CN114599004B - Base station layout method and device - Google Patents

Base station layout method and device Download PDF

Info

Publication number
CN114599004B
CN114599004B CN202210108543.XA CN202210108543A CN114599004B CN 114599004 B CN114599004 B CN 114599004B CN 202210108543 A CN202210108543 A CN 202210108543A CN 114599004 B CN114599004 B CN 114599004B
Authority
CN
China
Prior art keywords
base station
population
geometric precision
precision factor
average geometric
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202210108543.XA
Other languages
Chinese (zh)
Other versions
CN114599004A (en
Inventor
邓中亮
董展祎
张智超
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing University of Posts and Telecommunications
Original Assignee
Beijing University of Posts and Telecommunications
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing University of Posts and Telecommunications filed Critical Beijing University of Posts and Telecommunications
Priority to CN202210108543.XA priority Critical patent/CN114599004B/en
Publication of CN114599004A publication Critical patent/CN114599004A/en
Application granted granted Critical
Publication of CN114599004B publication Critical patent/CN114599004B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • 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
    • 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
    • H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
    • H04W16/18—Network planning tools
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W88/00—Devices specially adapted for wireless communication networks, e.g. terminals, base stations or access point devices
    • H04W88/08—Access point devices
    • 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
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Mobile Radio Communication Systems (AREA)
  • Position Fixing By Use Of Radio Waves (AREA)

Abstract

The invention provides a base station layout method and a device, wherein the method comprises the following steps: taking elements of each row of the matrix as coordinates of a base station to be solved in a target positioning space, and initializing a particle population to obtain an original population; obtaining a reverse learning population according to the original population; substituting the original population and the reverse learning population into fitness functions respectively to perform iterative calculation of the base station fitness to obtain optimal positions of individuals in the original population and the reverse learning population; and taking the determined optimal position as the base station layout of the target positioning space. The method can solve the problem that the algorithm is easy to fall into a local optimal solution, can improve the precision of the group intelligent optimization algorithm to the problem of layout optimization, performs layout optimization on the positioning base station in the mode, can obtain better base station layout coordinates, and can obtain higher positioning precision.

