CN113724495B - Traffic prediction method for city shared trip - Google Patents

Traffic prediction method for city shared trip Download PDF

Info

Publication number
CN113724495B
CN113724495B CN202110906993.9A CN202110906993A CN113724495B CN 113724495 B CN113724495 B CN 113724495B CN 202110906993 A CN202110906993 A CN 202110906993A CN 113724495 B CN113724495 B CN 113724495B
Authority
CN
China
Prior art keywords
traffic
travel
network
urban
representing
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
Application number
CN202110906993.9A
Other languages
Chinese (zh)
Other versions
CN113724495A (en
Inventor
马捷
王牵莲
陈景旭
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Southeast University
Original Assignee
Southeast University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Southeast University filed Critical Southeast University
Priority to CN202110906993.9A priority Critical patent/CN113724495B/en
Publication of CN113724495A publication Critical patent/CN113724495A/en
Application granted granted Critical
Publication of CN113724495B publication Critical patent/CN113724495B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count

Abstract

The invention discloses a traffic prediction method for urban shared travel, which comprises the steps of obtaining a topological structure of an urban traffic network, obtaining travel modes and relevant data in the urban traffic network, and obtaining OD traffic demands in the urban traffic network; constructing an urban multi-mode random P2P ride sharing user balanced traffic network, and establishing traffic demand constraint and ride sharing matching constraint of the network; calculating the generalized travel cost of the travelers according to the travel time perceived by the travelers, the comfort loss in the vehicles and the multi-angle comprehensive consideration of the operation mechanism on the windward line; and based on the logic travel selection behavior and the random P2P co-multiplying user balance principle, carrying out flow distribution on the network to obtain the path traffic flow of the urban multi-mode complex network. The invention can effectively predict the traffic flow of the modern urban traffic network, thereby providing reliable basis for relevant departments to establish management measures and industry standards.

