CN107067091A - A kind of urban ecological land space planning model based on ant colony optimization algorithm - Google Patents
A kind of urban ecological land space planning model based on ant colony optimization algorithm Download PDFInfo
- Publication number
- CN107067091A CN107067091A CN201610885084.0A CN201610885084A CN107067091A CN 107067091 A CN107067091 A CN 107067091A CN 201610885084 A CN201610885084 A CN 201610885084A CN 107067091 A CN107067091 A CN 107067091A
- Authority
- CN
- China
- Prior art keywords
- ant
- space
- grid
- formula
- ecological
- 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
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 22
- 238000005457 optimization Methods 0.000 title claims abstract description 17
- 238000000034 method Methods 0.000 claims abstract description 20
- 230000008901 benefit Effects 0.000 claims abstract description 18
- 238000013461 design Methods 0.000 claims abstract description 9
- 230000008569 process Effects 0.000 claims abstract description 7
- 238000012821 model calculation Methods 0.000 claims abstract description 5
- 230000006870 function Effects 0.000 claims description 46
- 239000003016 pheromone Substances 0.000 claims description 40
- 238000009826 distribution Methods 0.000 claims description 34
- 239000011159 matrix material Substances 0.000 claims description 21
- 238000011160 research Methods 0.000 claims description 6
- 230000007704 transition Effects 0.000 claims description 6
- 239000003610 charcoal Substances 0.000 claims description 3
- 230000001427 coherent effect Effects 0.000 claims description 3
- 239000002131 composite material Substances 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- VMXUWOKSQNHOCA-UKTHLTGXSA-N ranitidine Chemical compound [O-][N+](=O)\C=C(/NC)NCCSCC1=CC=C(CN(C)C)O1 VMXUWOKSQNHOCA-UKTHLTGXSA-N 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 239000007787 solid Substances 0.000 claims description 3
- 238000000205 computational method Methods 0.000 claims 1
- 239000004744 fabric Substances 0.000 claims 1
- 238000012546 transfer Methods 0.000 claims 1
- 238000002474 experimental method Methods 0.000 abstract description 8
- 238000005259 measurement Methods 0.000 abstract 1
- 230000002776 aggregation Effects 0.000 description 8
- 238000004220 aggregation Methods 0.000 description 7
- 238000011161 development Methods 0.000 description 5
- 238000004088 simulation Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 230000007812 deficiency Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000005054 agglomeration Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010494 dissociation reaction Methods 0.000 description 1
- 230000005593 dissociations Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000004321 preservation Methods 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
- 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
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of urban ecological land space planning model based on ant colony optimization algorithm, mainly include the following steps that:A, planning problem description;B, structure object of planning function;C, model structure design;D, model calculation process;E, model measurement experiment, the space layout that the urban ecological land space planning model disclosed by the invention based on ant colony optimization algorithm can be reasonably to urban ecological land are configured, hence it is evident that improve urban ecological land ecological benefits and space intensivism.
Description
Technical field
The present invention relates to urban ecological land planing method field, specially a kind of city life based on ant colony optimization algorithm
State land used space planning model.
Background technology
In developing country, Process of Urbanization is usually associated with the drastically expansion of city space so that the mankind are for various
The exploitation of resource, using reaching unprecedented intensity, the contradiction of man and nature environment.In huge pressure development
More under fragile ecological condition, how effectively to safeguard and recover the ecosystems services in city, coordinate urban development with
Contradiction between ecological protection, the problem of having become urgent and real.Therefore, required urban ecological land is protected for dimension
Urban ecosystem health, improvement life of urban resident quality and urban sustainable development is held to play an important roll and meaning.City
City's ecological land is that the non-constructive land protected urban ecological environment and delimited is empty to realize the target of urban sustainable development
Between.Generally comprise:Agricultural protection area, water conservation district, ecological preservation area and city long term growth need the greening that controls every
From land for non-urban construction use such as bands.Urban ecological land planning is the important foundation and premise of urban ecological system protection, its
Matter is a kind of complicated NP-hard combinatorial optimization problems, not only to ensure the quantity of planning index, it is also to be ensured that ecological benefits,
A series of extraterrestrial targets such as intensivism and integrality and urban development space and layout constraint.
The content of the invention
It is an object of the invention to provide a kind of urban ecological land space planning model based on ant colony optimization algorithm, with
The problem of solving to propose in above-mentioned background technology.