Description

Base station layout method and device
Technical Field
The present invention relates to the field of communications base stations, and in particular, to a base station layout method and apparatus.
Background
The problem of outdoor positioning base station layout can be regarded as an optimal value solving problem. And in a certain layout range, performing global optimization in the region through an intelligent optimization algorithm, and obtaining a global optimal solution through continuous iteration of the algorithm.
At present, the genetic algorithm, the particle swarm algorithm, the ant colony algorithm, the simulated annealing algorithm and the like which are commonly used in the swarm intelligence algorithm are more classical algorithms, and the novel algorithm is more novel, such as the goblet sea squirt algorithm, the gray wolf algorithm and the like.
The conventional intelligent group optimization algorithm has the characteristics that the classical algorithm has strong optimizing capability and better algorithm robustness, but the algorithm consumes a large amount of resources when performing genetic variation and other operations. The traditional particle swarm algorithm has strong optimizing capability for nonlinear problems, but the problem that the algorithm is easy to fall into a local optimal solution is difficult to solve, and the final solving precision of the algorithm is affected. Still other swarm intelligent optimization algorithms, such as swarm intelligent optimization algorithms fused by simulated annealing algorithms and genetic algorithms, cannot jump out of the locally optimal solution.
Disclosure of Invention
In view of the foregoing, embodiments of the present invention provide a base station layout method and apparatus to obviate or mitigate one or more disadvantages in the prior art.
One aspect of the present invention provides a base station layout method, comprising the steps of:
taking elements of each row of the matrix as coordinates of a base station to be solved in a target positioning space, and initializing a particle population to obtain an original population;
obtaining a reverse learning population according to the original population;
substituting the original population and the reverse learning population into fitness functions respectively to perform iterative calculation of the base station fitness to obtain optimal positions of individuals in the original population and the reverse learning population;
and taking the determined optimal position as the base station layout of the target positioning space.
In some embodiments of the present invention, substituting the original population and the reverse learning population into fitness functions to perform iterative calculation of the base station fitness includes:
setting iteration times;
in each iteration, the following operations are performed:
comparing the average geometric precision factor value obtained by the current iteration of the original population with the average geometric precision factor value obtained by the previous iteration of the original population, and reserving a smaller average geometric precision factor value as a first average geometric precision factor value;
comparing the average geometric precision factor value obtained by the current iteration of the reverse learning population with the average geometric precision factor value obtained by the last reverse learning population iteration, and reserving a smaller average geometric precision factor value as a second average geometric precision factor value;
selecting the smaller value of the first average geometric precision factor value and the second average geometric precision factor value as a target average geometric precision factor value, and comparing the target average geometric precision factor value with the current global optimal value;
and under the condition that the target average geometric precision factor value is smaller than the current global optimum value, replacing the current global optimum value with the target average geometric precision factor value, and taking the optimal position corresponding to the target average geometric precision factor value as the determined optimal position.
In some embodiments of the present invention, the average geometric precision factor value is calculated according to the following formula:
wherein AGDOP represents the mean geometric precision factor value, GDOP i The geometric precision factor of the ith receiving terminal in the target positioning space is represented, and n represents the number of sampling points selected in the target positioning space;
wherein,
wherein,indicating the square of the positioning error of the base station in the x-direction,/->Indicating the base station in the y-directionSquare of positioning error>Representing the square of the positioning error of the base station in the z-direction.
In some embodiments of the present invention, substituting the original population and the reverse learning population into fitness functions to perform iterative calculation of the base station fitness includes:
determining the updating speed and the updating position of particles in the population in the iterative process;
and performing iterative calculation according to the determined updating speed and the determined updating position.
In some embodiments of the invention, determining update rates and update locations of particles in a population during an iteration process includes:
the inertial weights are calculated according to the following formula:
wherein w represents inertial weight, i represents iteration number variation, and w max Represents the maximum value of inertial weight, w min Representing the minimum value of the inertia weight, and T represents the total number of iterations;
the update speed and update position are calculated separately according to the following formulas:
v(j,:)＝w*v(j,:)+c 1 *rand*(p(j,:)-x(j,:))+c 2 *rand*(g-x(j,:))
x(j,:)＝x(j,:)+v(j,:)
wherein v (j) represents the update speed, x (j) represents the update position, j represents the amount of change in the number of particles, c 1 And c 2 A learning factor representing individual experiences reflecting the particles c 2 Learning factors reflecting population experience of the particles are identified, p (j:) represents the location of the individual, and g represents the optimal individual.
In some embodiments of the invention, deriving a reverse learning population from an original population includes:
the original population is expressed according to the following formula:
X＝rand*(Xb-Xa)+Xa
wherein X represents an original population, xb represents an upper limit of the number of particles in the original population, xa represents a lower limit of the number of particles in the original population;
the reverse learning population is derived from the original population based on the following formula:
X * ＝X b +X a -X
wherein X is * Representing a reverse learning population.
Another aspect of the present invention provides a base station arrangement apparatus, comprising:
the initialization module is used for initializing the particle population by taking elements of each row of the matrix as coordinates of the base station to be solved in the target positioning space to obtain an original population;
the generation module is used for obtaining a reverse learning population according to the original population;
the computing module is used for substituting the original population and the reverse learning population into the fitness function respectively to perform iterative computation of the base station fitness so as to obtain the optimal positions of the individuals in the original population and the reverse learning population;
and the determining module is used for taking the determined optimal position as the base station layout of the target positioning space.
In some embodiments of the invention, the computing module comprises:
the setting unit is used for setting the iteration times;
the iteration module is used for executing the following operations in each iteration process:
comparing the average geometric precision factor value obtained by the current iteration of the original population with the average geometric precision factor value obtained by the previous iteration of the original population, and reserving a smaller average geometric precision factor value as a first average geometric precision factor value;
comparing the average geometric precision factor value obtained by the current iteration of the reverse learning population with the average geometric precision factor value obtained by the last reverse learning population iteration, and reserving a smaller average geometric precision factor value as a second average geometric precision factor value;
