CN108470444B - A kind of city area-traffic big data analysis System and method for based on genetic algorithm optimization - Google Patents
A kind of city area-traffic big data analysis System and method for based on genetic algorithm optimization Download PDFInfo
- Publication number
- CN108470444B CN108470444B CN201810234041.5A CN201810234041A CN108470444B CN 108470444 B CN108470444 B CN 108470444B CN 201810234041 A CN201810234041 A CN 201810234041A CN 108470444 B CN108470444 B CN 108470444B
- Authority
- CN
- China
- Prior art keywords
- city
- traffic
- network
- road
- road network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
Landscapes
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention belongs to urban transportation design fields, and in particular to a kind of city area-traffic big data analysis System and method for based on genetic algorithm optimization.Wherein, it goes on a journey distributional analysis module, city road network cross-channel flow analysis module, City Rail Transit System analysis module, city area-traffic system decision-making module the system comprises: city road network and pedestrian.The present invention is distributed using city road network and resident trip as object, using the Bi-level Programming Models in Continuous network design, the index of city road network and resident trip distribution is introduced into city road network optimization, establish the city road network optimization Bi-level Programming Models based on genetic algorithm, optimal solution is calculated by genetic algorithm, and the configuration of traffic system decision is realized based on optimal solution, greatly improve the data analysis capabilities and decision-making capability of city area-traffic.
Description
Technical field
The invention belongs to city intelligent field of traffic, and in particular to a kind of city area-traffic based on genetic algorithm optimization
Big data analysis System and method for.
Background technique
City is the activity centre that the mankind are engaged in various societies, politics, economy and culture life, is played in social development
Extremely important effect.And the development in urban transportation and city is closely related, is the mark for measuring a urban civilization progress.With
The high speed development of social economy and quickly propelling for urbanization process, the volume of traffic persistently increases considerably, transport need and road
Contradiction between the means of transportation of road is becoming increasingly acute, and urban transport problems is got worse.Not only cause traffic thing in urban traffic congestion
Therefore take place frequently, vehicle delay increase, and further bring the aggravation of energy waste and environmental pollution, cause undesirable social economy
Consequence.
In recent years, with the fast development of Chinese economy, urbanization, automobile progress faster, motor vehicles ownership are fast
Surge and add, the traffic condition in China increasingly deteriorates, and congested in traffic and the energy, environmental problem are got worse, bigger
City, traffic congestion have become the bottleneck for restricting urban economy development.
In order to improve transportation network service efficiency, congested in traffic and traffic safety problem is solved, countries in the world are to traffic
Stream carries out effective management aspect and has put into a large amount of research, it is intended to the newest research results solution of natural science applied and engineering technology
The traffic problems certainly got worse, the objective demand of urban transport problems and the development of modern science and technology promote intelligent transportation
The generation of system.Using the present computer technology, the communication technology, electronic technology, Optimized-control Technique as the intelligent transportation system of core
System is comprehensive solution traffic safety and congested in traffic effective means.Intelligent transportation analysis system therein includes being permitted again
Multiple subsystem, such as wagon flow is controlled with pedestrian stream monitoring processing, traffic signal optimization, automobile navigation provincialism or global, tight
Anxious event handling, traffic diverging display board and broadcasting media, road and bridge automatic charging, monitoring road conditions and maintenance, highway are public
Traffic administration and coordination, public transport priority operational management, the magnitude of traffic flow and predicting travel time, automatic stopping and service are stood
Body traffic one optimizationization coordination and management etc..Traffic Signals in Urban Roads optimal control is the core composition of intelligent transportation system
Part, has important practical significance to the research of urban traffic signal Optimal Control Theory and technology and theoretical value.Rationally
Effective Traffic Analysis control, it is possible to reduce or the traffic conflict point that may cause congested in traffic and traffic accident is eliminated,
Keep the delay time at stop of vehicle and pedestrian minimum, increases the traffic capacity with intersection, realize safety, the rapidity of traffic flow
And comfort, the far-reaching economic results in society with reality.Countries in the world are carrying out effective management aspect investment to traffic flow
A large amount of research, it is intended to the newest research results of natural science applied and engineering technology solve the traffic problems got worse,
Specifically also carried out many researchs in terms of Traffic Analysis optimal control, but due to the complexity of urban transportation itself,
Randomness, non-linear, traffic analysis optimizing control models are often very complicated, and the solution for traffic signal optimization Controlling model is calculated
Method has very much, still, most of traditional algorithm, due to it is computationally intensive or be easy to make performance indicator fall into local minimum and
Seriously constrain the application and development of model.
Genetic algorithm is the emerging a kind of random search to grow up and optimization bionic Algorithm.From American university in 1975
MICHIGAN professor and its student create since, genetic algorithm has caused the extensive pass of domestic and international academia and industrial circle
Note, becomes one of key technology quite active in this century computational intelligence.It is excellent that genetic algorithm provides a kind of solution complication system
The general framework of change problem does not depend on the specific field of problem, has very strong robustness to the type of problem.Currently, hereditary
Oneself is widely used in many key areas such as computer science, engineering technology, management science and social science to algorithm, and
Its application field is also in the course of continuous expansion.Compared with classical method, genetic algorithm or an emerging subject,
It in implementation method, could be improved, especially its theoretical basis pole needs perfect.Therefore, many experts and scholars it is studied its
In a hot subject be exactly issue of improvement to basic genetic algorithmic, the performance to enable genetic algorithm and feature are more sufficiently
It plays.
Genetic algorithm as the emerging a kind of random search to grow up and optimization bionic Algorithm, have the characteristics that it is very much, than
Such as using the coding of decision variable as operand, directly using target function value as search information, while multiple search are used
The search information of point, uses probabilistic search technology etc..Its these features rapidly develop it in recent years, excellent in function
Change, Combinatorial Optimization, automatic control, image processing, pattern-recognition, robot learning etc. field are applied.
Summary of the invention
The effectively optimizing that the present invention attempts to use Revised genetic algorithum solves ability, is based on traffic analysis optimal control mould
Type carries out operation, and according to the variation of road traffic flow, it is rationally efficient to urban transportation progress to adjust analysis and Control scheme in real time
Control, and then improve the traffic capacity, improve traffic order, save energy consumption, improve traffic benefits.In addition, using improved
Heredity is popularized and promoted to genetic algorithm to the application field of Widening genetic algorithm to solve the optimization problem of city analysis and Control
The application of algorithm is also of great significance.
The city area-traffic big data analysis system based on genetic algorithm optimization that the purpose of the present invention is to provide a kind of.
The object of the invention is also to provide a kind of city area-traffic big data analysis side based on genetic algorithm optimization
Method.
