CN115965171A - Micro-park site selection method based on ant colony optimization algorithm - Google Patents
Micro-park site selection method based on ant colony optimization algorithm Download PDFInfo
- Publication number
- CN115965171A CN115965171A CN202310224161.8A CN202310224161A CN115965171A CN 115965171 A CN115965171 A CN 115965171A CN 202310224161 A CN202310224161 A CN 202310224161A CN 115965171 A CN115965171 A CN 115965171A
- Authority
- CN
- China
- Prior art keywords
- park
- micro
- data
- grid
- ant
- 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.)
- Pending
Links
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 43
- 238000010187 selection method Methods 0.000 title claims abstract description 15
- 238000005457 optimization Methods 0.000 title claims description 8
- 238000000034 method Methods 0.000 claims abstract description 29
- 238000010276 construction Methods 0.000 claims abstract description 15
- 238000011835 investigation Methods 0.000 claims abstract 2
- 239000003016 pheromone Substances 0.000 claims description 65
- 241000257303 Hymenoptera Species 0.000 claims description 35
- 238000004458 analytical method Methods 0.000 claims description 12
- 238000010586 diagram Methods 0.000 claims description 12
- 238000012216 screening Methods 0.000 claims description 9
- 150000001875 compounds Chemical class 0.000 claims description 8
- 238000009826 distribution Methods 0.000 claims description 5
- 239000011159 matrix material Substances 0.000 claims description 5
- FGUUSXIOTUKUDN-IBGZPJMESA-N C1(=CC=CC=C1)N1C2=C(NC([C@H](C1)NC=1OC(=NN=1)C1=CC=CC=C1)=O)C=CC=C2 Chemical compound C1(=CC=CC=C1)N1C2=C(NC([C@H](C1)NC=1OC(=NN=1)C1=CC=CC=C1)=O)C=CC=C2 FGUUSXIOTUKUDN-IBGZPJMESA-N 0.000 claims 1
- 230000009024 positive feedback mechanism Effects 0.000 abstract description 3
- 239000002699 waste material Substances 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 20
- 230000008569 process Effects 0.000 description 9
- 238000004590 computer program Methods 0.000 description 7
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000005712 elicitor Substances 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000002431 foraging effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000011065 in-situ storage Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A30/00—Adapting or protecting infrastructure or their operation
- Y02A30/60—Planning or developing urban green infrastructure
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a micro-park site selection method based on an optimized ant colony algorithm, which comprises the following steps: extracting data of residential areas and current city parks based on the current land investigation data and the high-resolution satellite map interpretation data; calculating the current park service range according to the set service radius, and extracting the residential area which is not covered by the park service range; overlaying homeland space planning data and urban green land system special planning data in the uncovered residential buffer zone to screen out a proper micro-park construction range; and determining a micro-park site selection scheme in the micro-park construction range based on an improved ant colony algorithm. The method utilizes the characteristics that the ant colony algorithm model has strong self-organization, robustness and positive feedback mechanism and can perform distributed computation and the like to quickly screen out the optimal urban park site selection scheme so as to solve the problems of unreasonable spatial layout, resource waste, incapability of meeting the demand of service radius, poor accessibility and the like in the traditional site selection.
Description
Technical Field
The invention relates to the field of urban planning, in particular to a micro-park site selection method based on an ant colony optimization algorithm.
Background
Along with the continuous transformation of urban development modes and citizen life modes, urban leisure areas are seriously insufficient, especially in urban dense areas. A park system with balanced distribution is constructed according to the requirements of '300 meters see green and 500 meters see the park' of urban resident travel, and the service radius coverage rate of the park is improved. However, it is often difficult to construct large parks in cities with outstanding human spears, and the most economical and reasonable solution is to effectively utilize fragmentary open spaces, corner spaces and the like in the cities, i.e. to construct various parks such as parks in the places and pocket parks by 'micro-update' mode of cutting green at a break, building green at break, keeping white and increasing green.
The development of urban parks generally has the problems of unreasonable layout, non-conformity with the requirements of surrounding residents, waste of public facility resources of the parks and the like, and the problems are generally related to unscientific park planning and site selection, inaccurate planning and positioning and the like. On one hand, the park as one of the urban public service facilities should satisfy the principle of balanced proportioning, ensure the space accessibility and the participation right fairness of the park facilities, and ensure that people with different social backgrounds can conveniently and quickly enter the space; on the other hand, in order to save social cost, related departments also perform resource optimization configuration on public service facilities, and strive to achieve the balance of maximum park service population size and minimum economic cost (i.e. covering the most service population with the minimum number of parks). In recent years, researches on park sites by domestic and foreign scholars are mostly focused on large park sites such as general parks, special parks, regional greenbelts (forest parks, suburban parks, wetland parks, and the like), and the main directions of the researches include: the suitability of park site selection, the application of GIS technology in park site selection, the accessibility analysis of parks and the like have less discussion on how to select the optimal scheme of 'micro-park' site selection by using an algorithm model.
