CN109409560A - Urban track traffic for passenger flow abductive approach based on Multi-Agent simulation - Google Patents
Urban track traffic for passenger flow abductive approach based on Multi-Agent simulation Download PDFInfo
- Publication number
- CN109409560A CN109409560A CN201810934145.7A CN201810934145A CN109409560A CN 109409560 A CN109409560 A CN 109409560A CN 201810934145 A CN201810934145 A CN 201810934145A CN 109409560 A CN109409560 A CN 109409560A
- Authority
- CN
- China
- Prior art keywords
- passenger
- flow
- induction
- upper layer
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000004088 simulation Methods 0.000 title claims abstract description 39
- 238000013459 approach Methods 0.000 title claims abstract description 9
- 230000006698 induction Effects 0.000 claims abstract description 119
- 238000000034 method Methods 0.000 claims abstract description 41
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 37
- 230000002068 genetic effect Effects 0.000 claims abstract description 23
- 238000005457 optimization Methods 0.000 claims abstract description 20
- 230000006870 function Effects 0.000 claims description 45
- 238000012546 transfer Methods 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 14
- 238000005516 engineering process Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 8
- 230000008447 perception Effects 0.000 claims description 7
- 230000001680 brushing effect Effects 0.000 claims description 4
- 239000004744 fabric Substances 0.000 claims description 2
- 238000005094 computer simulation Methods 0.000 abstract 1
- 239000010410 layer Substances 0.000 description 65
- 239000003795 chemical substances by application Substances 0.000 description 15
- 210000000349 chromosome Anatomy 0.000 description 10
- 230000008859 change Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000035772 mutation Effects 0.000 description 5
- 108090000623 proteins and genes Proteins 0.000 description 5
- 230000003044 adaptive effect Effects 0.000 description 4
- 238000009795 derivation Methods 0.000 description 4
- 230000004927 fusion Effects 0.000 description 4
- 230000001939 inductive effect Effects 0.000 description 4
- 241000208340 Araliaceae Species 0.000 description 3
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 3
- 235000003140 Panax quinquefolius Nutrition 0.000 description 3
- 235000008434 ginseng Nutrition 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000008030 elimination Effects 0.000 description 2
- 238000003379 elimination reaction Methods 0.000 description 2
- 230000003426 interchromosomal effect Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 239000002355 dual-layer Substances 0.000 description 1
- 238000004043 dyeing Methods 0.000 description 1
- 230000009969 flowable effect Effects 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 230000008303 genetic mechanism Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Biophysics (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Genetics & Genomics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Development Economics (AREA)
- Evolutionary Computation (AREA)
- Game Theory and Decision Science (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Entrepreneurship & Innovation (AREA)
- Biomedical Technology (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Physiology (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention provides a kind of urban track traffic for passenger flow abductive approach based on Multi-Agent simulation, this method comprises: building considers the passenger flow dynamic induction optimization Bi-level Programming Models of induction information scope of release and content, upper layer Optimized model, for objective function, generates passenger flow induction scheme by genetic algorithm with the sum of the total Trip Costs of network and derived cost.Lower layer's simulation model is used to carry out simulation modeling in travel behaviour of the current passenger flow induction scheme to passenger, by emulate the period in every section on the volume of the flow of passengers and generalized cost be input in the Optimized model of upper layer, passenger flow induction scheme, the volume of the flow of passengers and generalized cost are updated in objective function by upper layer Optimized model, the fitness function currently taken off, by successive ignition, the highest optimal dynamic passenger flow induction scheme of fitness function value is obtained.The fining induction of " one scheme of a station " may be implemented in the present invention, can Assisted Passenger formulate reasonable path decision, it is crowded to alleviate Urban Rail Transit part passenger flow.
Description
Technical field
The present invention relates to urban track traffic for passenger flow administrative skill fields more particularly to a kind of based on Multi-Agent simulation
Urban track traffic for passenger flow abductive approach.
Background technique
With increasing for urban track traffic for passenger flow demand, the congested problem of urban mass transit network is got worse.It crosses
While spending the crowded efficiency of operation decline for making urban mass transit network, the trip experience of passenger is also affected, some are caused
Therefore passenger abandons rail traffic and selects other modes of transportation.Therefore, it formulates and the crowded measure of metro passenger flow is effectively relieved, it is right
Track level of service is promoted to play a significant role.
Metro operation department generallys use increase supply capacity or the mode of limitation passenger flow demand alleviates gauze congestion, such as increases
Add train quantity or controls the frequency that passenger is entered the station.But since the supply capacity of subway is limited, the frequency that enters the station of passenger is limited
The trip of passenger can be delayed, therefore, it is crowded that these methods cannot fundamentally alleviate Urban Rail Transit.Compared to this two
Kind method, passenger flow induction is a kind of more flexible passenger flow control means.It by placement passenger information system AT STATION or
Road conditions descriptive information of the navigation software into passenger's issuing traffic network carries out trip decision-making for passenger and provides a kind of reference.
Currently, passenger flow inducible system in the prior art is mainly directed towards friendship of all passengers' publications about entire transportation network
Logical situation, therefore the road conditions description information that all passengers receive is the same.
The shortcomings that above-mentioned passenger flow inducible system in the prior art are as follows: road traffic induction practice result shows to work as traffic
When the participant of induction only knows respective interests and ignores the presence and decision behavior of road network other passengers, it is likely that caused
More passengers are gathered on identical section simultaneously, to cause traffic congestion.
Summary of the invention
The embodiment provides a kind of urban track traffic for passenger flow abductive approach based on Multi-Agent simulation, with
The shortcomings that overcoming the prior art.
To achieve the goals above, this invention takes following technical solutions.
A kind of urban track traffic for passenger flow abductive approach based on Multi-Agent simulation constructs the passenger flow dynamic based on emulation
Induction optimization Bi-level Programming Models, passenger flow dynamic induction optimization Bi-level Programming Models include upper layer Optimized model and lower layer's emulation
Model, which comprises
It by the impedance on setting directed arc is issued about the volume of the flow of passengers, induction information in lower layer's simulation model
The function of range and content calculates the generalized cost function of each path and the probability that each path is selected, is then based on more
Intelligent body emulation technology obtains the flow in each emulation period on every directed arc, and the flow on each directed arc is transmitted
To the upper layer Optimized model；
The upper layer Optimized model is induced with passenger flow and is believed with the total Trip Costs of network and the minimum objective function of derived cost
The space-time unique of publication is ceased as decision variable, and the segmental arc flow based on underlying model input calls genetic algorithm to solve on described
The objective function of layer Optimized model, obtains optimal dynamic passenger flow induction strategies.