Description

Traffic prediction method for city shared trip
Technical Field
The invention belongs to the field of urban traffic engineering, and particularly relates to a traffic prediction method for urban shared trips.
Background
With the continuous rise of the holding amount of private cars, traffic congestion has become one of the most important problems facing city managers. However, practical experience of various countries in relieving traffic congestion shows that: the road is repaired once, the problem of traffic jam cannot be solved radically, and even more people are encouraged to drive to get on the road invisibly. The windmilling trip (also called ride-sharing trip) gathers travelers with partially or completely overlapped trip tracks into one vehicle, reduces the number of motor vehicles on the road and relieves the problem of traffic jam by improving the utilization rate of space in the vehicle, and is currently practiced in various big cities in China. The urban traffic flow prediction method based on the change requirements not only considers the situations of windward trip, private car trip and bus trip in the traffic network, but also considers the subjective perception of travelers on the time of the trip, the comfort experience in the car and the on-line operation mechanism of the windward trip, so that the urban traffic flow prediction method is in line with the characteristics of modern urban traffic in a sharing mode.
Disclosure of Invention
In order to solve the technical problems mentioned in the background art, the invention provides a traffic prediction method for urban shared trips, so that the traffic distribution of a modern urban traffic network can be predicted more efficiently and accurately.
In order to achieve the technical purpose, the technical scheme of the invention is as follows:
a traffic prediction method for city shared trips comprises the following steps:
(1) acquiring a topological structure of an urban traffic network, acquiring a travel mode and related data in the urban traffic network, and acquiring OD traffic demands in the urban traffic network;
(2) constructing an urban multi-mode random P2P ride sharing user balanced traffic network, and establishing traffic demand constraint and ride sharing matching constraint of the network;
(3) calculating the generalized travel cost of the travelers from the comprehensive consideration of the travel time perceived by the travelers, the comfort loss in the vehicles and the multi-angle operation mechanism on the windward line;
(4) based on the logic travel selection behavior and the random P2P co-riding user balance principle, flow distribution is carried out on the urban multi-mode random P2P co-riding user balance traffic network, and the path traffic flow of the network is obtained.
Further, in the step (1), the related data includes road alignment, road parameters, a traveler's time perception coefficient and inconvenience coefficient, a public transportation mileage parameter, and a tailwind time parameter, mileage parameter, and floating parameter.
Further, in the step (1), the manner of acquiring the OD traffic demand in the urban traffic network includes: travel demand investigation, OD demand reverse thrust, data obtained by an intelligent traffic monitoring system, mobile phone signaling data and GPS data.
Further, the specific process of step (2) is as follows:
firstly, inputting the topological structure of the urban traffic network and the traffic demand Q of OD to wwAnd the number i of each travel mode;
then, the following constraints are established:
and (3) traffic demand constraint:
Figure BDA0003202039500000021
Figure BDA0003202039500000022
wherein the content of the first and second substances,
Figure BDA0003202039500000023
representing the flow of travelers in a selection mode I on a path p connecting an OD pair w, wherein I belongs to SD, I belongs to RD, I belongs to R, I belongs to PT and respectively corresponds to four travel modes of a private car driver, a tailgating passenger and a bus passenger, and I represents the set of all travel modes;
co-multiplication matching constraint:
Figure BDA0003202039500000024
Figure BDA0003202039500000031
Figure BDA0003202039500000032
wherein, gamma isr(i) Indicating that i e RD is mapped to the corresponding tailwind passenger, NiIndicating the number of passengers carried in the vehicle by the driver following the wind,
Figure BDA0003202039500000033
representing the windward supply between OD and w,
Figure BDA0003202039500000034
representing the downwind demand between OD and w.
Further, in step (3), the generalized travel cost of the traveler:
Figure BDA0003202039500000035
wherein the content of the first and second substances,
Figure BDA0003202039500000036
travel time representing the traveler perception:
Figure BDA0003202039500000037
where ρ isiRefers to a time value parameter for the traveler who selects pattern i,
Figure BDA0003202039500000038
and
Figure BDA0003202039500000039
respectively car travel time on path p and road segment a,
Figure BDA00032020395000000310
and
Figure BDA00032020395000000311
respectively refer to the bus driving time on the path p and the road section a,
Figure BDA00032020395000000312