To achieve the above object, the present invention provides following technical scheme:A kind of urban ecology based on ant colony optimization algorithm
Land used space planning model, it is characterised in that:Mainly include the following steps that:
A, planning problem description:Including herein below:
A, urban ecological land benefit are general by indexs such as green cover degree, solid charcoal amount, green space position, landscape configurations
Influence;And Ecological Suitability research is the important foundation and premise of ecological benefits, both have closely contact;Using ecology
Suitability represents ecological benefits, ecological benefits problem is translated into acquisition research area Ecological Suitability sum maximized and ask
Topic, i.e. the target of ecological land planning is that as far as possible many Ecological Suitabilities are obtained under the conditions of certain area, i.e.,In formula, fecoGrid cell Ecological Suitability function is represented, k is k-th of grid cell, and m is grid cell sum;
B, urban ecological land need to meet:Maximum space compactness, i.e. maxfeco;minfdistRepresent it is minimum it is closest away from
From fcpRepresentation space compactness function, fdistRepresent closest distance function;
B, structure object of planning function:Unicity composite objective function is set up according to space constraints, the function representation
Urban ecological land distribution under multiple target space constraints, sets up object function as follows:
In formula, maxfgoalObject function maximization is represented,Represent ant
The average Ecological Suitability of ant, fdistRepresent closest space length, fciRepresent compactness index.Work as fdistDuring less than 1, sample
Coherent condition is put into, works as fdistDuring close to 0, sample point is assembled close to perfect, (0,1] between, work as fciIt is bigger, illustrate space
Form is compacter, works as fciDuring close to 1, spatial shape is up to most compact condition, and kc, kd, ke represent the tune of each factor respectively
Save coefficient;
C, model structure design:Comprise the following steps:
A, definition ant structure:Ant Array for structural body Ant [] is defined, the attribute information of ant is stored, including:Ant
Coordinate position, ant fitness value etc., after each iteration, ant Array for structural body is with the dynamic fresh information of taboo matrix;
B, taboo list and taboo matrix design:Taboo list Taboo is an important mechanisms of ant group algorithm;Taboo is recorded
Grid positions shared by ant colony, the matrix size be grid space ranks number, the matrix can realize ant taboo position with
The fast mapping of grid space, makes ant clearly to avoid position without traversal taboo list again in Searching Resolution Space and calculating
Put, improve search efficiency;The position that matrix stores ant according to ant taboo list in grid space is avoided, being represented with " -1 " should
Position is occupied by ant;
C, locus selection strategy:Ant is calculated to the probability of each optional grid by transition probability formula, turned
Move new probability formula as follows
In formulaRepresent that ant in kth time iteration, selects the probability of grid space position [i, j];τij(t) the is represented
The pheromones left in t iteration at position [i, j];nijThe heuristic information on position [i, j] is represented, n is defined hereinij
=feco(i, j);A is pheromones heuristic greedy method, represents that ant selects ant next time in the pheromones that grid space has been accumulated
Select the grid positions that the role of selection is tended to select pheromone concentration high;β is expected heuristic value, allowedkFor
Represent ant allows the grid space of selection;
D, Pheromone update expanding policy:The renewal of pheromones is expanded into each grid point location to grid space,
The Pheromone update of [i, j];Pheromones to whole grid space after each circulation are updated, such as following formula:In formula:τij(t+1) information of the grid space position [i, j] after updating is represented
Element, τij(t) pheromones of the grid space position [i, j] before updating are represented,In this circulation on grid [i, j]
Pheromones increment, ρ ∈ (0,1) represent pheromones volatility coefficient;
D, model calculation process:
Step1;Ant population and each parameter are initialized, taboo list and taboo matrix is set up, and calculate initial target function
Value;
Step2:Cycle-index Nc←Nc+1;
Step3:Ant number k ← k+1;
Step4:Calculate ant relative adaptability value, according to transition probability formula select k-th of ant grid positions [i,
J], and [i, j] ∈ alloWedk;
Step5:Assess object functionIf,Using greedy algorithm, Simultaneously
Update taboo list, taboo matrix and ant object array;
Step6:If ant k < M (M is ant total amount), jump to Step3, otherwise perform Step7.
Step7:Obtain current goal function FG(t+1), according to Pheromone update formula, grid space pheromones are updated;
Step8:If meeting termination condition, i.e., when cycle-index is Nc≤NcMax, then circulation terminates, and output grid is empty
Between cluster result.Otherwise, Step2 is jumped to, until meeting termination condition.
It is preferred that, herein below is also included in the step B:
A, urban ecology suitability:According to Ecological Suitability conceptual model, the expression formula of urban ecology suitability is:feco
=W1n+W2s+W3In p, formula, n, s, p represent natural factor, the social factor, the ecological protection factor, W respectively1、W2、W3Represent respective
Weight;
B, closest range index:, can be with sample prescription for point target in the distribution characteristics and correlation in space
Points average is deteriorated, the method such as minimum distance average, dot density distance function is measured between point, according to actual observation value with it is empty
Between theoretical value under distribution occasion compare, judge point general layout is uniform, aggregation, or random distribution;Because ant is in grid
Space representation is grid point, and the ant colony being made up of it forms Spatial Distribution Pattern a little in grid space, and grid extension is calculated
Method is as follows:
fdistIn=d (nn)/d (ran), formula, d (nn) is closest distance;D (ran) is the reason under the conditions of random distribution
By average distance;Work as fdistDuring < 1, sample point is in gather distribution;Work as fdistWhen=0, sampling point is assembled in perfect;Work as fdist> 1
When, sample point is in dispersed distribution;Formula
In formula, N is sample point number, i.e. ant colony space size;dijFor point to point of distance;min(dij) it is to most
The distance of neighbor point;FormulaIn formula, A is survey region area, due to fdist∈ [0, ∞) when, exponential quantity
It is bigger, illustrate that space clustering degree is higher;Using Logit functions, the interval of (0,1) is mapped that to, now formulaIn formula, fmod_distRevised closest range index is represented, is by Minimum square error now
C, spaces compact degree:Spaces compact degree is a kind of important indicator for being used to measure atural object shape information, and formula is represented
It is as follows:Wherein, ρ represents the girth of patch, and A represents the area of patch, fciRepresentation space compactness, between 0-1
Between, its value is bigger, and the spatial shape of patch is compacter, therefore object function is revised as
Compared with prior art, the beneficial effects of the invention are as follows:The present invention is directed to the deficiency of Traditional Space planing method, carries
Go out the urban ecological land space planning model based on ant colony optimization algorithm.Study and plan is avoided to the space of ant colony optimization algorithm
Slightly, selection strategy is improved, it is contemplated that the ecological benefits and space intensivism of urban ecological land, in object of planning function
Ecological Suitability, dimensional compactness and closest range index are introduced, and designs the raster symbol-base method of closest range index;
Urban ecological land space planning model disclosed by the invention based on ant colony optimization algorithm can be used reasonably urban ecology
The space layout on ground is configured, hence it is evident that improve urban ecological land ecological benefits and space intensivism.
Brief description of the drawings
Fig. 1 is model calculation flow chart of the invention;
Fig. 2 is constant grid space ant Distribution Pattern simulation drawing of the invention;
Fig. 3 is the ant Distribution Pattern simulation drawing in the cross grid space of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of protection of the invention.
Referring to Fig. 1, the present invention provides a kind of technical scheme:A kind of urban ecological land based on ant colony optimization algorithm is empty
Between plan model, mainly include the following steps that:
A, planning problem description:Including herein below:
A, urban ecological land benefit are general by indexs such as green cover degree, solid charcoal amount, green space position, landscape configurations
Influence;And Ecological Suitability research is the important foundation and premise of ecological benefits, both have closely contact;Using ecology
Suitability represents ecological benefits, ecological benefits problem is translated into acquisition research area Ecological Suitability sum maximized and ask
Topic, i.e. the target of ecological land planning is that as far as possible many Ecological Suitabilities are obtained under the conditions of certain area, i.e.,In formula, fecoGrid cell Ecological Suitability function is represented, k is k-th of grid cell, and m is that grid cell is total
Number;
B, urban ecological land need to meet:Maximum space compactness, i.e. maxfeco;minfdistRepresent it is minimum it is closest away from
From fcpRepresentation space compactness function, fdistRepresent closest distance function;
B, structure object of planning function:Unicity composite objective function is set up according to space constraints, the function representation
Urban ecological land distribution under multiple target space constraints, sets up object function as follows:
In formula, maxfgoalObject function maximization is represented,Represent ant
The average Ecological Suitability of ant, fdistRepresent closest space length, fciRepresent compactness index.Work as fdistDuring less than 1, sample
Coherent condition is put into, works as fdistDuring close to 0, sample point is assembled close to perfect, (0,1] between, work as fciIt is bigger, illustrate space
Form is compacter, works as fciDuring close to 1, spatial shape is up to most compact condition, and kc, kd, ke represent the tune of each factor respectively
Save coefficient;
C, model structure design:Comprise the following steps:
A, definition ant structure:Ant Array for structural body Ant [] is defined, the attribute information of ant is stored, including:Ant
Coordinate position, ant fitness value etc., after each iteration, ant Array for structural body is with the dynamic fresh information of taboo matrix;
B, taboo list and taboo matrix design:Taboo list Taboo is an important mechanisms of ant group algorithm;Taboo is recorded
Grid positions shared by ant colony, the matrix size be grid space ranks number, the matrix can realize ant taboo position with
The fast mapping of grid space, makes ant clearly to avoid position without traversal taboo list again in Searching Resolution Space and calculating
Put, improve search efficiency;The position that matrix stores ant according to ant taboo list in grid space is avoided, being represented with " -1 " should
Position is occupied by ant;
C, locus selection strategy:Ant is calculated to the probability of each optional grid by transition probability formula, turned
Move new probability formula as follows
In formulaRepresent that ant in kth time iteration, selects the probability of grid space position [i, j];τij(t) the is represented
The pheromones left in t iteration at position [i, j];nijThe heuristic information on position [i, j] is represented, n is defined hereinij
=feco(i, j);A is pheromones heuristic greedy method, represents that ant selects ant next time in the pheromones that grid space has been accumulated
Select the grid positions that the role of selection is tended to select pheromone concentration high;β is expected heuristic value, allowedkFor
Represent ant allows the grid space of selection;
D, Pheromone update expanding policy:The renewal of pheromones is expanded into each grid point location to grid space,
The Pheromone update of [i, j];Pheromones to whole grid space after each circulation are updated, such as following formula:In formula:τij(t+1) information of the grid space position [i, j] after updating is represented
Element, τij(t) pheromones of the grid space position [i, j] before updating are represented,In this circulation on grid [i, j]
Pheromones increment, ρ ∈ (0,1) represent pheromones volatility coefficient;
D, model calculation process:
Step1;Ant population and each parameter are initialized, taboo list and taboo matrix is set up, and calculate initial target function
Value;
Step2:Cycle-index Nc←Nc+1;
Step3:Ant number k ← k+1;
Step4:Calculate ant relative adaptability value, according to transition probability formula select k-th of ant grid positions [i,
J], and [i, j] ∈ allowedk;
Step5:Assess object functionIf,Using greedy algorithm, More simultaneously
New taboo list, taboo matrix and ant object array;
Step6:If ant k < M (M is ant total amount), jump to Step3, otherwise perform Step7.
Step7:Obtain current goal function FG(t+1), according to Pheromone update formula, grid space pheromones are updated;
Step8:If meeting termination condition, i.e., when cycle-index is Nc≤NcMax, then circulation terminates, and output grid is empty
Between cluster result.Otherwise, Step2 is jumped to, until meeting termination condition.
In the present embodiment, herein below is also included in step B:
A, urban ecology suitability:According to Ecological Suitability conceptual model, the expression formula of urban ecology suitability is:feco
=W1n+W2s+W3In p, formula, n, s, p represent natural factor, the social factor, the ecological protection factor, W respectively1、W2、W3Represent respective
Weight;
B, closest range index:, can be with sample prescription for point target in the distribution characteristics and correlation in space
Points average is deteriorated, the method such as minimum distance average, dot density distance function is measured between point, according to actual observation value with it is empty
Between theoretical value under distribution occasion compare, judge point general layout is uniform, aggregation, or random distribution;Because ant is in grid
Space representation is grid point, and the ant colony being made up of it forms Spatial Distribution Pattern a little in grid space, and grid extension is calculated
Method is as follows:
fdistIn=d (nn)/d (ran), formula, d (nn) is closest distance;D (ran) is the reason under the conditions of random distribution
By average distance;Work as fdistDuring < 1, sample point is in gather distribution;Work as fdistWhen=0, sampling point is assembled in perfect;Work as fdist> 1
When, sample point is in dispersed distribution;Formula
In formula, N is sample point number, i.e. ant colony space size;dijFor point to point of distance;min(dij) it is to most
The distance of neighbor point;FormulaIn formula, A is survey region area, due to fdist∈ [0, ∞) when, exponential quantity
It is bigger, illustrate that space clustering degree is higher;Using Logit functions, the interval of (0,1) is mapped that to, now formulaIn formula, fmod_distRevised closest range index is represented, is by Minimum square error now
C, spaces compact degree:Spaces compact degree is a kind of important indicator for being used to measure atural object shape information, and formula is represented
It is as follows:Wherein, ρ represents the girth of patch, and A represents the area of patch, fciRepresentation space compactness, between 0-1
Between, its value is bigger, and the spatial shape of patch is compacter, therefore object function is revised as
Experimental example one:
1st group of data are constant raster datas, the space distribution situation for testing ant colony random aggregation.Object function point
Other considers closest range index (NNI) and spaces compact degree index (CI).Test under the conditions of constant grid homogeneous space,
The performance impact and exponential relationship of each exponent pair ant accumulation shape.It is 500 to set ant quantity, and parameter see the table below institute
Show.Simulation process and result are shown in Fig. 2, in the case of parameter one, model iteration 1500 times, and NNI indexes are that 0.818, CI indexes are
0.207.In the case of parameter two, model iteration 1500 times, NNI indexes are that 0.816, CI indexes are 0.223.
Parameter | First group of parameter | Second group of parameter |
Closest range index | 1 | 0. |
Spaces compact degree index | 0 | 1 |
Pheromones intensity | 50 | 50 |
Initial information amount | 20 | 20 |
Volatility coefficient | 0.3 | 0.3 |
The information factor | 4 | 4 |
Expecting factor | 4 | 4 |
Iterations | 1500 | 1500 |
It is as follows to one interpretation of result of experiment:
1st, under homogeneous grid space, due to ant, suffered heuristic information is identical in all directions, ant space clustering
Distribution is main to be determined by legacy information element, in fig. 2 it can be seen that the space clustering distribution under two groups of parameters is entirely different.Can
See, ant distribution is demonstrated by very strong randomness under homogeneous grid space.
2nd, in the case where considering NNI exponential cases, aggregation patch is more, and NNI indexes are 0.368, in gathering distribution.Only considering
Under CI exponential cases, aggregation block is less, and CI indexes are 0.223, and Distribution Pattern is more concentrated.Illustrate that NNI indexes are advantageously formed
The space clustering Distribution Pattern more disperseed, CI indexes advantageously form the space clustering Distribution Pattern more concentrated.
3rd, under the conditions of homogeneous space, in the case where considering NNI indexes, NNI Exponential Convergence Speeds are very fast, and curve is more steady
It is fixed.And under CI indexes, CI Exponential Convergence Speeds are slower, convergence curve change is more unstable.
Experimental example two:
2nd group of data are used for the performance that test model finds global approximate optimal solution, and analysis NNI indexes and CI exponent pairs are empty
Between Distribution Pattern formed in produced influence, the cross region of test data and have 270 grids.Therefore, ant number is set
Measure as 270, arrange parameter following table.The simulation process and result of experiment two are as shown in Figure 3.
1st group of Experiment Parameter:Model considers Ecological Suitability weight, and iterations is 1500 times, in 320 times or so mesh
Offer of tender number curve, which is shown, basically reaches convergence state, and target function value reaches 0.9961, is in close proximity to 1.0.This explanation 270
Ant almost all is fallen into the grid of cross region.NNI exponential curves also basically reach convergence shape 520 times or so in iteration
State.CI Exponential Convergence Speeds are slower, just basically reach convergence 1400 times or so in iteration, its curve state fluctuation in left and right is brighter
Aobvious, final exponential quantity reaches 0.4 or so.
2nd group of Experiment Parameter:Model considers Ecological Suitability and NNI indexes.Model iteration 1500 times.It was found that ant
In addition to cross shape has been formed centrally within, ant is distributed on the outside of it, ant is closer to central area, aggregation extent
It is higher.Model 880 times or so in iteration, object function has basically reached convergence state, CI indexes now maintain 0.1
Reduced levels.
3rd group of Experiment Parameter:Model considers ecological suitability degree and CI indexes.Model iteration 3500 times, in iteration 580
Secondary or so object function curve basically reaches convergence state.Under Ecological Suitability and the constraint of CI indexes, ant forms one
Cross shape that is compacter and shrinking.Object function is about in iteration 800 times or so, and curve reaches convergence state, target
Functional value reaches about 0.6.
Interpretation of result to experiment two is as follows:
1st, when model only considers Ecological Suitability, ant almost all falls into cross regional extent, shows stronger complete
Office's optimal value property found.
2nd, NNI indexes and CI indexes have a significant impact to spatial framework
3rd, structure multiple objective function is combined to NNI indexes and CI indexes, it is possible to achieve the concentration of enhancing central area
Aggregation, can also take into account the scatter-gather general layout of neighboring area.
Two groups of experiments of the above show that model shows excellent space clustering effect and global optimizing ability, are referred to by different
Array, which is closed, can form a variety of Spatial Agglomeration forms, to solve the problems, such as that it is real that Ur-ban space planning provides flexible, effective model
Existing means.
The present invention is directed to the deficiency of Traditional Space planing method, proposes that the urban ecological land based on ant colony optimization algorithm is empty
Between plan model.Study space taboo strategy, selection strategy to ant colony optimization algorithm to be improved, it is contemplated that urban ecology is used
The ecological benefits and space intensivism on ground, in object of planning function introduce Ecological Suitability, dimensional compactness and it is closest away from
Dissociation index, and design the raster symbol-base method of closest range index;City disclosed by the invention based on ant colony optimization algorithm
Ecological land space planning model can be reasonably to urban ecological land space layout configure, hence it is evident that improve city
Ecological land ecological benefits and space intensivism.
Although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
A variety of changes, modification can be carried out to these embodiments, replace without departing from the principles and spirit of the present invention by understanding
And modification, the scope of the present invention is defined by the appended.
Claims (2)
1. a kind of urban ecological land space planning model based on ant colony optimization algorithm, it is characterised in that:Mainly include following
Step:
A, planning problem description:Including herein below:
The general shadow by indexs such as green cover degree, solid charcoal amount, green space position, landscape configurations of a, urban ecological land benefit
Ring;And Ecological Suitability research is the important foundation and premise of ecological benefits, both have closely contact;Using ecological suitable
Property represent ecological benefits, ecological benefits problem is translated into acquisition research area Ecological Suitability sum maximization problems, i.e.
The target of ecological land planning is that as far as possible many Ecological Suitabilities are obtained under the conditions of certain area, i.e.,In formula,
fecoGrid cell Ecological Suitability function is represented, k is k-th of grid cell, and m is grid cell sum;
B, urban ecological land need to meet:Maximum space compactness, i.e. maxfeco;minfdistRepresent minimum closest distance, fcp
Representation space compactness function, fdistRepresent closest distance function;
B, structure object of planning function:Unicity composite objective function is set up according to space constraints, many mesh of the function representation
The urban ecological land distribution under space constraints is marked, object function is set up as follows:
In formula, maxfgoalObject function maximization is represented,Represent the average Ecological Suitability of ant, fdistRepresent most adjacent
Near space distance, fciRepresent compactness index.Work as fdistDuring less than 1, sample point works as f into coherent conditiondistDuring close to 0, sample
This point is assembled close to perfect, (0,1] between, work as fciIt is bigger, illustrate that spatial shape is compacter, work as fciDuring close to 1, space
Form is up to most compact condition, and kc, kd, ke represent the adjustment factor of each factor respectively;
C, model structure design:Comprise the following steps:
A, definition ant structure:Ant Array for structural body Ant [] is defined, the attribute information of ant is stored, including:Ant coordinate
Position, ant fitness value etc., after each iteration, ant Array for structural body is with the dynamic fresh information of taboo matrix;
B, taboo list and taboo matrix design:Taboo list Taboo is an important mechanisms of ant group algorithm;Taboo records ant colony
Shared grid positions, the matrix size is the ranks number of grid space, and the matrix can realize ant taboo position and grid
The fast mapping in space, makes ant clearly to avoid position without traversal taboo list again in Searching Resolution Space and calculating,
Improve search efficiency;Avoid the position that matrix stores ant according to ant taboo list in grid space, the position being represented with " -1 "
Put occupied by ant;
C, locus selection strategy:Ant is calculated to the probability of each optional grid by transition probability formula, transfer is generally
Rate formula is as follows
In formulaRepresent that ant in kth time iteration, selects the probability of grid space position [i, j];τij(t) represent the t times
The pheromones left in iteration at position [i, j];nijThe heuristic information on position [i, j] is represented, n is defined hereinij=
feco(i, j);α is pheromones heuristic greedy method, represents that ant selects ant next time in the pheromones that grid space has been accumulated
The grid positions for selecting pheromone concentration high are tended in the role of selection;β is expected heuristic value, allowedkFor table
That shows ant allows the grid space of selection;
D, Pheromone update expanding policy:The renewal of pheromones is expanded into each grid point location to grid space, [i, j]
Pheromone update;Pheromones to whole grid space after each circulation are updated, such as following formula:In formula:τij(t+1) information of the grid space position [i, j] after updating is represented
Element, τij(t) pheromones of the grid space position [i, j] before updating are represented,In this circulation on grid [i, j]
Pheromones increment, ρ ∈ (0,1) represent pheromones volatility coefficient;
D, model calculation process:
Step1;Ant population and each parameter are initialized, taboo list and taboo matrix is set up, and calculate initial target functional value;
Step2:Cycle-index Nc←Nc+1;
Step3:Ant number k ← k+1;
Step4:Ant relative adaptability value is calculated, the grid positions [i, j] of k-th of ant are selected according to transition probability formula,
And [i, j] ∈ allowedk;
Step5:Assess object functionIf,Using greedy algorithm,More simultaneously
New taboo list, taboo matrix and ant object array;
Step6:If ant k < M (M is ant total amount), jump to Step3, otherwise perform Step7;
Step7:Obtain current goal function FG(t+1), according to Pheromone update formula, grid space pheromones are updated;
Step8:If meeting termination condition, i.e., when cycle-index is Nc≤NcMax, then circulation terminates, and output grid space
Cluster result.Otherwise, Step2 is jumped to, until meeting termination condition.
2. a kind of urban ecological land space planning model based on ant colony optimization algorithm according to claim 1, it is special
Levy and be:Also include herein below in the step B:
A, urban ecology suitability:According to Ecological Suitability conceptual model, the expression formula of urban ecology suitability is:feco=W1n+
W2s+W3In p, formula, n, s, p represent natural factor, the social factor, the ecological protection factor, W respectively1、W2、W3Represent respective weight;
B, closest range index:For point target in the distribution characteristics and correlation in space, it can be counted with sample prescription
Average is deteriorated, the method such as minimum distance average, dot density distance function is measured between point, according to actual observation value and equal space point
Theoretical value under the conditions of cloth compares, and what general layout was put in judgement is uniform, assembles, or random distribution;Because ant is in grid space
Grid point is expressed as, the ant colony being made up of it forms Spatial Distribution Pattern a little, grid extension computational methods in grid space
It is as follows:
fDist=In d (nn)/d (ran), formula, d (nn) is closest distance;D (ran) is that the theory under the conditions of random distribution is averaged
Distance;Work as fdistDuring < 1, sample point is in gather distribution;Work as fdistWhen=0, sampling point is assembled in perfect;Work as fdistDuring > 1, sample
Point is in dispersed distribution;Formula
In formula, N is sample point number, i.e. ant colony space size;dijFor point to point of distance;min(dij) it is to closest
The distance of point;FormulaIn formula, A is survey region area, due to fdist∈ [0, ∞) when, exponential quantity is got over
Greatly, illustrate that space clustering degree is higher;Using Logit functions, the interval of (0,1) is mapped that to, now formulaIn formula, fmod_distRevised closest range index is represented, now by Minimum square error
For
C, spaces compact degree:Spaces compact degree is a kind of important indicator for being used to measure atural object shape information, and formula is expressed as follows:Wherein, ρ represents the girth of patch, and A represents the area of patch, fciRepresentation space compactness, between 0-1,
Its value is bigger, and the spatial shape of patch is compacter, therefore object function is revised as
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610885084.0A CN107067091B (en) | 2016-10-11 | 2016-10-11 | Urban ecological land space planning model based on ant colony optimization algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610885084.0A CN107067091B (en) | 2016-10-11 | 2016-10-11 | Urban ecological land space planning model based on ant colony optimization algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107067091A true CN107067091A (en) | 2017-08-18 |
CN107067091B CN107067091B (en) | 2022-01-14 |
Family
ID=59616924
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610885084.0A Active CN107067091B (en) | 2016-10-11 | 2016-10-11 | Urban ecological land space planning model based on ant colony optimization algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107067091B (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107730133A (en) * | 2017-10-25 | 2018-02-23 | 哈尔滨工业大学 | A kind of energy landscape planing method |
CN108876003A (en) * | 2018-05-04 | 2018-11-23 | 河南大学 | A kind of method of determining city future mode of extension |
CN109598056A (en) * | 2018-11-30 | 2019-04-09 | 华南理工大学 | Measurement Method, system and the storage medium of town site form compactness |
CN112035584A (en) * | 2020-08-28 | 2020-12-04 | 北京清华同衡规划设计研究院有限公司 | Space planning scene simulation method and system |
CN112348239A (en) * | 2020-10-27 | 2021-02-09 | 中国建筑科学研究院有限公司 | Method for predicting intensity of artificial green land on heat island of alleviation city |
CN112819033A (en) * | 2021-01-12 | 2021-05-18 | 华中科技大学 | Rural settlement classification method and system |
CN113051638A (en) * | 2021-02-19 | 2021-06-29 | 中国科学院空天信息创新研究院 | Building height optimal configuration method and device |
CN113065806A (en) * | 2021-04-30 | 2021-07-02 | 河南大学 | Urbanization element flow distribution method based on neighborhood and grid |
CN114329743A (en) * | 2022-03-03 | 2022-04-12 | 如你所视(北京)科技有限公司 | House type optimization method, device and storage medium |
CN115329591A (en) * | 2022-08-29 | 2022-11-11 | 华中科技大学 | City spatial pattern design method, system and computer storage medium |
CN115602259A (en) * | 2022-09-27 | 2023-01-13 | 常州大学(Cn) | Method and system for researching influence of land utilization change of biomass liquid fuel on environment |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101118609A (en) * | 2007-09-13 | 2008-02-06 | 北京航空航天大学 | Cloud model microenvironment self-adapting ant colony optimizing method for resolving large scale TSP |
US20130004934A1 (en) * | 2011-06-05 | 2013-01-03 | Brett William Oliver | Method of organizing the populace by establishing neighborhood social-safety clubs in every neighborhood and a city-wide communications network that will then allow for the establishment of a city-wide evacuation program |
-
2016
- 2016-10-11 CN CN201610885084.0A patent/CN107067091B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101118609A (en) * | 2007-09-13 | 2008-02-06 | 北京航空航天大学 | Cloud model microenvironment self-adapting ant colony optimizing method for resolving large scale TSP |
US20130004934A1 (en) * | 2011-06-05 | 2013-01-03 | Brett William Oliver | Method of organizing the populace by establishing neighborhood social-safety clubs in every neighborhood and a city-wide communications network that will then allow for the establishment of a city-wide evacuation program |
Non-Patent Citations (5)
Title |
---|
JI-YUN BAI等: "Improved Ant Colony Algorithm with Emphasis on Data Processing and Dynamic City Choice", 《2009 INTERNATIONAL CONFERENCE ON INFORMATION ENGINEERING AND COMPUTER SCIENCE》 * |
孟晓琳 等: "基于信息素更新和挥发因子调整的改进蚁群算", 《成都大学学报(自然科学版)》 * |
尚正永: "《城市空间形态演变的多尺度研究》", 30 September 2015, 东南大学出版社 * |
王海鹰 等: "广州市城市生态用地空间冲突与生态安全隐患情景分析", 《自然资源学报》 * |
秦昆: "《GIS空间分析理论与方法》", 31 March 2010, 武汉大学出版社 * |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107730133A (en) * | 2017-10-25 | 2018-02-23 | 哈尔滨工业大学 | A kind of energy landscape planing method |
CN108876003A (en) * | 2018-05-04 | 2018-11-23 | 河南大学 | A kind of method of determining city future mode of extension |
CN109598056A (en) * | 2018-11-30 | 2019-04-09 | 华南理工大学 | Measurement Method, system and the storage medium of town site form compactness |
CN112035584A (en) * | 2020-08-28 | 2020-12-04 | 北京清华同衡规划设计研究院有限公司 | Space planning scene simulation method and system |
CN112035584B (en) * | 2020-08-28 | 2024-04-12 | 北京清华同衡规划设计研究院有限公司 | Space planning scenario simulation method and system |
CN112348239A (en) * | 2020-10-27 | 2021-02-09 | 中国建筑科学研究院有限公司 | Method for predicting intensity of artificial green land on heat island of alleviation city |
CN112819033A (en) * | 2021-01-12 | 2021-05-18 | 华中科技大学 | Rural settlement classification method and system |
CN113051638B (en) * | 2021-02-19 | 2023-12-08 | 中国科学院空天信息创新研究院 | Building height optimal configuration method and device |
CN113051638A (en) * | 2021-02-19 | 2021-06-29 | 中国科学院空天信息创新研究院 | Building height optimal configuration method and device |
CN113065806A (en) * | 2021-04-30 | 2021-07-02 | 河南大学 | Urbanization element flow distribution method based on neighborhood and grid |
CN113065806B (en) * | 2021-04-30 | 2022-10-28 | 河南大学 | Urbanization element flow distribution method based on neighborhood and grid |
CN114329743A (en) * | 2022-03-03 | 2022-04-12 | 如你所视(北京)科技有限公司 | House type optimization method, device and storage medium |
CN114329743B (en) * | 2022-03-03 | 2022-06-07 | 如你所视(北京)科技有限公司 | House type optimization method, device and storage medium |
CN115329591B (en) * | 2022-08-29 | 2023-06-20 | 华中科技大学 | Urban space pattern design method, system and computer storage medium |
CN115329591A (en) * | 2022-08-29 | 2022-11-11 | 华中科技大学 | City spatial pattern design method, system and computer storage medium |
CN115602259A (en) * | 2022-09-27 | 2023-01-13 | 常州大学(Cn) | Method and system for researching influence of land utilization change of biomass liquid fuel on environment |
Also Published As
Publication number | Publication date |
---|---|
CN107067091B (en) | 2022-01-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107067091A (en) | A kind of urban ecological land space planning model based on ant colony optimization algorithm | |
CN104239556B (en) | Adaptive trajectory predictions method based on Density Clustering | |
Wang et al. | Balancing risk and cost in fuzzy economic dispatch including wind power penetration based on particle swarm optimization | |
CN103136603B (en) | Intelligent land utilization layout optimal allocation method | |
Yao et al. | Rural spatial restructuring in ecologically fragile mountainous areas of southern China: A case study of Changgang Town, Jiangxi Province | |
Zhou et al. | Relationship between urban landscape structure and land surface temperature: Spatial hierarchy and interaction effects | |
CN103747419B (en) | A kind of indoor orientation method based on signal strength difference and dynamic linear interpolation | |
CN110334391A (en) | A kind of various dimensions constraint wind power plant collection electric line automatic planning | |
Yang et al. | An improved artificial bee colony algorithm for optimal land-use allocation | |
Gong et al. | Spatiotemporal dynamics in the cultivated and built-up land of Guangzhou: Insights from zoning | |
Liu et al. | Regional land-use allocation with a spatially explicit genetic algorithm | |
CN105447570B (en) | Pir sensor layout method in a kind of smart home followed the trail of for personnel positions | |
CN103136707B (en) | A kind of Land_use change layered configuration method | |
Huang et al. | Simulating urban growth affected by national and regional land use policies: Case study from Wuhan, China | |
Cheng et al. | The effects of urbanization on ecosystem services for biodiversity conservation in southernmost Yunnan Province, Southwest China | |
CN103473465B (en) | Land resource spatial configuration optimal method based on multiple target artificial immune system | |
CN106162663A (en) | A kind of based on the sensing node covering method improving ant colony algorithm | |
CN101763601A (en) | Land use partition method based on tabu search algorithm | |
CN106651017A (en) | Method for site selection of land consolidation project based on ant colony optimization algorithm | |
CN106658570A (en) | Mobile sink information collection path constructing method based on secondary grid partitioning | |
CN114529129A (en) | Low-carbon economical improvement method for urban green land planning design scheme | |
Luo et al. | Understanding the relationship between 2D/3D variables and land surface temperature in plain and mountainous cities: relative importance and interaction effects | |
CN114217609A (en) | Intelligent partitioning method for power grid line corridor zone meeting multiple constraint conditions | |
CN115841042A (en) | Urban ecological toughness three-dimensional evaluation method constructed based on toughness theory | |
CN110264010A (en) | Novel rural area electric power saturation load forecasting method |
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 |