Further, the passenger flow dynamic induction optimization Bi-level Programming Models based on emulation, passenger flow dynamic induce
Optimizing Bi-level Programming Models includes upper layer Optimized model and lower layer's simulation model, comprising:
It constructs Rail traffic network topological structure G (S, A), wherein S indicates that rail traffic station, A indicate directed arc, packet
Block section between stations A ' and transfer arc A ", i.e. A=A ' ∪ A " are included, is constructed based on the Rail traffic network topological structure based on emulation
Passenger flow dynamic induction optimization Bi-level Programming Models, the passenger flow dynamic induction optimization Bi-level Programming Models include upper layer Optimized model and
Lower layer's simulation model；
The upper layer Optimized model is induction information publishing policy Optimized model, for determining the space-time of publication induction information
Range achievees the purpose that the sum of travel cost and induction expense in network-wide basis is optimal；
Lower layer's simulation model assumes that section or the impedance changed on arc are about the volume of the flow of passengers, induction information scope of release
And the function of content, and induction information will affect perception of the passenger to trip route effectiveness, obtain bottom output each section and
Real-time passenger flow state and passenger on station urban rail gauze real-time distribution state, to obtain in each emulation period
The volume of the flow of passengers on each directed arc, and the volume of the flow of passengers on each directed arc is transferred to the upper layer Optimized model.
Further, the upper layer Optimized model is with the total Trip Costs of network and the minimum objective function of derived cost, with
The space-time unique of induction information publicationAs decision variable, the dynamic traffic flow x of section aaIt (t) is about upper layer decision
VariableFunction, obtained by lower layer's simulation model and be input in the Optimized model of upper layer；
The objective function and constraint condition of the upper layer Optimized model are expressed as follows:
s.t.
In formula,It indicates whether station s ∈ S when t-th of time interval issues the road conditions description information about arc a, takes
Publication is indicated when value is 1, indicates not issue when value is 0, ca(t) indicate that the practical broad sense on t-th of time interval inner arc a is taken
With β1It indicates to issue the cost of the crowded description information of an arc at a station in each time interval.
Further, the upper layer Optimized model is with the total Trip Costs of network and the minimum objective function of derived cost,
Using the space-time unique that passenger flow induction information is issued as decision variable, the segmental arc flow based on underlying model input calls heredity to calculate
Method solves the objective function of the upper layer Optimized model, obtains optimal dynamic passenger flow induction strategies, comprising:
Passenger's intelligent body is generated based on AFC System of Urban Mass Transit brushing card data, utilizes the passenger
Intelligent body emulate passenger under induction information travel route choice, traveling of entering the station, wait, get on the bus, getting off, it is outbound and transfer go out
Row process；
Assuming that the station that passenger is currently located is o, point of destination is d, and the departure time is t, and passenger retouches according to the road conditions of publication
The link proportion selection path stating information and perceiving, is usedIt indicates to take in the broad sense of the starting station o of the passenger segmental arc a issued
With then having:
WhenWhen value is 1,Indicate impedance and the metro operation portion of the segmental arc a that passenger perceives
The road conditions description information that door provides is related, whereinIndicate the road conditions description for the segmental arc a that station s is issued to passenger when period t
Information；WhenWhen value is 0,The impedance for the segmental arc a that passenger perceives at this time is exactly segmental arc a
Practical generalized cost ca(t)；
Practical generalized cost on the arc of section is equal to train in the runing time in sectionWith the dwell timeThe sum of multiplied by table
Show the coefficient gamma of the section degree of crowdinga(t), changing to the generalized cost function on arc is the transfer timeMultiplied by γa(t) it adds
Punishment parameter σ is changed to, is indicated are as follows:
Degree of crowding coefficient gammaa(t) it indicates are as follows:
Wherein,Indicate the load of segmental arc, φ (ω)=α ωγ；
In the generalized cost c for calculating every segmental arca(t) after, according to the belonging relation of segmental arc and pathCalculate OD it
Between every active path path generalized costCalculation formula are as follows:
Further, the method also includes:
The selected probability of each path, probability calculation formula are obtained according to Logit model are as follows:
After obtaining the selected probability of each path, extensive passenger is obtained in urban rail using Multi-Agent simulation technology
Real-time distribution state on gauze, the path after being entered the station using Multi-Agent simulation technology to each passenger in each emulation period
Housing choice behavior, get on the bus, get off, transfer process is emulated, obtain every passenger real-time position on urban rail gauze, thus
To the volume of the flow of passengers in each emulation period on every section, the flow of each directed arc is inputted for upper layer Optimized model.
Further, the method also includes:
The upper layer Optimized model generates passenger flow induction scheme by genetic algorithmLower layer's emulation module is imitated
True algorithm is for emulating the passenger flow induction scheme that passenger obtains upper layer Optimized modelFeedback, i.e., emulation passenger current
Induction schemeUnder, by the generalized cost c for perceiving every active patha(t) when it is specifically chosen any paths trip
It enters the station, get on the bus, getting off, changing to and is outbound, being emulated, obtained by the trip process to each passenger in each emulation period
To the real-time Trip distribution situation x of rail traffic road networka(t), the volume of the flow of passengers x on every section in period t will be emulateda(t) and
Generalized cost ca(t) it is input in the Optimized model of upper layer, the upper layer Optimized model is by the passenger flow induction schemePassenger flow
Measure xa(t) and generalized cost ca(t) it is updated in objective function, is currently solvedUnder fitness function, by multiple
Iteration obtains fitness function value highest, the i.e. the smallest optimal dynamic passenger flow induction scheme of objective function.
As can be seen from the technical scheme provided by the above-mentioned embodiment of the present invention, the method that the embodiment of the present invention proposes can be with
Automatically generate the induction scheme of fining, realize " one scheme of a station ", can help rail transportation operation department determine start into
The time of row passenger flow induction and the road conditions description information which station to issue which section at respectively in each period.By examining
The range and content for considering induction information publication can formulate reasonable path decision with Assisted Passenger, keep away from the angle of passenger
More crowded section is opened, trip experience is promoted；It can change from the angle of Rail Transit System by optimizing induction information
Become the optimizing paths of part passenger, so that the Trip distribution on gauze is more balanced, whole service level is obtained
Improve, large passenger flow risk obtains a degree of elimination.
The additional aspect of the present invention and advantage will be set forth in part in the description, these will become from the following description
Obviously, or practice through the invention is recognized.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, required use in being described below to embodiment
Attached drawing be briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for this
For the those of ordinary skill of field, without creative efforts, it can also be obtained according to these attached drawings others
Attached drawing.
Fig. 1 is a kind of passenger flow dynamic induction optimization Bi-level Programming Models frame based on emulation provided in an embodiment of the present invention
Figure.
Fig. 2 is a kind of passenger flow Model Framework figure provided in an embodiment of the present invention.
