CN106909986A - A kind of soil re-development plan method of use ant colony multiple target layout optimization model - Google Patents
A kind of soil re-development plan method of use ant colony multiple target layout optimization model Download PDFInfo
- Publication number
- CN106909986A CN106909986A CN201710034752.3A CN201710034752A CN106909986A CN 106909986 A CN106909986 A CN 106909986A CN 201710034752 A CN201710034752 A CN 201710034752A CN 106909986 A CN106909986 A CN 106909986A
- Authority
- CN
- China
- Prior art keywords
- land
- ant
- pheromones
- optimization
- target
- 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
- 238000005457 optimization Methods 0.000 title claims abstract description 139
- 238000000034 method Methods 0.000 title claims abstract description 70
- 239000002689 soil Substances 0.000 title claims abstract description 39
- 238000011161 development Methods 0.000 title claims abstract description 22
- 239000003016 pheromone Substances 0.000 claims abstract description 116
- 230000008859 change Effects 0.000 claims abstract description 38
- 230000008569 process Effects 0.000 claims abstract description 21
- 238000012804 iterative process Methods 0.000 claims abstract description 11
- 238000011156 evaluation Methods 0.000 claims abstract description 9
- 238000009825 accumulation Methods 0.000 claims abstract description 8
- 230000008901 benefit Effects 0.000 claims description 17
- 230000008020 evaporation Effects 0.000 claims description 12
- 238000001704 evaporation Methods 0.000 claims description 12
- 238000000205 computational method Methods 0.000 claims description 11
- 230000007704 transition Effects 0.000 claims description 10
- 230000007812 deficiency Effects 0.000 abstract description 5
- 241000257303 Hymenoptera Species 0.000 description 6
- 238000006243 chemical reaction Methods 0.000 description 5
- 238000013461 design Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 230000003472 neutralizing effect Effects 0.000 description 3
- 238000013139 quantization Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000009024 positive feedback mechanism Effects 0.000 description 2
- 230000002028 premature Effects 0.000 description 2
- 238000010025 steaming Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 244000144992 flock Species 0.000 description 1
- 238000007429 general method Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000011017 operating method Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 238000002922 simulated annealing Methods 0.000 description 1
- GOLXNESZZPUPJE-UHFFFAOYSA-N spiromesifen Chemical compound CC1=CC(C)=CC(C)=C1C(C(O1)=O)=C(OC(=O)CC(C)(C)C)C11CCCC1 GOLXNESZZPUPJE-UHFFFAOYSA-N 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
- 238000005303 weighing Methods 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
- G06Q50/16—Real estate
- G06Q50/165—Land development
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Development Economics (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)
- Catching Or Destruction (AREA)
Abstract
The invention discloses a kind of soil re-development plan method of use ant colony multiple target layout optimization model, including:Multiple optimization aims and constraint restrictive condition are set;Initialization algorithm parameter, the algorithm parameter includes:Iterations, ant quantity, the pheromones cube of each ant;Land_use change situation in initialization predeterminable area is the land use pattern for initializing each plot in predeterminable area;The iteration of the iterations is carried out, the process of each iteration includes:Solution is built, solution evaluation is carried out, Pheromone update is carried out according to result appraisal result;After iterative process terminates, the pheromones cube according to accumulation determines the new land use pattern in each plot in predeterminable area.Invention increases space optimization target and the consideration to schedule optimization, the deficiency of conventional Land optimization model has been filled up.
Description
Technical field
The present invention relates to land development or rule and method technical field, more particularly to use the soil redevelopment of Optimized model
Planing method.
Background technology
Land_use change layout refers to different land use type distributional pattern spatially, is land use planning space
The important evidence of control, can its reasonability is related to planning with science smoothly implement to be realized with the object of planning.Land_use change
Layout optimization refers to, by adjusting the locus of each land-use style under the number constraint of different land use type, and to realize soil
Maximized using comprehensive benefit.The same space unit has different suitability degree sizes to different land use type, and Land_use change layout is excellent
The basic goal of change is that each land-use style is configured to its suitability degree space cell high.
With reference to the concept of Land use structure type, Functional Land Use optimization is defined as:Functional Land Use optimizes
It is in order to reach certain ecological economy optimal objective, according to the self-characteristic and appraisal of land suitability of land resource, from soil
The aspect such as the mechanism, function, layout and the intensity that utilize, inhabitation to soil, produce, have a rest and the function such as traffic carries out quantity
Configuration and space layout, to improve land utilization efficiency and benefit, maintain the relative equilibrium of land ecosystem, realize that soil is provided
The sustainable use in source.
The redevelopment of city existing land is built upon on the basis of the initial development of city, by certain means to city
Original land-use style, structure, function and layout etc. enter line replacement upgrading, excavate urban land in potentiality, improve soil
Utilization benefit and soil economic, social or environmental benefit.The concept and city optimized according to Functional Land Use are deposited
The characteristics of amount soil is redeveloped, city existing land redevelopment Elementary Function optimization is:In the base of the existing land development in city
On plinth, according to the target of requirement and the maximizing the benefits of soil Energy-efficient routing, according to the characteristic of urban land resource itself
And appraisal of land suitability, it then follows the national economic and social development planning, urban planning, Land_use change are generally planned, passed through
Certain science and technology and management method, unreasonable structure, function unsound existing land low to utilization ratio in city
Redevelopment unit carries out the substitution of materials and function change, land-use style, structure, function and layout from original soil etc. from space
Enter line replacement upgrading, excavate soil internal potential, improve the utilization rate in soil and economic, the social or environmental benefit in soil,
Realize the sustainable use of land resource.
The target of urban redevelopment Elementary Function optimization is by economic benefit, social benefit, the ecology of unit of redeveloping
The raising of the aspects such as benefit, realize the making overall plans and coordinate of urban redevelopment unit, it is intensive efficiently, conservation culture, safety is livable and passes
Hold shared.
At present, lot of domestic and international scholar is studied Land_use change method for optimizing resources, respectively from theoretical principle, mould
The aspects such as type structure, algorithm optimization and GIS applications, coupling system dynamics, landscape ecology are related to GIS geoanalysis etc. to be learned
Section, pilot study has been carried out to Land_use change most optimum distribution of resources.
During the existing land re-development plan of city, multi-objective optimization question can be faced, multiple-objection optimization is excellent comprising several
Change target and constraint restrictive condition, these optimization aims can be minimized simultaneously, maximize or the two all has.As for constraint bar
Part is just more flexible, specifically can be needed to set according to particular problem.General, multi-objective optimization question can have m
Variable parameter, n object function and k constraints are constituted, and its mathematical definition form is as follows:
Max or minF (x)=[f1(x),f2(x),...,fn(x)]
G (x)=(g1(x),g2(x),...,gp(x)), p=1,2 ..., P
H (x)=(h1(x),h2(x),...,hq(x)), q=1,2 ..., Q
x∈Ω
Wherein, x=(x1,x2,...,xm)T, x is decision vector, represents that M represents variable number;F (x) represents target letter
Number, N represents object function number;G (x) represents constraints, and P represents constraints number;Ω is decision space, is by decision-making
What vector was constituted.
As a example by minimizing multi-objective problem (i.e. all of optimization aim is all minimized), the calculating of MAXMIN methods is illustrated
Formula:
Wherein,Represent i-th fitness of solution in minimization problem;It is i-th m-th target of solution
Value;WithM-th maximum and minimum value of target in all solutions are represented respectively.P is parameter, and p value is bigger, then fit
Answer the discrimination of angle value higher.Therefore fitness value is also limited to 0 and arrives in just infinite scope, fitness value is one for 1
Critical point.If solving all desired values of s all than the difference that another is solved, the fitness value of this solution is less than 1, is also known as
Rule solution or non-pareto solutions;Otherwise, if there is no a solution in all desired values all due to solution s, the then fitness value of s
1 can be more than or equal to, such solution is known as non-governance and solves or pareto solutions.
But the MAXMIN fitness computational methods of prototype version are not omnipotent, general methods, it is only applicable to solve most
The problem of smallization multiple target, the multi-objective optimization question faced in practical application also has maximization multi-objective problem and maximization
The multi-objective optimization question that minimum coexists.To solve this problem, fitness computational methods are modified first:
Wherein,To maximize the fitness of multi-objective problem, the min operation operator in primal algorithm is changed
Two orders of variable in middle molecule, i.e., by calculatingWhenIt is changed into calculatingWhenAlternatively change the method for calculating overall distance between certain solution and other solutions.
Above-mentioned algorithm proposes or changes just for a certain particular type optimization problem, and all targets all maximize or
Minimize.But in the algorithm can not solve same optimization problem, a part of optimization aim requirement is minimized, and another part is excellent
Change the maximized situation of target call.
Multi-objective optimization question solution is diversity, is difficult such issues that cause to solve, the number of solution nor unique, and
It is an a series of set being deconstructed into by optimizations for being referred to as " non-to rule solution ", also referred to as Pareto collection.By Pareto collection structures
Into curve or curved surface be referred to as what Pareto forward positions were to determine.The process of optimization is exactly one constantly to be allowed by current Pareto
The process in optimal Pareto forward positions is approached in the Pareto forward positions being deconstructed into.
In the prior art,
Have than more typical multiple target solution optimizing evaluation:
(1) weighted sum method
The general principle of weighted sum method be by multiple target linear combinations so as to be converted into a single-object problem,
Judge the quality of solution by comparing the desired value after converting.
(2) goal ordering method
In goal ordering method, policymaker enters according to existing priori according to the significance level of each optimization aim
Row sequence, then according to ranking results, contrasts the size of corresponding optimization aim in different solutions respectively, finally show that each optimizes
Quality, it is possible to according to good and bad degree sort.
(3) ε-leash law
The principle of ε-leash law is that first most important one in multiple optimization aims is optimized, other target conducts
Constraints is processed, and by that analogy, each optimization aim is optimized as simple target.Thus multiple target is asked
Topic is converted into a single-object problem.
(4) Objective Programming
The basic thought of Objective Programming is that one group of possibility comprising different priorities is completed under certain constraints
It is conflicting target, the desired value that it must be obtained according to desired by the situation of Solve problems first provides each target, this
A little values will be added in former problem as additional constraints.Therefore, former problem just translate into ask optimization aim with it is prior
The problem of the absolute deviation minimum between desired desired value.
Intelligent algorithm focuses primarily upon three aspects:One is traditional intelligence algorithm, and representational algorithm such as simulated annealing is calculated
Method and artificial neural network;Two is evolution algorithm, and representational algorithm is genetic algorithm;Three is Swarm Intelligence Algorithm, representative
Algorithm be ant colony optimization algorithm and particle swarm optimization algorithm.The characteristics of these algorithms are common is " changing the time with precision ".For
For complicated combinatorial optimization problem, the number solved in the range of feasible zone is an astronomical figure, and the method for exhaustion is practically impossible to
, intelligent optimization algorithm can search out the overall situation approximate most in time range that is limited or can tolerating in feasible zone
Excellent solution is also acceptable, based on this strategy, intelligent optimization algorithm can have soon found that close to globally optimal solution it is approximate most
Excellent solution.
Ant colony optimization algorithm is a kind of random device, and the process of its computing is really to be entered by the continuous iteration of human oasis exploited
Row optimization.Due to the intrinsic randomness feature of a colony optimization algorithm, the process that it searches for optimal solution in feasible zone is sometimes very
Slowly, or even there is not convergent situation.It is verified under certain condition, ant colony optimization algorithm can converge to optimal solution.
Ant group algorithm has had been developed that many follow-on mutation, but the framework of ant group algorithm does not have therefore change
It is too big.All of ant colony optimization algorithm is still all iterative algorithm, in the presence of pheromones, by artificial constantly circulation come
Search optimal solution.
What must typically be included in multiple steps in ant group algorithm mainly has three processes, i.e. initialization information element and phase
Related parameter, ant builds solution, evaluates solution quality and fresh information element.
(1) initialization information element and parameter
Pheromone Matrix is initialized using greedy search algorithm or Principle of Statistics, relevant parameter is then according to experiment
Result or universal experience value set.Set information element initial value and parameter quality directly affect algorithm optimal speed and
As a result.There is experiment to show, good parameter setting can keep the volume balance of algorithm, algorithm hunting zone will not be shunk
It is narrower, so as to be absorbed in dead state, search procedure is lacked enough gravitation, so as to cause going out for excessive search work
It is existing.
(2) solution is built
It is suitably face adjacent near point by move to ant that ant builds solution, so that colony of ants parallel asynchronous
Access problem closes on state.By continuous circulation and accumulative effect, final every human oasis exploited all represents one completely
Solution.Ant is according to pheromone concentration and heuristic information in this process, using a random local decision method choice
Mobile next step, this decision-making technique is called does transition probability.
(3) solution is evaluated
Because ant group algorithm is a kind of iterative algorithm, during Pheromone update after each iteration, basis
The quality of the solution representated by every ant determines the number of release pheromone.So, objective and accurate comments each solution
Valency, has directly influenced the direction of search and convergence rate of algorithm.For single-object problem, can be with desired value come straight
Connect the quality for weighing solution.But for multi-objective optimization question, it is necessary to by certain multi-objective assessment method to each
Solution is estimated, and appropriate operation is done finally according to assessment result.
(4) fresh information element
Fresh information element is exactly the process of modification information element concentration.The concentration of pheromones may put or connect because of ant
Release pheromone on the side for connecing and increase, it is also possible to due to pheromones evaporate and reduce.From from the point of view of reality, release new
Pheromones increased the probability that ant accesses certain point, and these points are possible to many ants and accessed, or at least
One ant accessed, and the solution for generating is so as to attract later ant to access again.Opposite process is pheromones
Evaporation, it plays a part of forgetting, can avoid algorithm towards the solution region Premature Convergence of and non-optimal so that
Algorithm has the new region in more chances exploration solution spaces, makes solution variation.The renewal opportunity of pheromones and update mode root
According to the different and different of specific algorithm.
The more original ant group algorithm of ant colony optimization algorithm has three improvement of aspect, and one is selection of the ant colony when solution is built
More away from enthusiasm, the priori that preferably can be accumulated using previous ant is scanned for probability, improves positive feedback efficiency;
Two is that information updating rule is improved, i.e., global information element updates;Three is that ant often takes a step forward, at once just through
Extra release pheromone on path, and local information element updates.
Multi-target method of the prior art is mostly, by assigning certain weight, multiple target value to be converted to single goal
Value, the simple target value after conversion be the increase in individual preference after formed, it is impossible to objectively reflect the overall matter for changing solution
Amount, and the quantization of weight almost relies on personal deflection, hobby and experience completely.
Multi-target method of the prior art is mostly, by assigning certain weight, multiple target value to be converted to single goal
Value, the simple target value after conversion be the increase in individual preference after formed, it is impossible to objectively reflect the overall matter for changing solution
Amount, and the quantization of weight almost relies on personal deflection, hobby and experience completely.Ant colony optimization algorithm phase of the prior art
There is improvement to original ant algorithm, but applied very deficient in the research for solving land-use optimization field.
The content of the invention
Change solution to solve to be converted to objectively respond out caused by monocular scale value by multiple target value in the prior art
The problem of total quality, the invention provides a kind of soil re-development plan side of use ant colony multiple target layout optimization model
Method.
The invention provides a kind of soil re-development plan method of use ant colony multiple target layout optimization model, including:
Multiple optimization aims and constraint restrictive condition are set;
Initialization algorithm parameter, the algorithm parameter includes:Iterations, ant quantity, the pheromones of each ant are stood
Cube;
Land_use change situation in initialization predeterminable area is the land use pattern for initializing each plot in predeterminable area;
The iteration of the iterations is carried out, the process of each iteration includes:Solution is built, solution evaluation is carried out, according to solution
Evaluation result carries out Pheromone update;
After iterative process terminates, the pheromones cube according to accumulation determines the new soil profit in each plot in predeterminable area
Use type.
The above method also has the characteristics that:
Described information element cube includes multilayer, the value phase of the level that the plain cube of described information includes and iterations
Together;Each layer includes multiple grids of same number, each layer of grid distributed architecture all same, each grid and ground in each layer
The position of block is corresponding.
The above method also has the characteristics that:
The optimization aim includes at least one of following target:Make overall plans and coordinate target, intensive target, conservation culture mesh
Mark, the livable target of safety, space optimization target;Wherein, making overall plans and coordinate target includes Land-use entropy maximization;The collection
About efficient target includes:Maximization of economic benefit;The conservation culture target includes:Value of ecosystem service is maximized;Institute
Stating the livable target of safety includes:Land_use change compatibility is maximized;The space optimization target includes:Spaces compact degree is minimized
Maximized with spatial connectivity;
The constraint restrictive condition includes at least one in following condition:Basic constraints, land function constraint bar
Part, space constraints;Wherein, the basic constraints includes:The soil gross area is constrained, the face of all kinds of land use patterns
Product limitation;The space constraints include:Each grid cell can only be by a kind of land use pattern institute within the same time
Land use pattern in covering, each grid cell is rear before optimization or keeps constant or can only be converted into another
Land use pattern.
The above method also has the characteristics that:
It is described to carry out when solution is evaluated using mixing fitness computational methods, the adaptation of each solution is calculated according to below equation
Degree:
Wherein,
When k-th optimization aim needs to minimize, i'=i, j'=j;
When k-th optimization aim needs to maximize, i'=j, j'=i;
It is k-th desired value of the i-th ' individual solution to refer to, i.e., the i-th ' ant reaches k-th pheromones of target release
Amount;WithK-th maximum and minimum value of target in all solutions are represented respectively.
The above method also has the characteristics that:
When solution is built pheromones increment is calculated using following formula:
Wherein, Δ τkRepresent the pheromones amount that kth ant is discharged after an iteration, fitnesskIt is kth ant
Mixing fitness value, gencurRepresent current iteration number of times.
The above method also has the characteristics that:
In an iterative process, ant often changes the land use pattern in grid plot, all will at once call local letter
Corresponding pheromones value in pheromones cube corresponding to the plain renewal Policy Updates grid of breath, specifically, using following public affairs
Formula is updated:
Wherein, k represents the land use pattern that ant is converted to the land use pattern on grid plot (i, j);
Pheromones value in expression pheromones cube corresponding to grid plot (i, j, k);ξ is reference value, steaming when being local updating
Hair rate;N represents candidate's land use pattern number.
The above method also has the characteristics that:
After iterative process terminates, global renewal is carried out according in the following manner:
Wherein, u represents the land use pattern on grid plot (i, j),Expression pheromones cube medium square (i, j,
K) the pheromones value corresponding to;ρ is global information element evaporation rate;U represents candidate's land use pattern number;Fitnessbs is so far
It is the mixing fitness value of optimal ant;Gencur is current iteration number of times;T is represented and take after each iteration preceding T fitness
Maximum ant is updated value to pheromones cube;Fitnessi is i-th fitness of maximum in current iteration number of times
Value.
The above method also has the characteristics that:
It is described to be carried out also including Optimization Steps after Pheromone update according to result appraisal result, specifically include:
Select a sub-block at random in survey region, the grid plot comprising multiple lines and multiple rows in this sub-block, according to the son
Every kind of land use pattern area and the proportionate relationship of area in model constraints, calculate type transfer general according to following formula in block
Rate:
Wherein, TPi is i-th kind of transition probability of land use pattern in block, in different times, the transition probability of TPi
It is different;Areai is i-th kind of area of land use pattern in whole survey region;Specified in constraints
The lower limit of i kind land use pattern areas;N is land use pattern number in survey region;
Land type with maximum t/p value is converted into the type with minimum TP values.
Multi-target method of the prior art is mostly, by assigning certain weight, multiple target value to be converted to single goal
Value, the simple target value after conversion be the increase in individual preference after formed, it is impossible to objectively reflect the overall matter for changing solution
Amount, and the quantization of weight almost relies on personal deflection, hobby and experience completely.Therefore how to balance each optimization aim it
Between relation, be to evaluate the good and bad key of solution.The present invention is that mixing multiple target solution is commented using MAXMIN multiple target solution evaluation methods
Valency method, can consider all targets as an entirety, can be excavated without each desired value of balance of supervisor's factor
The substantive characteristics of multiple target solution.
The optimization of traditional main accent type quantity of land-use optimization, invention increases space optimization target and pair when
Between sequence optimisation consideration, filled up the deficiency of conventional Land optimization model.The present invention has advantages below:
1st, set up urban land use space and time optimization model, from making overall plans and coordinate, it is intensive efficiently, conservation culture, safety it is livable,
The aspects such as space optimization set up city existing land re-development plan multiple target collection, increased space optimization target and to time sequence
The consideration of optimization is arranged, the deficiency of conventional Land optimization model has been filled up.
2nd, the present invention uses MAXMIN multiple target solution evaluation methods, all targets can be considered as an entirety,
The substantive characteristics of multiple target solution can be excavated without the balance desired value of supervisor's factor.Hybrid MAXMIN of the invention
Method is not proposed or changed, is not limited to all targets and all maximizes or minimum just for a certain particular type optimization problem
Change, can solve in same optimization problem, a part of optimization aim requirement is minimized, and the requirement of another part optimization aim is maximized
Situation.
3rd, from flow, pheromones definition, pheromone updating rule, pheromones increment definition, Optimizing operator for building solution etc.
Aspect is improved, and optimizes land-use optimization model.Pheromones are defined as " three-dimensional ", referred to as pheromones cube.
4th, pheromone updating rule of the invention shows as, and including global information in ant colony optimization algorithm updates and local
Two processes of Pheromone update.
5th, Optimizing operator aspect, for the block variation pattern of land use pattern, designs block-filter optimizations
Operator.In terms of structure is solved, human oasis exploited relies primarily on Optimizing operator, and last solution is referred to as pheromones accumulative solution, and pheromones are final
Solution is obtained according to pheromones cube, excellent on the whole with bigger fitness value compared with the solution of last time iteration
In other solutions.
6th, on algorithm initialization, for land-use optimization problem, the initial solution of AP-ACS algorithms is exactly current
Land_use change situation, before algorithm performs, every ant all records the copy of a current Land_use change situation, rather than by just
Solution after beginningization, the starting point of every ant is the same.After algorithm is entered, directly using Optimizing operator to Land_use change feelings
Condition is optimized, it is to avoid to the unreasonable planning of present status of land utilization during random initializtion.
7th, on solution builds, AP-ACS algorithms establish special Optimizing operator for human oasis exploited provides optimization function, and
The positive feedback mechanism for not relying on pheromones builds solution, so every ant is not against pheromones but relative in structure Xie Shishi
One structure of solution of complete independently.
8th, optimum programming result generation on, in AP-ACS algorithms, due to human oasis exploited build solution when rely primarily on it is excellent
Change operator, rather than the accumulation results of pheromones, so cause the last solution of AP-ACS algorithms to be made up of two parts, a part
It is the solution after last time iteration representated by every ant, the number of this part solution is exactly the number of ant;And another part is
One directly builds according to pheromones cube, and in the present invention this solution is referred to as pheromones accumulative solution.By information
The pheromones accumulative solution that plain cube is produced compared with the solution of last time iteration, with bigger fitness value, on the whole
It is better than other solutions.
Brief description of the drawings
The accompanying drawing for constituting a part of the invention is used for providing a further understanding of the present invention, schematic reality of the invention
Apply example and its illustrate, for explaining the present invention, not constitute inappropriate limitation of the present invention.In the accompanying drawings:
Fig. 1 is the flow chart of the soil re-development plan method that ant colony multiple target layout optimization model is used in the present invention.
Specific embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
A part of embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.Need
Illustrate, in the case where not conflicting, the feature in embodiment and embodiment in the application can mutually be combined.
From solution m, this angle is improved the present invention to ACS algorithms.It is embodied in two aspects:
A, conventional combination optimization problem are usually " zero starting point ", that is to say, that ant group algorithm is do not have in initial neutralizing
Any reference, the process of initial neutralizing is exactly a random building process from scratch.And for land-use optimization
For problem, be not but so because the starting point of optimization be exactly present status of land utilization in itself, the process of initial neutralizing is can
With what is omitted;
B, the stop condition for the ant group algorithm of conventional combination problem be usually with algorithmic statement as standard, i.e., certain or
Certain several optimization aim is reached when tend towards stability after certain value.And in land-use optimization, the value of optimization aim can be with soil
Ground utilization power constantly changes and changes, and it is exactly there was only a kind of soil in survey region that can reach convergent unique states
Use pattern.However, such case can not possibly occur in practice.So, solve the ant group algorithm of land-use optimization
End condition can not be converging to standard.
Included using the soil re-development plan method of ant colony multiple target layout optimization model in the present invention:
Step 101, sets multiple optimization aims and constraint restrictive condition;
Step 102, initialization algorithm parameter, the algorithm parameter includes:Iterations, ant quantity, each ant
Pheromones cube;
Step 103, the Land_use change situation in initialization predeterminable area is the soil for initializing each plot in predeterminable area
Use pattern;
Step 104, carries out the iteration of the iterations, and the process of each iteration includes:Solution is built, solution evaluation is carried out,
Pheromone update is carried out according to result appraisal result;
Step 105, after iterative process terminates, the pheromones cube according to accumulation determines the new of each plot in predeterminable area
Land use pattern.
The following detailed description of the method for the present invention.
In step 101, target includes at least one of following target:Make overall plans and coordinate target, intensive target, conservation culture
Target, the livable target of safety, space optimization target.This 5 targets can typically be included.
Wherein,
Making overall plans and coordinate target includes following subfunction:Land-use entropy maximization.Land-use entropy maximization
Meaning be:The Land-use entropy for optimizing unit is bigger, and the order degree of Land Use System is higher, structural to get over
By force.Computational methods are:Pu=au/ S, wherein S are the gross area for optimizing unit, and au is u kinds soil
The area of use pattern.
Intensive efficient target includes following subfunction:Maximization of economic benefit.The meaning of maximization of economic benefit is:Pass through
The maximization of the economic output of all kinds of Land_use changes is realized in function optimization configuration.Computational methods are:Wherein
euU kinds land use pattern economic output benefit coefficient per capita, is replaced with the average land price of land use pattern.
Conservation culture target includes following subfunction:Value of ecosystem service is maximized.Value of ecosystem service is most
The meaning of bigization is:Conservation culture degree in optimization unit is maximized.Computational methods are:Wherein S
It is u kind land use pattern value of ecosystem service coefficients.
The livable target of safety includes following subfunction:Land_use change compatibility is maximized.Land_use change compatibility is maximized
Meaning be:Consider the compatibility issues such as purposes, function environment between adjacent plot land use pattern.Computational methods are:compatibleijIt is Land_use change compatibility.
Space optimization target includes following subfunction:Spaces compact degree is minimized and spatial connectivity is maximized.
Spaces compact degree minimize meaning be:Reflect the size of the compactness of town site spatial distribution,
The plot with identical land use pattern is encouraged to flock together.Computational methods are:Its
Middle ZujRepresent that land use pattern is the area of the plot i and plot j of u.
The maximized meaning of spatial connectivity can be adjacent to possess the plot of identical land use pattern in survey region
Or connection.Computational methods are:
In step 101, constraint restrictive condition includes at least one in following condition:Basic constraints, land function
Constraints, space constraints.
Basic constraints includes:The soil gross area is constrained, the limitation of the area of all kinds of land use patterns.
After optimization with business live/live based on function optimization unit in,
Residential estate >=70% (optimization unit)
Commerce services industry facilities land >=5% (community)
Public administration and public service facility land used >=10% (community)
Public facilities >=10% (community)
Greenery patches and land for squares >=20% (community).
The area limitation of land use pattern is exemplified below after optimization:
Industrial land >=70% (optimization unit)
Commerce services industry facilities land >=5% (community)
Public administration and public service facility land used >=10% (community)
Public facilities >=10% (community)
Greenery patches and land for squares >=20% (community).
Land function constraints includes:Forbid building area, Ecology Restriction (Ecological Control green line line), water conservation district
(city blue line), history culture protection (the purple line in city), substantial risk facility management and control area (city yellow line).
Space constraints include:Each grid cell can only be covered within the same time by a kind of land use pattern
Land use pattern in lid, each grid cell is rear before optimization or keeps constant or can only be converted into another soil
Ground use pattern.
In a step 102 use information element cube.For traditional combinatorial optimization problem, the structure one of pheromones
As be " two dimension ", and for land-use optimization problem, pheromones be defined as " it is three-dimensional, as pheromones cube
Body.
Pheromones cube includes multilayer, and the level that described information element cube includes is identical with the value of iterations;
Each layer includes multiple grids of same number, each layer of grid distributed architecture all same, each grid and plot in each layer
Position it is corresponding.
In the first iterative process, each ant creeps in cubical first layer plane of its pheromones, and discharges information
Element, ant carries out the judgement of ground block type to each grid, and discharges the pheromones of various concentrations, pheromone concentration essence
On be ground block type transition probability, ant can discharge the ground block type and be converted into the general of all ground block type in each grid
Rate, the possibility of probability corresponding conversion higher is bigger.After first time iteration, to the letter of all ants of first time iteration
Breath element is sued for peace, and is averaged, as the integrated information element concentration after first time iteration, that is, formed after an iteration
Ground block type transition probability, judges which plot class needs to translate into other ground block type accordingly.Again this integrated information element concentration
On the basis of, all ants carry out second iteration of itself respectively, i.e., each ant is flat in the cubical second layer of its pheromones
Creeped in face, by that analogy, after reaching iterations, according to the final cubical parameter determination reallocation of land knot of pheromones
Really.
At step 104, the fitness value of the solution for being calculated using improved Hybrid MAXMIN methods is carried out solution and commented
Using mixing fitness computational methods during valency, the fitness of each solution is calculated according to below equation:
Wherein,
When k-th optimization aim needs to minimize, i'=i, j'=j;
When k-th optimization aim needs to maximize, i'=j, j'=i;
I.e. when optimization aim is required for minimizing,It is equal toWhen optimization aim needs maximum
During change,It is equal to
It is k-th desired value of the i-th ' individual solution to refer to, i.e., the i-th ' ant reaches k-th pheromones of target release
Amount;WithK-th maximum and minimum value of target in all solutions are represented respectively.
Improved MAXMIN methods property shows as:
(1) the non-fitness value for ruling solution is more than or equal to 1, and the adaptive value for ruling solution is less than 1;
(2)The independence and diversity of solution are encouraged, and punishes concentration class non-governance solution high;
(3) when pareto forward positions are convex,Preference is located at the solution in forward position centre position;And before working as pareto
During along being recessed,Preference is located at the solution at forward position two ends.
(4) fitness for ruling solution is only influenceed by non-governance solution, and unrelated with concentration class;
(5) the non-fitness for ruling solution is in close relations with concentration class, is both influenceed by other non-governance solutions, and by critical distance
Interior governance solution influence.
The fitness value of the solution that the present invention is calculated using improved Hybrid MAXMIN methods as pheromones group
Into one of part.Fitness value is bigger, illustrates that this solution is more superior, then building the ant of this solution will discharge more letters
Breath element so that be obtained in that the bigger chance that is adopted by the represented program results of this solution, at step 104, is building
During solution pheromones increment is calculated using following formula:
Wherein, Δ τkRepresent the pheromones amount that kth ant is discharged after an iteration, fitnesskIt is kth ant
Mixing fitness value, gencurRepresent current iteration number of times.
Pheromone updating rule is the pass that another directly affects ant colony optimization algorithm global convergence and computational efficiency
One of key factor, it includes two processes of pheromone release and evaporation.Local information element is included in ant colony optimization algorithm to update
Two processes are updated with global information.
It refers to that all ants often carry out the operating procedure that a step will be carried out that local information element updates, and the step is combined
Pheromones are evaporated and two processes of release.The evaporation of pheromones be it is a kind of avoid all ants too early quickly to poor solution or
A kind of discovery mechanism that locally optimal solution is concentrated.In fact, the reduction of pheromone concentration helps to be visited in whole heuristic process
Rope other different solution spaces.For true ant colony, their pheromones are in nature similarly in evaporation.So
And such evaporation acts on unimportant for true ant.Opposite, for human oasis exploited, the effect of pheromones evaporation is but
It is extremely important because ant group algorithm problem problem to be solved to find routing problem of looking for food than ant much more complex.
In ant group optimization, those tend to forget past mistake or selection inferior mechanism be all human oasis exploited necessary to, because
For they can be such that structure of problem of the ant to having acquired constantly is improved.Additionally, the evaporation of human oasis exploited pheromones is another
Individual important function is so that pheromones have a upper limit for maximum, it is to avoid the pheromones of some regions are led due to Rapid Accumulation
Cause algorithm Premature Convergence.Local information element updates to be included:In an iterative process, ant often changes the soil profit in grid plot
With type, all will at once call and believe accordingly in the pheromones cube that local information element updates corresponding to the Policy Updates grids
Breath element value, specifically, being updated using following formula:
Wherein, k represents the land use pattern that ant is converted to the land use pattern on grid plot (i, j);
Pheromones value in expression pheromones cube corresponding to grid plot (i, j, k);ξ is reference value, steaming when being local updating
Hair rate;N represents candidate's land use pattern number.
It refers to that after an iteration, the pheromones evaporation and demonstration carried out from global angle are grasped that global information element updates
Make.After iterative process terminates, global renewal is carried out according in the following manner:
Wherein, u represents the land use pattern on grid plot (i, j),Expression pheromones cube medium square (i, j,
K) the pheromones value corresponding to;ρ is global information element evaporation rate;U represents candidate's land use pattern number;fitnessbsSo far it is
The mixing fitness value of optimal ant;gencurIt is current iteration number of times;T is represented and take after each iteration preceding T fitness value most
Big ant is updated to pheromones cube;fitnessiIt is i-th fitness value of maximum in current iteration number of times.
Urban land change mainly has two ways:One is the neighbour in the combination area of city and country or two kinds of land use patterns
The linear change that socket part point is carried out;Two is the block change carried out inside zonule.Bulk for land use pattern becomes
Change mode, the present invention designs block-filter Optimizing operators.After Pheromone update is carried out according to result appraisal result also
Including Optimization Steps, specifically include:
Select a sub-block at random in survey region, multiple lines and multiple rows grid plot is included in this sub-block, according to the son
Every kind of land use pattern area and the proportionate relationship of area in model constraints, calculate type transfer general according to following formula in block
Rate:
Wherein, TPi is i-th kind of transition probability of land use pattern in block, in different times, the transition probability of TPi
It is different;Areai is i-th kind of area of land use pattern in whole survey region;Specified in constraints
The lower limit of i kind land use pattern areas;N is land use pattern number in survey region;
Land type with maximum t/p value is converted into the type with minimum TP values.
Work as TPi<When 0, illustrate i-th kind of area of land use pattern less than the area lower limit in constraints, it should to increase
Plus.Therefore, conversion principle is:Land type with maximum t/p value is converted into the type with minimum TP values.
The final program results of the ant colony optimization algorithm after present invention improvement is produced by the ant of last time iteration
, but directly drawn according to Pheromone Matrix combination pseudorandom ratio, therefore referred to as pheromones accumulation ant group optimization is calculated
Method (Accumulated Pheromone ACS, AP-ACS).Wherein, the bigger path of pheromone concentration by ant select it is general
Rate is bigger, the Path selection that each iteration ant creeps all be last iteration produce pheromone concentration after result on carry out
, pheromone concentration is added up in each iteration, different from random algorithm, therefore is pseudorandom.
The optimization of traditional main accent type quantity of land-use optimization, invention increases space optimization target and pair when
Between sequence optimisation consideration, filled up the deficiency of conventional Land optimization model.The present invention has advantages below:
1st, set up urban land use space and time optimization model, from making overall plans and coordinate, it is intensive efficiently, conservation culture, safety it is livable,
The aspects such as space optimization set up city existing land re-development plan multiple target collection, increased space optimization target and to time sequence
The consideration of optimization is arranged, the deficiency of conventional Land optimization model has been filled up.
2nd, the present invention uses MAXMIN multiple target solution evaluation methods, all targets can be considered as an entirety,
The substantive characteristics of multiple target solution can be excavated without the balance desired value of supervisor's factor.Hybrid MAXMIN of the invention
Method is not proposed or changed, is not limited to all targets and all maximizes or minimum just for a certain particular type optimization problem
Change, can solve in same optimization problem, a part of optimization aim requirement is minimized, and the requirement of another part optimization aim is maximized
Situation.
3rd, from flow, pheromones definition, pheromone updating rule, pheromones increment definition, Optimizing operator for building solution etc.
Aspect is improved, and optimizes land-use optimization model.Pheromones are defined as " three-dimensional ", referred to as pheromones cube.
4th, pheromone updating rule of the invention shows as, and including global information in ant colony optimization algorithm updates and local
Two processes of Pheromone update.
5th, Optimizing operator aspect, for the block variation pattern of land use pattern, designs block-filter optimizations
Operator.In terms of structure is solved, human oasis exploited relies primarily on Optimizing operator, and last solution is referred to as pheromones accumulative solution, and pheromones are final
Solution is obtained according to pheromones cube, excellent on the whole with bigger fitness value compared with the solution of last time iteration
In other solutions.
6th, on algorithm initialization, for land-use optimization problem, the initial solution of AP-ACS algorithms is exactly current
Land_use change situation, before algorithm performs, every ant all records the copy of a current Land_use change situation, rather than by just
Solution after beginningization, the starting point of every ant is the same.After algorithm is entered, directly using Optimizing operator to Land_use change feelings
Condition is optimized, it is to avoid to the unreasonable planning of present status of land utilization during random initializtion.
7th, on solution builds, AP-ACS algorithms establish special Optimizing operator for human oasis exploited provides optimization function, and
The positive feedback mechanism for not relying on pheromones builds solution, so every ant is not against pheromones but relative in structure Xie Shishi
One structure of solution of complete independently.
8th, optimum programming result generation on, in AP-ACS algorithms, due to human oasis exploited build solution when rely primarily on it is excellent
Change operator, rather than the accumulation results of pheromones, so cause the last solution of AP-ACS algorithms to be made up of two parts, a part
It is the solution after last time iteration representated by every ant, the number of this part solution is exactly the number of ant;And another part is
One directly builds according to pheromones cube, and this solution herein is referred to as pheromones accumulative solution.By pheromones
The pheromones accumulative solution that cube is produced, with bigger fitness value, on the whole will compared with the solution of last time iteration
Better than other solutions.
Descriptions above can combine implementation individually or in a variety of ways, and these variants all exist
Within protection scope of the present invention.
One of ordinary skill in the art will appreciate that all or part of step in the above method can be instructed by program
Related hardware is completed, and described program can be stored in computer-readable recording medium, such as read-only storage, disk or CD
Deng.Alternatively, all or part of step of above-described embodiment can also be realized using one or more integrated circuits, accordingly
Ground, each module/unit in above-described embodiment can be realized in the form of hardware, it would however also be possible to employ the shape of software function module
Formula is realized.The present invention is not restricted to the combination of the hardware and software of any particular form.
It should be noted that herein, term " including ", "comprising" or its any other variant be intended to non-row
His property is included, so that article or equipment including a series of key elements not only include those key elements, but also including not having
There are other key elements being expressly recited, or it is this article or the intrinsic key element of equipment also to include.Without more limits
In the case of system, the key element limited by sentence " including ... ", it is not excluded that in the article or equipment including the key element
Also there is other identical element.
The above embodiments are merely illustrative of the technical solutions of the present invention and it is unrestricted, reference only to preferred embodiment to this hair
It is bright to be described in detail.It will be understood by those within the art that, technical scheme can be modified
Or equivalent, without deviating from the spirit and scope of technical solution of the present invention, all should cover in claim model of the invention
In the middle of enclosing.
Claims (8)
1. a kind of soil re-development plan method of use ant colony multiple target layout optimization model, it is characterised in that including:
Multiple optimization aims and constraint restrictive condition are set;
Initialization algorithm parameter, the algorithm parameter includes:Iterations, ant quantity, the pheromones cube of each ant;
Land_use change situation in initialization predeterminable area is the land use pattern for initializing each plot in predeterminable area;
The iteration of the iterations is carried out, the process of each iteration includes:Solution is built, solution evaluation is carried out, according to result appraisal
Result carries out Pheromone update;
After iterative process terminates, the pheromones cube according to accumulation determines the new Land_use change class in each plot in predeterminable area
Type.
2. the soil re-development plan method of ant colony multiple target layout optimization model, its feature are used as claimed in claim 1
It is,
Described information element cube includes multilayer, and the level that described information element cube includes is identical with the value of iterations;
Each layer includes multiple grids of same number, each layer of grid distributed architecture all same, each grid and plot in each layer
Position it is corresponding.
3. the soil re-development plan method of ant colony multiple target layout optimization model, its feature are used as claimed in claim 1
It is,
The optimization aim includes at least one of following target:Make overall plans and coordinate target, intensive target, conservation culture target,
The livable target of safety, space optimization target;Wherein, making overall plans and coordinate target includes Land-use entropy maximization;It is described intensive
Efficient target includes:Maximization of economic benefit;The conservation culture target includes:Value of ecosystem service is maximized;It is described
The livable target of safety includes:Land_use change compatibility is maximized;The space optimization target includes:Spaces compact degree minimize and
Spatial connectivity is maximized;
The constraint restrictive condition includes at least one in following condition:Basic constraints, land function constraints, sky
Between constraints;Wherein, the basic constraints includes:The soil gross area is constrained, the area of all kinds of land use patterns limit
System;The space constraints include:Each grid cell can only cover within the same time by a kind of land use pattern,
Land use pattern in each grid cell is rear before optimization or keeps constant or can only be converted into another soil
Use pattern.
4. the soil re-development plan method of ant colony multiple target layout optimization model, its feature are used as claimed in claim 1
It is,
It is described to carry out when solution is evaluated using mixing fitness computational methods, the fitness of each solution is calculated according to below equation:
Wherein,
When k-th optimization aim needs to minimize, i'=i, j'=j;
When k-th optimization aim needs to maximize, i'=j, j'=i;
It is k-th desired value of the i-th ' individual solution to refer to, i.e., the i-th ' ant reaches k-th pheromones amount of target release;WithK-th maximum and minimum value of target in all solutions are represented respectively.
5. the soil re-development plan method of ant colony multiple target layout optimization model, its feature are used as claimed in claim 1
It is,
When solution is built pheromones increment is calculated using following formula:
Wherein, Δ τkRepresent the pheromones amount that kth ant is discharged after an iteration, fitnesskIt is mixing for kth ant
Close fitness value, gencurRepresent current iteration number of times.
6. the soil re-development plan method of ant colony multiple target layout optimization model, its feature are used as claimed in claim 1
It is,
In an iterative process, ant often changes the land use pattern in grid plot, all will at once call local information element
Corresponding pheromones value in the pheromones cube corresponding to the Policy Updates grids is updated, specifically, entering using following formula
Row updates:
Wherein, k represents the land use pattern that ant is converted to the land use pattern on grid plot (i, j);Represent
Pheromones value in pheromones cube corresponding to grid plot (i, j, k);ξ is reference value, evaporation rate when being local updating;
N represents candidate's land use pattern number.
7. the soil re-development plan method of ant colony multiple target layout optimization model, its feature are used as claimed in claim 1
It is,
After iterative process terminates, global renewal is carried out according in the following manner:
Wherein, u represents the land use pattern on grid plot (i, j),Represent pheromones cube medium square (i, j, k) institute
Corresponding pheromones value;ρ is global information element evaporation rate;U represents candidate's land use pattern number;Fitnessbs is so far for most
The mixing fitness value of excellent ant;Gencur is current iteration number of times;T is represented and take after each iteration preceding T fitness value most
Big ant is updated to pheromones cube;Fitnessi is i-th fitness value of maximum in current iteration number of times.
8. the soil re-development plan method of ant colony multiple target layout optimization model, its feature are used as claimed in claim 1
It is,
It is described to be carried out also including Optimization Steps after Pheromone update according to result appraisal result, specifically include:
Select a sub-block at random in survey region, the grid plot comprising multiple lines and multiple rows in this sub-block, according in the sub-block
Every kind of land use pattern area and the proportionate relationship of area in model constraints, type transition probability is calculated according to following formula:
Wherein, TPi is i-th kind of transition probability of land use pattern in block, and in different times, the transition probability of TPi differs
Sample;Areai is i-th kind of area of land use pattern in whole survey region;I-th kind specified in constraints
The lower limit of land use pattern area;N is land use pattern number in survey region;
Land type with maximum t/p value is converted into the type with minimum TP values.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710034752.3A CN106909986B (en) | 2017-01-18 | 2017-01-18 | Land redevelopment planning method using ant colony multi-objective layout optimization model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710034752.3A CN106909986B (en) | 2017-01-18 | 2017-01-18 | Land redevelopment planning method using ant colony multi-objective layout optimization model |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106909986A true CN106909986A (en) | 2017-06-30 |
CN106909986B CN106909986B (en) | 2020-12-25 |
Family
ID=59207250
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710034752.3A Active CN106909986B (en) | 2017-01-18 | 2017-01-18 | Land redevelopment planning method using ant colony multi-objective layout optimization model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106909986B (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108154221A (en) * | 2017-12-21 | 2018-06-12 | 武汉大学 | The population innovatory algorithm that one kind optimizes towards " three lines " collaboration |
CN108335007A (en) * | 2017-10-31 | 2018-07-27 | 上海市政工程设计研究总院(集团)有限公司 | A kind of computation model and its computational methods of urban land redevelopment intensity |
CN109871578A (en) * | 2019-01-08 | 2019-06-11 | 郑州轻工业学院 | A kind of satellite capsule layout method based on ant colony labor division |
CN112036567A (en) * | 2020-09-18 | 2020-12-04 | 北京机电工程研究所 | Genetic programming method, apparatus and computer readable medium |
CN112036537A (en) * | 2020-08-04 | 2020-12-04 | 中国农业大学 | Three-dimensional path planning method and system for land scraper navigation |
CN112801487A (en) * | 2021-01-21 | 2021-05-14 | 中国科学院新疆生态与地理研究所 | Method for converting land use type into plant function type, terminal and storage medium |
US11144681B2 (en) | 2017-11-10 | 2021-10-12 | Autodesk, Inc. | Generative design pipeline for urban and neighborhood planning |
CN114896799A (en) * | 2022-05-23 | 2022-08-12 | 北京师范大学 | Method and device for simulating and processing land utilization and cover change |
CN116738702A (en) * | 2023-06-05 | 2023-09-12 | 广州地铁设计研究院股份有限公司 | Multi-objective optimization method for land utilization structure of station area based on TOD mode |
CN117829198A (en) * | 2024-01-03 | 2024-04-05 | 南通大学 | High-dimensional massive parallel attribute reduction method for guiding rough hypercube by informative |
US12008293B2 (en) | 2021-11-19 | 2024-06-11 | Autodesk, Inc. | Techniques for automatically generating designs having characteristic topologies for urban design projects |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050196047A1 (en) * | 2004-02-03 | 2005-09-08 | Yuri Owechko | Object recognition system incorporating swarming domain classifiers |
CN101136081A (en) * | 2007-09-13 | 2008-03-05 | 北京航空航天大学 | Unmanned operational aircraft multiple plains synergic tasks distributing method based on ant colony intelligent |
CN103136603A (en) * | 2013-03-26 | 2013-06-05 | 武汉大学 | Intelligent land utilization layout optimal allocation method |
KR20160078662A (en) * | 2014-12-24 | 2016-07-05 | 한국과학기술원 | Cross-layer framework and its operation of bio-inspired algorithm for wireless mesh networks |
-
2017
- 2017-01-18 CN CN201710034752.3A patent/CN106909986B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050196047A1 (en) * | 2004-02-03 | 2005-09-08 | Yuri Owechko | Object recognition system incorporating swarming domain classifiers |
CN101136081A (en) * | 2007-09-13 | 2008-03-05 | 北京航空航天大学 | Unmanned operational aircraft multiple plains synergic tasks distributing method based on ant colony intelligent |
CN103136603A (en) * | 2013-03-26 | 2013-06-05 | 武汉大学 | Intelligent land utilization layout optimal allocation method |
KR20160078662A (en) * | 2014-12-24 | 2016-07-05 | 한국과학기술원 | Cross-layer framework and its operation of bio-inspired algorithm for wireless mesh networks |
Non-Patent Citations (2)
Title |
---|
蔡婉君 等: "改进蚁群算法优化周期性车辆路径问题", 《运筹与管理》 * |
高小永: "基于多目标蚁群算法的土地利用优化配置", 《中国博士学位论文全文数据库 基础科学辑》 * |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108335007A (en) * | 2017-10-31 | 2018-07-27 | 上海市政工程设计研究总院(集团)有限公司 | A kind of computation model and its computational methods of urban land redevelopment intensity |
US11275872B2 (en) | 2017-11-10 | 2022-03-15 | Autodesk, Inc. | Techniques for automatically generating urban and neighborhood designs |
US11922099B2 (en) | 2017-11-10 | 2024-03-05 | Autodesk, Inc. | Techniques for automatically generating designs having characteristic topologies for urban design projects |
US11144681B2 (en) | 2017-11-10 | 2021-10-12 | Autodesk, Inc. | Generative design pipeline for urban and neighborhood planning |
US11157662B2 (en) * | 2017-11-10 | 2021-10-26 | Autodesk, Inc. | Techniques for automatically generating designs having characteristic topologies for urban design projects |
US11222146B2 (en) | 2017-11-10 | 2022-01-11 | Autodesk, Inc. | Techniques for automatically generating designs having characteristic topologies for urban design projects |
CN108154221A (en) * | 2017-12-21 | 2018-06-12 | 武汉大学 | The population innovatory algorithm that one kind optimizes towards " three lines " collaboration |
US12008292B2 (en) | 2018-11-08 | 2024-06-11 | Autodesk, Inc. | Techniques for automatically analyzing competing design objectives when generating designs for urban design projects |
CN109871578A (en) * | 2019-01-08 | 2019-06-11 | 郑州轻工业学院 | A kind of satellite capsule layout method based on ant colony labor division |
CN109871578B (en) * | 2019-01-08 | 2020-05-05 | 郑州轻工业学院 | Satellite cabin layout method based on ant colony labor division |
CN112036537A (en) * | 2020-08-04 | 2020-12-04 | 中国农业大学 | Three-dimensional path planning method and system for land scraper navigation |
CN112036537B (en) * | 2020-08-04 | 2023-12-26 | 中国农业大学 | Three-dimensional path planning method and system for land leveler navigation |
CN112036567B (en) * | 2020-09-18 | 2023-10-31 | 北京机电工程研究所 | Genetic programming method, apparatus and computer readable medium |
CN112036567A (en) * | 2020-09-18 | 2020-12-04 | 北京机电工程研究所 | Genetic programming method, apparatus and computer readable medium |
CN112801487A (en) * | 2021-01-21 | 2021-05-14 | 中国科学院新疆生态与地理研究所 | Method for converting land use type into plant function type, terminal and storage medium |
US12008293B2 (en) | 2021-11-19 | 2024-06-11 | Autodesk, Inc. | Techniques for automatically generating designs having characteristic topologies for urban design projects |
CN114896799A (en) * | 2022-05-23 | 2022-08-12 | 北京师范大学 | Method and device for simulating and processing land utilization and cover change |
CN114896799B (en) * | 2022-05-23 | 2023-05-23 | 北京师范大学 | Simulation processing method and device for land utilization and coverage change |
CN116738702A (en) * | 2023-06-05 | 2023-09-12 | 广州地铁设计研究院股份有限公司 | Multi-objective optimization method for land utilization structure of station area based on TOD mode |
CN117829198A (en) * | 2024-01-03 | 2024-04-05 | 南通大学 | High-dimensional massive parallel attribute reduction method for guiding rough hypercube by informative |
Also Published As
Publication number | Publication date |
---|---|
CN106909986B (en) | 2020-12-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106909986A (en) | A kind of soil re-development plan method of use ant colony multiple target layout optimization model | |
Trivedi et al. | A genetic algorithm–differential evolution based hybrid framework: case study on unit commitment scheduling problem | |
Zhang et al. | Simulating multi-objective land use optimization allocation using Multi-agent system—A case study in Changsha, China | |
Cai et al. | A multi-objective chaotic ant swarm optimization for environmental/economic dispatch | |
Nasir et al. | A comprehensive review on water cycle algorithm and its applications | |
CN105809279B (en) | A kind of water resources optimal operation method based on multi-target quantum shuffled frog leaping algorithm | |
Deb et al. | A hybrid multi-objective chicken swarm optimization and teaching learning based algorithm for charging station placement problem | |
CN107769237B (en) | Multi-energy system coordinated dispatching method and device based on electric car access | |
CN105509749A (en) | Mobile robot path planning method and system based on genetic ant colony algorithm | |
CN103116865A (en) | Multidimensional collaborative power grid planning method | |
CN107977711B (en) | Multi-agent genetic method oriented to 'three-line' cooperative optimization | |
Wang et al. | Rank-driven salp swarm algorithm with orthogonal opposition-based learning for global optimization | |
CN105761192A (en) | Intelligent method and intelligent integrated system for village-town area land use planning | |
CN107958424A (en) | A kind of Economic Dispatch strategy based on improvement gravitation search algorithm | |
CN106529818A (en) | Water quality evaluation prediction method based on fuzzy wavelet neural network | |
CN110298491A (en) | A kind of transportation network node selecting method based on slime mould swarm intelligence | |
Jiang et al. | An improved reinforcement-immune algorithm for agricultural resource allocation optimization | |
CN103473465B (en) | Land resource spatial configuration optimal method based on multiple target artificial immune system | |
CN104657442B (en) | Multiple target community discovery method based on Local Search | |
Wang et al. | Multi-objective optimization of IoT-based green building energy system using binary metaheuristic algorithms | |
Héliodore et al. | Metaheuristics for intelligent electrical networks | |
Beiranvand et al. | A systematic review of optimization of dams reservoir operation using the meta-heuristic algorithms | |
Liu et al. | A land-use spatial allocation model based on modified ant colony optimization | |
CN110222133A (en) | A kind of multiclass land use simulating and predicting method and device considering landscape index | |
CN113379268A (en) | Agricultural machinery scheduling method for resolving genetic algorithm initial population based on Christofises |
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 | ||
TR01 | Transfer of patent right |
Effective date of registration: 20210903 Address after: No. 9 Dengzhuang South Road, Haidian District, Beijing 100094 Patentee after: Research Institute of aerospace information innovation, Chinese Academy of Sciences Address before: 100101 Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, No. 20 Datun Road, Chaoyang District, Beijing Patentee before: Li Hongga Patentee before: Jiang Renrong Patentee before: Huang Xiaoxia |
|
TR01 | Transfer of patent right |