selecting the smaller value of the first average geometric precision factor value and the second average geometric precision factor value as a target average geometric precision factor value, and comparing the target average geometric precision factor value with the current global optimal value;
and under the condition that the target average geometric precision factor value is smaller than the current global optimum value, replacing the current global optimum value with the target average geometric precision factor value, and taking the optimal position corresponding to the target average geometric precision factor value as the determined optimal position.
Another aspect of the present invention provides a base station arrangement comprising a processor and a memory, the memory having stored therein computer instructions for executing the computer instructions stored in the memory, the arrangement implementing the steps of the above method when the computer instructions are executed by the processor.
Another aspect of the invention provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method as described above.
According to the base station layout method and device, the problem that the algorithm is easy to fall into a local optimal solution can be solved by adding the reverse learning method on the basis of the particle swarm algorithm, furthermore, the accuracy of the swarm intelligent optimization algorithm on the layout optimizing problem can be improved by using the linear decreasing inertia weight method, the 5G outdoor positioning base station is subjected to layout optimizing in the mode, the better base station layout coordinates can be obtained, and the higher positioning accuracy can be obtained.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention. The objectives and other advantages of the invention may be realized and attained by the structure particularly pointed out in the written description and drawings.
It will be appreciated by those skilled in the art that the objects and advantages that can be achieved with the present invention are not limited to the above-described specific ones, and that the above and other objects that can be achieved with the present invention will be more clearly understood from the following detailed description.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate and together with the description serve to explain the invention. The components in the figures are not necessarily to scale, emphasis instead being placed upon illustrating the principles of the invention. Corresponding parts in the drawings may be exaggerated, i.e. made larger relative to other parts in an exemplary device actually manufactured according to the present invention, for convenience in showing and describing some parts of the present invention. In the drawings:
FIG. 1 is a flowchart of a method for helping a group intelligent optimization algorithm jump out of a locally optimal solution according to an embodiment of the invention;
FIG. 2 is a schematic diagram of an outdoor positioning layout scenario according to another embodiment of the present invention;
FIG. 3 is a flow chart of a method of algorithm optimization in another embodiment of the invention;
FIG. 4 is a flow chart of a method for layout of a base station according to another embodiment of the present invention;
fig. 5 is a block diagram of a base station layout device according to another embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the following embodiments and the accompanying drawings, in order to make the objects, technical solutions and advantages of the present invention more apparent. The exemplary embodiments of the present invention and the descriptions thereof are used herein to explain the present invention, but are not intended to limit the invention.
It should be noted here that, in order to avoid obscuring the present invention due to unnecessary details, only structures and/or processing steps closely related to the solution according to the present invention are shown in the drawings, while other details not greatly related to the present invention are omitted.
It should be emphasized that the term "comprises/comprising" when used herein is taken to specify the presence of stated features, elements, steps or components, but does not preclude the presence or addition of one or more other features, elements, steps or components.
It is also noted herein that the term "coupled" may refer to not only a direct connection, but also an indirect connection in which an intermediate is present, unless otherwise specified.
Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. In the drawings, the same reference numerals represent the same or similar components, or the same or similar steps.
The particle swarm optimization is a mature swarm intelligent optimization algorithm, is an intelligent optimization algorithm provided by biologists through simulating the behavior of a bird community, and is optimized through updating the position and the speed value of particles, so that the algorithm has fewer parameters, is easy to realize, and has strong global searching capability on nonlinear problems.
Considering that a relatively reliable evaluation index is required to be determined for the layout problem of the base station, the layout of the 5G positioning base station mostly adopts GDOP (Geometric Dilution Precision, geometric precision factor) as the evaluation index of the layout precision, the GDOP is used for representing the geometric layout quality degree of satellites in satellite positioning, the more the satellites are distributed in space, the better the geometric layout is, the smaller the GDOP value is, and if the satellites are almost on a straight line, the geometric configuration of the satellites is poor, and the GDOP value is large. The evaluation index can be directly applied to the layout problem of the 5G outdoor positioning base station. And taking the index as a fitness function of the group intelligent algorithm, and carrying out iterative solution of an optimal solution on the index through a proper group intelligent algorithm to obtain the required 5G outdoor positioning optimal base station layout coordinates.
Aiming at the problem that the existing intelligent group optimization algorithm such as a particle swarm algorithm cannot solve the problem of sinking into a local optimal solution and the accuracy of the algorithm is affected, in the example, a method capable of helping the intelligent group optimization algorithm to jump out of the local optimal solution is provided, as shown in fig. 1, firstly, a GDOP calculation formula under a TDOA (Time Difference of Arrival ) solution method is deduced, and then, an outdoor positioning scene model of a 5G positioning base station is determined. After the preparation work is determined, the derived GDOP calculation formula is used as an adaptability function in the optimizing process of the improved particle swarm algorithm to calculate, and then the optimal base station layout and the minimum GDOP value are obtained.
The method is specifically described below:
s1: GDOP calculation formula derivation based on TDOA:
when four-station time difference positioning is performed in three-dimensional space, it is assumed that the positions of the main positioning base station A1 and the 3 auxiliary positioning base stations A2, A3, A4 are (x 1 ,y 1 ,z 1 )，(x 2 ,y 2 ,z 2 )，(x 3 ,y 3 ,z 3 )，(x 4 ,y 4 ,z 4 ) The position coordinates of the positioning terminal m are expressed as (x, y, z). And obtaining a positioning solution nonlinear equation set shown as follows through the geometric relations of the four positioning base stations and the receiving terminal in space:
where Δri represents the difference in distance between the terminal and each station; ri (i=1, 2,3, 4) represents the distance between the terminal and each station, Δti is the difference between the time when the primary positioning base station transmits a signal and the secondary positioning base station arrives at the positioning terminal; c represents the propagation speed of light in vacuum.
Differentiating the difference Δri of the distances of the positioning base station from the receiving terminal, where i=2, 3,4, yields:
to simplify the above equation, let the variables within the above formula be:
substituting the variable formula into the above formula 1 can result in:
d(Δr i )＝(a ix -a 1x )dx+(a iy -a 1y )dy+(a iz -a 1z )dz+(b1-bi)(i＝2,3,4)
wherein,
b i ＝a ix dx i +a iy dy i +a iz dz i (i＝1,2,3,4)
the transformation of the above equation 2 using a matrix can be obtained:
dΔR＝AdX+dX s