Fig. 3 is genetic algorithmic procedures provided in an embodiment of the present invention diagram.
Fig. 4 is a kind of simulation algorithm schematic diagram provided in an embodiment of the present invention.
Specific embodiment
Embodiments of the present invention are described below in detail, the example of the embodiment is shown in the accompanying drawings, wherein from beginning
Same or similar element or element with the same or similar functions are indicated to same or similar label eventually.Below by ginseng
The embodiment for examining attached drawing description is exemplary, and for explaining only the invention, and is not construed as limiting the claims.
Those skilled in the art of the present technique are appreciated that unless expressly stated, singular " one " used herein, " one
It is a ", " described " and "the" may also comprise plural form.It is to be further understood that being arranged used in specification of the invention
Diction " comprising " refer to that there are the feature, integer, step, operation, element and/or component, but it is not excluded that in the presence of or addition
Other one or more features, integer, step, operation, element, component and/or their group.It should be understood that when we claim member
Part is " connected " or when " coupled " to another element, it can be directly connected or coupled to other elements, or there may also be
Intermediary element.In addition, " connection " used herein or " coupling " may include being wirelessly connected or coupling.Wording used herein
"and/or" includes one or more associated any cells for listing item and all combinations.
Those skilled in the art of the present technique are appreciated that unless otherwise defined, all terms used herein (including technology art
Language and scientific term) there is meaning identical with the general understanding of those of ordinary skill in fields of the present invention.Should also
Understand, those terms such as defined in the general dictionary, which should be understood that, to be had and the meaning in the context of the prior art
The consistent meaning of justice, and unless defined as here, it will not be explained in an idealized or overly formal meaning.
In order to facilitate understanding of embodiments of the present invention, it is done by taking several specific embodiments as an example below in conjunction with attached drawing further
Explanation, and each embodiment does not constitute the restriction to the embodiment of the present invention.
In order to solve the problems, such as that existing passenger flow inducible system may cause partial orbit transit's routes congestion, the present invention is implemented
Example proposes the fining passenger flow induction scheme of " one scheme of a station ", the i.e. scope of release by consideration induction information and content,
The publication that induction information in different choosing period of time is carried out at some stations, makes optimal trip decision-making in Assisted Passenger
Meanwhile reaching partly or wholly gauze and loading more balanced, the total the smallest purpose of trip impedance of network.It is intended to through optimization visitor
Induction information is flowed, perception of the passenger to path effectiveness is influenced, so that the optimizing paths of changing section passenger, keep passenger flow balanced
Ground is distributed on road network, is finally reached and is alleviated the overcrowding purpose of urban track traffic local line netter stream.
The operation of urban track traffic is related to operation department and the big main body of passenger two, therefore the target of passenger flow induction is not only wanted
Optimal trip decision-making is made from user perspective Assisted Passenger, and to alleviate the large passenger flow of rail network from operation department's angle
It is crowded, balanced gauze carriage load.Therefore, passenger flow induction problem is considered as dual layer resist decision process by the present invention, and building considers
The passenger flow of induction information scope of release and content dynamic induction optimization Bi-level Programming Models, and design fusion Multi-Agent simulation and
The integrated intelligent algorithm of genetic algorithm solves model.Fig. 1 is a kind of visitor based on emulation provided in an embodiment of the present invention
Flowable state induction optimization Bi-level Programming Models frame diagram.Wherein, upper layer Optimized model is with the total Trip Costs of network and derived cost
The sum of be objective function, make the smallest induction information scope of release of target function value for decision, i.e., within each emulation period
Select which station as the station of publication induction information respectively, and the induction letter in which section is issued at each selected station respectively
Breath.The travel behaviour of passenger emulates under the induction information scope of release that lower layer's simulation model is used to upper layer model decision
Modeling.It is considered herein that the generalized cost of segmental arc is the function of induction information scope of release, content and the segmental arc volume of the flow of passengers, pass through benefit
With Logit model and based on the simulation algorithm of multiple agent, can be obtained under the induction information scope of release that upper layer model decision goes out
The real-time Trip distribution situation of Metro Network.
In the present invention, the content of induction information refers to the road conditions descriptive information in selected section, refers specifically to each emulation
The load in section is selected in period, it is definite value 1.4 that the load in selected section is taken in the present invention, therefore passenger feels at the starting station
It is related whether the generalized cost in the section known with the starting station issues the road conditions descriptive information in the section.For not selected
Section, generalized cost of the passenger in the section that the starting station is experienced is its actual generalized cost.
As shown in Figure 1.Metro operation administrative department as upper layer gives to be provided as the passenger within the scope of the road network of lower layer
The crowded descriptive information of certain passenger flow, and passenger makes trip by oneself interests or preference and determines under these induction informations
Plan runs department further according to the reaction of passenger, makes the decision for meeting interests of the whole.On this basis, the present invention lures passenger flow
The problem of leading is considered as an optimal investment policy problem, refers under the conditions of certain investment and recovery, considers the autonomous housing choice behavior of passenger
While, by issuing induction information at local station, so that the Trip distribution of entire track road network reaches certain system index
Optimal purpose.By being solved to Bi-level Programming Models, the present invention produce by when induction scheme, realize " a station one
The fining induction of induction ".
1. upper layer Optimized model
It constructs Rail traffic network topological structure G (S, A), wherein S indicates that rail traffic station, A indicate directed arc, packet
Include block section between stations A ' and transfer arc A ", i.e. A=A ' ∪ A ".
In the passenger flow dynamic induction optimization Bi-level Programming Models based on emulation, upper layer Optimized model is induction information publication
Strategy optimization model, for determining that the range of publication induction information, time reach the travel cost in network-wide basis and induction expense
With the sum of optimal purpose.
Upper layer Optimized model is with the total Trip Costs of network and the minimum objective function of derived cost, with induction information publication
Space-time uniqueAs decision variable.The objective function and constraint condition of upper layer Optimized model are expressed as follows:
s.t.
In formula,It indicates whether station s ∈ S when t-th of time interval issues the road conditions description information about arc a, takes
Publication is indicated when value is 1, indicates not issue when value is 0.ca(t) indicate that the practical broad sense on t-th of time interval inner arc a is taken
With.β1It indicates to issue the derived cost of the road conditions description information of an arc at a station in each time interval.Section a's is dynamic
State magnitude of traffic flow xa(t) be lower layer's simulation model decision variable, be about upper layer decision variableFunction, imitated by lower layer
True mode is obtained and is input in the Optimized model of upper layer.