The object of the present invention is achieved like this:
A kind of city area-traffic big data analysis system based on genetic algorithm optimization, including city road network go out with pedestrian
Row distributional analysis module, city road network cross-channel flow analysis module, City Rail Transit System analysis module, city area-traffic
System decision-making module；
The city road network includes gone on a journey by pedestrian network and road network network phase interaction with pedestrian's trip distributional analysis module
With and the double-layer network that is formed, upper layer network are that pedestrian goes on a journey network, by the node of upper layer network and lower layer's network, acquisition by
The Traffic Systems big data of the volume of the flow of passengers and magnitude of traffic flow composition on whole nodes of upper layer network and lower layer's network, and count
Calculating indicates stream of people's distribution characteristics, cross-channel handling capacity, stream of people's service ability, cross-channel operation organizational complexity, equipment investment and fortune
The city area-traffic utilization rate index of these factors of working cost；
City road network cross-channel flow analysis module establishes optimization single goal according to the city area-traffic utilization rate index
Function, and above-mentioned single-goal function is optimized using genetic algorithm, determine the current optimal solution of cross-channel；
City Rail Transit System analysis module is based on city road network and pedestrian's trip distributional analysis module and city road network
Cross-channel flow analysis module generates feeder buses candidate line set by input condition of the volume of the flow of passengers of traffic station, according to connecing
The dual layer resist network of mode of transportation building feeder buses line network planning is refuted, upper layer network in City Rail Transit System to go on a journey
The minimum target of the sum of the weighting of cost, system operation cost, monomer vehicle driving quantity, the line combination side in optimization system
All data of case, the vehicle configuration of route and departure frequency, the above layer network output of lower layer's network are input, calculate difference and connect
The Trip Costs for refuting mode of transportation utilize genetic algorithm solving model；
City area-traffic system decision-making module is used for according to city road network cross-channel flow analysis module and city rail
The optimal solution that transportation system analysis module obtains determines the current allocation plan with urban track traffic of city road network cross-channel.
Preferably, the city road network and pedestrian's trip distributional analysis module calculate following city area-traffic utilization rate
Index:
The unidirectional load factor of road:
Peak unit time maximum unidirectional load factor:
Road is averaged load factor:
Public transport is averaged load factor:
Urban road area density:
L is the mileage length of urban road；E is region area；
Urban population density:
R is urban population amount；
Urban road economic density:
GDP is city gross national product；
City vehicle traffic density:
I is city vehicle traffic mileage；
City area-traffic combined density:
City area-traffic road network degree of communication:
L0 is urban area total mileage, and θ is the ratio of non-linear coefficient, i.e. airline mileage and total kilometrage；H is regional traffic
Total section number of road network, N are the number of nodes of regional traffic road network；
Urban transportation ideal link length:
U is economic indicator coefficient；
The urban transportation ideal size degree of approach:
Urban traffic road is laid out equilibrium degree
It is wherein the reasonable number of partitions of road network scale in P0 planning region, P is total number of partitions in scale region.
Preferably, the city road network cross-channel flow analysis module is obtained is acquired by pedestrian's trip network and road network network
And the city area-traffic utilization rate index calculated；And constraint condition is set；When exceeding constraint condition, in genetic computation
Road network is closed, until city area-traffic utilization rate index no longer exceeds constraint condition.
Preferably, the constraint condition includes:
The constraint of road network coverage area:
D*A≤Fmax
Fmax is that limit degree is fully loaded in road individual event；
Q*W≤Gmax
Gmax is that public traffic is fully loaded with limit degree；
Maximum load factor constraint:
The maximum load factor that μm each road channel ax should meet；
mmin≤Tε≤mmax
Mmin is the minimum marshalling number of each cross-channel；Mmmax is the minimum marshalling number of each cross-channel.
Preferably, city road network cross-channel flow analysis module uses weigthed sums approach, will be utilized by city area-traffic
The multiple-objection optimization that rate index is constituted is converted to single object optimization；City road network after conversion optimizes single-goal function
ρ=τ 1* α+τ 2* β+τ 3* γ+τ 4* δ
τ 1+ τ 2+ τ 3+ τ 4=1
τ 1 is the weight of α；τ 2 is the weight of β；τ 3 is the weight of γ；τ 4 is the weight of δ.
Preferably, city road network cross-channel flow analysis module further uses genetic algorithm, based on constraint condition to upper
Single goal is stated to optimize；Optimization process are as follows:
1) chromosome coding is encoded according to the value range of each α, β, γ, δ variable and constraint condition,
2) chromosome fitness function value is calculated, using the single-goal function after conversion as the fitness letter of genetic algorithm
Number, Fit (X)=τ 1* α-τ 2* β-τ 3* γ-τ 4* δ
The fitness function of Fit (X) expression chromosome；
3) chiasma makes a variation, and before cross and variation, is ranked up to each filial generation fitness, and it is maximum to retain fitness
Two filial generations are operated without cross and variation, wherein are intersected and used single point crossing, variation is also made a variation using single-point；
3.1) to city area-traffic utilization rate index random assignment, initial population is generated；
3.2) adjustment chromosome population is feasible solution；
3.3) it calculates chromosome fitness value and records optimal solution；
3.4) judge whether to reach maximum evolutionary generation, then calculate terminates in this way, such as otherwise carries out in next step；
3.5) chromosome selected, intersected and mutation operation, and returned 3.2).
Preferably, upper layer network and lower net of the City Rail Transit System analysis module to City Rail Transit System
Network is modeled and is solved；Wherein
The model Z (x, y) of the upper layer network are as follows:
Wherein x, y are urban area coordinate,
Lower layer's network Model B (x, y):
Wherein J is that the section of transportation network is gathered, and π is any section, and J=J0 ∪ J1, J0 are existing section, and J1 is planning
Section, R, S are respectively starting point set and whole settled point set；R, s is respectively any starting point and whole settled point；xπFor section π's
The magnitude of traffic flow,The magnitude of traffic flow between origin and destination r and s on the p of path, qrsFor the transport need amount between origin and destination r and s,For section path association factor, yπFor upper layer decision variable,yπ For the lower limit of section π ability increment,For section π ability
The upper limit of increment, tπ(xπ, yπ) be section π on travel time function, Hπ(yπ) it is the investment cost letter for widening existing section π
Number, ω is proportionality coefficient.
City Rail Transit System analysis module is as follows to the process of above-mentioned model solution using genetic algorithm:
(1) it encodes；The upper layer network of the City Rail Transit System and lower layer's network solution to model space variable are turned
The genotypic data structure being changed in genetic algorithm is encoded with the bit string of a regular length, forms heredity
The optimization solution of chromosome in algorithm, that is, the upper layer network and lower layer's network model of assuming the City Rail Transit System includes
There is N road, regular length is used to indicate chromosome for the 0-1 variable of N, wherein 0 represents corresponding section and remains stationary not
Become, 1, which represents corresponding section, will carry out increasing its traffic capacity；
(2) initialization algorithm parameter；The urban track traffic is randomly generated according to binary coding method in first calculate
The initial population of the optimization solution of the upper layer network and lower layer's network model of system, and control parameter is initialized, Population Size scale
M, maximum number of iterations B, crossover probability cp, mutation probability mp, feasible initial population are increased by randomly selecting n section
Scheme generates, and is denoted asI=0,1,2 ..., n, the number of iterations are denoted as k=0；
(3) compare fitness value；IndividualFitness value be
By fitness valueBy being ranked up from small to large；
(4) selection operation；Using roulette method select probability, when each runner, it is corresponding that probability s ∈ U (0,1) is randomly generated
Fitness value selects individual i, recycles k times altogether, generates k male parent；
(5) crossover operation；New daughter generation is the result intersected two-by-two to k male parent of above-mentioned generation；It is random to produce
Raw s ∈ U (0,1) carries out crossover operation, crossover probability cp, by the way of operation is intersected using double point of contacts, i.e., at random from two
Two point of contacts are chosen in individual, exchange the gene between two point of contacts；
(6) s ∈ U (0,1) is randomly generated in the way of the variation of the single-gene of individual in mutation operation, mutation operation from each and every one
One of gene of body carries out, to promote the generation of new individual；
(7) if city area-traffic utilization rate index exceeds above-mentioned constraint condition, termination algorithm；Otherwise (3) are jumped to.