wherein dx= [ dX, dy, dz] T Indicating the positioning error of the system to the receiving terminal, and the station address position measurement error of each positioning base station is dDeltaR= [ dDeltar ] 1 ,dΔr 2 ,dΔr 3 ] T The error has a larger influence on the positioning result of the base station, dXS = [ b1-b2, b1-b3, b1-b4 ]] T The measurement error representing the difference in arrival times of the primary and secondary positioning base stations is used as an important parameter for the subsequent calculation.
After conversion, a correlation coefficient matrix can be obtained as follows:
therefore, the positioning error estimation value of the receiving terminal can be obtained by the least square method as follows:
dX＝(A T A) -1 A T [dΔR-dXS](equation 2)
And (3) making:
D＝(A T A) -1 A T ＝[b ij ] 3*3
equation 2 can be expressed as:
dX＝D[dΔR-dXS]
assuming that the variances of the site position error components of each positioning base station in three directions are equal, the positioning error variances in the directions of x, y and z can be obtained as follows:
finally, the geometric accuracy factor GDOP of the four-base station moveout positioning system can be expressed as:
because the TC-OFDM outdoor positioning system is a positioning coverage problem when outdoor positioning is carried out, a large number of sampling points are required to be distributed in the whole space, the sampling points are equivalent to receiving terminals, each sampling point can obtain a GDOP value, the average calculation is carried out on all the sampled GDOP values, AGDOP of the outdoor positioning space can be obtained, the layout quality of a base station can be completely represented, and the formula is as follows:
s2: determining a 5G positioning base station outdoor layout scene model:
in this example, an outdoor positioning scene of 100m x 10m is provided to perform layout simulation, a 3-dimensional coordinate system is established by taking a certain point of the cubic space as an origin of coordinates, and according to the geometric layout principle of the GDOP, the more the geometric configuration of the satellite is dispersed relative to the receiving terminal, when the positioning terminal can be covered by the package, the better the geometric configuration of the satellite, the smaller the corresponding GDOP value, and the smaller positioning error is represented. According to the principle, the positioning base station can be placed on four symmetrical high lines of the positioning space cube, so that the whole positioning area can be dispersed and covered to the maximum extent, and the mathematical expression can be expressed as:
one sampling point is arranged every five meters in a 100 m-100 m two-dimensional ground space, and one sampling point is arranged every two meters in a ten-meter height dimension, so 2646 sampling points are arranged in the simulation environment, and the layout quality of the base station is evaluated by calculating the average GDOP value (AGDOP) of all the sampling points. Fig. 2 is a schematic diagram of an outdoor positioning layout scene, wherein four thickened high lines are random search areas of a station distribution, a black cuboid is an outdoor positioning station distribution area model, the above is a scene model of the whole outdoor positioning, and the following algorithm calculation is performed based on the model.
S3: performing local optimal solution calculation to determine base station coordinates through a particle swarm algorithm, and obtaining optimal base station layout coordinates and a minimum GDOP:
in order to solve the problem that the group intelligent optimization algorithm is easy to fall into a local optimal solution, the method of reverse learning and linear decreasing inertia weight is introduced into the classical particle swarm algorithm:
the reverse learning method (OBL) is based on an intelligent optimization algorithm, the range of a search space can be effectively enlarged by adopting the reverse learning method, the global searching capability of the algorithm is improved, and the probability of finding a global optimal solution can be increased by utilizing the current population and the opposite population. Can be defined as:
there is a solution x e [ a, b ], and a reverse solution of x can be expressed as:
x * ＝a+b-x
let x= (X) 1 ,x 2 ,…,x l ) For a candidate solution in space, the fitness function value f (X) can be calculated, and the solution is reversedHas a fitness function value f (X) * ) If f (X) * )>f (X), then X in the population is replaced with X * Otherwise, the method does not need to replace, so that the searching range of the population is enlarged, the algorithm is easier to jump out of the local optimum, and the global optimum solution is obtained.
The weight is linearly decreased, the linear weight is added into the algorithm, the variable that the weight can balance the speed of the algorithm can be found, the larger the weight is, the larger the speed value is, and the larger the searching range of the algorithm is. The smaller the weight, the smaller the speed value and the smaller the search range of the algorithm, thus distinguishing the global search and the local search capability of the algorithm. In order to enhance the searching capability of the algorithm, in this example, a Linearly Decreasing Weight (LDW) is proposed, with the following formula:
wherein d represents the current iteration number, k represents the total number of iterations, w start Generally take 0.9, w end Typically 0.4 is taken. The inertia weight is adaptively adjusted along with the change of the iteration times, and the searching capacity of the algorithm is adjusted linearly.
To this end, in this example, the algorithm optimization may be performed as shown in fig. 3, including: initializing a particle population, initializing a reverse learning population, carrying out formula solution on an optimal initial value, iteratively updating the optimal position and the optimal value of the population, calculating linear decreasing inertia weight, updating position and speed values, carrying out boundary processing and the like.
1) Initializing a particle population:
the initializing population is a matrix of N x D, N is the number of particles, D is the dimension of particles, and considering that four unknowns exist when solving the coordinates of a base station, D is set to 4, each dimension of particles has a certain range, therefore, a general formula needs to be set when initializing the particles, and assuming that the upper limit of the positions of the particles is Xb and the lower limit of the positions of the particles is Xa, the formula of initializing the particle population is set as follows:
X＝rand*(Xb-Xa)+Xa
the particle population can be initialized by substituting different values according to the formula and repeating the process for 4 times, and then the reverse learning population needs to be initialized.
2) Initializing a reverse learning population:
the reverse learning population is calculated according to the following formula, and is obtained through initialization:
X * ＝X b +X a -X
3) Initializing an optimal position and an optimal value:
after the initial population is obtained, an initial optimal position and an optimal value of the particles are calculated. Specifically, during initialization, the population is set as a matrix of 40 x 4, 4 elements in each row of the matrix are coordinates of a base station to be solved, the 4 elements in each row are taken as a group into a formula, namely, the 4 elements are taken into a fitness function to calculate individual fitness values, and meanwhile, elements in the reverse learning population are taken into the fitness function to calculate, so that initial individual optimal positions and optimal values of the original population and the reverse learning population can be obtained. When the initial value is set, a global optimal value is set randomly, the obtained individual optimal value is compared with the global optimal value, the smaller one is taken, and then the optimal value and the position are updated, so that a new optimal value and a new position can be obtained through iterative updating.
4) The iterative process:
the number of iterations is set relatively low to avoid excessive consumption of resources, for example, the number of iterations may be set to 200. In the iterative process, the individual fitness value obtained by the iteration is compared with the individual fitness value of the previous generation, and the smaller individual fitness value is reserved. Comparing the individual fitness value obtained by the reverse learning population with the individual fitness value of the reverse learning population of the previous generation, keeping the smaller one, comparing the values of the two iterations to obtain the last smaller one, comparing the value with the global optimal value, and taking the smaller one to update the optimal position and the optimal value, which is the one-iteration process.
5) Updating the position and velocity values:
before updating the position and velocity values, firstly calculating inertial weights, wherein the inertial weights determine the development and exploration capabilities of an algorithm, and the calculation formula is as follows:
where i is the variation of the number of iterations, w max Is the maximum value of inertial weight, w min And T is the total number of iterations, and is the minimum value of the inertia weight.
The updated position and velocity values are calculated separately according to the following formula:
v(j,:)＝w*v(j,:)+c 1 *rand*(p(j,:)-x(j,:))+c 2 *rand * (g-x(j,:))
x(j,:)＝x(j,:)+v(j,:)
wherein j is the variation of the number of particles, c 1 And c 2 For learning factors, the individual experience and the population experience of the particles are respectively reflected, p (j:) is the position of the individual, and g is the optimal individual.
6) Boundary condition calculation:
during the updating process of the speed and the position of the particles, the particles may fly out of the boundary, and the result is wrong due to the fact that the particle exceeds the searching range, so that the moving range of the particles is set to ensure that the behavior of the particles can meet the preset requirement.
The boundary condition is set according to the initialization of the population, and the matlab calculation formula can be expressed as follows:
wherein ii represents the dimensional change amount, V max Represents the set maximum speed, V min Indicating the set speed minimum.
Then, calculating boundary conditions of the reverse learning population, wherein the matlab calculation formula is as follows:
x * (j,ii)＝X b +X a -x(j,ii)
both velocity values may share the same velocity, which has been added in previous iterations.
In the above example, a reverse learning method and a linear decreasing inertia weight method are added on the basis of the traditional particle swarm algorithm, so that the problem that the algorithm is easy to fall into a local optimal solution is solved, the accuracy of the swarm intelligent optimization algorithm on the layout optimizing problem is improved, better base station layout coordinates are obtained on the 5G outdoor positioning base station layout optimizing problem through the algorithm, and higher positioning accuracy is obtained.
Specifically, as shown in fig. 4, in this example, a base station layout method is provided, as shown in fig. 4, which may include the following steps:
step 401: taking elements of each row of the matrix as coordinates of a base station to be solved in a target positioning space, and initializing a particle population to obtain an original population;
step 402: obtaining a reverse learning population according to the original population;
step 403: substituting the original population and the reverse learning population into fitness functions respectively to perform iterative calculation of the base station fitness to obtain optimal positions of individuals in the original population and the reverse learning population;
step 404: and taking the determined optimal position as the base station layout of the target positioning space.
The base station may be a 5G outdoor positioning base station.
In the above example, the problem that the conventional particle swarm algorithm is easy to be trapped in the local optimal solution is solved by adding the reverse learning method on the basis of the conventional particle swarm algorithm.
Further, when the original population and the reverse learning population are respectively substituted into the fitness function to perform iterative calculation of the base station fitness, the method may be performed according to the following steps:
s1: setting iteration times;
s2: in each iteration, the following operations are performed:
comparing the average geometric precision factor value obtained by the current iteration of the original population with the average geometric precision factor value obtained by the previous iteration of the original population, and reserving a smaller average geometric precision factor value as a first average geometric precision factor value;
comparing the average geometric precision factor value obtained by the current iteration of the reverse learning population with the average geometric precision factor value obtained by the last reverse learning population iteration, and reserving a smaller average geometric precision factor value as a second average geometric precision factor value;
selecting the smaller value of the first average geometric precision factor value and the second average geometric precision factor value as a target average geometric precision factor value, and comparing the target average geometric precision factor value with the current global optimal value;
and under the condition that the target average geometric precision factor value is smaller than the current global optimum value, replacing the current global optimum value with the target average geometric precision factor value, and taking the optimal position corresponding to the target average geometric precision factor value as the determined optimal position.
In this example, a GDOP formula under TDOA solution is also given, and the base station layout is performed with the determined GDOP formula, where the average geometric precision factor value may be calculated according to the following formula:
wherein AGDOP represents the mean geometric precision factor value, GDOP i The geometric precision factor of the ith receiving terminal in the target positioning space is represented, and n represents the number of sampling points selected in the target positioning space;
wherein,
wherein,indicating the square of the positioning error of the base station in the x-direction,/->Indicating the square of the positioning error of the base station in the y-direction,/->Representing the square of the positioning error of the base station in the z-direction.
When the original population and the reverse learning population are respectively substituted into the fitness function to perform iterative calculation of the base station fitness, the updating speed and the updating position are determined by introducing inertial weights, so that the situation of sinking into a local optimal solution can be further avoided, and in particular, the updating speed and the updating position of particles in the population in the iterative process can be determined; and performing iterative calculation according to the determined updating speed and the determined updating position.
When determining the update speed and update position of particles in the population in the iterative process, the inertial weight can be calculated according to the following formula:
wherein w represents inertial weight, i represents iteration number variation, and w max Represents the maximum value of inertial weight, w min Representing the minimum value of the inertia weight, and T represents the total number of iterations;
further, the update speed and the update position may be calculated respectively according to the following formulas:
v(j,:)＝w*v(j,:)+c 1 *rand*(p(j,:)-x(j,:))+c 2 *rand*(g-x(j,:))
x(j,:)＝x(j,:)+v(j,:)
wherein v (j) represents the update speed, x (j) represents the update position, j represents the amount of change in the number of particles, c 1 And c 2 A learning factor representing individual experiences reflecting the particles c 2 Learning factors reflecting population experience of the particles are identified, p (j:) represents the location of the individual, and g represents the optimal individual.
For the original population, it can be expressed by the following formula:
X＝rand*(Xb-Xa)+Xa
wherein X represents an original population, xb represents an upper limit of the number of particles in the original population, xa represents a lower limit of the number of particles in the original population;
after the original population is obtained, a reverse learning population can be obtained from the original population based on the following formula:
X * ＝X b +X a -X
wherein X is * Representing a reverse learning population.
And initializing a reverse learning population by considering the particle population initialization, carrying out formula solving to obtain an optimal initial value, and calculating linear decreasing inertia weight and updating position and speed values by iteratively updating the optimal position and the optimal value of the population. During the updating of the speed and position of the particles, the particles may fly out of the boundary, and the result is wrong due to the fact that the particle is out of the searching range, so that the movement range of the particles is set (namely, the boundary condition is determined) to ensure that the behavior of the particles can meet the preset requirement.