2. lower layer's simulation model
Current invention assumes that the impedance on section or transfer arc is the letter about the volume of the flow of passengers, induction information scope of release and content
Number, thus induction information will affect perception of the passenger to trip route effectiveness.In the present invention, gathering around on induction information and road network
Stifled is dynamically changeable, need by when solve induction scheme, thus each section for needing to obtain bottom output and the reality on station
When passenger flow state, description passenger obtains extensive passenger in the real-time distribution state of urban rail gauze to the feedback of induction information,
The input of link flow is provided for upper layer Optimized model.
Lower layer's simulation model is that the dynamic Trip distribution constructed based on Multi-Agent simulation technology deduces model.In order to obtain
Trip decision-making of passenger when whether there is or not induction information, needs to calculate the impedance of every segmental arc.
The present invention by section the degree of crowding and the travel time be converted into section generalized cost, by determine passenger begin
Whether hair station issues the road conditions description information in certain section, perception of the passenger to section generalized cost is influenced, so as to adjust path
Housing choice behavior is evenly distributed in all passengers on different sections, makes the Trip Costs in entire Rail traffic network
It is minimum.
Fig. 2 is a kind of passenger flow Model Framework figure provided in an embodiment of the present invention, is based on frame shown in Fig. 2, this hair
A kind of process flow for urban track traffic for passenger flow fining abductive approach based on Multi-Agent simulation that bright embodiment provides
Including following processing step:
Step 1: generating train intelligent body and passenger's intelligent body.Train intelligent body is generated according to time-table, with AFC
It is raw based on (Automatic Fare Collection System, AFC System of Urban Mass Transit) brushing card data
At passenger's intelligent body, for emulate passenger under induction information travel route choice, traveling of entering the station, wait, get on the bus, get off, go out
It a series of trip processes such as stands, change to.
Step 2: considering the travel behaviour modeling of passenger's intelligent body of induction information.
For the optimizing paths modeling to passenger, it is necessary first to calculate the generalized cost of arc.
Assuming that the station that passenger is currently located is o, point of destination is d, and the departure time is t, and passenger is according to the section perceived
Impedance selects path.The size of the perception impedance value of passenger and gauze section or base impedance and metro operation on transfer arc
The road network passenger flow congestion information that department provides is related.WithIt indicates to take in the broad sense of the starting station o of the passenger segmental arc a issued
With then having:
WhenWhen value is 1,Indicate impedance and the metro operation portion of the segmental arc a that passenger perceives
The road conditions description information that door provides is related.Wherein,Indicate the road conditions description for the segmental arc a that station s is issued to passenger when period t
Information, the present invention takeIt is 1.4, it is meant that rated passenger capacity of the load of segmental arc a considerably beyond train.WhenIt takes
When value is 0,The impedance for the segmental arc a that passenger perceives at this time is exactly the practical broad sense expense of segmental arc a
Use ca(t).Practical generalized cost on the arc of section is equal to train in the runing time in sectionWith the dwell timeThe sum of multiplied by arc
Section load factor γa(t).Changing to the generalized cost function on arc is the transfer timeMultiplied by γa(t) along with transfer punishment ginseng
Number σ, indicates are as follows:
Degree of crowding coefficient gammaa(t) it indicates are as follows:
Wherein,Indicate the load of segmental arc；φ (ω) be crowded punishment, calculation expression be φ (ω)=
αωγ, it is the exponential function of segmental arc load.Therefore, segmental arc load is higher, and the crowded influence to generalized cost is bigger.ω0、ω1All
It is the parameter for describing the degree of crowding, value is different, represents degree of crowding difference, in the present invention ω0Value is 0.7, ω1Value
It is 1.2；
In the generalized cost c for calculating every segmental arcaIt (t), can be according to the belonging relation of segmental arc and path afterIt calculates
The path generalized cost of every active path between ODCalculation formula are as follows:
ParameterFor 0-1 variable, when value is 1, indicate directed arc a on kth active path of the OD to od；Value
Indicate directed arc a not on kth active path of the OD to od for 0.
Finally, the selected probability of each path is obtained according to Logit model, for imitating passenger's travel behaviour
Very.Probability calculation formula are as follows:
Step 3: simulation result output.
In simulation process, the basis such as the real-time statistics section of the present invention volume of the flow of passengers, load factor, outbound amount passenger flow index.Its
In, input of the section volume of the flow of passengers of timesharing as upper layer Optimized model.
The present invention respectively solves upper and lower layer model with genetic algorithm and passenger's simulation algorithm using C# programming.
3. merging the hybrid intelligent derivation algorithm of passenger flow emulation and genetic algorithm
Mainly pass through successive ignition generates optimal solution to the purpose of genetic algorithmIn committed step 4.1,4.1,4.3,
It makes a variation, intersect, take less than c in selection operationa(t) andBut it is needed when evaluating the quality for the solution that upper layer model generates
Use caIt (t), i.e., will solutionWith solvingUnder c obtained by underlying modela(t) and xa(t) it is updated in objective function,
By iterating, finally made the smallest optimal solution of objective function
In the hybrid intelligent derivation algorithm of the emulation of fusion passenger flow and genetic algorithm, upper layer genetic algorithm and lower layer's emulation are calculated
Method interaction.The upper layer Optimized model generates passenger flow induction scheme by genetic algorithmLower layer's emulation module
Simulation algorithm for emulating the passenger flow induction scheme that passenger obtains upper layer Optimized modelFeedback, i.e., emulation passenger exist
Current induction schemeUnder, by the generalized cost c for perceiving every active patha(t) it is specifically chosen any paths trip,
When enter the station, get on the bus, getting off, changing to and is outbound, being imitated by the trip process to each passenger in each emulation period
Very, the real-time Trip distribution situation x of rail traffic road network is obtaineda(t), the volume of the flow of passengers x on every section in period t will be emulateda
(t) and generalized cost ca(t) it is input in the Optimized model of upper layer, the upper layer Optimized model is by the passenger flow induction schemeVolume of the flow of passengers xa(t) and generalized cost ca(t) it is updated in objective function, is currently solvedUnder fitness function,
By successive ignition, fitness function value highest, the i.e. the smallest optimal dynamic passenger flow induction scheme of objective function are obtained.It is logical
The hybrid intelligent derivation algorithm using fusion passenger flow emulation and genetic algorithm is crossed, each emulation period optimal induction is finally obtained
Scheme.