indicating a link-to-path conversion coefficient, if the path p contains the link a,
Figure BDA00032020395000000313
if not, then,
Figure BDA00032020395000000314
Figure BDA00032020395000000315
indicating loss of comfort in the vehicle:
Figure BDA00032020395000000316
wherein, γiIs the inconvenience coefficient for the traveler of mode i;
Figure BDA00032020395000000317
the operation mechanism on the downwind line is represented as follows:
Figure BDA00032020395000000318
wherein the content of the first and second substances,
Figure BDA00032020395000000319
represents the trip cost of the traveler generated by windward,
Figure BDA00032020395000000320
representing the mileage of a path p between OD and w, bi、
Figure BDA0003202039500000041
And riRespectively is a time length parameter, a mileage parameter and a floating parameter of trip along the windmill,
Figure BDA0003202039500000042
representing lagrange multipliers, Γ, generated by a co-product matching constraintrd(i) Representing the mapping of i e R downwind passengers to matched downwind drivers;
Figure BDA0003202039500000043
cfand ctFor the cost of each of the other miscellaneous items,
Figure BDA0003202039500000044
representing the fare of the bus, cfRepresenting the fixed cost of a private car, ctRepresenting the cost of use of the private car.
Further, the specific process of step (4) is as follows:
based on the principle that logit travel selection behavior and random P2P share user balance, the flow distribution in the network follows:
Figure BDA0003202039500000045
Figure BDA0003202039500000046
wherein the content of the first and second substances,
Figure BDA0003202039500000047
representing the probability that the traveler of OD to w selects to travel on the path p in the mode i, and theta is a parameter of Gumbel distribution which is met by a random error item in the logit distribution;
within the feasible set Ω of f, find the vector f*E omega meets the following formula to realize flow distribution:
Figure BDA0003202039500000048
wherein the content of the first and second substances,
Figure BDA0003202039500000049
w is the set of all OD pairs in the urban traffic network, PwIs the set of all paths between OD pairs w; Ω represents a set of path flows that satisfy demand constraints and co-product matching constraints;
Figure BDA00032020395000000410
represents from
Figure BDA00032020395000000411
Is removed and
Figure BDA00032020395000000412
the associated entry, superscript T, represents transpose.
Adopt the beneficial effect that above-mentioned technical scheme brought:
the method not only considers the conditions of windmill trip, private car trip and bus trip in the traffic network, but also considers the subjective perception of travelers on the time of trip, the comfort experience in cars and the operation mechanism on the windmill line, better conforms to the characteristics of modern urban traffic in a shared environment, can effectively predict the traffic flow of the modern urban traffic network, and thus provides reliable basis for management departments and related enterprises and public institutions to formulate management measures and industry standards.
Drawings
FIG. 1 is a flow chart of a method of the present invention;
FIG. 2 is a topological structure diagram of an urban transportation network in an embodiment;
fig. 3 is a travel demand diagram of the urban transportation network in the embodiment.
Detailed Description
The technical scheme of the invention is explained in detail in the following with the accompanying drawings.
The invention designs a traffic prediction method for city shared travel, as shown in fig. 1, and the specific implementation process is as follows.
1) And obtaining the topological structure of the complex network according to the urban traffic network.
According to the geographic position and the traffic elements of urban traffic, each area of a city is divided into a plurality of traffic cells. Each traffic cell can be a traffic travel generation source, which is called a traffic travel starting point or an O point; or may be an attraction source of the trip, called the destination or D of the trip. A starting point and an end pointA pair of origin-destination points, referred to as OD pairs, is denoted by w. The set of all OD pairs in the traffic network is denoted W. The traffic flow between W and OD is also called OD demand, QwAnd (4) showing.
And determining the travel modes adopted by travelers in the urban traffic network according to the traffic survey. One trip mode is called a trip mode and is denoted by i. The set of all travel patterns in the transportation network is denoted by I.
The traffic cells in a city are connected by a plurality of urban roads, which are called road segments in the network topology, denoted as a. The set of all road segments in the traffic network is denoted a. X for traffic flow of pattern i on route aa，iAnd (4) showing.
There are typically multiple routes available between OD and w, which are referred to as paths in the traffic network, denoted as p. P for the set of all paths between OD and wwAnd (4) showing. The set of all paths in the traffic network is denoted by P, P ═ u @wPw. For traffic flow of mode i on route p connecting OD pair w