The boundary condition is set according to the initialization of the population, and the matlab calculation formula can be expressed as follows:
wherein ii represents the dimensional change amount, V max Represents the set maximum speed, V min Indicating the set speed minimum.
Then, calculating boundary conditions of the reverse learning population, wherein the matlab calculation formula is as follows:
x * (j,ii)＝X b +X a -x(j,ii)
based on the same inventive concept, a base station layout device is also provided in the embodiments of the present invention, as described in the following embodiments. Since the base station layout device has a similar principle to the base station layout method, the implementation of the base station layout device can refer to the implementation of the base station layout method, and the repetition is omitted. As used below, the term "unit" or "module" may be a combination of software and/or hardware that implements the intended function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated. Fig. 5 is a block diagram of a base station layout device according to an embodiment of the present invention, and as shown in fig. 5, may include: the structure is described below, with an initialization module 501, a generation module 502, a calculation module 503, and a determination module 504.
The initializing module 501 is configured to initialize a particle population to obtain an original population by taking elements of each row of the matrix as coordinates of a base station to be solved in a target positioning space;
a generating module 502, configured to obtain a reverse learning population according to the original population;
a calculation module 503, configured to respectively substitute the original population and the reverse learning population into fitness functions to perform iterative calculation of the base station fitness, so as to obtain optimal positions of individuals in the original population and the reverse learning population;
a determining module 504, configured to take the determined optimal position as a base station layout of the target positioning space.
In one embodiment, the calculating module 503 may specifically include: the setting unit is used for setting the iteration times; the iteration module is used for executing the following operations in each iteration process: comparing the average geometric precision factor value obtained by the current iteration of the original population with the average geometric precision factor value obtained by the previous iteration of the original population, and reserving a smaller average geometric precision factor value as a first average geometric precision factor value; comparing the average geometric precision factor value obtained by the current iteration of the reverse learning population with the average geometric precision factor value obtained by the last reverse learning population iteration, and reserving a smaller average geometric precision factor value as a second average geometric precision factor value; selecting the smaller value of the first average geometric precision factor value and the second average geometric precision factor value as a target average geometric precision factor value, and comparing the target average geometric precision factor value with the current global optimal value; and under the condition that the target average geometric precision factor value is smaller than the current global optimum value, replacing the current global optimum value with the target average geometric precision factor value, and taking the optimal position corresponding to the target average geometric precision factor value as the determined optimal position.
In one embodiment, the average geometric precision factor value may be calculated as follows:
wherein AGDOP represents the mean geometric precision factor value, GDOP i The geometric precision factor of the ith receiving terminal in the target positioning space is represented, and n represents the number of sampling points selected in the target positioning space;
wherein,
wherein,indicating the square of the positioning error of the base station in the x-direction,/->Indicating the square of the positioning error of the base station in the y-direction,/->Representing the square of the positioning error of the base station in the z-direction.
In one embodiment, the iterative calculation of the base station fitness by substituting the original population and the reverse learning population into fitness functions respectively may include:
determining the updating speed and the updating position of particles in the population in the iterative process;
and performing iterative calculation according to the determined updating speed and the determined updating position.
In one embodiment, determining the update rate and update location of particles in the population during the iterative process may include:
the inertial weights are calculated according to the following formula:
wherein w represents inertial weight, i represents iteration number variation, and w max Represents the maximum value of inertial weight, w min Representing the minimum value of the inertia weight, and T represents the total number of iterations;
the update speed and update position are calculated separately according to the following formulas:
v(j,:)＝w*v(j,:)+c 1 *rand*(p(j,:)-x(j,:))+c 2 *rand*(g-x(j,:))
x(j,:)＝x(j,:)+v(j,:)
wherein v (j) represents the update speed, x (j) represents the update position, j represents the amount of change in the number of particles, c 1 And c 2 A learning factor representing individual experiences reflecting the particles c 2 Learning factors reflecting population experience of the particles are identified, p (j:) represents the location of the individual, and g represents the optimal individual.
In one embodiment, the original population may be expressed as follows:
X＝rand*(Xb-Xa)+Xa
wherein X represents an original population, xb represents an upper limit of the number of particles in the original population, xa represents a lower limit of the number of particles in the original population;
the reverse learning population can be derived from the original population based on the following formula:
X * ＝X b +X a -X
wherein X is * Representing a reverse learning population.
Correspondingly, the invention also provides a base station arrangement device/system comprising a computer device, the computer device comprising a processor and a memory, the memory having stored therein computer instructions, the processor being adapted to execute the computer instructions stored in the memory, the base station arrangement device/system implementing the steps of the method as described above when the computer instructions are executed by the processor.
The embodiments of the present invention also provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the edge computing server deployment method described above. The computer readable storage medium may be a tangible storage medium such as Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, floppy disks, hard disk, a removable memory disk, a CD-ROM, or any other form of storage medium known in the art.
Those of ordinary skill in the art will appreciate that the various illustrative components, systems, and methods described in connection with the embodiments disclosed herein can be implemented as hardware, software, or a combination of both. The particular implementation is hardware or software dependent on the specific application of the solution and the design constraints. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, a plug-in, a function card, or the like. When implemented in software, the elements of the invention are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine readable medium or transmitted over transmission media or communication links by a data signal carried in a carrier wave.
It should be understood that the invention is not limited to the particular arrangements and instrumentality described above and shown in the drawings. For the sake of brevity, a detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present invention are not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between steps, after appreciating the spirit of the present invention.
In this disclosure, features that are described and/or illustrated with respect to one embodiment may be used in the same way or in a similar way in one or more other embodiments and/or in combination with or instead of the features of the other embodiments.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, and various modifications and variations can be made to the embodiments of the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (7)

1. The base station layout method based on the particle swarm optimization algorithm is characterized by comprising the following steps:
initializing a particle population to obtain an original population, wherein the particle population is an N-D matrix formed by coordinates of base stations to be solved in a target positioning space, each row of elements of the matrix is the coordinates of each base station to be solved in one candidate solution of the base station layout, N is the number of particles in the particle population, the number of the candidate solutions of the base station layout in the target positioning space is represented, D is the dimension of each particle in the particle population, and the number of the base stations to be solved corresponding to each candidate solution of the base station layout in the target positioning space is represented;
obtaining a reverse learning population according to the original population;
substituting the original population and the reverse learning population into fitness functions respectively to perform iterative calculation of the base station fitness to obtain optimal positions of individuals in the original population and the reverse learning population, wherein the fitness functions are calculation formulas of geometric precision factors;
correspondingly, the step of substituting the original population and the reverse learning population into the fitness function to perform iterative calculation of the base station fitness comprises the following steps:
setting iteration times;
in each iteration, the following operations are performed:
comparing an average geometric precision factor value obtained by the current iteration of the original population according to the coordinates of each base station to be solved in the target positioning space with an average geometric precision factor value obtained by the previous iteration of the original population, and reserving a smaller average geometric precision factor value as a first average geometric precision factor value;
comparing the average geometric precision factor value obtained by the current iteration of the reverse learning population according to the coordinates of each base station to be solved in the target positioning space with the average geometric precision factor value obtained by the previous iteration of the reverse learning population, and reserving a smaller average geometric precision factor value as a second average geometric precision factor value;
selecting the smaller value of the first average geometric precision factor value and the second average geometric precision factor value as a target average geometric precision factor value, and comparing the target average geometric precision factor value with the current global optimal value;
under the condition that the target average geometric precision factor value is smaller than the current global optimum value, replacing the current global optimum value with the target average geometric precision factor value, and taking the coordinates of the base station to be solved in the target positioning space corresponding to the target average geometric precision factor value as the coordinates of the base station to be solved in the target positioning space determined by the current iteration; in each iteration process, updating a speed value and a position value of coordinates of a base station to be solved in a target positioning space determined by the current iteration by combining the inertia weight of the current iteration times; according to preset speed boundary conditions and position boundary conditions of the base station to be solved, carrying out boundary processing on updated speed values exceeding the speed boundary conditions and/or updated position values exceeding the position boundary conditions to obtain optimal speed and optimal positions corresponding to the target average geometric precision factor values;
and taking the coordinates of each base station to be solved corresponding to the global optimal value determined by the maximum iteration number as the base station layout of the target positioning space.
2. The method of claim 1, wherein the average geometric precision factor value is calculated according to the formula:
wherein AGDOP represents the mean geometric precision factor value, GDOP i The geometric precision factor of the ith receiving terminal in the target positioning space is represented, and n represents the number of sampling points selected in the target positioning space;
wherein,
wherein,indicating the square of the positioning error of the base station in the x-direction,/->Indicating the square of the positioning error of the base station in the y-direction,/->Representing the square of the positioning error of the base station in the z-direction.
3. The method of claim 1, wherein updating the velocity value and the position value of the coordinates of the base station to be solved in the target positioning space determined by the current iteration in combination with the inertia weight of the current iteration number comprises:
the inertial weights are calculated according to the following formula:
wherein w represents inertial weight, i represents iteration number variation, and w max Represents the maximum value of inertial weight, w min Representing the minimum value of the inertia weight, and T represents the total number of iterations;
the update speed and update position are calculated separately according to the following formulas:
v(j，：)＝w * v(j，：)+c 1 *rand*(p(j，：)-x(j，：))+c 2 *rand * (g-x(j，：))
x(j，：)＝x(j，：)+v(j，：)
wherein v (j) represents the update speed, x (j) represents the update position, j represents the amount of change in the number of particles, c 1 And c 2 A learning factor representing individual experiences reflecting the particles c 2 Learning factors reflecting population experience of the particles are identified, p (j:) represents the location of the individual, and g represents the optimal individual.
4. The method of claim 1, wherein deriving the reverse learning population from the original population comprises:
the original population is expressed according to the following formula:
X＝rand*(Xb-Xa)+Xa
wherein X represents an original population, xb represents an upper limit of the number of particles in the original population, xa represents a lower limit of the number of particles in the original population;
the reverse learning population is derived from the original population based on the following formula:
X * ＝X b +X a -X
wherein X is * Representing a reverse learning population.
5. A base station layout device based on a particle swarm optimization algorithm, comprising:
the initialization module is used for initializing a particle population to obtain an original population, wherein the particle population is an N-by-D matrix formed by coordinates of base stations to be solved in a target positioning space, each row of elements of the matrix is coordinates of each base station to be solved in one candidate solution of the base station layout, N is the number of particles in the particle population, the number of the candidate solutions of the base station layout in the target positioning space is represented, D is the dimension of each particle in the particle population, and the number of the base stations to be solved corresponding to each candidate solution of the base station layout in the target positioning space is represented;
the generation module is used for obtaining a reverse learning population according to the original population;
the computing module is used for substituting the original population and the reverse learning population into the fitness function respectively to perform iterative computation of the base station fitness so as to obtain the optimal positions of the individuals in the original population and the reverse learning population; wherein, the fitness function is a calculation formula of a geometric precision factor; the computing module comprises a setting unit and an iteration unit;
the setting unit is used for setting iteration times;
the iteration unit is used for executing the following operations in each iteration process:
comparing an average geometric precision factor value obtained by the current iteration of the original population according to the coordinates of each base station to be solved in the target positioning space with an average geometric precision factor value obtained by the previous iteration of the original population, and reserving a smaller average geometric precision factor value as a first average geometric precision factor value;
comparing the average geometric precision factor value obtained by the current iteration of the reverse learning population according to the coordinates of each base station to be solved in the target positioning space with the average geometric precision factor value obtained by the previous iteration of the reverse learning population, and reserving a smaller average geometric precision factor value as a second average geometric precision factor value;
selecting the smaller value of the first average geometric precision factor value and the second average geometric precision factor value as a target average geometric precision factor value, and comparing the target average geometric precision factor value with the current global optimal value;
under the condition that the target average geometric precision factor value is smaller than the current global optimum value, replacing the current global optimum value with the target average geometric precision factor value, and taking the coordinates of the base station to be solved in the target positioning space corresponding to the target average geometric precision factor value as the coordinates of the base station to be solved in the target positioning space determined by the current iteration; in each iteration process, updating a speed value and a position value of coordinates of a base station to be solved in a target positioning space determined by the current iteration by combining the inertia weight of the current iteration times; according to preset speed boundary conditions and position boundary conditions of the base station to be solved, carrying out boundary processing on updated speed values exceeding the speed boundary conditions and/or updated position values exceeding the position boundary conditions to obtain optimal speed and optimal positions corresponding to the target average geometric precision factor values;
and the determining module is used for taking the coordinates of each base station to be solved corresponding to the global optimal value determined by the maximum iteration number as the base station layout of the target positioning space.
6. A base station arrangement comprising a processor and a memory, wherein the memory has stored therein computer instructions for executing the computer instructions stored in the memory, which when executed by the processor, implement the steps of the method according to any of claims 1 to 4.
7. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the steps of the method according to any one of claims 1 to 4.
CN202210108543.XA 2022-01-28 2022-01-28 Base station layout method and device Active CN114599004B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210108543.XA CN114599004B (en) 2022-01-28 2022-01-28 Base station layout method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210108543.XA CN114599004B (en) 2022-01-28 2022-01-28 Base station layout method and device