(1) upper layer Optimized model: genetic algorithm
Genetic algorithm is that one kind passes through simulation natural evolution rule (survival of the fittest, genetic mechanism of selecting the superior and eliminating the inferior) evolution
Randomization searching method.The initial solution that it is randomly generated from one group is known as " population ", starts search process, each of population
Individual is all a solution of problem, is indicated with chromosome.These chromosomes measure dye with fitness function in each generation
The quality of colour solid forms the next generation by selection, intersection, mutation operator.The principle of selection is that fitness is higher, and selected is general
Rate is bigger, and after iteration several times, for algorithmic statement in best chromosome, it is likely to the optimal solution or suboptimum of problem
Solution.Fig. 3 is shown in genetic algorithm diagram, and basic operation process is as follows:
1) it encodes: the feature of required selection being numbered, each feature is exactly a gene, and a solution is exactly one
The combination of string gene.In the present invention, the decision variable of upper layer model isIndicate whether AT STATION s is sent out in emulation period t
The road conditions descriptive information of cloth directed arc a is 0-1 variable.Therefore, the feasible solution of model is set using traditional binary coding
It is calculated as corresponding gene order or chromosome.Item chromosome vector HlIt indicates, represents a feasible solution of problem.Population is used
H expression, one of genetic fragmentIndicate whether issue about the passenger flow on each directed arc in some station si
Induction information.The result of final upper layer Optimized model output are as follows:
H={ H1,H2,...HL}
2) initialize: setting maximum evolutionary generation G and evolutionary generation counter, L individual of random generation are used as initial kind
Group.In the present invention, it needs to population H={ H1,H2,...HLInitialization, start iteration as initial point.
3) it assesses individual adaptation degree in population: calculating population H={ H1,H2,...HLIn each individual HlFitness.This
In invention, fitness function calculation formula are as follows: f (Hl)=1/Z (Hl).The adaptive value of individual is higher, illustrates using mesh when the program
The value of scalar functions is smaller, and selected to be genetic to follow-on probability higher.
4) selection operation: after the adaptive value for calculating each individual, the standard of the ratio of adaptive value alternatively can be used, is obtained
To the adaptive value ratio of each individual, referred to as selected probability.After selected probability has been calculated, individual is carried out by the method for roulette
Selection, obtain population same as former group size.
5) crossover operation: intersection will namely correspond to gene section and exchange to obtain new chromosome on a group chromosome, then
New genome is obtained, new group is formed.Assuming that interchromosomal is intersected with certain probability, and random selection is handed over
Crunode.In the present invention, interleaved mode schematically as follows:
6) mutation operation: variation namely changes some gene on chromosome string by a small probability, to obtain
New group.Mutation operation helps avoid local optimum.Assuming that interchromosomal is made a variation with certain probability, and random
Select change point.In the present invention, variation mode schematically as follows:
7) termination condition: the present invention is using the method for setting maximum algebra to determine whether terminating genetic algorithm.
(2) lower layer's simulation model: passenger's simulation algorithm
In the present invention, using studying passenger based on the emulation technology of multiple agent whether there is or not the traffic rows under induction information
To carry out tracking description with the variation in space at any time to the movement of every passenger.Specific step is as follows: 1) initialization emulation ginseng
Number, including emulation time started, end time, simulation step length etc..
2) it within each emulation period, generates each between the active path OD.
3) according to the amount of entering the station at each station in the emulation period each in AFC brushing card data, passenger's intelligent body is generated.
4) generalized cost in every segmental arc in each emulation period is utilizedCalculate each active path between each OD
Generalized costLogit model is recycled to obtain the selected probability of each path, and will be every according to roulette rule
A passenger's intelligent body distribution is on active path.
5) by passenger's emulator, provide the system time of each passenger, current state (i.e. intelligent body generate, enter the station, etc.
To, get on the bus, change to, just in outbound, outbound completion), current location, to obtain the visitor in each emulation period in every segmental arc
Flow xa(t)。
Fig. 4 is a kind of simulation algorithm signal for solving track traffic for passenger flow and inducing optimization problem provided in an embodiment of the present invention
Figure
(3) overall derivation algorithm
The overall algorithm frame for solving urban track traffic for passenger flow induction optimization problem is described as follows:
Step 1: initialization.Initialization model and algorithm parameter value σ, β, ξ, ζ, M,qod(t)、λs、Ca(t)、The upper limit that the number of iterations is arranged is G, population scale L.It is t=1 that current induction period, which is arranged,.
Step 2: for upper layer model, one initial induction strategies set or initial population are setSetting
Current algebra is g=0.
Step 3: solving lower layer's simulation model.The induction scheme determined for each by upper layer modelIt will
It is updated in underlying model the reaction for obtaining passenger to the induction scheme, and obtains the passenger flow under the induction scheme in gauze
Distribution situation.
Method particularly includes: pass through formula firstPassenger is calculated at the starting station
The section generalized cost perceived, then passes through formulaCalculate between each OD pairs every effectively
The generalized cost in path, and the selected probability of each path is obtained using Logit model.Finally utilize Multi-Agent simulation skill
Art enter the station to each passenger in each emulation period after optimizing paths, the processes such as get on the bus, get off, change to emulate,
The online online real-time position of every passenger is obtained, to obtain the volume of the flow of passengers x in each emulation period on every sectiona(t,
g).Step 4: solving upper layer Optimized model.X is solved according to obtained in step 3a(t, g) calculates each dyeing in initial population
The fitness of body.And by following operation, the induction strategies that upper layer optimizes are obtained
Step 4.1: mutation operation is created that the new chromosome of L item using mutation operator.
Step 4.2: crossover operation implements crossing operation to L chromosome.
Step 4.3: selection operation guarantees that optimum individual is genetic in the next generation using selection operator.
Step 5: verifying termination condition 1.It, will if the number of iterations is greater than GAnd xa(t, g) is as model
Optimal solution；Otherwise, g=g+1 is enabled, and returns to step poly- 3.
Step 6: verifying termination condition 2.If t > n (the stage sum that n is emulation) terminates；Otherwise, t=t+1 is enabled, is returned
Return to step 2.
Embodiment two
The present invention carries out the verifying of model and algorithm by taking Beijing Metro as an example.The data for needing to input include: Beijing Metro
Gauze topology data, passenger flow timesharing OD data, the interior travel time parameter in passenger station, time-table data.By calculating,
50 stations should be selected to issue tutorial message in peak period in the morning.
In addition, the present invention is capable of providing the induction scheme of fining, " one scheme of every station " is realized.That is, each
Station can obtain the passenger flow induction scheme of a differentiation, so that the road network crowded state that the passenger at each station sees is different
's.It is meant that present period from the station in the passenger flow congestion information about some section that a station is distributed to passenger
Passenger be likely encountered if by the section crowded, formulate reasonable trip decision-making so as to Assisted Passenger.
It is of the invention the result shows that, passenger flow induction information will affect perception of the passenger to trip route effectiveness, to influence
The optimizing paths of passenger.By taking Tiantong Yuan station to Chaoyang Men station as an example, passenger flow induction information is not issued at Tiantong Yuan station
In the case of, select the passenger of route (b) trip most.And when issuing passenger flow induction information at Tiantong Yuan station, it selects path (a)
The passenger of trip is most.Concrete outcome is shown in Table 1.