Disclosure of Invention
The invention provides a micro park site selection method based on an ant colony algorithm, aiming at the technical problems in the prior art, and the method comprises the following steps:
extracting data of residential areas and current city parks based on current land survey data and high-resolution satellite map interpretation data;
calculating the current park service range according to the set service radius, and extracting the residential area covered by the current park service range;
superposing homeland space planning data, urban green land system special planning data, violation building space range data and non-built vacant land range data in a buffer zone of an uncovered residential area, and screening out a proper micro-park construction range according to conditions;
and determining a micro-park site selection scheme in the micro-park construction range based on an improved ant colony algorithm.
According to the micro-park site selection method based on the ant colony optimization algorithm, the ant colony algorithm model is used for having strong self-organization, robustness and positive feedback mechanism and can perform distributed calculation and other characteristics to quickly screen out the optimal city park site selection scheme, so that the problems that the space layout is unreasonable, resources are wasted, the service radius cannot meet the demand and the accessibility is poor in the traditional site selection are solved.
Drawings
FIG. 1 is a flow chart of a method for locating a micro park based on an optimized ant colony algorithm according to the present invention;
FIG. 2 is an overall flow chart of a micro-park siting method based on an optimized ant colony algorithm;
FIG. 3 is a schematic view of a presence park service coverage;
FIG. 4 is a schematic diagram of a flow chart of an improved ant colony algorithm;
FIG. 5 is a schematic diagram of a search area partitioned by a grid environment model.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention. In addition, technical features of various embodiments or individual embodiments provided by the present invention may be arbitrarily combined with each other to form a feasible technical solution, and such combination is not limited by the sequence of steps and/or the structural composition mode, but must be realized by a person skilled in the art, and when the technical solution combination is contradictory or cannot be realized, such a technical solution combination should not be considered to exist and is not within the protection scope of the present invention.
Aiming at the technical problems that the park site selection should find the best scheme that the service population covered most by the minimum number/area of micro parks and the time cost required by the travel of all the service populations should be the minimum, the invention provides the micro park site selection method based on the optimized ant colony algorithm, and the best city park site selection scheme which is characterized in that the ant colony algorithm model has strong self-organization, robustness and positive feedback mechanism and can perform distributed calculation and the like is utilized to quickly screen the population covered most by the minimum number/area of micro parks and the sum of the travel costs of all the covered populations is the minimum (namely the sum of the distances from all the covered populations to the park is the shortest), so that the problems that the space layout is unreasonable, the resources are wasted, the service radius cannot meet the demands and the accessibility is poor when the traditional site selection is carried out are solved.
Fig. 1 is a flowchart of a micro-park site selection method based on an optimized ant colony algorithm provided by the present invention, as shown in fig. 1 and fig. 2, the method includes:
s1, extracting data of a residential area and a current city park based on current land survey data and high-resolution satellite map interpretation data.
It can be understood that the field research current data and the high-resolution satellite image interpretation data are collected, park green land data including suburb parks, comprehensive parks, community parks, special parks, paradises and the like in various data are extracted, data inspection is carried out, and repetition is avoided. And extracting residential land data in various plans, including first-class residential land, second-class residential land and third-class residential land, and performing data inspection to avoid repetition.
And S2, calculating the current park service range according to the set service radius, and extracting the residential area covered by the current park service range.
As an embodiment, the calculating the current park service range according to the set service radius and extracting the residential area covered by the current park service range includes: calculating the coverage area of each park according to the set service radius according to the type of each park from the boundary of each park in the extracted park green space data; fusing the coverage areas of all parks to form a park coverage area diagram; and based on an erasing tool in the GIS space analysis tool, erasing the park coverage area map from the residential land, and extracting the residential land uncovered by the park service area.
It can be understood that, the step S1 extracts the existing park data and residential site, and the step calculates the service range covered by the existing park data according to the existing park data. Specifically, the park with various extracted park data is calculated from the park boundary, and the suburban park calculates the coverage according to the service radius of 2000 m; the special park calculates the coverage range according to the service radius of 3000 meters; the comprehensive park calculates the coverage range according to the service radius of 1000 meters; the community park calculates the coverage range according to the service radius of 500 meters; the paradise calculates the coverage according to a service radius of 300 meters.
The coverage areas of all parks are fused to form a map of park coverage, namely all the coverage areas which can be covered by the existing park. And erasing a park coverage map from the residential land by using an erasing tool in the GIS space analysis tool, and extracting the residential land uncovered by the park service range.
And S3, superposing the homeland space planning data, the special planning data of the urban green land system, the illegal building space range data, the non-built vacant land range data and the urban updating range data in the buffer zone not covered with the residential zone, and analyzing to obtain the suitable micro-park construction range.
As an embodiment, the step of superposing homeland space planning data, urban green land system special planning data, violation building space range data, non-built vacant land range data and the like in the uncovered residential area buffer area, and screening according to conditions to obtain a suitable micro-park construction range includes: collecting urban homeland space planning data and urban green land system special planning data, and extracting micro park data with the area smaller than a set area threshold value in the planning data; collecting violation building space range data, non-built open space range data and city updating range data with the area smaller than the set area threshold; analyzing data on the basis of the uncovered residential area, analyzing a buffer area according to a set radius by using a buffer area analysis tool, and extracting land data which has intersection with the uncovered residential area in the set radius range from planned micro park data, illegal building space range data, non-built land range data and city update range data; screening land data which have intersection with the uncovered residential area within a set radius range to obtain a first micro-park data pool; screening the first micro-park data pool by taking the adjacent urban road as a condition to obtain a second micro-park data pool; obtaining the distribution of urban residential land buildings and the number of people accommodated in each building; and calculating the number of the population covered by each micro-park according to the set radius by adopting a buffer analysis method.
It will be appreciated that in populated areas not covered by existing parks, micro-parks need to be established, first of all, which places are suitable for establishing micro-parks.
Specifically, city homeland space planning data and city green land system special planning data are collected, and park data with the area smaller than 10000 square meters in the planning data is extracted, namely the planned micro-park data exists.
Collecting data of space range of illegal building with area less than 10000 square meters, data of range of non-built open area, data of city updating range and the like, wherein the places can be used for building micro parks.
Analyzing data on the basis of existing parks which do not cover residential areas, performing buffer area analysis by using a GIS buffer area analysis tool according to the radius of 300 meters, and extracting planned park data, illegal building space range data, non-built open space range data and city update range data which are intersected with the buffer areas, wherein the intersected places are suitable for building parks.
The method mainly analyzes and establishes the micro-park, so that a micro-park data pool 1 (hereinafter referred to as a first micro-park data pool) is obtained by screening by taking a square meter with the area of 400 square meters and less than or equal to 10000 square meters as conditions on the basis; the data in the step S34 is screened with the immediate-proximity urban road as a condition to obtain the micro-park data pool 2 (second micro-park data pool).
The distribution of urban residential buildings and the number of the population contained in each building are obtained, a buffer analysis method is adopted, the number of the population covered by the paradise in the micro-park data pool 2 is calculated according to the radius of 300 meters, and the number of the population covered by the pocket park is calculated according to the radius of 200 meters, namely the number of the population covered by each micro-park is counted.
And S4, determining a micro-park site selection scheme in the micro-park construction range based on an improved ant colony algorithm.
It will be appreciated that for the micro-park data pool 2, the most appropriate micro-park addressing scheme is determined. The embodiment of the invention adopts an improved ant colony algorithm to determine the optimal micro-park site selection method.
Firstly, introducing a basic ant colony algorithm, wherein the ant colony algorithm is a heuristic algorithm based on foraging and routing of ants in the nature and is a random search algorithm model mainly used for simulating collective behavior of the ants; the method is a heuristic algorithm, and the core of the method is to transmit selection probability through the coaction of pheromone and heuristic information. The path selected by ant is random, and the algorithm is divided into solving and updating informationTwo pheromone stages, initialization pheromone initialization on all edges
Wherein m is the number of ants (people covered by the micro-park), and/or the combination thereof>
Is a path length generated according to the nearest neighbor method. After initialization, ants randomly select cities and proceed with a selection path according to the selection probability rules as follows. For ant k, the probability of moving from location i to location j at time t, which selects the probability of j going forward from city i, is shown in equation (1).
Wherein, the first and the second end of the pipe are connected with each other,
，/>
represents the set of city nodes that ant k has visited, M is the set of total city nodes, and->
Represents the concentration of the pheromone on side (i, j) at time t, in combination with a signal from a sensor>
Referred to as a heuristic factor, <' > based on the number of pixels in the image>
Represents the distance between two points i, j in a city, for ant k, if +>
The larger the heuristic factor, the smaller the probability that an ant will select that path among the numerous paths. />
Is a heuristic factor of pheromone and reflects the existence of ants in searchingThe information accumulated in the rope process plays a role in the movement of ants, if->
The larger the value, the more the ant tends to select the path that other ants take; />
The heuristic factor is expected to reflect the degree of importance of the heuristic information of the ants in the process of searching in the ant selection path. All ants sequentially traverse all nodes from the initial node to the initial node according to formula (1), so as to obtain a solution, the process is called generation, and m ants can obtain m solutions.
In the pheromone updating stage, each ant can leave a certain amount of pheromones on the edge where each ant can pass through as the basis for solving the next round of ants, and the formula is as follows:
in the formula:
called pheromone volatilization factor, can lead ants to forget the poor decision made before in the exploration process,
the pheromone released by ant k at the last time on edge (i, j) is shown in formula (3):
in the formula (I), the compound is shown in the specification,
for the path found by ant k from t to t + 1->
Of the length of (c). It can be seen that>
The smaller, the path
The larger the pheromone increment obtained above, the greater the probability of being selected next time.
By analyzing the basic ant colony algorithm, the following disadvantages are obtained:
1) In the basic ant colony algorithm, the initialization pheromone is a fixed value, and the concentration of the initialization pheromone is uniformly distributed in each grid, so that the searching efficiency of ants is reduced.
2) The basic ant colony algorithm updates pheromones of all paths searched by ants, so that the efficiency of searching the shortest path is reduced, and the searching behaviors of the ants cannot be quickly concentrated in the neighborhood of the shortest path; due to the positive feedback effect of the ant colony algorithm, when the ant is trapped into a local optimal solution too early in the iterative search process, the search scope of the algorithm on a solution space may be limited, and the finding of a better global optimal solution by subsequent ants is hindered.
Based on this, the embodiment of the present invention is improved on the basis of the basic ant colony algorithm, and the following introduces the improved ant colony algorithm, and the flow steps of the improved ant colony algorithm can be seen in fig. 4, which includes:
a, initializing improved algorithm parameters, such as ant number m, iteration number N and pheromone elicitation factor
Desired elicitor factor->
The number h of parks to be selected; number of covered buildings>
(ii) a Number of people>
And the like.
And setting an initial pheromone concentration, wherein when the initial pheromone concentration is set, the initial pheromone concentration is aimed atThe initialization pheromone concentration uniform distribution obtained in the basic ant colony algorithm reduces the searching efficiency of ants, and the shortcoming of the algorithm is improved. In the process of the ant colony walking path, each ant searches for and selects the shortest path from the starting point to the end point. In order to avoid the phenomenon that ant colony is immobilized in situ in an optimizing path, when an pheromone concentration matrix is set, each map grid is provided with one pheromone concentration, the pheromone concentrations of all the map grids form the pheromone concentration matrix, the pheromone concentration values of the map grids at a starting point and an end point and a surrounding path are set in a gradually decreasing mode, and the pheromone concentration is set in the map grids at the starting point and the end point and the surrounding path
This interval is advantageous for avoiding the behavior of blind search in the early stage. Therefore, the method is beneficial to the ant colony to search the optimal path direction in the initial stage, and the searching efficiency is effectively improved.
It should be noted that, based on the prior knowledge, the optimal path is always concentrated near the connection line between the starting point (demand point) and the end point (target point), and the map model is divided into 2 regions of different importance, that is, a core region 1 and a normal region 2. The grid environment model divides the search area as shown in fig. 5. The concentration of the raster pheromone along the AB path in the core region is set to
The pheromone concentration of other grids is decreased according to the distance from AB until the center point of the grid model, and the pheromone concentration is reduced to
(ii) a Pheromone concentrations in general area 2 are all>
。
After the pheromone concentration is initialized, the following steps are executed:
and b, randomly arranging a map grid as an initial grid for each ant in the ant group, and selecting an adjacent grid by the ant to advance according to probability.
It can be understood that the neighborhood of the grid where the ant is currently located is searched, the serial number of the transferable free grid is recorded and stored in the matrix, the serial number is used as the next optional node, and the non-transferable grid is added into the taboo table.
And for the transferable free grid, confirming the forwarding target grid of the ant by utilizing a path selection probability formula.
Specifically, the path selection probability formula is as follows (4):
in the formula (I), the compound is shown in the specification,
represents the probability of ant k moving from grid i to grid j at time t, and->
Representing that ants can select a neighborhood grid set in the next step; />
Improved pheromone concentration for ants going from grid i to grid j at time t; />
Is a heuristic factor; />
The concentration of pheromone from the ant to the initial grid i to s; />
For a heuristic function of grid i to the initial grid, <' >>
Is a pheromone elicitor factor>
Is the desired heuristic.
It can be understood that, for the free grids where the ants can move next, the path selection probability of each free grid can be calculated according to formula (4), and the grid with the maximum path selection probability is used as the target grid where the ants move next.
c, judging whether all ants go to the terminal grid or not, if so, executing the step d; if not, returning to the step b.
It can be understood that, each ant moves according to the mode in the step b, in the moving process, after judging whether each ant moves from the starting point to the end point, if yes, executing d, if not, the ant continues to move until the end point is reached.
And d, finishing the iteration, calculating the objective function value of each ant, taking the path through which the ant corresponding to the maximum objective function value passes as the optimal path of the iteration, and updating the pheromone concentration of each path of the iteration according to an improved pheromone increment formula.
It can be understood that, after all ants move from the starting point grid to the end point grid, the iteration is finished, the corresponding objective function value is calculated for the path passed by each ant, and the path with the maximum objective function value is screened out to be used as the optimal path of the iteration.
As an example, an objective function of micro-park site selection is constructed based on the building cost of the micro-park, the total population covered by the micro-park, and the time cost required for citizens to travel to the micro-park.
Specifically, an objective function is constructed by analyzing basic conditions to be met by micro-park site selection.
The optimal scheme finally generated by the embodiment of the invention comprehensively considers the following three dimensions: (1) construction cost (the number of micro parks is preferably small); (2) coverage (i.e., coverage of a preferably large population); (3) the time cost for citizens to go out (the sum of the total distances from the population to the park in the coverage area is preferably small). Since there is a conflict between these three dimensions, i.e. when the coverage is as large as possible, it is inevitable that the construction cost is too high. The final optimization, i.e. the trade-off between these three factors, will eventually give an optimal solution that is acceptable from whatever dimension.
The objective function represents the description of the optimization objectives of the problem which needs to be solved currently, and the ant colony algorithm mainly searches through the fitness value obtained by calculating the objective function, so that the determination of the objective function is very important.
Micro-park site selection needs to meet the three dimensions, and needs to meet the following requirements:
(1) Cover the largest population in the radius with the fewest number of micro-parks:
in the formula (I), the compound is shown in the specification,
coefficients representing the objective function; />
Representing the population density on the current building; n represents dividing the residential area without park coverage into n demand grids, and then acquiring r target grids from the micro-park data pool 2;
representing the current building base area; />
And (3) representing the attraction of the h addressing positions to the population on the current building p, wherein u is an attraction coefficient, the attraction to the surrounding buildings is smaller when the value of u is larger, and the value of u is usually set to be 1.
(2) The sum of the distances from all population numbers in the coverage area to the micro-park should be minimal:
in the formula (I), the compound is shown in the specification,
to representThe Euclidean distance from q to h addressing positions of the people in a certain covered building,
representing the sum of the distances between the h address points and the road; />
Coefficients representing the objective function.
c. Constructing an objective function:
in the formula, maxf goal The representative of the maximization of the objective function is,
representing the number of iteratively selected parks, P max Represents the maximum value of the population number within the coverage radius, D min Representing the minimum of the sum of the distances of all the people to the mini-park, an objective function->
And when the value is maximum, the iteration optimal path is obtained.
And (3) calculating the objective function value of each path of the iteration through a formula (7), and updating the pheromone concentration of each path after the iteration after finding the optimal path. Specifically, the pheromone concentration of each path is updated according to the improved pheromone increment formulas (8) to (9) by taking the thought of an elite strategy ant colony system as reference. I.e. after each iteration, the path taken by the elite ant that found the global optimal solution (i.e. the objective function value is maximal) is given an extra amount of pheromone, making the current optimal solution more attractive to ants in the next iteration. At this time, the pheromone update formula is as follows:
in the formula:
for improved pheromones, be>
Represents the additional increment of pheromone on the path (i, j) taken by elite ants.
Considering the influence of iteration times, the pheromone increment formula is improved as follows:
in the formula, U represents the constant of pheromone released by ants on the passing path; n represents the total number of iterations,
representing the current iteration number; />
Indicating the number of elite ants. By means of this incremental improvement formula, it can be concluded that, as the number of iterations N increases, a value is based on>
And &>
The value of (A) is gradually increased, the positive feedback effect of the algorithm is gradually enhanced, and the search range can be slowly concentrated to the neighborhood of the current optimal solution. The method can ensure that the algorithm can search a solution space as comprehensively as possible in the initial stage of iteration, can also ensure the convergence efficiency in the later stage of iteration, and cannot fall into a local optimal solution too early, so that a global optimal solution cannot be found.
It will be appreciated that for the optimal path after this iteration, the pheromone concentration is updated according to equation (8) and equation (9), and for the other paths, according to the first term in equation (8), i.e. according to the first term in equation (8)
Its pheromone concentration is updated, i.e. for the optimal path it is increased more than for the other paths.
And e, taking the updated pheromone concentration of each path after the iteration is finished as the initial pheromone concentration of the next iteration, and repeatedly executing the steps b to e.
It can be understood that the pheromone concentration of each ant (corresponding to each path) updated after the last iteration is finished is used as the initial pheromone concentration in the next iteration, the steps b to e are repeatedly executed, the loop iteration is carried out, and the optimal path after each iteration is found.
And f, when the iteration times reach the maximum iteration times, obtaining the optimal path of each iteration, and determining the optimal micro-park site selection scheme based on the optimal path of each iteration.
It can be understood that when the number of loop iterations reaches the set maximum number of iterations, the iteration is terminated, and the optimal path after the last iteration, namely the optimal addressing scheme of the micro-park, is obtained.
The method for selecting the site of the micro park, which is provided by the invention, has the following advantages that:
(1) High efficiency: the park belongs to public service facilities, generally is selected and built by government departments, in the previous site selection process, taking a certain city as an example, a natural resource department firstly leads to a park distribution scheme based on related planning data, and then consults 5 departments, such as housing, urban and rural construction bureaus, development and reform bureaus, transportation bureaus, emergency management bureaus and municipal garden affair centers, to determine a final scheme, wherein the time of the natural resource department is spent for at least 1 person and 2 days, and the time of the other departments for 5 persons is 0.5 days. The urban micro-park site selection method adopting the ant colony algorithm optimized in the invention can output a scientific and reasonable micro-park site selection scheme within 2 hours by only 1 person, greatly improves the efficiency of micro-park site selection, and saves administrative cost.
(2) Scientifically: the method can quantitatively calculate that the resident population is covered to the maximum extent by the minimum park number, the sum of the cost from the covered population to the park is minimum, the technical difficulties that the original site selection method is difficult to quantify and unscientific are solved, the park service radius coverage rate can be scientifically and effectively improved, and the balance of the park service population scale maximization and the economic cost minimization is obtained.
(3) Universality: the invention constructs a model based on the specific requirements of '300 meters seeing green and 500 meters seeing garden', can obtain the optimal site selection scheme by inputting corresponding parameters and data, and is suitable for large cities and small cities.
It should be noted that, in the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to relevant descriptions of other embodiments for parts that are not described in detail in a certain embodiment.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (9)
1. A micro park site selection method based on an ant colony optimization algorithm is characterized by comprising the following steps:
extracting data of residential areas and current city parks based on the current land investigation data and the high-resolution satellite map interpretation data;
calculating the current park service range according to the set service radius, and extracting the residential area covered by the current park service range;
superposing the homeland space planning data, the special planning data of the urban green land system, the space range data of the illegal buildings and the range data of the non-built vacant lands in the buffer zone of the uncovered residential zone, and screening out the suitable micro-park construction range according to conditions;
and determining a micro-park site selection scheme in the micro-park construction range based on an improved ant colony algorithm.
2. The method of claim 1, wherein the calculating a current park service range according to a set service radius and extracting a residential area covered by the current park service range includes:
calculating the coverage area of each park according to the set service radius according to the type of each park from the boundary of each park in the extracted park green space data;
fusing the coverage areas of all parks to form a park coverage area diagram;
and based on an erasing tool in the GIS space analysis tool, erasing the park coverage area map from the residential land, and extracting the residential land uncovered by the park service area.
3. The micro-park site selection method of claim 1, wherein the step of overlaying homeland space planning data, urban green space system special planning data, illegal building space range data and non-built vacant land range data in the uncovered residential buffer zone and screening the suitable micro-park construction range according to conditions comprises the steps of:
collecting urban homeland space planning data and urban green land system special planning data, and extracting micro park data with an area smaller than a set area threshold value in the planning data;
collecting violation building space range data, non-built open space range data and city updating range data with the area smaller than the set area threshold;
analyzing data on the basis of the uncovered residential area, performing buffer area analysis according to a set radius by using a buffer area analysis tool, and extracting land data which has intersection with the uncovered residential area in the set radius range from planned micro park data, illegal building space range data, non-built vacant land range data and city update range data;
screening land data which have intersection with the uncovered residential area within a set radius range to obtain a first micro-park data pool;
screening the first micro-park data pool by taking the adjacent city road as a condition to obtain a second micro-park data pool;
acquiring the distribution of urban residential land buildings and the number of population contained in each building;
and calculating the number of the population covered by each micro-park according to the set radius by adopting a buffer analysis method.
4. The micro park site selection method of claim 1, wherein determining a micro park site selection plan based on the improved ant colony algorithm within the micro park construction scope comprises:
initializing ant colony algorithm parameters and setting initial pheromone concentration;
b, randomly arranging a map grid for each ant in the ant group as an initial grid, and selecting an adjacent grid by the ant to advance according to probability;
c, judging whether all ants go to the terminal grid or not, if so, executing the step d; if not, returning to the step b;
d, finishing the iteration, calculating an objective function value of each ant, taking the path through which the ant passes corresponding to the maximum objective function value as the optimal path of the iteration, and updating the pheromone concentration of each path of the iteration according to an improved pheromone increment formula;
e, taking the updated pheromone concentration of each path after the iteration is finished as the initial pheromone concentration of the next iteration, and repeatedly executing the steps b-e;
and f, after each iteration is finished, updating the optimal path, and when the iteration times reach the maximum iteration times, determining the obtained optimal path as the optimal micro-park site selection scheme.
5. A micro-park addressing method according to claim 4, wherein said randomly arranging for each ant in the ant colony a map grid as a starting grid, ants choose adjacent grids to go forward according to probability, comprising:
searching a neighborhood of a grid where the ant is currently located, recording the serial number of the transferable free grid, storing the serial number into a matrix, using the matrix as a next optional node, and adding the non-transferable grid into a taboo table;
for the transferable free grids, calculating the moving probability of each ant from the current grid to each transferable free grid based on a path selection probability formula, and determining the free grid corresponding to the maximum moving probability as a target grid for the ant to go forward;
wherein the path selection probability formula is:
in the formula (I), the compound is shown in the specification,
represents the ant k, the probability of moving from grid i to grid j at time t, and->
Representing that ants can select a neighborhood grid set in the next step; />
Improved pheromone concentration for ants going from grid i to grid j at time t;
a heuristic for going from grid i to grid j at time t; />
The improved pheromone concentration of the ants from the grid i to the initial grid s at the time t; />
For a heuristic function of grid i to an initial grid s, <' >>
Elicitation of pheromonesSub-, R>
Is the desired heuristic.
6. A micro park site selection method according to claim 5, further comprising:
and constructing an objective function of micro-park site selection based on the construction cost of the micro-park, the total population number covered by the micro-park and the time cost required for citizens to travel to the micro-park.
7. The micro-park siting method according to claim 6, wherein constructing an objective function of micro-park siting based on the building cost of micro-park, the total population covered by micro-park and the time cost required for citizens to travel to micro-park comprises:
cover the largest population in the radius with the fewest number of micro-parks:
in the formula (I), the compound is shown in the specification,
coefficients representing the objective function; />
Representing population density on the current building p; n represents that a residential area without park coverage is divided into n map grids, and then r target grids are obtained from a second micro-park data pool;
represents the base area of the current building p; />
Representing the attraction of the h addressing location points to the population on the current building p, wherein u is an attraction coefficient, and the larger the value of u is, the larger the attraction coefficient is, the attraction coefficient indicates thatSetting the value of u to be 1 when the attraction to the surrounding buildings is smaller;
the sum of the distances from the micro-park to all population numbers in the coverage area should be minimal:
in the formula (I), the compound is shown in the specification,
representing the Euclidean distance of q to h addressed locations of a person within a certain building covered, and->
Representing the sum of the distances between the h selected points and the road; />
Coefficients representing the objective function;
constructing an objective function:
in the formula, maxf goal The representative of the maximization of the objective function is,
indicating the number of iteratively selected parks, P max Represents the maximum value of the population number within the coverage radius, D min The minimum value of the sum of the distances from all the population to the micro-park is represented, and the objective function
And when the value is maximum, the iteration optimal path is obtained.
8. A micro-park addressing method according to claim 5, wherein in step d, updating pheromone concentration of each path of the current iteration according to an improved pheromone increment formula comprises:
for the optimal path, the pheromone concentration is updated based on the following formula:
in the formula (I), the compound is shown in the specification,
for improved pheromone concentration, be->
Represents additional increments of pheromones on the path (i, j) taken by elite ants, and/or>
Is pheromone volatilization factor;
wherein the pheromone increment formula is as follows:
in the formula, U represents the constant of pheromone released by ants on the passing path; n represents the total number of iterations,
representing the current iteration number; />
Expressing the number of elite ants;
for the other paths, the pheromone concentration is updated based on the following formula:
9. the micro-park addressing method according to claim 4, wherein determining the optimal micro-park addressing scheme based on the optimal path of the final iteration in step f comprises:
and selecting an optimal path which is continuously updated according to iteration as an optimal micro-park site selection scheme.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310224161.8A CN115965171A (en) | 2023-03-10 | 2023-03-10 | Micro-park site selection method based on ant colony optimization algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310224161.8A CN115965171A (en) | 2023-03-10 | 2023-03-10 | Micro-park site selection method based on ant colony optimization algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115965171A true CN115965171A (en) | 2023-04-14 |
Family
ID=87354959
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310224161.8A Pending CN115965171A (en) | 2023-03-10 | 2023-03-10 | Micro-park site selection method based on ant colony optimization algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115965171A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116128014A (en) * | 2023-04-17 | 2023-05-16 | 深圳市明源云科技有限公司 | Hydrant layout method, device, electronic equipment and computer readable storage medium |
| CN116862063A (en) * | 2023-07-12 | 2023-10-10 | 山东宜鑫致远信息科技有限公司 | Smart city planning optimization method and system based on big data |
| CN117649063A (en) * | 2024-01-30 | 2024-03-05 | 东莞市城建规划设计院 | Public service facility site selection planning method based on demographic big data |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103914734A (en) * | 2014-03-20 | 2014-07-09 | 浙江工业大学 | Micro-grid capacity address optimizing and distributing method based on improved ant colony algorithm |
| CN104504603A (en) * | 2014-12-03 | 2015-04-08 | 住房和城乡建设部城乡规划管理中心 | Urban garden digital system and site selection method |
| CN105787595A (en) * | 2016-02-29 | 2016-07-20 | 泰华智慧产业集团股份有限公司 | Emergency logistic transfer station site selection method based on improved ant colony algorithm |
| CN109993349A (en) * | 2019-03-11 | 2019-07-09 | 同济大学 | A kind of optimization method and device of city refuge addressing |
| CN111523698A (en) * | 2020-03-20 | 2020-08-11 | 全球能源互联网集团有限公司 | Ant colony site selection method and device for macroscopically site selection of clean energy base |
| CN113034323A (en) * | 2021-02-20 | 2021-06-25 | 温州设计集团有限公司 | Intelligent garden management platform based on GIS and big data technology |
