributes a residence information and employment ground information;
Obtain the activity pattern of each sample;
Obtain the activity venue of each sample;
Obtain the trip mode of each sample;
Obtain the travel time of each sample;
According to described activity pattern, activity venue, trip mode and travel time, determine in estimation range between zones of different at times, the traffic trip demand of point mode.
2. method according to claim 1, is characterized in that, described social economy characteristic comprises sex, age, income, vehicles recoverable amount.
3. method according to claim 2, is characterized in that, described Land_use change attribute comprises the living space of estimation range, commercial space, the size of population of industrial area and community and job quantity, apart from intown distance.
4. the method according to claim 1 or 2 or 3, it is characterized in that, described activity pattern comprises " family-work-family ", " family-work-family-work-family ", " family-work-other-family ", " family-work-other-work-family ", " family-other-family ".
5., according to the arbitrary described method of claim 1-4, it is characterized in that, the step of the activity pattern of each sample of described acquisition, comprising:
Calculate the utility value of each specimen needle to each activity pattern, computing formula is:
wherein, V
jfor this sample is for the utility value of activity pattern j, i is sample number, and n is total sample number; A
ijfor the parameter item demarcated, Xi is the variable-value of sample;
Calculate the probable value of each activity pattern of each samples selection, computing formula is:
M is the quantity of activity pattern;
The selection result of the activity pattern of each sample is obtained according to described probable value.
6., according to the arbitrary described method of claim 1-5, it is characterized in that, described trip mode comprises car, public transport, bicycle, walking.
7., according to the arbitrary described method of claim 1-6, it is characterized in that, the described travel time comprise morning peak before, morning peak, daytime, evening peak, after evening peak.
8. a Traffic Demand Forecasting system, is characterized in that, comprising:
Basic information database sets up unit, obtains social economy's characteristic and the Land_use change attribute of estimation range, sets up sample basic information database;
Selected cell, for each sample distributes a residence information and employment ground information;
Activity pattern forecast model unit, obtains the activity pattern of each sample;
Activity venue forecast model unit, obtains the activity venue of each sample;
Trip mode forecast model unit, obtains the trip mode of each sample;
Travel time prediction model unit, obtains the travel time of each sample;
Output unit, according to described activity pattern, activity venue, trip mode and travel time, determine in estimation range between zones of different at times, the traffic trip demand of point mode.
9. system according to claim 8, is characterized in that, described activity pattern forecast model unit comprises:
The utility value computing module of activity pattern, calculate the utility value of each specimen needle to each activity pattern, computing formula is:
wherein, V
jfor this sample is for the utility value of activity pattern j, i is sample number, and n is total sample number; A
ijfor the parameter item demarcated, Xi is the variable-value of sample;
The probable value computing module of activity pattern, calculates the probable value of each activity pattern of each samples selection, and computing formula is:
m is the quantity of activity pattern;
Result computing module, obtains the selection result of the activity pattern of each sample according to described probable value.
10. system according to claim 8 or claim 9, it is characterized in that, described activity pattern comprises " family-work-family ", " family-work-family-work-family ", " family-work-other-family ", " family-work-other-work-family ", " family-other-family ".
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510202393.9A CN104766146A (en) | 2015-04-24 | 2015-04-24 | Traffic demand forecasting method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510202393.9A CN104766146A (en) | 2015-04-24 | 2015-04-24 | Traffic demand forecasting method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104766146A true CN104766146A (en) | 2015-07-08 |
Family
ID=53647960
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510202393.9A Pending CN104766146A (en) | 2015-04-24 | 2015-04-24 | Traffic demand forecasting method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104766146A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106682812A (en) * | 2016-11-24 | 2017-05-17 | 西安建筑科技大学 | Comprehensive transport system passenger transport mode sharing rate-distance transfer curve determination method |
| CN106846214A (en) * | 2016-11-24 | 2017-06-13 | 西安建筑科技大学 | Method of the analysis transport hub accessibility to region public transportation mode competitive influence |
| CN107679668A (en) * | 2017-10-16 | 2018-02-09 | 东南大学 | The electric bicycle travel time prediction method of duration model based on risk |
| CN107943920A (en) * | 2017-11-21 | 2018-04-20 | 东南大学 | A kind of trip crowd recognition method based on subway brushing card data |
| CN108009747A (en) * | 2017-12-21 | 2018-05-08 | 北京工业大学 | A kind of multiple dynamic decision process information acquisition method of trip mode |
| CN108133302A (en) * | 2016-12-01 | 2018-06-08 | 上海浦东建筑设计研究院有限公司 | A kind of public bicycles potential demand Forecasting Methodology based on big data |
| CN108460537A (en) * | 2018-03-23 | 2018-08-28 | 华南理工大学 | A method of bicycle demand is shared based on big data and user psychology prediction |
| CN108615360A (en) * | 2018-05-08 | 2018-10-02 | 东南大学 | Transport need based on neural network Evolution Forecast method day by day |
| CN108876035A (en) * | 2018-06-01 | 2018-11-23 | 东南大学 | The traffic distribution and traffic flow for considering traveler destination preference distribute built-up pattern |
| CN108876042A (en) * | 2018-06-08 | 2018-11-23 | 东南大学 | The R language processing method of novel traffic distribution and traffic flow distribution built-up pattern |
| CN109544920A (en) * | 2018-11-22 | 2019-03-29 | 广东岭南通股份有限公司 | The acquisition of bus trip cost, analysis method and system based on transaction data |
| CN110222893A (en) * | 2019-06-06 | 2019-09-10 | 武汉元光科技有限公司 | Dispensing location recommendation method, device and the electronic equipment of shared traffic resource |
| CN110222892A (en) * | 2019-06-06 | 2019-09-10 | 武汉元光科技有限公司 | The get-off stop prediction technique and device of passenger |
| CN116091115A (en) * | 2023-01-29 | 2023-05-09 | 四川国蓝中天环境科技集团有限公司 | Network taxi sharing rate prediction method based on built environment and travel characteristics |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102054222A (en) * | 2010-12-10 | 2011-05-11 | 吉林大学 | Method for quantizing urban motor vehicle emission load based on resident trip analysis |
| CN102279950A (en) * | 2011-08-02 | 2011-12-14 | 中国铁道科学研究院电子计算技术研究所 | Railway transit fare clearing method based on data mining and neural network |
| US20120191505A1 (en) * | 2011-01-24 | 2012-07-26 | International Business Machines Corporation | Predicting dynamic transportation demand with mobility data |
| CN102708283A (en) * | 2012-04-23 | 2012-10-03 | 东南大学 | Modeling and simulating method for travelling times of residents based on travelling chain |
| CN102750427A (en) * | 2012-07-23 | 2012-10-24 | 中国地质大学（武汉） | Urban traffic planning simulation method and system based on multi-agent activity model |
| CN103116702A (en) * | 2013-02-01 | 2013-05-22 | 东南大学 | Bicycle-mode traveling selection forecasting method based on activity chain mode |
| CN103279802A (en) * | 2013-04-17 | 2013-09-04 | 吉林大学 | Method for predicting daily activity-travel time of commuter |
-
2015
- 2015-04-24 CN CN201510202393.9A patent/CN104766146A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102054222A (en) * | 2010-12-10 | 2011-05-11 | 吉林大学 | Method for quantizing urban motor vehicle emission load based on resident trip analysis |
| US20120191505A1 (en) * | 2011-01-24 | 2012-07-26 | International Business Machines Corporation | Predicting dynamic transportation demand with mobility data |
| CN102279950A (en) * | 2011-08-02 | 2011-12-14 | 中国铁道科学研究院电子计算技术研究所 | Railway transit fare clearing method based on data mining and neural network |
| CN102708283A (en) * | 2012-04-23 | 2012-10-03 | 东南大学 | Modeling and simulating method for travelling times of residents based on travelling chain |
| CN102750427A (en) * | 2012-07-23 | 2012-10-24 | 中国地质大学（武汉） | Urban traffic planning simulation method and system based on multi-agent activity model |
| CN103116702A (en) * | 2013-02-01 | 2013-05-22 | 东南大学 | Bicycle-mode traveling selection forecasting method based on activity chain mode |
| CN103279802A (en) * | 2013-04-17 | 2013-09-04 | 吉林大学 | Method for predicting daily activity-travel time of commuter |
Non-Patent Citations (1)
| Title |
|---|
| 陆化普 等: "《交通规划理论与方法》", 28 February 1998, 清华大学出版社 * |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106846214A (en) * | 2016-11-24 | 2017-06-13 | 西安建筑科技大学 | Method of the analysis transport hub accessibility to region public transportation mode competitive influence |
| CN106682812A (en) * | 2016-11-24 | 2017-05-17 | 西安建筑科技大学 | Comprehensive transport system passenger transport mode sharing rate-distance transfer curve determination method |
| CN108133302B (en) * | 2016-12-01 | 2021-12-14 | 上海浦东建筑设计研究院有限公司 | Public bicycle potential demand prediction method based on big data |
| CN108133302A (en) * | 2016-12-01 | 2018-06-08 | 上海浦东建筑设计研究院有限公司 | A kind of public bicycles potential demand Forecasting Methodology based on big data |
| CN107679668A (en) * | 2017-10-16 | 2018-02-09 | 东南大学 | The electric bicycle travel time prediction method of duration model based on risk |
| CN107943920A (en) * | 2017-11-21 | 2018-04-20 | 东南大学 | A kind of trip crowd recognition method based on subway brushing card data |
| CN108009747A (en) * | 2017-12-21 | 2018-05-08 | 北京工业大学 | A kind of multiple dynamic decision process information acquisition method of trip mode |
| CN108460537A (en) * | 2018-03-23 | 2018-08-28 | 华南理工大学 | A method of bicycle demand is shared based on big data and user psychology prediction |
| CN108615360A (en) * | 2018-05-08 | 2018-10-02 | 东南大学 | Transport need based on neural network Evolution Forecast method day by day |
| CN108615360B (en) * | 2018-05-08 | 2022-02-11 | 东南大学 | Traffic demand day-to-day evolution prediction method based on neural network |
| CN108876035A (en) * | 2018-06-01 | 2018-11-23 | 东南大学 | The traffic distribution and traffic flow for considering traveler destination preference distribute built-up pattern |
| CN108876042A (en) * | 2018-06-08 | 2018-11-23 | 东南大学 | The R language processing method of novel traffic distribution and traffic flow distribution built-up pattern |
| CN109544920B (en) * | 2018-11-22 | 2021-10-22 | 广东岭南通股份有限公司 | Bus trip cost obtaining and analyzing method and system based on transaction data |
| CN109544920A (en) * | 2018-11-22 | 2019-03-29 | 广东岭南通股份有限公司 | The acquisition of bus trip cost, analysis method and system based on transaction data |
| CN110222893A (en) * | 2019-06-06 | 2019-09-10 | 武汉元光科技有限公司 | Dispensing location recommendation method, device and the electronic equipment of shared traffic resource |
| CN110222892A (en) * | 2019-06-06 | 2019-09-10 | 武汉元光科技有限公司 | The get-off stop prediction technique and device of passenger |
| CN110222892B (en) * | 2019-06-06 | 2021-07-06 | 武汉元光科技有限公司 | Passenger getting-off station prediction method and device |
| CN110222893B (en) * | 2019-06-06 | 2021-11-16 | 武汉元光科技有限公司 | Method and device for recommending delivery places of shared traffic resources and electronic equipment |
| CN116091115A (en) * | 2023-01-29 | 2023-05-09 | 四川国蓝中天环境科技集团有限公司 | Network taxi sharing rate prediction method based on built environment and travel characteristics |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104766146A (en) | Traffic demand forecasting method and system | |
| Bagheri et al. | An explanation of urban sprawl phenomenon in Shiraz Metropolitan Area (SMA) | |
| Tian et al. | Simulation of urban expansion and encroachment using cellular automata and multi-agent system model—A case study of Tianjin metropolitan region, China | |
| Dasgupta et al. | The clouds distributed operating system: Functional description, implementation details and related work | |
| Abdullahi et al. | Sustainable brownfields land use change modeling using GIS-Based weights-of-evidence approach | |
| Ho et al. | Road traffic emission inventory for air quality modelling and to evaluate the abatement strategies: A case of Ho Chi Minh City, Vietnam | |
| Ma et al. | The spatial coupling effect between urban public transport and commercial complexes: A network centrality perspective | |
| Cordera et al. | Is accessibility relevant in trip generation? Modelling the interaction between trip generation and accessibility taking into account spatial effects | |
| CN106951999A (en) | The modeling of a kind of travel modal and the moment Combination selection that sets out and analysis method | |
| CN104636828A (en) | Public bicycle station supply and demand prediction method based on Markov chain | |
| Nichols et al. | Urban form and life-cycle energy consumption: Case studies at the city scale | |
| Liaghat et al. | A multi-criteria evaluation using the analytic hierarchy process technique to analyze coastal tourism sites | |
| Mendiola et al. | The relationship between urban development and the environmental impact mobility: A local case study | |
| CN107958610A (en) | A kind of function area of mixed usage parking stall predictor method shared based on berth | |
| Baynes et al. | Estimating current and future global urban domestic material consumption | |
| Hankaew et al. | Inferring and modeling migration flows using mobile phone network data | |
| Lerman et al. | Urban area types and spatial distribution of pedestrians: Lessons from Tel Aviv | |
| CN112508332B (en) | Gradual rural settlement renovation partitioning method considering multidimensional characteristics | |
| Mantelas et al. | Using fuzzy cellular automata to access and simulate urban growth | |
| Ma et al. | Investigating the impact of spatial-temporal grid size on the microscopic forecasting of the inflow and outflow gap in a free-floating bike-sharing system | |
| Zhi et al. | Quantifying the heterogeneous impacts of the urban built environment on traffic carbon emissions: New insights from machine learning techniques | |
| Curado et al. | Identifying mobility patterns by means of centrality algorithms in multiplex networks | |
| Ma et al. | Integrating logistic regression with ant colony optimization for smart urban growth modelling | |
| Bibliográfico | Intersecting geostatistics with transport demand modeling: a bibliographic survey | |
| Duan et al. | Applying Bayesian spatio-temporal models to demand analysis of shared bicycle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150708 |
|
| RJ01 | Rejection of invention patent application after publication |