Figure BDA0003202039500000061
And (4) showing. The following relationships exist between the traffic flows of the paths and the road segments:
Figure BDA0003202039500000062
Figure BDA0003202039500000063
in the above formula, the first and second carbon atoms are,
Figure BDA0003202039500000064
indicating a link-to-path conversion coefficient, if the path p contains the link a,
Figure BDA0003202039500000065
if it is not included in the list, then,
Figure BDA0003202039500000066
according to the prior investigation, the topological structure of the urban traffic network is obtained as shown in figure 2. Travelers in this example network all own a private car. The network includes 4 types of travel modes: private car drivers, tailgating passengers and bus passengers respectively correspond to i e to SD, i e to RD, i to R and i to PT.
2) And acquiring travel cost parameters of the urban traffic network.
And related parameters such as road alignment, length and the like are obtained by visiting a design institute or a construction unit. And obtaining the online operation standard (comprising a time length parameter, a mileage parameter and a floating parameter) and the public transportation mileage parameter of the tailgating by online inquiry or on-site investigation. The time perception coefficient and the inconvenience perception coefficient of the traveler can be obtained by means of early questionnaire survey and later data fitting.
Through investigation, the values of the travel cost parameters in the urban transportation network are shown in table 1:
TABLE 1
Figure BDA0003202039500000067
Figure BDA0003202039500000071
3) And obtaining the current travel demand in the urban traffic network.
The method for acquiring the urban travel demand is more, and compared with the traditional methods, the method comprises travel demand investigation, OD demand reverse deduction and the like. The travel demand survey method comprises the steps of issuing survey questionnaires to urban residents for OD survey to obtain travel demand distribution, namely Q, among traffic districts of the cityw. The OD demand reverse-deducing method selectively and directly investigates the section traffic flow of part of road sections, and the OD demand between the traffic districts of the city is reversely deduced by the section traffic flow. OD demand back-stepping is applicable to situations where large-scale trip demand surveys cannot be conducted or are not conducted. In addition, with the development of mobile communication means, intelligent traffic monitoring systemThe data obtained by the system, the mobile phone signaling data and the GPS data are gradually applied to the process of obtaining the travel demand.
Through a series of methods for acquiring travel demands, the travel demands of the urban transportation network of the example network can be obtained as shown in fig. 3, namely, only one OD in the network has a demand Q for (1, 2)w＝6。
4) Establishing an urban multi-mode random P2P shared user balanced traffic network model, and determining the constraints existing in the network model, wherein the specific flow is as follows:
step 1: in planning software or a program, according to the road network topological structure obtained in the step 1), marking each OD pair w, each road section a, each path p and each mode i (shown as a table 2) in the road network; inputting the traffic demand Q obtained in step 3)w。
The travel patterns and their numbers for this example network are shown in table 1. For OD pair (1, 2), there are three paths in the network: path 1, first → fourth; path 2, ② → ③; path 3 (c → c).
TABLE 2
Figure BDA0003202039500000072
Figure BDA0003202039500000081
Step 2: aiming at a network model, establishing a constraint:
traffic demand constraints
Figure BDA0003202039500000082
Figure BDA0003202039500000083
I ═ SD ═ RD ═ R ═ PT represents the 4 travel modes present in the network: private car drivers, tailgating passengers and bus passengers respectively correspond to i e to SD, i e to RD, i to R and i to PT.
② co-multiplication matching constraint
Figure BDA0003202039500000084
Γr(i) Showing that i belongs to RD and the downwind driver is mapped to i corresponding to RD′E.g. R, passenger on tailgating, i.e. gammar：RD→R。NiIs an integer and indicates the number of passengers carried in the vehicle by the tailrace driver i. In the example network are
Figure BDA0003202039500000085
Figure BDA0003202039500000086
Figure BDA0003202039500000087
The supply-demand relationship for the windward market is based on each OD pair.
Figure BDA0003202039500000088
The amount of tailwind supply between OD pairs w is shown, which means the amount of flow between OD pairs w for the tailwind drivers i e.RD.
Figure BDA0003202039500000089
Expressing the downwind demand between OD and w, refers to the downwind passenger Γ corresponding to OD to wr(i) e.R flow. In the example network are
Figure BDA00032020395000000810
5) Establishing a generalized travel cost function in a network, wherein the specific flow is as follows:
step 1: obtaining driving data of vehicles on multiple days on each road section through traffic investigation, and calculating a travel time calculation function of the road section; or using the existing empirical formula (such as BPR function) to obtain the travel time of the road network.