Table 1 issues the travel cost of first three paths of induction information front and back passenger's selection
Calculated result shows that (15min) fining passenger flow induction scheme proposed by the present invention can in an induction period
The maximum hourage saved in network-wide basis totally 46319 minutes, demonstrate effectiveness of the invention.
In conclusion the urban track traffic for passenger flow abductive approach based on Multi-Agent simulation that the embodiment of the present invention proposes
The induction scheme of fining can be automatically generated, is realized " one scheme of a station ", the determination of rail transportation operation department can be helped to open
Begin the time for carrying out passenger flow induction and the road conditions description information which station to issue which section at respectively in each period.It is logical
The issuing time to passenger flow induction information, space and content is crossed to optimize, it, can be with Assisted Passenger system from the angle of passenger
Fixed reasonable path decision, avoids more crowded section, promotes trip experience；It, can from the angle of Rail Transit System
So that part route, section and the load of transfer stop decline, the Trip distribution on gauze is more balanced, so that whole service water
Flat to be improved, large passenger flow security risk obtains certain elimination.Achievement of the invention will carry out passenger flow for metro operation department
Induction information publication work provides the decision support for rationally having evidence.
The present invention designs fusion Multi-Agent simulation and the integrated intelligent algorithm of genetic algorithm carries out Bi-level Programming Models
It solves.The decision that underlying model is made based on upper layer model, it is dynamic under the decision using being obtained based on Multi-Agent simulation algorithm
State Trip distribution situation, and it is input to layer model；The dynamic volume of the flow of passengers that upper layer model is inputted based on underlying model calls heredity
Algorithm obtains induction information scope of release optimal in each emulation period by successive ignition.
Those of ordinary skill in the art will appreciate that: attached drawing is the schematic diagram of one embodiment, module in attached drawing or
Process is not necessarily implemented necessary to the present invention.
As seen through the above description of the embodiments, those skilled in the art can be understood that the present invention can
It realizes by means of software and necessary general hardware platform.Based on this understanding, technical solution of the present invention essence
On in other words the part that contributes to existing technology can be embodied in the form of software products, the computer software product
It can store in storage medium, such as ROM/RAM, magnetic disk, CD, including some instructions are used so that a computer equipment
(can be personal computer, server or the network equipment etc.) executes the certain of each embodiment or embodiment of the invention
Method described in part.
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for device or
For system embodiment, since it is substantially similar to the method embodiment, so describing fairly simple, related place is referring to method
The part of embodiment illustrates.Apparatus and system embodiment described above is only schematical, wherein the conduct
The unit of separate part description may or may not be physically separated, component shown as a unit can be or
Person may not be physical unit, it can and it is in one place, or may be distributed over multiple network units.It can root
According to actual need that some or all of the modules therein is selected to achieve the purpose of the solution of this embodiment.Ordinary skill
Personnel can understand and implement without creative efforts.
The foregoing is only a preferred embodiment of the present invention, but scope of protection of the present invention is not limited thereto,
In the technical scope disclosed by the present invention, any changes or substitutions that can be easily thought of by anyone skilled in the art,
It should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with scope of protection of the claims
Subject to.
Claims (6)
1. a kind of urban track traffic for passenger flow abductive approach based on Multi-Agent simulation, which is characterized in that building is based on emulation
Passenger flow dynamic induction optimization Bi-level Programming Models, the passenger flow dynamic induction optimization Bi-level Programming Models include upper layer Optimized model
With lower layer's simulation model, which comprises
It is about the volume of the flow of passengers, induction information scope of release by the impedance on setting directed arc in lower layer's simulation model
And the function of content, the generalized cost function of each path and the probability that each path is selected are calculated, is then based on mostly intelligent
Body emulation technology obtains the flow in each emulation period on every directed arc, and the flow on each directed arc is transferred to institute
State upper layer Optimized model；
The upper layer Optimized model is with the total Trip Costs of network and the minimum objective function of derived cost, with passenger flow induction information hair
For the space-time unique of cloth as decision variable, it is excellent that the segmental arc flow based on underlying model input calls genetic algorithm to solve the upper layer
The objective function for changing model, obtains optimal dynamic passenger flow induction strategies.
2. the method according to claim 1, wherein the passenger flow dynamic induction optimization based on emulation is double-deck
Plan model, passenger flow dynamic induction optimization Bi-level Programming Models include upper layer Optimized model and lower layer's simulation model, comprising:
It constructs Rail traffic network topological structure G (S, A), wherein S indicates that rail traffic station, A indicate directed arc, including station
Between section A ' and transfer arc A ", i.e. A=A ' ∪ A ", based on the Rail traffic network topological structure construct the passenger flow based on emulation
Dynamic induction optimization Bi-level Programming Models, passenger flow dynamic induction optimization Bi-level Programming Models include upper layer Optimized model and lower layer
Simulation model；
The upper layer Optimized model is induction information publishing policy Optimized model, for determining the space-time model of publication induction information
It encloses, achievees the purpose that the sum of travel cost and induction expense in network-wide basis is optimal；
Lower layer's simulation model assumes section or the impedance of changing on arc is about the volume of the flow of passengers, induction information scope of release and interior
The function of appearance, and induction information will affect perception of the passenger to trip route effectiveness, obtain each section and the station of bottom output
On real-time passenger flow state and passenger urban rail gauze real-time distribution state, to obtain each in each emulation period
The volume of the flow of passengers on directed arc, and the volume of the flow of passengers on each directed arc is transferred to the upper layer Optimized model.
3. according to the method described in claim 2, it is characterized in that, the upper layer Optimized model is with the total Trip Costs of network and lures
Leading cost minimization is objective function, the space-time unique issued with induction informationAs decision variable, the dynamic traffic of section a
Flow xaIt (t) is about upper layer decision variableFunction, obtained by lower layer's simulation model and be input to upper layer Optimized model
In；
The objective function and constraint condition of the upper layer Optimized model are expressed as follows:
In formula,Indicate whether station s ∈ S when t-th of time interval issues the road conditions description information about arc a, value 1
When indicate publication, value be 0 when indicate do not issue, ca(t) the practical generalized cost on t-th of time interval inner arc a, β are indicated1
It indicates to issue the cost of the crowded description information of an arc at a station in each time interval.