The city area-traffic big data analysis method based on genetic algorithm optimization that the present invention also provides a kind of, including such as
Lower step:
(1) double-layer network for being interacted by pedestrian's trip network and road network network and being formed is established, upper layer network is row
People's trip network, the node of upper layer network are that trip generates point, and connecting each other between node is connected by line；Lower layer's network is road
Net network, the node of lower layer's network are intersection, and line indicates section between node；Each node of upper layer network acquires this node
The volume of the flow of passengers at place simultaneously carries out flow analysis；Each node of lower layer's network acquires the magnitude of traffic flow at this node place and carries out flow point
Analysis；Acquisition by whole nodes of upper layer network and lower layer's network the volume of the flow of passengers and the Traffic Systems that form of the magnitude of traffic flow it is big
Data, and computational chart let others have a look at flow distribution feature, cross-channel handling capacity, stream of people's service ability, cross-channel operation organizational complexity, equipment
The city area-traffic utilization rate index of investment and these factors of running cost；
(2) the city area-traffic utilization rate index is obtained；And constraint condition is set, when exceeding constraint condition,
Road network is closed in genetic computation, until city area-traffic utilization rate index exceeds constraint condition:
(3) city area-traffic utilization rate index and constraint condition are utilized, establishing indicates the current shape of city road network cross-channel
The optimization single-goal function of state, and above-mentioned single-goal function is optimized using genetic algorithm；
(4) upper layer network of City Rail Transit System and lower layer's network are modeled and is solved
(5) according to the optimal solution obtained in step (3) and (4), city road network cross-channel passage and urban track traffic are determined
Allocation plan.
Preferably, the city area-traffic utilization rate index of calculating includes:
The unidirectional load factor of road:
Peak unit time maximum unidirectional load factor:
Road is averaged load factor:
Public transport is averaged load factor:
Urban road area density:
L is the mileage length of urban road；E is region area；
Urban population density:
R is urban population amount；
Urban road economic density:
GDP is city gross national product；
City vehicle traffic density:
I is city vehicle traffic mileage；
City area-traffic combined density:
City area-traffic road network degree of communication:
L0 is urban area total mileage, and θ is the ratio of non-linear coefficient, i.e. airline mileage and total kilometrage；H is regional traffic
Total section number of road network, N are the number of nodes of regional traffic road network；
Urban transportation ideal link length:
U is economic indicator coefficient；
The urban transportation ideal size degree of approach:
Urban traffic road is laid out equilibrium degree
It is wherein the reasonable number of partitions of road network scale in P0 planning region, P is total number of partitions in scale region.
Preferably, it obtains by pedestrian's trip network and road network network acquires and the city area-traffic utilization rate calculated refers to
Mark；And constraint condition is set；When exceeding constraint condition, road network is closed in genetic computation, until city area-traffic benefit
No longer exceed constraint condition with rate index.
Preferably, the constraint condition includes:
The constraint of road network coverage area:
D*A≤Fmax
Fmax is that limit degree is fully loaded in road individual event；
Q*W≤Gmax
Gmax is that public traffic is fully loaded with limit degree；
Maximum load factor constraint:
The maximum load factor that μm each road channel ax should meet；
mmin≤Tε≤mmax
Mmin is the minimum marshalling number of each cross-channel；Mmmax is the minimum marshalling number of each cross-channel.
Preferably, more by being made of city area-traffic utilization rate index using weigthed sums approach in step (3)
Objective optimization is converted to single object optimization；City road network after conversion optimizes single-goal function
ρ=τ 1* α+τ 2* β+τ 3* γ+τ 4* δ
τ 1+ τ 2+ τ 3+ τ 4=1
τ 1 is the weight of α；τ 2 is the weight of β；τ 3 is the weight of γ；τ 4 is the weight of δ.
Preferably, city road network cross-channel flow analysis module further uses genetic algorithm, based on constraint condition to upper
Single goal is stated to optimize；Optimization process are as follows:
1) chromosome coding is encoded according to the value range of each α, β, γ, δ variable and constraint condition,
2) chromosome fitness function value is calculated, using the single-goal function after conversion as the fitness letter of genetic algorithm
Number, Fit (X)=τ 1* α-τ 2* β-τ 3* γ-τ 4* δ
The fitness function of Fit (X) expression chromosome；
3) chiasma makes a variation, and before cross and variation, is ranked up to each filial generation fitness, and it is maximum to retain fitness
Two filial generations are operated without cross and variation, wherein are intersected and used single point crossing, variation is also made a variation using single-point；
3.1) to city area-traffic utilization rate index random assignment, initial population is generated；
3.2) adjustment chromosome population is feasible solution；
3.3) it calculates chromosome fitness value and records optimal solution；
3.4) judge whether to reach maximum evolutionary generation, then calculate terminates in this way, such as otherwise carries out in next step；
3.5) chromosome selected, intersected and mutation operation, and returned 3.2).
Preferably, in step (4), upper wire of the City Rail Transit System analysis module to City Rail Transit System
Network and lower layer's network are modeled and are solved；Wherein
The model Z (x, y) of the upper layer network are as follows:
Wherein x, y are urban area coordinate,
Lower layer's network Model B (x, y):
Wherein J is that the section of transportation network is gathered, and π is any section, and J=J0 ∪ J1, J0 are existing section, and J1 is planning
Section, R, S are respectively starting point set and whole settled point set；R, s is respectively any starting point and whole settled point；xπFor section π's
The magnitude of traffic flow,The magnitude of traffic flow between origin and destination r and s on the p of path, qrsFor the transport need amount between origin and destination r and s,For section path association factor, yπFor upper layer decision variable,yπ For the lower limit of section π ability increment,For section π ability
The upper limit of increment, tπ(xπ, yπ) be section π on travel time function, Hπ(yπ) it is the investment cost letter for widening existing section π
Number, ω is proportionality coefficient.
Preferably, as follows using process of the genetic algorithm to above-mentioned model solution in step (4):
(1) it encodes；The upper layer network of the City Rail Transit System and lower layer's network solution to model space variable are turned
The genotypic data structure being changed in genetic algorithm is encoded with the bit string of a regular length, forms heredity
The optimization solution of chromosome in algorithm, that is, the upper layer network and lower layer's network model of assuming the City Rail Transit System includes
There is N road, regular length is used to indicate chromosome for the 0-1 variable of N, wherein 0 represents corresponding section and remains stationary not
Become, 1, which represents corresponding section, will carry out increasing its traffic capacity；
(2) initialization algorithm parameter；The urban track traffic is randomly generated according to binary coding method in first calculate
The initial population of the optimization solution of the upper layer network and lower layer's network model of system, and control parameter is initialized, Population Size scale
M, maximum number of iterations B, crossover probability cp, mutation probability mp, feasible initial population are increased by randomly selecting n section
Scheme generates, and is denoted asI=0,1,2 ..., n, the number of iterations are denoted as k=0；
(3) compare fitness value；IndividualFitness value be
By fitness valueBy being ranked up from small to large；
(4) selection operation；Using roulette method select probability, when each runner, it is corresponding that probability s ∈ U (0,1) is randomly generated
Fitness value selects individual i, recycles k times altogether, generates k male parent；
(5) crossover operation；New daughter generation is the result intersected two-by-two to k male parent of above-mentioned generation；It is random to produce
Raw s ∈ U (0,1) carries out crossover operation, crossover probability cp, by the way of operation is intersected using double point of contacts, i.e., at random from two
Two point of contacts are chosen in individual, exchange the gene between two point of contacts；
(6) s ∈ U (0,1) is randomly generated in the way of the variation of the single-gene of individual in mutation operation, mutation operation from each and every one
One of gene of body carries out, to promote the generation of new individual；
(7) if city area-traffic utilization rate index exceeds above-mentioned constraint condition, termination algorithm；Otherwise (3) are jumped to.