The segment travel time in this example network is calculated as in table 3:
TABLE 3
Figure BDA0003202039500000091
Step 2: and calculating the generalized travel cost of the travelers according to the travel cost parameters and the travel time of the road network and from the comprehensive consideration of the travel time perceived by the travelers, the comfort loss in the vehicles, the operation mechanism on the windward line and other angles. The specific calculation is as follows:
Figure BDA0003202039500000092
the generalized travel cost for a traveler of pattern i on path p connecting OD to w is expressed as
Figure BDA0003202039500000093
The notation in the generalized travel cost calculation formula is as follows:
(ii) perceived travel time
Figure BDA0003202039500000094
Figure BDA0003202039500000095
ρiRefers to a time value parameter for the traveler who selects pattern i.
Figure BDA0003202039500000101
And
Figure BDA0003202039500000102
respectively car travel time on path p and road segment a,
Figure BDA0003202039500000103
and
Figure BDA0003202039500000104
respectively refer to the bus driving time on the path p and the road section a.
Traveler perceived cost of transit time in urban traffic network
Figure BDA0003202039500000105
Figure BDA0003202039500000106
② loss of comfort in the vehicle
Figure BDA0003202039500000107
Figure BDA0003202039500000108
γiIs the inconvenient perception coefficient of the traveler of pattern i. The loss of comfort in the vehicle comes from the process of sharing the space in the vehicle with strangers in the ride sharing behavior, so that only the windward driver i belongs to the RD and the windward passenger i belongs to the R, and the cost is borne.
Loss of comfort in a vehicle in an urban traffic network
Figure BDA0003202039500000109
Figure BDA00032020395000001010
Thirdly, an on-line operation mechanism of the downwind turbine:
Figure BDA00032020395000001011
Figure BDA00032020395000001012
represents the trip cost of the traveler through the on-wind App. bi、
Figure BDA00032020395000001013
And riRespectively are a duration parameter, a mileage parameter and a floating parameter of the trip along the windmill.
Figure BDA00032020395000001014
Representing lagrangian multipliers generated by a co-product matching constraint. Gamma-shapedrd(i) Indicating that i e R downwind passengers are mapped onto matching downwind drivers i' e RD, i.e. Γrd：R→RD。
Travel cost of travelers in urban traffic network through on-board App
Figure BDA00032020395000001015
Comprises the following steps:
Figure BDA0003202039500000111
fourthly, cost of other miscellaneous items
Figure BDA0003202039500000112
cfAnd ct：
Figure BDA0003202039500000113
Figure BDA0003202039500000114
Indicating the fare of the bus, taubAnd the mileage unit price of the bus is represented.
cfRepresenting a fixed cost parameter of a private car, ctRepresenting the operating cost of the private car.
So far, the generalized travel cost of each mode in the urban transportation network is as follows:
Figure BDA0003202039500000115
6) based on a logic trip selection behavior and a random P2P (peer-to-peer) common-riding user balance principle, flow distribution is carried out on the network to obtain the path traffic flow of the urban multi-mode complex network, and the specific flow is as follows:
step 1: based on the principle that logit travel selection behavior and random P2P share the user balance, the traffic distribution in the traffic network follows:
Figure BDA0003202039500000116
Figure BDA0003202039500000117
in the formula (I), the compound is shown in the specification,
Figure BDA0003202039500000118
representing the probability that the traveler of OD pair w chooses to travel on path p in pattern i, and θ refers to the parameter of the Gumbel distribution that is satisfied by the random error term in the logit distribution.
Let θ be 1, the traffic distribution principle in the urban traffic network follows:
Figure BDA0003202039500000121
Figure BDA0003202039500000122
step 2: traffic distribution is performed according to the following variational inequality:
within the feasible set Ω, find the vector f*E Ω satisfies the formula:
Figure BDA0003202039500000123
wherein the content of the first and second substances,
Figure BDA0003202039500000124
Ω represents a feasible set of f, i.e., a set of path flows that satisfy traffic demand constraints and ride-sharing matching constraints;
Figure BDA0003202039500000125
Figure BDA0003202039500000126
represents from
Figure BDA0003202039500000127
Is removed and
Figure BDA0003202039500000128
the item concerned.
By solving the variation inequality, the flow prediction, trip cost and trip time in the urban traffic network are as shown in table 4:
TABLE 4
Figure BDA0003202039500000129
The embodiments are only for illustrating the technical idea of the present invention, and the technical idea of the present invention is not limited thereto, and any modifications made on the basis of the technical scheme according to the technical idea of the present invention fall within the scope of the present invention.

Claims (2)

1. A traffic prediction method for city shared trips is characterized by comprising the following steps:
(1) acquiring a topological structure of an urban traffic network, acquiring a travel mode and related data in the urban traffic network, and acquiring OD traffic demands in the urban traffic network;
(2) constructing an urban multi-mode random P2P ride sharing user balanced traffic network, and establishing traffic demand constraint and ride sharing matching constraint of the network;
(3) calculating the generalized travel cost of the travelers from the comprehensive consideration of the travel time perceived by the travelers, the comfort loss in the vehicles and the multi-angle operation mechanism on the windward line;
(4) based on a logic travel selection behavior and a random P2P co-riding user balancing principle, carrying out flow distribution on the urban multi-mode random P2P co-riding user balancing traffic network to obtain a path traffic flow of the network;
the specific process of the step (2) is as follows:
firstly, inputting the topological structure of the urban traffic network and the traffic demand Q of OD to wwAnd the number i of each travel mode;
then, the following constraints are established:
and (3) traffic demand constraint:
Figure FDA0003644831970000011
Figure FDA0003644831970000012
wherein the content of the first and second substances,
Figure FDA0003644831970000013
representing the flow of travelers in a selection mode I on a path p connecting an OD pair w, wherein I belongs to SD, I belongs to RD, I belongs to R, I belongs to PT and respectively corresponds to four travel modes of a private car driver, a tailgating passenger and a bus passenger, and I represents the set of all travel modes;
co-multiplication matching constraint:
Figure FDA0003644831970000014
Figure FDA0003644831970000015
Figure FDA0003644831970000021
wherein, gamma isr(i) Indicating that i e RD is mapped to the corresponding tailwind passenger, NiIndicating the number of passengers carried in the vehicle by the driver following the wind,
Figure FDA0003644831970000022
representing the windward supply between OD and w,
Figure FDA0003644831970000023
representing the downwind demand between OD and w;
in step (3), the generalized travel cost of the traveler:
Figure FDA0003644831970000024
wherein the content of the first and second substances,
Figure FDA0003644831970000025
travel time representing the traveler perception:
Figure FDA0003644831970000026
where ρ isiRefers to a time value parameter for the traveler who selects pattern i,
Figure FDA0003644831970000027
and
Figure FDA0003644831970000028
respectively car travel time on path p and road segment a,
Figure FDA0003644831970000029
and
Figure FDA00036448319700000210
respectively refer to the bus driving time on the path p and the road section a,
Figure FDA00036448319700000211
indicating a link-to-path conversion coefficient, if the path p contains the link a,
Figure FDA00036448319700000212
if not, then,
Figure FDA00036448319700000213
Figure FDA00036448319700000214
indicating loss of comfort in the vehicle:
Figure FDA00036448319700000215
wherein, γiIs the inconvenience coefficient for the traveler of mode i;
Figure FDA00036448319700000216
wherein the content of the first and second substances,
Figure FDA00036448319700000217
represents the trip cost of the traveler generated by windward,
Figure FDA00036448319700000218
representing the mileage of a path p between OD and w, bi、
Figure FDA00036448319700000219
And riRespectively is a time length parameter, a mileage parameter and a floating parameter of trip along the windmill,
Figure FDA00036448319700000220
representing lagrange multipliers, Γ, generated by a co-product matching constraintrd(i) Representing the mapping of i e R downwind passengers to matched downwind drivers;
Figure FDA00036448319700000221
cfand ctFor the cost of each of the other miscellaneous items,
Figure FDA00036448319700000222
representing the fare of the bus, cfRepresenting the fixed cost of a private car, ctRepresents the cost of use of a private car;
the specific process of the step (4) is as follows:
based on the principle of logic travel selection behavior and random P2P co-multiplying user balance, the flow distribution in the network follows:
Figure FDA0003644831970000031
Figure FDA0003644831970000032
wherein the content of the first and second substances,
Figure FDA0003644831970000033
representing the probability that the traveler of OD to w selects to travel on the path p in the mode i, and theta is a parameter of Gumbel distribution which is met by a random error item in the logit distribution;
within the feasible set Ω of f, find the vector f*E omega meets the following formula to realize flow distribution:
Figure FDA0003644831970000034
wherein the content of the first and second substances,
Figure FDA0003644831970000035
w is the set of all OD pairs in the urban traffic network, PwIs the set of all paths between OD pairs w; Ω represents a set of path flows that satisfy demand constraints and co-product matching constraints;
Figure FDA0003644831970000036
Figure FDA0003644831970000037
represents from
Figure FDA0003644831970000038
Is removed and
Figure FDA0003644831970000039
related items, superscript T denotes transpose;
in the step (1), the related data comprises road alignment, road parameters, time perception coefficient and inconvenience coefficient of travelers, public transportation mileage parameters, and time parameters, mileage parameters and floating parameters of windmills.
2. The traffic prediction method for city shared travel according to claim 1, wherein in step (1), the manner of obtaining the OD traffic demand in the city traffic network comprises: travel demand investigation, OD demand reverse thrust, data obtained by an intelligent traffic monitoring system, mobile phone signaling data and GPS data.
CN202110906993.9A 2021-08-09 2021-08-09 Traffic prediction method for city shared trip Active CN113724495B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110906993.9A CN113724495B (en) 2021-08-09 2021-08-09 Traffic prediction method for city shared trip

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110906993.9A CN113724495B (en) 2021-08-09 2021-08-09 Traffic prediction method for city shared trip

Publications (2)

Publication Number Publication Date
CN113724495A CN113724495A (en) 2021-11-30
CN113724495B true CN113724495B (en) 2022-07-01

Family

ID=78675198

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110906993.9A Active CN113724495B (en) 2021-08-09 2021-08-09 Traffic prediction method for city shared trip

Country Status (1)

Country Link
CN (1) CN113724495B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114758498B (en) * 2022-04-01 2023-06-20 中南大学 Urban directed traffic corridor identification method based on multidirectional optimal expansion
CN117235556B (en) * 2023-11-13 2024-02-27 浙江大学城乡规划设计研究院有限公司 Traffic manager-oriented multi-mode traffic composite network construction method

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107945510A (en) * 2017-11-14 2018-04-20 东南大学 A kind of section detecting method for considering transport need and road network operational efficiency
CN110414833A (en) * 2019-07-26 2019-11-05 东南大学 A kind of city multimodel traffic network capacity Coordination Evaluation method
CN110580404A (en) * 2019-07-26 2019-12-17 东南大学 Network operation capacity determination method based on urban multi-mode traffic network
CN111881227A (en) * 2020-05-21 2020-11-03 北京嘀嘀无限科技发展有限公司 Method and system for determining carpool order access map

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107945510A (en) * 2017-11-14 2018-04-20 东南大学 A kind of section detecting method for considering transport need and road network operational efficiency
CN110414833A (en) * 2019-07-26 2019-11-05 东南大学 A kind of city multimodel traffic network capacity Coordination Evaluation method
CN110580404A (en) * 2019-07-26 2019-12-17 东南大学 Network operation capacity determination method based on urban multi-mode traffic network
CN111881227A (en) * 2020-05-21 2020-11-03 北京嘀嘀无限科技发展有限公司 Method and system for determining carpool order access map

Non-Patent Citations (6)

* Cited by examiner, † Cited by third party
Title
孙彪等.上班族"共享+公共交通"换乘模式服务设计初探.《设计》.(第21期), *
张扬永."移动互联网+"出行共享平台的研究与设计.《湖北工程学院学报》.(第06期), *
沈弼龙等.大数据背景下动态共乘的研究进展.《计算机研究与发展》.(第01期), *
王丽丽.互联网背景下的汽车共享模式与对策.《中国科技论坛》.2017,(第09期), *
范琪等.基于广义出行费用的城市综合交通方式优势出行距离研究.《交通运输系统工程与信息》.2018,(第04期), *
葛颖恩等.共享交通的运营与管理综述.《上海大学学报(自然科学版)》.2020,(第03期), *

Also Published As

Publication number Publication date
CN113724495A (en) 2021-11-30

Similar Documents

Publication Publication Date Title
CN105205557B (en) A kind of City Routine Transit Network Design method
CN113724495B (en) Traffic prediction method for city shared trip
CN109034465A (en) Consider the charging station bi-level optimization method that charging station addressing is coupled with trip route
CN107323300A (en) A kind of electric automobile reservation charging method based on way station car conjunctive model
CN110458456B (en) Demand response type public transportation system scheduling method and system based on artificial intelligence
CN107798867B (en) Congestion traffic network balancing method based on electric automobile and diesel locomotive mixed traffic flow
CN104680027B (en) A kind of energy-saving and emission-reduction integrated evaluating method towards mammoth tanker
CN103208034B (en) A kind of track traffic for passenger flow forecast of distribution model is set up and Forecasting Methodology
CN106127357A (en) A kind of customization public transport automatic routing system based on reservation data and method
Zhu et al. The potential of ride-pooling in VKT reduction and its environmental implications
CN106127325A (en) A kind of dynamic public traffic network system based on user's request
CN108460527A (en) A kind of planing method of the public electrically-charging equipment of electric vehicle
CN106295875A (en) A kind of open service district addressing location mode
US10311170B2 (en) System for providing infrastructure impacts on an urban area
CN110598971B (en) Responsive bus service planning method based on ant colony algorithm
CN114936666A (en) Electric vehicle charging navigation method and system based on vehicle-station-platform system
CN114842641B (en) Multi-mode chain traffic distribution method for province domain
Deb et al. Comprehensive Review of Planning Models for Charging Station Placement
ZHANG et al. Research on Dynamic Taxi Ride-Sharing Price Model
Xu et al. Research on dynamic taxi ride-sharing price model
CN110992122A (en) Network-based fair wind wheel matching method for people to vehicles
Qu et al. The application of Lagrange relaxation on taxi dispatchments during evening rush hours
CN110851769B (en) Network bearing capacity-based electric bus network reliability evaluation method
CN116681323B (en) Carbon emission calculation method based on personal trip chain, electronic equipment and medium
Shao et al. A Combined Travel Planning Model of Shared Car and Public Transportation Based on Improved Ant Colony Algorithm

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