4. according to the method described in claim 3, it is characterized in that, the upper layer Optimized model with the total Trip Costs of network and
The minimum objective function of derived cost is based on underlying model using the space-time unique that passenger flow induction information is issued as decision variable
The segmental arc flow of input calls genetic algorithm to solve the objective function of the upper layer Optimized model, obtains optimal dynamic passenger flow and lures
Lead strategy, comprising:
Passenger's intelligent body is generated based on AFC System of Urban Mass Transit brushing card data, utilizes passenger's intelligence
Body emulate passenger under induction information travel route choice, traveling of entering the station, wait, get on the bus, getting off, it is outbound and transfer trip
Journey；
Assuming that the station that passenger is currently located is o, point of destination is d, and the departure time is t, and passenger describes to believe according to the road conditions of publication
The link proportion selection path for ceasing and perceiving, is usedIndicate the generalized cost in the starting station o of the passenger segmental arc a issued,
Then have:
WhenWhen value is 1,Indicate that the impedance for the segmental arc a that passenger perceives is mentioned with metro operation department
The road conditions description information of confession is related, whereinIndicate the road conditions description letter for the segmental arc a that station s is issued to passenger when period t
Breath；WhenWhen value is 0,The impedance for the segmental arc a that passenger perceives at this time is exactly segmental arc a
Practical generalized cost ca(t)；
Practical generalized cost on the arc of section is equal to train in the runing time in sectionWith the dwell timeThe sum of multiplied by indicate area
The coefficient gamma of the section degree of crowdinga(t), changing to the generalized cost function on arc is the transfer timeMultiplied by γa(t) along with transfer
Punishment parameter σ is indicated are as follows:
Degree of crowding coefficient gammaa(t) it indicates are as follows:
Wherein,Indicate the load of segmental arc, φ (ω)=α ωγ；
In the generalized cost c for calculating every segmental arca(t) after, according to the belonging relation of segmental arc and pathIt calculates every between OD
The path generalized cost of active pathCalculation formula are as follows:
5. according to the method described in claim 4, it is characterized in that, the method also includes:
The selected probability of each path, probability calculation formula are obtained according to Logit model are as follows:
After obtaining the selected probability of each path, extensive passenger is obtained in urban rail gauze using Multi-Agent simulation technology
On real-time distribution state, using Multi-Agent simulation technology to it is each emulation the period in each passenger enter the station after Path selection
Behavior, get on the bus, get off, transfer process is emulated, every passenger real-time position on urban rail gauze is obtained, to obtain every
The volume of the flow of passengers in a emulation period on every section, the flow of each directed arc is inputted for upper layer Optimized model.
6. according to the method described in claim 5, it is characterized in that, the method also includes:
The upper layer Optimized model generates passenger flow induction scheme by genetic algorithmThe emulation of lower layer's emulation module is calculated
Method is for emulating the passenger flow induction scheme that passenger obtains upper layer Optimized modelFeedback, i.e., emulation passenger lured in current
Lead schemeUnder, by the generalized cost c for perceiving every active patha(t) be specifically chosen any paths trip, when into
It stands, get on the bus, getting off, changing to and is outbound, being emulated, obtained by the trip process to each passenger in each emulation period
The real-time Trip distribution situation x of rail traffic road networka(t), the volume of the flow of passengers x on every section in period t will be emulateda(t) and it is wide
Adopted expense ca(t) it is input in the Optimized model of upper layer, the upper layer Optimized model is by the passenger flow induction schemeThe volume of the flow of passengers
xa(t) and generalized cost ca(t) it is updated in objective function, is currently solvedUnder fitness function, by repeatedly changing
In generation, obtains fitness function value highest, the i.e. the smallest optimal dynamic passenger flow induction scheme of objective function.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810934145.7A CN109409560B (en) | 2018-08-16 | 2018-08-16 | Urban rail transit passenger flow induction method based on multi-agent simulation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810934145.7A CN109409560B (en) | 2018-08-16 | 2018-08-16 | Urban rail transit passenger flow induction method based on multi-agent simulation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109409560A true CN109409560A (en) | 2019-03-01 |
| CN109409560B CN109409560B (en) | 2022-07-15 |
Family
ID=65464335
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810934145.7A Active CN109409560B (en) | 2018-08-16 | 2018-08-16 | Urban rail transit passenger flow induction method based on multi-agent simulation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109409560B (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110162931A (en) * | 2019-06-21 | 2019-08-23 | 北京交通大学 | Urban track traffic large-scale road network high-speed simulation system |
| CN110399690A (en) * | 2019-07-31 | 2019-11-01 | 佳都新太科技股份有限公司 | Subway station pedestrian simulation method, apparatus, electronic equipment and storage medium |
| CN110852502A (en) * | 2019-11-06 | 2020-02-28 | 北京交通大学 | Time-based path optimization method |
| CN111582691A (en) * | 2020-04-28 | 2020-08-25 | 北京交通大学 | Double-layer planning-based transportation capacity matching method for multiple transportation modes of passenger transport hub |
| CN112101685A (en) * | 2020-11-18 | 2020-12-18 | 成都智元汇信息技术股份有限公司 | Full-road-network passenger flow direction statistics and passenger flow management and control simulation method and system |
| CN112182901A (en) * | 2020-10-10 | 2021-01-05 | 福建船政交通职业学院 | Urban tourist trip simulation method and system |
| CN112418574A (en) * | 2019-08-21 | 2021-02-26 | 上海宝信软件股份有限公司 | Artificial intelligence-based urban rail transit operation simulation system and method |
| CN112633940A (en) * | 2020-12-30 | 2021-04-09 | 北京交通大学 | Demand response type urban rail transit time-of-use fare formulation method |
| CN112906179A (en) * | 2020-11-27 | 2021-06-04 | 西南交通大学 | Urban rail transit passenger flow control optimization method based on fluid queuing network |
| CN115203982A (en) * | 2022-09-14 | 2022-10-18 | 环球数科集团有限公司 | Parallel computing method and simulation system for intelligent operation of public transport vehicle |
| CN115482655A (en) * | 2022-04-18 | 2022-12-16 | 同济大学 | Path induction method based on partial least square Kriging model |
| CN116702520A (en) * | 2023-08-07 | 2023-09-05 | 北京交通发展研究院 | Passenger rail transit travel condition simulation method and device |
| CN117690301A (en) * | 2024-02-04 | 2024-03-12 | 福建省高速公路科技创新研究院有限公司 | Expressway diversion induction strategy considering induction compliance rate |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105070047A (en) * | 2015-08-20 | 2015-11-18 | 华南理工大学 | Dynamic bus taking inducing method for BRT station passengers |