The beneficial effects of the present invention are:
The present invention is distributed using city road network and resident trip as research object, has been analysed in depth city road network and has been gone out with resident
Functional relation between row distribution, has had found city road network and resident trip is distributed inherent mechanism and shadow based on genetic algorithm
The factor of sound establishes the computation model for evaluating interaction strength between the two.Meanwhile using the bilayer in Continuous network design
The index of city road network and resident trip distribution is introduced into city road network optimization, establishes based on genetic algorithm by plan model
City road network optimize Bi-level Programming Models, greatly improve the data analysis capabilities and decision-making capability of city area-traffic.
Detailed description of the invention
Fig. 1 is the city area-traffic big data analysis system structure signal of the present invention based on genetic algorithm optimization
Figure；
Fig. 2 is the flow chart of the city area-traffic big data analysis method based on genetic algorithm optimization.
Specific embodiment
The present invention is described further with reference to the accompanying drawing.
Embodiment 1
As shown in Figure 1, a kind of city area-traffic big data analysis system based on genetic algorithm optimization, including city road
Net and pedestrian trip distributional analysis module, city road network cross-channel flow analysis module, City Rail Transit System analysis module, city
City's Regional Transportation System decision-making module.
The city road network includes mutual by pedestrian's trip network and road network network with pedestrian's trip distributional analysis module
The double-layer network for acting on and being formed, upper layer network are pedestrian's trip network, and the node of upper layer network is to go on a journey to generate point, between node
Connect each other by line be connected；Lower layer's network is road network network, and the node of lower layer's network is intersection, and line indicates between node
Section；Each node of upper layer network acquires the volume of the flow of passengers at this node place and carries out flow analysis；Each node of lower layer's network
It acquires the magnitude of traffic flow at this node place and carries out flow analysis；The city road network passes through upper with pedestrian's trip distributional analysis module
The node of layer network and lower layer's network is acquired by the volume of the flow of passengers and the magnitude of traffic flow on whole nodes of upper layer network and lower layer's network
The Traffic Systems big data of composition, and computational chart let others have a look at flow distribution feature, cross-channel handling capacity, stream of people's service ability, hand over
Road transport seeks the city area-traffic utilization rate index of organizational complexity, equipment investment and running cost these factors.
City road network cross-channel flow analysis module establishes optimization single goal according to the city area-traffic utilization rate index
Function, and above-mentioned single-goal function is optimized using genetic algorithm, determine cross-channel transit scenario.
City Rail Transit System analysis module is based on city road network and pedestrian's trip distributional analysis module and city road network
Cross-channel flow analysis module generates feeder buses candidate line set by input condition of the volume of the flow of passengers of traffic station, according to connecing
The dual layer resist network of mode of transportation building feeder buses line network planning is refuted, upper layer network in City Rail Transit System to go on a journey
The minimum target of the sum of the weighting of cost, system operation cost, monomer vehicle driving quantity, the line combination side in optimization system
All data of case, the vehicle configuration of route and departure frequency, the above layer network output of lower layer's network are input, calculate difference and connect
The Trip Costs for refuting mode of transportation, using genetic algorithm solving model, required optimal solution can be used for rail traffic assigner
It flows and returns to upper layer network analysis city entirety traffic target value.
The city road network and pedestrian's trip distributional analysis module pass through the node of upper layer network and lower layer's network, acquisition
By the volume of the flow of passengers and the Traffic Systems big data that forms of the magnitude of traffic flow on whole nodes of upper layer network and lower layer's network, and
Calculate following city area-traffic utilization rate index:
The unidirectional load factor of road:
Peak unit time maximum unidirectional load factor:
Road is averaged load factor:
Public transport is averaged load factor:
Urban road area density:
L is the mileage length of urban road；E is region area；
Urban population density:
R is urban population amount；
Urban road economic density:
GDP is city gross national product；
City vehicle traffic density:
I is city vehicle traffic mileage；
City area-traffic combined density:
City area-traffic road network degree of communication:
L0 is urban area total mileage, and θ is the ratio of non-linear coefficient, i.e. airline mileage and total kilometrage；H is regional traffic
Total section number of road network, N are the number of nodes of regional traffic road network；
Urban transportation ideal link length:
U is economic indicator coefficient；
The urban transportation ideal size degree of approach:
Urban traffic road is laid out equilibrium degree
It is wherein the reasonable number of partitions of road network scale in P0 planning region, P is total number of partitions in scale region.
The city road network cross-channel flow analysis module, which is obtained, to be acquired and is calculated by pedestrian's trip network and road network network
City area-traffic utilization rate index；And constraint condition is set；When exceeding constraint condition, road is closed in genetic computation
Net, until city area-traffic utilization rate index no longer exceeds constraint condition.
The constraint condition includes:
The constraint of road network coverage area:
D*A≤Fmax
Fmax is that limit degree is fully loaded in road individual event；
Q*W≤Gmax
Gmax is that public traffic is fully loaded with limit degree；
Maximum load factor constraint:
The maximum load factor that μm each road channel ax should meet；
mmin≤Tε≤mmax
Mmin is the minimum marshalling number of each cross-channel；Mmmax is the minimum marshalling number of each cross-channel.
The city road network cross-channel flow analysis module utilizes city area-traffic utilization rate index and constraint condition,
The optimization single-goal function of city road network cross-channel prevailing state is established, and excellent to the progress of above-mentioned single-goal function using genetic algorithm
Change and solves, specifically:
City road network cross-channel flow analysis module uses weigthed sums approach, will be made of city area-traffic utilization rate index
Multiple-objection optimization be converted to single object optimization；City road network after conversion optimizes single-goal function
ρ=τ 1* α+τ 2* β+τ 3* γ+τ 4* δ
τ 1+ τ 2+ τ 3+ τ 4=1
τ 1 is the weight of α；τ 2 is the weight of β；τ 3 is the weight of γ；τ 4 is the weight of δ；
City road network cross-channel flow analysis module further uses genetic algorithm, based on constraint condition to above-mentioned single goal into
Row optimization；Optimization process are as follows:
1) chromosome coding is encoded according to the value range of each α, β, γ, δ variable and constraint condition,
2) chromosome fitness function value is calculated, using the single-goal function after conversion as the fitness letter of genetic algorithm
Number, Fit (X)=τ 1* α-τ 2* β-τ 3* γ-τ 4* δ
The fitness function of Fit (X) expression chromosome；
3) chiasma makes a variation, and before cross and variation, is ranked up to each filial generation fitness, and it is maximum to retain fitness
Two filial generations are operated without cross and variation, wherein are intersected and used single point crossing, variation is also made a variation using single-point；
3.1) to city area-traffic utilization rate index random assignment, initial population is generated；
3.2) adjustment chromosome population is feasible solution；
3.3) it calculates chromosome fitness value and records optimal solution；
3.4) judge whether to reach maximum evolutionary generation, then calculate terminates in this way, such as otherwise carries out in next step；
3.5) chromosome selected, intersected and mutation operation, and returned 3.2).
The city area-traffic utilization rate index optimal solution obtained is solved using by genetic algorithm optimization, determines city road
The cross-channel transit scenario of net cross-channel flow.The City Rail Transit System analysis module is to the upper of City Rail Transit System
Layer network and lower layer's network are modeled and are solved；
The model Z (x, y) of the upper layer network are as follows:
Wherein x, y are urban area coordinate,
Lower layer's network Model B (x, y):
Wherein J is that the section of transportation network is gathered, and π is any section, and J=J0 ∪ J1, J0 are existing section, and J1 is planning
Section, R, S are respectively starting point set and whole settled point set；R, s is respectively any starting point and whole settled point；xπFor section π's
The magnitude of traffic flow,The magnitude of traffic flow between origin and destination r and s on the p of path, qrsFor the transport need amount between origin and destination r and s,For section path association factor, yπFor upper layer decision variable,yπ For the lower limit of section π ability increment,For section π ability
The upper limit of increment, tπ(xπ, yπ) be section π on travel time function, Hπ(yπ) it is the investment cost letter for widening existing section π
Number, ω is proportionality coefficient.
City Rail Transit System analysis module is as follows to the process of above-mentioned model solution using genetic algorithm:
Step 1: coding；By the upper layer network of the City Rail Transit System and lower layer's network solution to model space variable
The genotypic data structure in genetic algorithm is converted to, is encoded with the bit string of a regular length, is formed and is lost
Chromosome in propagation algorithm assumes that the optimization of the upper layer network and lower layer's network model of the City Rail Transit System unpacks
N road has been included, regular length is used to indicate chromosome for the 0-1 variable of N, wherein 0 represents corresponding section and remains stationary
Constant, 1, which represents corresponding section, will carry out increasing its traffic capacity；
Step 2: initialization algorithm parameter；The city rail friendship is randomly generated according to binary coding method in first calculate
The initial population of the optimization solution of the upper layer network and lower layer's network model of way system, and control parameter is initialized, Population Size rule
Mould M, maximum number of iterations B, crossover probability cp, mutation probability mp, feasible initial population are increased by randomly selecting n section
Add scheme to generate, is denoted asI=0,1,2 ..., n, the number of iterations are denoted as k=0；
Step 3: comparing fitness value；IndividualFitness value be
By fitness valueBy being ranked up from small to large；
Step 4: selection operation；Using roulette method select probability, when each runner, probability s ∈ U (0,1) is randomly generated
Corresponding fitness value, selects individual i, recycles k times altogether, generates k male parent；
Step 5: crossover operation；New daughter generation is the result intersected two-by-two to k male parent of above-mentioned generation；At random
It generates s ∈ U (0,1), carries out crossover operation, crossover probability cp, by the way of operation is intersected using double point of contacts, i.e., at random from two
Two point of contacts are chosen in individual, exchange the gene between two point of contacts；
Step 6: s ∈ U (0,1) is randomly generated in the way of the variation of the single-gene of individual in mutation operation, mutation operation from
One of gene of individual carries out, to promote the generation of new individual；
Step 7: if city area-traffic utilization rate index exceeds above-mentioned constraint condition, termination algorithm；Otherwise step is jumped to
Rapid 3.
The upper layer network and lower layer's network model of the City Rail Transit System are solved using the above genetic algorithm, are obtained
Indicate with Trip Costs in City Rail Transit System, system operation cost, monomer vehicle driving quantity, line combination scheme,
The optimization solution that the vehicle configuration and departure frequency of route, Transportation costs of plugging into optimize.
City area-traffic system decision-making module is used for according to city road network cross-channel flow analysis module and city rail
The optimal solution that transportation system analysis module obtains determines the current allocation plan with urban track traffic of city road network cross-channel.
Above system establishes friendship by a set of city area-traffic big data analysis system based on genetic algorithm optimization
The new solution of one kind of wildcard flow problem, proposes a kind of chromosome coding processing method, can be expressed with floating-point code
Discrete 0-l variable establishes guarantor's flow distribution feature, cross-channel handling capacity, stream of people's clothes by the path analysis of genetic algorithm
The city road network cross-channel that business ability, cross-channel operation organizational complexity, equipment investment and these factors of running cost optimize is current
Scheme and City Rail Transit System allocation plan greatly improve the analysis speed and analysis precision of system.
Embodiment 2
The present invention also provides a kind of city area-traffic big data analysis method based on genetic algorithm optimization, such as Fig. 2
It is shown, include the following steps:
(1) double-layer network for being interacted by pedestrian's trip network and road network network and being formed is established, upper layer network is row
People's trip network, the node of upper layer network are that trip generates point, and connecting each other between node is connected by line；Lower layer's network is road
Net network, the node of lower layer's network are intersection, and line indicates section between node；Each node of upper layer network acquires this node
The volume of the flow of passengers at place simultaneously carries out flow analysis；Each node of lower layer's network acquires the magnitude of traffic flow at this node place and carries out flow point
Analysis；Acquisition by whole nodes of upper layer network and lower layer's network the volume of the flow of passengers and the Traffic Systems that form of the magnitude of traffic flow it is big
Data, and computational chart let others have a look at flow distribution feature, cross-channel handling capacity, stream of people's service ability, cross-channel operation organizational complexity, equipment
The city area-traffic utilization rate index of investment and these factors of running cost.
Specifically, the city area-traffic utilization rate index of calculating includes:
The unidirectional load factor of road:
Peak unit time maximum unidirectional load factor:
Road is averaged load factor:
Public transport is averaged load factor:
Urban road area density:
L is the mileage length of urban road；E is region area；
Urban population density:
R is urban population amount；
Urban road economic density:
GDP is city gross national product；
City vehicle traffic density:
I is city vehicle traffic mileage；
City area-traffic combined density:
City area-traffic road network degree of communication:
L0 is urban area total mileage, and θ is the ratio of non-linear coefficient, i.e. airline mileage and total kilometrage；H is regional traffic
Total section number of road network, N are the number of nodes of regional traffic road network；
Urban transportation ideal link length:
U is economic indicator coefficient；
The urban transportation ideal size degree of approach:
Urban traffic road is laid out equilibrium degree
It is wherein the reasonable number of partitions of road network scale in P0 planning region, P is total number of partitions in scale region；
(2) the city area-traffic utilization rate index is obtained；And constraint condition is set, when exceeding constraint condition,
Road network is closed in genetic computation, until city area-traffic utilization rate index exceeds constraint condition:
The constraint condition includes:
The constraint of road network coverage area:
D*A≤Fmax
Fmax is that limit degree is fully loaded in road individual event；
Q*W≤Gmax
Gmax is that public traffic is fully loaded with limit degree；
Maximum load factor constraint:
The maximum load factor that μm each road channel ax should meet；
mmin≤Tε≤mmax
Mmin is the minimum marshalling number of each cross-channel；Mmmax is the minimum marshalling number of each cross-channel.
(3) city area-traffic utilization rate index and constraint condition are utilized, establishing indicates the current shape of city road network cross-channel
The optimization single-goal function of state, and above-mentioned single-goal function is optimized using genetic algorithm.Specifically:
Multiple-objection optimization is converted to by single object optimization using weigthed sums approach；The city road network single-goal function of foundation is such as
Under:
ρ=τ 1* α+τ 2* β+τ 3* γ+τ 4* δ
τ 1+ τ 2+ τ 3+ τ 4=1
τ 1 is the weight of α；τ 2 is the weight of β；τ 3 is the weight of γ；τ 4 is the weight of δ；
Constraint condition is based on using genetic algorithm to optimize above-mentioned single goal；
1) chromosome coding is encoded according to the value range of each α, β, γ, δ variable and constraint condition,
2) chromosome fitness function value is calculated, using the single-goal function after conversion as the fitness letter of genetic algorithm
Number, Fit (X)=τ 1* α-τ 2* β-τ 3* γ-τ 4* δ
The fitness function of Fit (X) expression chromosome；
3) chiasma makes a variation, and before cross and variation, is ranked up to each filial generation fitness, and it is maximum to retain fitness
Two filial generations are operated without cross and variation, wherein are intersected and used single point crossing, variation is also made a variation using single-point；
3.1) to city area-traffic utilization rate index random assignment, initial population is generated；
3.2) adjustment chromosome population is feasible solution；
3.3) it calculates chromosome fitness value and records optimal solution；
3.4) judge whether to reach maximum evolutionary generation, then calculate terminates in this way, such as otherwise carries out in next step；
3.5) chromosome selected, intersected and mutation operation, and returned 3.2)；
The city area-traffic utilization rate index optimal solution obtained is solved using by genetic algorithm optimization, determines city road
The cross-channel transit scenario of net cross-channel flow.
(4) upper layer network and lower net of City Rail Transit System analysis module described in City Rail Transit System
Network is modeled and is solved；
The model of the upper layer network are as follows:
Wherein x, y are urban area coordinate,
Lower layer's network model:
Wherein J is that the section of transportation network is gathered, and π is any section, and J=J0 ∪ J1, J0 are existing section, and J1 is planning
Section, R, S are respectively starting point set and whole settled point set；R, s is respectively any starting point and whole settled point；xπFor section π's
The magnitude of traffic flow,The magnitude of traffic flow between origin and destination r and s on the p of path, qrsFor the transport need amount between origin and destination r and s,For section path association factor, yπFor upper layer decision variable,yπ For the lower limit of section π ability increment,For section π ability
The upper limit of increment, tπ(xπ, yπ) be section π on travel time function, Hπ(yπ) it is the investment cost letter for widening existing section π
Number, ω is proportionality coefficient；
City Rail Transit System analysis module is as follows to the process of above-mentioned model solution using genetic algorithm:
Step 1: coding；By setting for the upper layer network of the City Rail Transit System and lower layer's network solution to model space
Meter variable is converted to the genotypic data structure in genetic algorithm, is encoded with the bit string of a regular length,
Formed genetic algorithm in chromosome, that is, assume the City Rail Transit System upper layer network and lower layer's network model it is excellent
Neutralizing includes N road, and using regular length is that the 0-1 variable of N indicates chromosome, wherein 0 represents corresponding section maintenance
Original state is constant, and 1, which represents corresponding section, will carry out increasing its traffic capacity；
Step 2: initialization algorithm parameter；The city rail friendship is randomly generated according to binary coding method in first calculate
The initial population of the optimization solution of the upper layer network and lower layer's network model of way system, and control parameter is initialized, Population Size rule
Mould M, maximum number of iterations B, crossover probability cp, mutation probability mp, feasible initial population are increased by randomly selecting n section
Add scheme to generate, is denoted asI=0,1,2 ..., n, the number of iterations are denoted as k=0；
Step 3: comparing fitness value；IndividualFitness value be
By fitness valueBy being ranked up from small to large；
Step 4: selection operation；Using roulette method select probability, when each runner, probability s ∈ U (0,1) is randomly generated
Corresponding fitness value, selects individual i, recycles k times altogether, generates k male parent；
Step 5: crossover operation；New daughter generation is the result intersected two-by-two to k male parent of above-mentioned generation；At random
It generates s ∈ U (0,1), carries out crossover operation, crossover probability cp, by the way of operation is intersected using double point of contacts, i.e., at random from two
Two point of contacts are chosen in individual, exchange the gene between two point of contacts；
Step 6: s ∈ U (0,1) is randomly generated in the way of the variation of the single-gene of individual in mutation operation, mutation operation from
One of gene of individual carries out, to promote the generation of new individual；
Step 7: if city area-traffic utilization rate index exceeds constraint condition, termination algorithm；Otherwise step 3 is jumped to.
(5) optimal solution obtained according to city road network cross-channel flow analysis module and City Rail Transit System, determines
The current allocation plan with urban track traffic of city road network cross-channel.
The method of the present invention fully considers time-varying characteristics of passenger flow and its defeated to section using city area-traffic as research object
The standard deviation for considering section conveying capacity utilization rate is added in the influence for sending ability to utilize time lack of uniformity in optimization aim
The sum of rate minimizes, and establishes traffic plan optimization system and method based on genetic algorithm.Further, it proposes to consider passenger flow
The calculation method of time-varying characteristics.The result shows that with single cross-channel compared with the uniform traffic of nested cross-channel, the optimal side of present invention gained
The traffic used time, 53% and 67% was separately optimized in time equalization in case.
Here it must be noted that other unaccounted structures that the present invention provides are because be all the known knot of this field
Structure, title or function according to the present invention, those skilled in the art can find the document of related record, therefore not do
It further illustrates.The technical means disclosed in the embodiments of the present invention is not limited only to technological means disclosed in above embodiment, also
Including technical solution consisting of any combination of the above technical features.
Claims (9)
1. a kind of city area-traffic big data analysis system based on genetic algorithm optimization, which is characterized in that including city road
Net and pedestrian trip distributional analysis module, city road network cross-channel flow analysis module, City Rail Transit System analysis module, city
City's Regional Transportation System decision-making module；
The city road network and pedestrian go on a journey distributional analysis module include go on a journey network and the interaction of road network network by pedestrian and
The double-layer network of formation, upper layer network are that pedestrian's trip network is acquired by the node of upper layer network and lower layer's network by upper layer
The Traffic Systems big data of the volume of the flow of passengers and magnitude of traffic flow composition on whole nodes of network and lower layer's network, and computational chart
It lets others have a look at flow distribution feature, cross-channel handling capacity, stream of people's service ability, cross-channel operation organizational complexity, equipment investment and operating charges
With the city area-traffic utilization rate index of these factors；
City road network cross-channel flow analysis module establishes the optimization monocular offer of tender according to the city area-traffic utilization rate index
Number, and above-mentioned single-goal function is optimized using genetic algorithm, determine the current optimal solution of cross-channel；
City Rail Transit System analysis module is based on city road network and pedestrian's trip distributional analysis module and city road network cross-channel
Flow analysis module generates feeder buses candidate line set by input condition of the volume of the flow of passengers of traffic station, hands over according to plugging into
Logical mode constructs the dual layer resist network of feeder buses line network planning, upper layer network with go on a journey in City Rail Transit System at
The minimum target of the sum of the weighting of sheet, system operation cost, monomer vehicle driving quantity, the line combination side in optimization system
All data of case, the vehicle configuration of route and departure frequency, the above layer network output of lower layer's network are input, calculate difference and connect
The Trip Costs for refuting mode of transportation utilize genetic algorithm solving model；
City area-traffic system decision-making module is used for according to city road network cross-channel flow analysis module and urban track traffic
The optimal solution that Systems Analysis Module obtains determines the current allocation plan with urban track traffic of city road network cross-channel.
2. the city area-traffic big data analysis system according to claim 1 based on genetic algorithm optimization, feature
It is, the city road network and pedestrian's trip distributional analysis module calculate following city area-traffic utilization rate index:
The unidirectional load factor of road:
Peak unit time maximum unidirectional load factor:
Road is averaged load factor:
Public transport is averaged load factor:
Urban road area density:
L is the mileage length of urban road；E is region area；
Urban population density:
R is urban population amount；
Urban road economic density:
GDP is city gross national product；
City vehicle traffic density:
I is city vehicle traffic mileage；
City area-traffic combined density:
City area-traffic road network degree of communication:
L0 is urban area total mileage, and θ is the ratio of airline mileage and total kilometrage；H is total section number of regional traffic road network, N
For the number of nodes of regional traffic road network；
Urban transportation ideal link length:
U is economic indicator coefficient；
The urban transportation ideal size degree of approach:
Urban traffic road is laid out equilibrium degree
It is wherein the reasonable number of partitions of road network scale in P0 planning region, P is total number of partitions in scale region.
3. the city area-traffic big data analysis system according to claim 2 based on genetic algorithm optimization, feature
It is, the city road network cross-channel flow analysis module obtains the city for being acquired and being calculated by pedestrian's trip network and road network network
Regional traffic utilization rate index；And constraint condition is set；When exceeding constraint condition, road network is closed in genetic computation, directly
No longer exceed constraint condition to city area-traffic utilization rate index.
4. the city area-traffic big data analysis system according to claim 3 based on genetic algorithm optimization, feature
It is, city road network cross-channel flow analysis module uses weigthed sums approach, by what is be made of city area-traffic utilization rate index
Multiple-objection optimization is converted to single object optimization；City road network after conversion optimizes single-goal function
ρ=τ 1* α+τ 2* β+τ 3* γ+τ 4* δ
τ 1+ τ 2+ τ 3+ τ 4=1
τ 1 is the weight of α；τ 2 is the weight of β；τ 3 is the weight of γ；τ 4 is the weight of δ.
5. the city area-traffic big data analysis system according to claim 4 based on genetic algorithm optimization, feature
It is, city road network cross-channel flow analysis module further uses genetic algorithm, is carried out based on constraint condition to above-mentioned single goal
Optimization；Optimization process are as follows:
1) chromosome coding is encoded according to the value range of each α, β, γ, δ variable and constraint condition,
2) chromosome fitness function value is calculated, using the single-goal function after conversion as the fitness function of genetic algorithm, Fit
(X)=τ 1* α-τ 2* β-τ 3* γ-τ 4* δ
The fitness function of Fit (X) expression chromosome；
3) chiasma makes a variation, and before cross and variation, is ranked up to each filial generation fitness, retains fitness maximum two
Filial generation is operated without cross and variation, wherein is intersected and is used single point crossing, variation is also made a variation using single-point；
3.1) to city area-traffic utilization rate index random assignment, initial population is generated；
3.2) adjustment chromosome population is feasible solution；
3.3) it calculates chromosome fitness value and records optimal solution；
3.4) judge whether to reach maximum evolutionary generation, then calculate terminates in this way, such as otherwise carries out in next step；
3.5) chromosome selected, intersected and mutation operation, and returned 3.2).
6. a kind of city area-traffic big data analysis method based on genetic algorithm optimization, which is characterized in that including walking as follows
It is rapid:
(1) double-layer network for being interacted by pedestrian's trip network and road network network and being formed is established, upper layer network goes out for pedestrian
Row network, the node of upper layer network are that trip generates point, and connecting each other between node is connected by line；Lower layer's network is road network net
Network, the node of lower layer's network are intersection, and line indicates section between node；Each node of upper layer network acquires this node place
The volume of the flow of passengers simultaneously carries out flow analysis；Each node of lower layer's network acquires the magnitude of traffic flow at this node place and carries out flow analysis；
Acquisition is by the volume of the flow of passengers and the big number of Traffic Systems that forms of the magnitude of traffic flow on whole nodes of upper layer network and lower layer's network
According to, and computational chart let others have a look at flow distribution feature, cross-channel handling capacity, stream of people's service ability, cross-channel operation organizational complexity, equipment throw
The city area-traffic utilization rate index of money and these factors of running cost；
(2) the city area-traffic utilization rate index is obtained；And constraint condition is set, when exceeding constraint condition, is being lost
It passes in calculating and closes road network, until city area-traffic utilization rate index exceeds constraint condition:
(3) city area-traffic utilization rate index and constraint condition are utilized, establishing indicates city road network cross-channel prevailing state
Optimize single-goal function, and above-mentioned single-goal function is optimized using genetic algorithm；
(4) upper layer network of City Rail Transit System and lower layer's network are modeled and is solved
(5) it according to the optimal solution obtained in step (3) and (4), determines that city road network cross-channel is current and urban track traffic is matched
Set scheme.
7. the city area-traffic big data analysis method according to claim 6 based on genetic algorithm optimization, feature
It is, the city area-traffic utilization rate index of calculating includes:
The unidirectional load factor of road:
Peak unit time maximum unidirectional load factor:
Road is averaged load factor:
Public transport is averaged load factor:
Urban road area density:
L is the mileage length of urban road；E is region area；
Urban population density:
R is urban population amount；
Urban road economic density:
GDP is city gross national product；
City vehicle traffic density:
I is city vehicle traffic mileage；
City area-traffic combined density:
City area-traffic road network degree of communication:
L0 is urban area total mileage, and θ is the ratio of airline mileage and total kilometrage；H is total section number of regional traffic road network, N
For the number of nodes of regional traffic road network；
Urban transportation ideal link length:
U is economic indicator coefficient；
The urban transportation ideal size degree of approach:
Urban traffic road is laid out equilibrium degree
It is wherein the reasonable number of partitions of road network scale in P0 planning region, P is total number of partitions in scale region.
8. the city area-traffic big data analysis method according to claim 7 based on genetic algorithm optimization, feature
It is, in step (3), using weigthed sums approach, the multiple-objection optimization being made of city area-traffic utilization rate index is converted
For single object optimization；City road network after conversion optimizes single-goal function
ρ=τ 1* α+τ 2* β+τ 3* γ+τ 4* δ
τ 1+ τ 2+ τ 3+ τ 4=1
τ 1 is the weight of α；τ 2 is the weight of β；τ 3 is the weight of γ；τ 4 is the weight of δ.
9. the city area-traffic big data analysis method according to claim 8 based on genetic algorithm optimization, feature
It is, city road network cross-channel flow analysis module further uses genetic algorithm, is carried out based on constraint condition to above-mentioned single goal
Optimization；Optimization process are as follows:
1) chromosome coding is encoded according to the value range of each α, β, γ, δ variable and constraint condition,
2) chromosome fitness function value is calculated, using the single-goal function after conversion as the fitness function of genetic algorithm, Fit
(X)=τ 1* α-τ 2* β-τ 3* γ-τ 4* δ
The fitness function of Fit (X) expression chromosome；
3) chiasma makes a variation, and before cross and variation, is ranked up to each filial generation fitness, retains fitness maximum two
Filial generation is operated without cross and variation, wherein is intersected and is used single point crossing, variation is also made a variation using single-point；
3.1) to city area-traffic utilization rate index random assignment, initial population is generated；
3.2) adjustment chromosome population is feasible solution；
3.3) it calculates chromosome fitness value and records optimal solution；
3.4) judge whether to reach maximum evolutionary generation, then calculate terminates in this way, such as otherwise carries out in next step；
3.5) chromosome selected, intersected and mutation operation, and returned 3.2).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810234041.5A CN108470444B (en) | 2018-03-21 | 2018-03-21 | A kind of city area-traffic big data analysis System and method for based on genetic algorithm optimization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810234041.5A CN108470444B (en) | 2018-03-21 | 2018-03-21 | A kind of city area-traffic big data analysis System and method for based on genetic algorithm optimization |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108470444A CN108470444A (en) | 2018-08-31 |
| CN108470444B true CN108470444B (en) | 2019-03-08 |
Family
ID=63264648
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810234041.5A Active CN108470444B (en) | 2018-03-21 | 2018-03-21 | A kind of city area-traffic big data analysis System and method for based on genetic algorithm optimization |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108470444B (en) |
Families Citing this family (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109214580B (en) * | 2018-09-06 | 2021-07-30 | 东南大学 | Commercial land layout optimization method based on traffic system performance |
| CN109272175A (en) * | 2018-11-15 | 2019-01-25 | 山东管理学院 | A kind of data collection system and method based on Urban Migrant network |
| CN111310294A (en) * | 2018-12-11 | 2020-06-19 | 深圳先进技术研究院 | Method for establishing and issuing evaluation index system of traffic management and control service index |
| CN109686091B (en) * | 2019-01-17 | 2020-07-14 | 中南大学 | Traffic flow filling algorithm based on multi-source data fusion |
| CN109756861A (en) * | 2019-01-31 | 2019-05-14 | 北京理工大学 | The node deployment method of heterogeneous sensor network under a kind of urban environment |
| CN109887267B (en) * | 2019-03-21 | 2021-04-30 | 华侨大学 | Conventional public transportation adjusting method for common line segment of rail transit |
| CN110223514B (en) * | 2019-06-06 | 2020-05-19 | 北京交通发展研究院 | Urban traffic running state analysis method and device and electronic equipment |
| CN110443403B (en) * | 2019-06-21 | 2023-08-25 | 上海市政交通设计研究院有限公司 | Optimization system and solving method for urban traffic microcirculation network |
| CN110491143A (en) * | 2019-08-25 | 2019-11-22 | 苏州布德泽信息科技有限公司 | A kind of current multi-target optimal design method of traffic |
| CN110909434B (en) * | 2019-10-11 | 2023-03-14 | 东南大学 | Urban public transport trunk line network design method under low-carbon guidance |
| CN111832873B (en) * | 2020-01-10 | 2022-05-06 | 吉林建筑大学 | Pipe diameter determining method and system for water supply pipeline in old urban area |
| CN111626480B (en) * | 2020-05-06 | 2023-06-09 | 杭州师范大学 | Resource optimization method for double-layer traffic network under dynamic routing |
| CN111915464B (en) * | 2020-07-04 | 2022-06-28 | 西南交通大学 | Subway interruption interval passenger connection model system and method based on consideration of conventional public transport network |
| CN112016213B (en) * | 2020-08-31 | 2021-09-03 | 哈尔滨工业大学 | Closed cell opening decision method considering environmental influence |
| CN111859717B (en) * | 2020-09-22 | 2020-12-29 | 北京全路通信信号研究设计院集团有限公司 | Method and system for minimizing regional multi-standard rail transit passenger congestion coefficient |
| CN112767688B (en) * | 2020-12-27 | 2022-05-06 | 交通运输部规划研究院 | Regional road network freight car flow distribution method based on traffic observation data |
| CN113299059B (en) * | 2021-04-08 | 2023-03-17 | 四川国蓝中天环境科技集团有限公司 | Data-driven road traffic control decision support method |
| CN113240175B (en) * | 2021-05-11 | 2024-02-02 | 北京百度网讯科技有限公司 | Distribution route generation method, distribution route generation device, storage medium, and program product |
| CN113409576B (en) * | 2021-06-24 | 2022-01-11 | 北京航空航天大学 | Bayesian network-based traffic network dynamic prediction method and system |
| CN114358418B (en) * | 2021-12-31 | 2024-06-07 | 中冶赛迪信息技术(重庆)有限公司 | Network planning system and method for low-carbon urban steel plant |
| CN114664112B (en) * | 2022-03-16 | 2023-09-12 | 广州小鹏汽车科技有限公司 | Garage-oriented parking space recommendation method, server and storage medium |
| CN115497306A (en) * | 2022-11-22 | 2022-12-20 | 中汽研汽车检验中心（天津）有限公司 | Speed interval weight calculation method based on GIS data |
| CN116682262B (en) * | 2023-06-14 | 2024-03-08 | 中国科学院地理科学与资源研究所 | Multi-mode traffic cost evaluation method |
| CN116543564B (en) * | 2023-07-07 | 2023-09-15 | 新唐信通(浙江)科技有限公司 | Optimization method and system applied to traffic control |
| CN117422602B (en) * | 2023-11-07 | 2024-06-07 | 北京城建设计发展集团股份有限公司 | Multi-dimensional fusion method and system for rail transit planning |
| CN117275260B (en) * | 2023-11-21 | 2024-02-02 | 山东理工大学 | Emergency control method for urban road intersection entrance road traffic accident |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101630440B (en) * | 2009-06-01 | 2011-03-16 | 北京交通大学 | Operation coordination optimizing method of common public transit connecting with urban rail transit and system thereof |
| CN102044149B (en) * | 2011-01-12 | 2012-08-08 | 北京交通大学 | City bus operation coordinating method and device based on time variant passenger flows |
| CN103942948B (en) * | 2014-04-10 | 2016-03-16 | 中南大学 | Based on the generation method of the urban public bus lines network of sectionally smooth join |
| CN106373384B (en) * | 2016-09-26 | 2018-10-09 | 福州大学 | Outlying district regular bus circuit Real-time Generation |
-
2018
- 2018-03-21 CN CN201810234041.5A patent/CN108470444B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN108470444A (en) | 2018-08-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108470444B (en) | A kind of city area-traffic big data analysis System and method for based on genetic algorithm optimization | |
| CN108647802B (en) | Anti-congestion method based on double-layer traffic network model | |
| CN114117700A (en) | Urban public transport network optimization research method based on complex network theory | |
| Zhao et al. | Dynamic path planning of emergency vehicles based on travel time prediction | |
| Zhang et al. | Optimal signal timing method of intersections based on bus priority | |
| Song et al. | Simultaneous optimization of 3D alignments and station locations for dedicated high‐speed railways | |
| CN108427273A (en) | A kind of Feedback Control Design method reducing traffic congestion phenomenon | |
| CN105427605A (en) | Method for efficiency calculation of setting of bus transit lane with consideration of transportation means transfer | |
| CN114037175B (en) | Large-scale public transportation network hierarchical optimization method based on multi-scale clustering | |
| CN104821086B (en) | Method for positioning low-efficient road section combination in large-scale traffic network | |
| CN116976045A (en) | Multi-target constraint simulation method for control subarea under non-congestion state | |
| CN115048576A (en) | Flexible recommendation method for airport passenger group travel mode | |
| CN112258856A (en) | Method for establishing regional traffic signal data drive control model | |
| Rui et al. | Simulated annealing algorithm for solving a bi-level optimization model on high-speed railway station location | |
| Li et al. | Traffic flow guidance and optimization of connected vehicles based on swarm intelligence | |
| Ma et al. | Bus-priority intersection signal control system based on wireless sensor network and improved particle swarm optimization algorithm | |
| Feng et al. | Urban Arterial Signal Coordination Using Spatial and Temporal Division Methods | |
| Yao et al. | A path planning model based on spatio-temporal state vector from vehicles trajectories | |
| Qing et al. | The forecast and the optimization control of the complex traffic flow based on the hybrid immune intelligent algorithm | |
| Zhai et al. | Traffic flow control of the intersection in urban traffic system under the environment of internet of vehicles. | |
| CN112991745A (en) | Traffic flow dynamic cooperative allocation method under distributed framework | |
| Feihu et al. | Emergency supplies research on crossing points of transport network based on genetic algorithm | |
| Zhang et al. | Region-based evaluation particle swarm optimization with dual solution libraries for real-time traffic signal timing optimization | |
| Ke et al. | Optimization of China’s freight transportation structure based on adaptive genetic algorithm under the background of carbon peak | |
| Luo et al. | Dynamic distribution and planning for traffic flow of the urban ecological road network based on blockchain technology |
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 |