| CN114240098A (en) * | 2021-12-02 | 2022-03-25 | 浙江大学德清先进技术与产业研究院 | Multi-source data-based intelligent garden supervision and park site selection method |
| CN115330086A (en) * | 2022-10-11 | 2022-11-11 | 吉奥时空信息技术股份有限公司 | Photovoltaic land automatic site selection method under multi-condition constraint of spatial big data |
-
2023
- 2023-03-10 CN CN202310224161.8A patent/CN115965171A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103914734A (en) * | 2014-03-20 | 2014-07-09 | 浙江工业大学 | Micro-grid capacity address optimizing and distributing method based on improved ant colony algorithm |
| CN104504603A (en) * | 2014-12-03 | 2015-04-08 | 住房和城乡建设部城乡规划管理中心 | Urban garden digital system and site selection method |
| CN105787595A (en) * | 2016-02-29 | 2016-07-20 | 泰华智慧产业集团股份有限公司 | Emergency logistic transfer station site selection method based on improved ant colony algorithm |
| CN109993349A (en) * | 2019-03-11 | 2019-07-09 | 同济大学 | A kind of optimization method and device of city refuge addressing |
| CN111523698A (en) * | 2020-03-20 | 2020-08-11 | 全球能源互联网集团有限公司 | Ant colony site selection method and device for macroscopically site selection of clean energy base |
| CN113034323A (en) * | 2021-02-20 | 2021-06-25 | 温州设计集团有限公司 | Intelligent garden management platform based on GIS and big data technology |
| CN114240098A (en) * | 2021-12-02 | 2022-03-25 | 浙江大学德清先进技术与产业研究院 | Multi-source data-based intelligent garden supervision and park site selection method |
| CN115330086A (en) * | 2022-10-11 | 2022-11-11 | 吉奥时空信息技术股份有限公司 | Photovoltaic land automatic site selection method under multi-condition constraint of spatial big data |
Non-Patent Citations (1)
| Title |
|---|
| 张金光等: "基于GIS 适宜性评价的中小城市公园选址研究", 南京林业大学学报( 自然科学版) * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116128014A (en) * | 2023-04-17 | 2023-05-16 | 深圳市明源云科技有限公司 | Hydrant layout method, device, electronic equipment and computer readable storage medium |
| CN116862063A (en) * | 2023-07-12 | 2023-10-10 | 山东宜鑫致远信息科技有限公司 | Smart city planning optimization method and system based on big data |
| CN116862063B (en) * | 2023-07-12 | 2024-04-19 | 甘肃飞天云科技信息有限公司 | Smart city planning optimization method and system based on big data |
| CN117649063A (en) * | 2024-01-30 | 2024-03-05 | 东莞市城建规划设计院 | Public service facility site selection planning method based on demographic big data |
| CN117649063B (en) * | 2024-01-30 | 2024-05-07 | 东莞市城建规划设计院 | Public service facility site selection planning method based on demographic big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115965171A (en) | Micro-park site selection method based on ant colony optimization algorithm | |
| CN109919819B (en) | Construction, evaluation and optimization method of regional ecological network | |
| CN109559055A (en) | The landscape ecological efficiency evaluation method of civic landscape planning | |
| CN108446470A (en) | Medical facilities analysis method of reachability based on track of vehicle data and population distribution | |
| CN115630978B (en) | Multi-traffic facility site selection method based on population employment distribution | |
| Ahmed | Modelling spatio-temporal urban land cover growth dynamics using remote sensing and GIS techniques: A case study of Khulna City | |
| CN112954623B (en) | Resident occupancy rate estimation method based on mobile phone signaling big data | |
| CN115641718B (en) | Short-time traffic flow prediction method based on bayonet flow similarity and semantic association | |
| CN114418215A (en) | Smart city power transmission line planning method based on artificial intelligence | |
| Hamdy | Using remote sensing techniques to assess the changes in the rate of urban green spaces in Egypt: a case study of greater Cairo | |
| Mao et al. | Quantifying spatiotemporal dynamics of urban building and material metabolism by combining a random forest model and GIS-based material flow analysis | |
| Samper | An urban design framework of informal development stages: Exploring self-build and growth in informal settlements | |
| CN116415756B (en) | Urban virtual scene experience management system based on VR technology | |
| ZiaeeVafaeyan et al. | Land use change model based on bee colony optimization, Markov chain and a neighborhood decay cellular automata | |
| CN107067075B (en) | Urban land ecological safety space detection model based on artificial bee colony algorithm | |
| CN117407470A (en) | Green space ecological optimization decision-making auxiliary system and method based on big data | |
| Beirão et al. | Urban design with patterns and shape rules | |
| Talebi et al. | Forest road planning to improve tourism accessibility: a comparison of different methods applied in a real case study | |
| CN117037483A (en) | Traffic flow prediction method based on multi-head attention mechanism | |
| CN116756695A (en) | Urban function collaborative optimization method integrating geographic features and flow features | |
| CN117151499A (en) | Monitoring and evaluating method and system for homeland space planning | |
| CN116307857A (en) | Built-up area environment evaluation method based on remote sensing image scene understanding | |
| CN113988659B (en) | Three-dimensional compact digital city design method and device and computer equipment | |
| Sun et al. | Study on safe evacuation routes based on crowd density map of shopping mall | |
| Yang et al. | An adaptive workflow to generate street network and amenity allocation for walkable neighborhood design |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230414 |
|
| RJ01 | Rejection of invention patent application after publication |