| CN105882695A (en) * | 2016-03-17 | 2016-08-24 | 北京交通大学 | Foresight associated control method for passenger flow congestion of urban railway traffic network |
| WO2017045294A1 (en) * | 2015-09-17 | 2017-03-23 | 华南理工大学 | Method for designing routine urban public transit network |
| CN107545320A (en) * | 2017-07-03 | 2018-01-05 | 北京交通大学 | A kind of urban track traffic passenger paths planning method and system based on graph theory |
| CN107705039A (en) * | 2017-10-27 | 2018-02-16 | 华东交通大学 | Urban track traffic for passenger flow Precise control method and system based on passenger flow demand |
-
2018
- 2018-08-16 CN CN201810934145.7A patent/CN109409560B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105070047A (en) * | 2015-08-20 | 2015-11-18 | 华南理工大学 | Dynamic bus taking inducing method for BRT station passengers |
| WO2017045294A1 (en) * | 2015-09-17 | 2017-03-23 | 华南理工大学 | Method for designing routine urban public transit network |
| CN105882695A (en) * | 2016-03-17 | 2016-08-24 | 北京交通大学 | Foresight associated control method for passenger flow congestion of urban railway traffic network |
| CN107545320A (en) * | 2017-07-03 | 2018-01-05 | 北京交通大学 | A kind of urban track traffic passenger paths planning method and system based on graph theory |
| CN107705039A (en) * | 2017-10-27 | 2018-02-16 | 华东交通大学 | Urban track traffic for passenger flow Precise control method and system based on passenger flow demand |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110162931A (en) * | 2019-06-21 | 2019-08-23 | 北京交通大学 | Urban track traffic large-scale road network high-speed simulation system |
| CN110399690A (en) * | 2019-07-31 | 2019-11-01 | 佳都新太科技股份有限公司 | Subway station pedestrian simulation method, apparatus, electronic equipment and storage medium |
| CN112418574A (en) * | 2019-08-21 | 2021-02-26 | 上海宝信软件股份有限公司 | Artificial intelligence-based urban rail transit operation simulation system and method |
| CN110852502A (en) * | 2019-11-06 | 2020-02-28 | 北京交通大学 | Time-based path optimization method |
| CN110852502B (en) * | 2019-11-06 | 2022-12-16 | 北京交通大学 | Time-based path optimization method |
| CN111582691B (en) * | 2020-04-28 | 2022-04-22 | 北京交通大学 | Double-layer planning-based transportation capacity matching method for multiple transportation modes of passenger transport hub |
| CN111582691A (en) * | 2020-04-28 | 2020-08-25 | 北京交通大学 | Double-layer planning-based transportation capacity matching method for multiple transportation modes of passenger transport hub |
| CN112182901A (en) * | 2020-10-10 | 2021-01-05 | 福建船政交通职业学院 | Urban tourist trip simulation method and system |
| CN112182901B (en) * | 2020-10-10 | 2023-04-25 | 福建船政交通职业学院 | Urban tourist trip simulation method and system |
| CN112101685A (en) * | 2020-11-18 | 2020-12-18 | 成都智元汇信息技术股份有限公司 | Full-road-network passenger flow direction statistics and passenger flow management and control simulation method and system |
| CN112906179A (en) * | 2020-11-27 | 2021-06-04 | 西南交通大学 | Urban rail transit passenger flow control optimization method based on fluid queuing network |
| CN112633940A (en) * | 2020-12-30 | 2021-04-09 | 北京交通大学 | Demand response type urban rail transit time-of-use fare formulation method |
| CN115482655A (en) * | 2022-04-18 | 2022-12-16 | 同济大学 | Path induction method based on partial least square Kriging model |
| CN115482655B (en) * | 2022-04-18 | 2023-08-29 | 同济大学 | Path induction method based on partial least square Kriging model |
| CN115203982A (en) * | 2022-09-14 | 2022-10-18 | 环球数科集团有限公司 | Parallel computing method and simulation system for intelligent operation of public transport vehicle |
| CN116702520A (en) * | 2023-08-07 | 2023-09-05 | 北京交通发展研究院 | Passenger rail transit travel condition simulation method and device |
| CN117690301A (en) * | 2024-02-04 | 2024-03-12 | 福建省高速公路科技创新研究院有限公司 | Expressway diversion induction strategy considering induction compliance rate |
| CN117690301B (en) * | 2024-02-04 | 2024-04-23 | 福建省高速公路科技创新研究院有限公司 | Expressway diversion induction method considering induction compliance rate |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109409560B (en) | 2022-07-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109409560A (en) | Urban track traffic for passenger flow abductive approach based on Multi-Agent simulation | |
| Zheng et al. | Using a heuristic approach to design personalized tour routes for heterogeneous tourist groups | |
| El-Tantawy et al. | Multiagent reinforcement learning for integrated network of adaptive traffic signal controllers (MARLIN-ATSC): methodology and large-scale application on downtown Toronto | |
| Arbex et al. | Efficient transit network design and frequencies setting multi-objective optimization by alternating objective genetic algorithm | |
| Bazzan | Opportunities for multiagent systems and multiagent reinforcement learning in traffic control | |
| CN107330716A (en) | A kind of customization public transport pricing method for considering system optimal | |
| Yang et al. | Optimal toll design in second-best link-based congestion pricing | |
| CN104766484A (en) | Traffic control and guidance system and method based on evolutionary multi-objective optimization and ant colony algorithm | |
| CN101777990A (en) | Method for selecting multi-objective immune optimization multicast router path | |
| CN109033718A (en) | A kind of dynamic emergency evacuation method of city rail traffic route failure | |
| He et al. | Congestion avoidance routing based on large-scale social signals | |
| CN105930914A (en) | City bus optimal charging structure charge determination method based on origin-destination distance | |
| CN110222924A (en) | Multimode track traffic station passenger flow control system and control method | |
| Liang et al. | A cooperative coevolutionary optimization design of urban transit network and operating frequencies | |
| Li et al. | A dynamic and scalable user-centric route planning algorithm based on polychromatic sets theory | |
| Han et al. | Modelling and simulation of hierarchical scheduling of real‐time responsive customised bus | |
| Owais et al. | Simple and effective solution methodology for transit network design problem | |
| Deng et al. | Optimal design of the feeder-bus network based on the transfer system | |
| CN113724507A (en) | Traffic control and vehicle induction cooperation method and system based on deep reinforcement learning | |
| CN106656819A (en) | DTN opportunity prediction routing method based on timetable | |
| Gidófalvi et al. | Instant social ride-sharing | |
| Zhang et al. | Exponential rank differential evolution algorithm for disaster emergency vehicle path planning | |
| Davis et al. | Decentralized optimization of vehicle route planning—a cross-city comparative study | |
| CN116702404A (en) | Fuzzy double-target electric vehicle charging station planning optimization method considering target priority | |
| CN108200623A (en) | A kind of centralized path computation and power-economizing method based on genetic 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 | ||
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20190301 Assignee: Beijing Zhongke digital remote information technology Co.,Ltd. Assignor: Beijing Jiaotong University Contract record no.: X2020990000344 Denomination of invention: Passenger Flow Guidance Method for Urban Rail Transit Based on Multi-Agent Simulation License type: Common License Record date: 20200713 |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |