CN108495252A - Indoor positioning network element Optimal Deployment Method based on genetic algorithm and simulated annealing - Google Patents
Indoor positioning network element Optimal Deployment Method based on genetic algorithm and simulated annealing Download PDFInfo
- Publication number
- CN108495252A CN108495252A CN201810165059.4A CN201810165059A CN108495252A CN 108495252 A CN108495252 A CN 108495252A CN 201810165059 A CN201810165059 A CN 201810165059A CN 108495252 A CN108495252 A CN 108495252A
- Authority
- CN
- China
- Prior art keywords
- network element
- genetic algorithm
- simulated annealing
- optimal
- layout
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/025—Services making use of location information using location based information parameters
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/02—Arrangements for optimising operational condition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/33—Services specially adapted for particular environments, situations or purposes for indoor environments, e.g. buildings
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
Abstract
The invention discloses the indoor positioning network element Optimal Deployment Methods based on genetic algorithm and simulated annealing, belong to indoor positioning field, comprise the following steps：Step (1)：Carry out network element layout；Step (2)：Determine the control parameter that self-adapted genetic algorithm needs；Step (3)：Network element layout is initialized；Step (4)：Calculate fitness；Step (5)：Determine whether to meet the hereditary condition of convergence；Step (6)：Select the higher network element layout of fitness；Step (7)：Crossover operation is carried out to binary coding and obtains filial generation；Step (8)：Inversion operation is carried out to binary coding to be made a variation；Step (9)：It generates new network element and lays space；Step (10)：Simulated annealing operation is carried out to group；Step (11)：Generate optimal network element layout result；Step (12)：Optimal network element layout result is exported, is terminated.The existing stronger ability of searching optimum of the present invention, also has stronger local search ability, improves positioning accuracy, improve search efficiency.
Description
Technical field
The invention belongs to indoor positioning fields, more particularly to the indoor positioning network element based on genetic algorithm and simulated annealing is excellent
Change layout method.
Background technology
With the development of network technology and the communication technology, location-based service becomes to become more and more important, since the overwhelming majority of people is living
It is dynamic all to carry out indoors, therefore indoor positioning is concerned by people more and more, wherein the indoor positioning based on UWB
Technology can reach the positioning accuracy of Centimeter Level under specific scene, be widely used in various indoor positioning products
In, but the locating base station deployment cost of UWB is very high, when the limited amount of network element, how being laid out can make positioning believe
Number coverage area is maximum, positioning accuracy is up to a meaningful research topic.
Network element optimization location problem is a np hard problem, and current research is all rested on to be found most using heuritic approach
The degree of excellent solution.Wherein genetic algorithm can in a random way seek from probability meaning to optimal solution, document " Agapie A,
Wright A H.Theoretical analysis of steady state genetic algorithms[J]
.Applications of Mathematics,2014,59(5):509-525.Theoretical analysis of
Steady state genetic algorithms " solve the planning problem of wireless network using genetic algorithm, but hereditary
There is no feasible feedback mechanisms for algorithm, the problems such as will produce a large amount of redundancy iteration in some cases, cause efficiency low, together
When practical application in genetic algorithm will appear be also easy to produce precocious phenomenon, the problems such as local optimal searching ability is poor.Simulated annealing
With stronger local search ability, and search process can be made to avoid being absorbed in locally optimal solution, it is not suitable for entire search space,
It is difficult to which search process is made to enter most promising region of search.Document " Han R, Feng C, Xia H, et al.Coverage
optimization for dense deployment small cell based on ant colony algorithm
[C],2014IEEE80th.IEEE,2014:1-5 " is laid out the mainly cost by network element deployment using ant group algorithm to network element
It is used as packing objective with covering, but in the initial stage of ant group algorithm search, there are the feelings seldom even without available information
Condition, therefore ant group algorithm convergence rate is slow.Indoors in terms of location simulation, a kind of high-precision indoor positioning analogue system of document
Research and realization, a kind of network element can be inputted in specific indoor scene and is laid out to obtain the positioning signal covering of area to be targeted
Rate and average localization error.
Invention content
It is an object of the invention to open local search abilities strong, the efficient room based on genetic algorithm and simulated annealing
Interior positioning network element Optimal Deployment Method.
The object of the present invention is achieved like this：
Indoor positioning network element Optimal Deployment Method based on genetic algorithm and simulated annealing, comprises the following steps：
Step (1)：Carry out network element layout：Network element is numbered and laid to the sequence of positions that network element can be laid, while will be each
The number of network element is converted into binary coding：
The gridding in the plan view of specific indoor scene, it is believed that the intersection point of grid is that can lay net on indoor scene exterior wall
Network element is laid in all positions for laying network element and is numbered in order, while the number of each network element being converted in the position of member
For binary coding.
Step (2)：Determine the control parameter that self-adapted genetic algorithm needs, including population scale, maximum iteration, friendship
Pitch probability and mutation probability：
Self-adapted genetic algorithm need control parameter include：Population scale, maximum iteration, crossover probability and variation
Probability.In network element layout, n network element is needed, the binary coding of each network element is m bits, each network element layout
Regard the chromosome of a long len=n*m as.If population invariable number is k, population scale is the matrix of k*len.
Step (3)：Network element layout is initialized：N inequality of random selection in network element group is laid all
Network element is laid out as initial NE；
Step (4)：Calculate fitness：
Fitness：
In above formula, N indicates the number of localization region test point, ERRORiIndicate the position error of anchor point i.
Step (5)：Whether iterative criterion meets the hereditary condition of convergence, and step is jumped to if meeting the hereditary condition of convergence
(9), step (6) is otherwise jumped to；
Step (6)：Select the higher network element layout of fitness：
A random number r is generated between 0 and total fitness, then in the way of roulette to population at individual carry out with
Machine is sampled, population at individual xiSelected probability F (xi)：
In above formula, f (xi) it is population at individual xiFitness；The higher network element layout of fitness is chosen.
Step (7)：By the higher network element layout of fitness according to crossover probability PbCrossover operation is carried out to binary coding
Obtain filial generation：
Take single-point crossover operation：Random real number 0≤r≤1 is firstly generated, crossover probability 0 is set<Pb<1, if r
<PbThen intersected, otherwise without.If necessary to intersect, then crossover location is randomly choosed again, after crossover location
Binary string coding exchange.
Step (8)：By the higher network element layout of fitness according to mutation probability PyInversion operation is carried out to binary coding
It is made a variation：
Random real number 0≤r≤1 is generated, if r<PyThen into row variation, 0<Py<1 is mutation probability；It such as needs to carry out
Variation, it is necessary first to definitive variation position rand*chromo_size, if 0 without variation, otherwise to variable position
Binary coding carries out inversion operation and generates variation, makes 1 to become 0,0 and becomes 1.
Step (9)：Local optimum network element layout result is generated, and new network element is generated according to coordinate information and lays space：
After obtaining local optimum network element layout result by self-adapted genetic algorithm, local optimum network element layout result is converted
Binary coding be decimal coded and corresponding coordinate information.Under the premise of keeping height value z constant, in xOy planes
Centered on each network element position in local optimum network element layout result, regular hexagon is done respectively, and calculate each positive six
Centered on the coordinate information and each network element position of side shape vertex position space is laid together as new network element.；Positive six side
Newly number is to add behind decimal coded " 00 " to the network element of the central point of shape, and the vertex number of each regular hexagon is by positive six side
According to addition " 01 " " 02 " " 03 " " 04 " " 05 " successively clockwise behind the decimal coded of the network element of the central point of shape
“06”。
Step (10)：Simulated annealing operation is carried out to group with the network element placement algorithm of simulated annealing, is got relatively most
The method of excellent network element layout：
The network element placement algorithm of simulated annealing：From a certain higher temperature, with the decline of temperature parameter, according to current
The positioning accuracy of network element layout is laid spatial positioning accuracy with new network element and is received new network element laying space with certain probability, is led to
Randomly selecting for the be possible to situation being laid out to network element in entire physical space is crossed, relatively optimal network element cloth is finally got
The method of office.
Step (11)：Optimal network element layout result is generated with the method that relatively optimal network element is laid out；
Step (12)：Optimal network element layout result is exported, is terminated.
Beneficial effects of the present invention are：
The present invention incorporates mechanism of Simulated Annealing wherein using self-adapted genetic algorithm as main process, is carried out adjusting and optimizing
Group.Existing stronger ability of searching optimum, also has stronger local search ability, improves positioning accuracy.Due to carry out
Network element layout group, the network element layout result for not only increasing search efficiency, and obtaining are changed before simulated annealing
It is more nearly actual optimal network element layout result.
Description of the drawings
Fig. 1 is the indoor positioning network element Optimal Deployment Method flow chart based on genetic algorithm and simulated annealing；
Fig. 2 is network element layout change schematic diagram in specific implementation mode scene；
No. 3 network elements recompiles situation schematic diagram in Fig. 3 specific implementation scenes.
Specific implementation mode
Further describe the present invention below in conjunction with the accompanying drawings：
Indoor positioning network element Optimal Deployment Method based on genetic algorithm and simulated annealing, comprises the following steps：
Step (1)：Carry out network element layout：Network element is numbered and laid to the sequence of positions that network element can be laid, while will be each
The number of network element is converted into binary coding：
The gridding in the plan view of specific indoor scene, it is believed that the intersection point of grid is that can lay net on indoor scene exterior wall
Network element is laid in all positions for laying network element and is numbered in order, while the number of each network element being converted in the position of member
For binary coding.
Step (2)：Determine the control parameter that self-adapted genetic algorithm needs, including population scale, maximum iteration, friendship
Pitch probability and mutation probability：
Self-adapted genetic algorithm need control parameter include：Population scale, maximum iteration, crossover probability and variation
Probability.In network element layout, n network element is needed, the binary coding of each network element is m bits, each network element layout
Regard the chromosome of a long len=n*m as.If population invariable number is k, population scale is the matrix of k*len.
Step (3)：Network element layout is initialized：N inequality of random selection in network element group is laid all
Network element is laid out as initial NE；
Step (4)：Calculate fitness：
Fitness：
In above formula, N indicates the number of localization region test point, ERRORiIndicate the position error of anchor point i.
Step (5)：Whether iterative criterion meets the hereditary condition of convergence, and step is jumped to if meeting the hereditary condition of convergence
(9), step (6) is otherwise jumped to；
Step (6)：Select the higher network element layout of fitness：
A random number r is generated between 0 and total fitness, then in the way of roulette to population at individual carry out with
Machine is sampled, population at individual xiSelected probability F (xi)：
In above formula, f (xi) it is population at individual xiFitness；The higher network element layout of fitness is chosen.
Step (7)：By the higher network element layout of fitness according to crossover probability PbCrossover operation is carried out to binary coding
Obtain filial generation：
Take single-point crossover operation：Random real number 0≤r≤1 is firstly generated, crossover probability 0 is set<Pb<1, if r
<PbThen intersected, otherwise without.If necessary to intersect, then crossover location is randomly choosed again, after crossover location
Binary string coding exchange.
Step (8)：By the higher network element layout of fitness according to mutation probability PyInversion operation is carried out to binary coding
It is made a variation：
Random real number 0≤r≤1 is generated, if r<PyThen into row variation, 0<Py<1 is mutation probability；It such as needs to carry out
Variation, it is necessary first to definitive variation position rand*chromo_size, if 0 without variation, otherwise to variable position
Binary coding carries out inversion operation and generates variation, makes 1 to become 0,0 and becomes 1.
Step (9)：Local optimum network element layout result is generated, and new network element is generated according to coordinate information and lays space：
After obtaining local optimum network element layout result by self-adapted genetic algorithm, local optimum network element layout result is converted
Binary coding be decimal coded and corresponding coordinate information.Under the premise of keeping height value z constant, in xOy planes
Centered on each network element position in local optimum network element layout result, regular hexagon is done respectively, and calculate each positive six
Centered on the coordinate information and each network element position of side shape vertex position space is laid together as new network element.；Positive six side
Newly number is to add behind decimal coded " 00 " to the network element of the central point of shape, and the vertex number of each regular hexagon is by positive six side
According to addition " 01 " " 02 " " 03 " " 04 " " 05 " successively clockwise behind the decimal coded of the network element of the central point of shape
“06”。
Step (10)：Simulated annealing operation is carried out to group with the network element placement algorithm of simulated annealing, is got relatively most
The method of excellent network element layout：
The network element placement algorithm of simulated annealing：From a certain higher temperature, with the decline of temperature parameter, according to current
The positioning accuracy of network element layout is laid spatial positioning accuracy with new network element and is received new network element laying space with certain probability, is led to
Randomly selecting for the be possible to situation being laid out to network element in entire physical space is crossed, relatively optimal network element cloth is finally got
The method of office.
Step (11)：Optimal network element layout result is generated with the method that relatively optimal network element is laid out；
Step (12)：Optimal network element layout result is exported, is terminated.
Embodiment 1 is given below：
Such as Fig. 2 a, Fig. 2 b, Fig. 2 c, I represents the wall of building, and II represents network element, and dark network element is currently available
Network element layout result.The size of scene is 8m*4m*3m, due to engineering construction require can only be on the wall and from wall 1m within
Network element is laid in place, therefore density of setting is the grid of 2m*2m on plane map, and on the wall by the setting of network element installation position
Grid on, totally 12, the random distribution highly between 2.8m-3m, using the position of No. 1 network element as coordinate origin according to up time
Network element number is successively 1-12 by needle.
Step (1)：Binary coding is carried out to it, since network element number is up to 12, uses tetrad
It is encoded, " 1-12 " number network element is encoded to " 0001-1100 " successively；
Step (2)：Determine that population scale is 50, maximum iteration 20, crossover probability 0.6, mutation probability are
0.01；
Step (3)：Rule of thumb select to number four network elements for 1,5,7,11 as initial layout, as shown in Figure 2 a；
Step (4)：Fitness is calculated according to published high-precision indoor positioning analogue system above-mentioned；
Step (5)：Whether iterative criterion fitness meets the condition less than 3m, jumps to step (9) if met, is unsatisfactory for
It jumps to step (6) and is ready for genetic manipulation；
Step (6) arrives step (8)：It is laid out in group in network element and carries out genetic manipulation, obtain locally optimal solution, it is assumed that met
It is 3,8,10, No. 12 network elements after the locally optimal solution transcoding obtained when the condition of convergence, as shown in Figure 2 b；
Step (9)：Change network element layout group simultaneously to recompile it, such as Fig. 3, by taking No. 3 network elements as an example, including 7
A network element position, therefore share 7*4=28 network element in new network element layout group；
Step (10) arrives step (12)：To above-mentioned group carry out simulated annealing operation, obtain network element layout result be 300,
801,1004, No. 1204 network elements, as shown in Figure 2 c.
The present invention incorporates mechanism of Simulated Annealing wherein using self-adapted genetic algorithm as main process, is carried out adjusting and optimizing
Group.Existing stronger ability of searching optimum, also has stronger local search ability, improves positioning accuracy.Due to carry out
Network element layout group, the network element layout result for not only increasing search efficiency, and obtaining are changed before simulated annealing
It is more nearly actual optimal network element layout result.
The above is not intended to restrict the invention, and for those skilled in the art, the present invention can have various
Change and variation.All within the spirits and principles of the present invention, any modification, equivalent replacement, improvement and so on should all include
Within protection scope of the present invention.
Claims (9)
1. the indoor positioning network element Optimal Deployment Method based on genetic algorithm and simulated annealing, it is characterised in that：Including following step
Suddenly：
Step (1)：Carry out network element layout：Network element is numbered and laid to the sequence of positions that network element can be laid, while by each network element
Number be converted into binary coding；
Step (2)：Determine the control parameter that self-adapted genetic algorithm needs, including population scale, maximum iteration, intersection are generally
Rate and mutation probability；
Step (3)：Network element layout is initialized：In all network elements for laying n inequality of random selection in network element group
It is laid out as initial NE；
Step (4)：Calculate fitness；
Step (5)：Whether iterative criterion meets the hereditary condition of convergence, and step (9) is jumped to if meeting the hereditary condition of convergence,
Otherwise step (6) is jumped to；
Step (6)：Select the higher network element layout of fitness；
Step (7)：By the higher network element layout of fitness according to crossover probability PbCrossover operation is carried out to binary coding and obtains son
Generation；
Step (8)：By the higher network element layout of fitness according to mutation probability PyInversion operation is carried out to binary coding to be become
It is different；
Step (9)：Local optimum network element layout result is generated, and new network element is generated according to coordinate information and lays space；
Step (10)：Simulated annealing operation is carried out to group with the network element placement algorithm of simulated annealing, is got relatively optimal
The method of network element layout；
Step (11)：Optimal network element layout result is generated with the method that relatively optimal network element is laid out；
Step (12)：Optimal network element layout result is exported, is terminated.
2. the indoor positioning network element Optimal Deployment Method according to claim 1 based on genetic algorithm and simulated annealing,
It is characterized in that：The step (1) is specially：
The gridding in the plan view of specific indoor scene, it is believed that the intersection point of grid is that can lay network element on indoor scene exterior wall
Network element is laid in all positions for laying network element and is numbered in order, while the number of each network element is converted into two in position
Scale coding.
3. the indoor positioning network element Optimal Deployment Method according to claim 1 based on genetic algorithm and simulated annealing,
It is characterized in that：The step (2) is specially：
Self-adapted genetic algorithm need control parameter include：Population scale, maximum iteration, crossover probability and variation are general
Rate；In network element layout, n network element is needed, the binary coding of each network element is m bits, each network element layout is seen
At the chromosome of a long len=n*m；If population invariable number is k, population scale is the matrix of k*len.
4. the indoor positioning network element Optimal Deployment Method according to claim 1 based on genetic algorithm and simulated annealing,
It is characterized in that：Fitness in the step (4)：
In above formula, N indicates the number of localization region test point, ERRORiIndicate the position error of anchor point i.
5. the indoor positioning network element Optimal Deployment Method according to claim 1 based on genetic algorithm and simulated annealing,
It is characterized in that：The step (6) is specially：
A random number r is generated between 0 and total fitness, then population at individual is taken out at random in the way of roulette
Sample, population at individual xiSelected probability F (xi)：
In above formula, f (xi) it is population at individual xiFitness；The higher network element layout of fitness is chosen.
6. the indoor positioning network element Optimal Deployment Method according to claim 1 based on genetic algorithm and simulated annealing,
It is characterized in that：The step (7) is specially：
Take single-point crossover operation：Random real number 0≤r≤1 is firstly generated, crossover probability 0 is set<Pb<1, if r<PbThen
Intersected, otherwise without；If necessary to intersect, then randomly choose crossover location again, by crossover location it is later two
System string encoding is exchanged.
7. the indoor positioning network element Optimal Deployment Method according to claim 1 based on genetic algorithm and simulated annealing,
It is characterized in that：The step (8) is specially：
Random real number 0≤r≤1 is generated, if r<PyThen into row variation, 0<Py<1 is mutation probability；Such as become
It is different, it is necessary first to definitive variation position rand*chromo_size, if 0 without variation, otherwise to the two of variable position
Scale coding carries out inversion operation and generates variation, makes 1 to become 0,0 and becomes 1.
8. the indoor positioning network element Optimal Deployment Method according to claim 1 based on genetic algorithm and simulated annealing,
It is characterized in that：The step (9) is specially：
After local optimum network element layout result being obtained by self-adapted genetic algorithm, the two of conversion local optimum network element layout result
Scale coding is decimal coded and corresponding coordinate information；Under the premise of keeping height value z constant, with office in xOy planes
Centered on each network element position in the optimal network element layout result in portion, regular hexagon is done respectively, and calculate each regular hexagon
Centered on the coordinate information of vertex position and each network element position space is laid together as new network element；Regular hexagon
Newly number is to add behind decimal coded " 00 " to the network element of central point, and the vertex number of each regular hexagon is by regular hexagon
According to addition " 01 " " 02 " " 03 " " 04 " " 05 " " 06 " successively clockwise behind the decimal coded of the network element of central point.
9. the indoor positioning network element Optimal Deployment Method according to claim 1 based on genetic algorithm and simulated annealing,
It is characterized in that：The step (10) is specially：
The network element placement algorithm of simulated annealing：From a certain higher temperature, with the decline of temperature parameter, according to current network
The positioning accuracy of layout is laid spatial positioning accuracy with new network element and is received new network element laying space with certain probability, by right
The be possible to situation that network element is laid out in entire physical space randomly selects, and finally gets relatively optimal network element layout
Method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810165059.4A CN108495252B (en) | 2018-02-28 | 2018-02-28 | Indoor positioning network element optimization layout method based on genetic algorithm and simulated annealing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810165059.4A CN108495252B (en) | 2018-02-28 | 2018-02-28 | Indoor positioning network element optimization layout method based on genetic algorithm and simulated annealing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108495252A true CN108495252A (en) | 2018-09-04 |
| CN108495252B CN108495252B (en) | 2020-07-28 |
Family
ID=63341098
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810165059.4A Active CN108495252B (en) | 2018-02-28 | 2018-02-28 | Indoor positioning network element optimization layout method based on genetic algorithm and simulated annealing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108495252B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110705758A (en) * | 2019-09-11 | 2020-01-17 | 哈尔滨工程大学 | Underwater network-oriented network element optimization layout method |
| CN113159265A (en) * | 2021-03-24 | 2021-07-23 | 国网河南省电力公司电力科学研究院 | Traction load parameter identification method and system based on SVM-ant colony algorithm |
| CN113505456A (en) * | 2021-06-29 | 2021-10-15 | 上海勘察设计研究院(集团)有限公司 | Optimal design method for measurement control network |
| CN117150636A (en) * | 2023-11-01 | 2023-12-01 | 江西立盾光电科技有限公司 | Indoor plant planting layout method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5495419A (en) * | 1994-04-19 | 1996-02-27 | Lsi Logic Corporation | Integrated circuit physical design automation system utilizing optimization process decomposition and parallel processing |
| CN102521443A (en) * | 2011-12-06 | 2012-06-27 | 河海大学 | Logistics node facility layout optimization method based on computer vision |
| CN103729680A (en) * | 2013-12-24 | 2014-04-16 | 西安电子科技大学 | RFID network topology method based on multi-agent evolutionary algorithm |
| CN104486641A (en) * | 2014-11-20 | 2015-04-01 | 清华大学 | Multi-service broadcasting single-frequency network optimizing method based on superposition codes |
-
2018
- 2018-02-28 CN CN201810165059.4A patent/CN108495252B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5495419A (en) * | 1994-04-19 | 1996-02-27 | Lsi Logic Corporation | Integrated circuit physical design automation system utilizing optimization process decomposition and parallel processing |
| CN102521443A (en) * | 2011-12-06 | 2012-06-27 | 河海大学 | Logistics node facility layout optimization method based on computer vision |
| CN103729680A (en) * | 2013-12-24 | 2014-04-16 | 西安电子科技大学 | RFID network topology method based on multi-agent evolutionary algorithm |
| CN104486641A (en) * | 2014-11-20 | 2015-04-01 | 清华大学 | Multi-service broadcasting single-frequency network optimizing method based on superposition codes |
Non-Patent Citations (1)
| Title |
|---|
| 方睿,朱碧颖,粟藩臣: "《基于模拟退火思想的遗传算法参数选择》", 《计算机应用》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110705758A (en) * | 2019-09-11 | 2020-01-17 | 哈尔滨工程大学 | Underwater network-oriented network element optimization layout method |
| CN110705758B (en) * | 2019-09-11 | 2023-03-21 | 哈尔滨工程大学 | Underwater network-oriented network element optimization layout method |
| CN113159265A (en) * | 2021-03-24 | 2021-07-23 | 国网河南省电力公司电力科学研究院 | Traction load parameter identification method and system based on SVM-ant colony algorithm |
| CN113159265B (en) * | 2021-03-24 | 2022-09-09 | 国网河南省电力公司电力科学研究院 | Traction load parameter identification method and system based on SVM-ant colony algorithm |
| CN113505456A (en) * | 2021-06-29 | 2021-10-15 | 上海勘察设计研究院(集团)有限公司 | Optimal design method for measurement control network |
| CN113505456B (en) * | 2021-06-29 | 2022-03-01 | 上海勘察设计研究院(集团)有限公司 | Optimal design method for measurement control network |
| CN117150636A (en) * | 2023-11-01 | 2023-12-01 | 江西立盾光电科技有限公司 | Indoor plant planting layout method and system |
| CN117150636B (en) * | 2023-11-01 | 2024-01-09 | 江西立盾光电科技有限公司 | Indoor plant planting layout method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108495252B (en) | 2020-07-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108495252A (en) | Indoor positioning network element Optimal Deployment Method based on genetic algorithm and simulated annealing | |
| CN110619454B (en) | Power distribution network planning method based on improved genetic algorithm and PRIM algorithm | |
| CN110348048B (en) | Power distribution network optimization reconstruction method based on consideration of heat island effect load prediction | |
| CN110162041A (en) | A kind of robot path planning method based on self-adapted genetic algorithm | |
| CN102014412B (en) | Wireless network telephone traffic balanced optimization method based on antenna parameter adjustment | |
| CN105046363B (en) | A kind of region distribution system single-line diagram layout and optimization method | |
| CN103778477B (en) | Monitor station cloth station method and apparatus | |
| CN108803332A (en) | Based on the paths planning method for improving biogeography | |
| CN102395194B (en) | ANFIS (Adaptive Neural Fuzzy Inference System) indoor positioning method based on improved GA(Genetic Algorithm) optimization in WLAN (Wireless Local Area Network) environment | |
| CN112052544B (en) | Wind farm collecting network design method, system, storage medium and computing equipment | |
| JP2016163353A (en) | Planning method and planning device of radio network | |
| CN111314841A (en) | WSN positioning method based on compressed sensing and improved genetic algorithm | |
| CN109858698A (en) | Vehicle supply and demand optimization method, device, equipment and the storage medium of target area | |
| CN109888817B (en) | Method for carrying out position deployment and capacity planning on photovoltaic power station and data center | |
| CN105512752A (en) | Urban public service facility site selection method | |
| CN108769996A (en) | Beaconing nodes layout method and localization method used for positioning | |
| Emeksiz | Multi-gen genetic programming based improved innovative model for extrapolation of wind data at high altitudes, case study: Turkey | |
| CN108650682A (en) | A kind of the base station installation aiding device and its method of the ultra dense set networks of 5G | |
| CN114189871A (en) | Electric power 5G base station layout method considering correction signal propagation model | |
| CN109615142A (en) | A kind of wind farm wind velocity combination forecasting method based on wavelet analysis | |
| Wang | Optimization of wireless network node deployment in smart city based on adaptive particle swarm optimization | |
| CN110505634A (en) | One kind realizing wireless aps disposition optimization method based on genetic algorithm | |
| Zhang et al. | A Node Placement Optimization Algorithm in Heterogeneous WSN Based on Neighbor Nodes | |
| CN116894400B (en) | Spatial combination site selection method based on visual sense network | |
| Yang et al. | Genetic algorithm-based analysis of base station siting optimization [J] |
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 |