Publications (2)

Publication Number Publication Date
CN114599004A CN114599004A (en) 2022-06-07
CN114599004B true CN114599004B (en) 2024-01-05

Family

ID=81806347

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210108543.XA Active CN114599004B (en) 2022-01-28 2022-01-28 Base station layout method and device

Country Status (1)

Country Link
CN (1) CN114599004B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115209427B (en) * 2022-09-16 2022-11-22 长沙迪迈数码科技股份有限公司 Method, device and equipment for optimizing arrangement of underground UWB positioning base station

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105426955A (en) * 2015-08-20 2016-03-23 武汉科技大学 Disturbance-based elite reverse learning particle swarm optimization implementation method
CN105530651A (en) * 2015-11-27 2016-04-27 南京邮电大学 Optimal base station layout method in wireless positioning system
CN106326188A (en) * 2016-08-31 2017-01-11 中国人民解放军信息工程大学 Task division system based on backward learning of radius particle swarm optimization and method thereof
CN107145066A (en) * 2017-04-07 2017-09-08 北京科技大学 A kind of multi-parameters optimization method
WO2018072351A1 (en) * 2016-10-20 2018-04-26 北京工业大学 Method for optimizing support vector machine on basis of particle swarm optimization algorithm
KR20180085562A (en) * 2017-01-19 2018-07-27 금오공과대학교 산학협력단 Search and reconnaissance method by multiple drones using particle swarm algorithm
CN108830372A (en) * 2018-06-08 2018-11-16 湖北工业大学 A kind of adaptive particle swarm optimization method of Traveling Salesman Problem
AU2020102550A4 (en) * 2020-10-14 2020-12-24 Wuhan University The location optimization of 5G base stations (BSs) in urban outdoor area that considers signal blocking effect
CN112217557A (en) * 2020-09-30 2021-01-12 哈尔滨工程大学 Marine dynamic network base station layout optimization method
CN112911705A (en) * 2021-02-02 2021-06-04 湖南大学 Bayesian iteration improved particle swarm optimization algorithm-based indoor positioning method
CN113534042A (en) * 2021-07-14 2021-10-22 深圳市微能信息科技有限公司 TDOA (time difference of arrival) positioning algorithm based on improved reverse learning cuckoo search
CN113645630A (en) * 2021-06-30 2021-11-12 北京邮电大学 Base station layout method and device, electronic equipment and storage medium

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101871196B1 (en) * 2016-10-31 2018-06-27 광운대학교 산학협력단 Passive tracking system and method for indoor moving object
CN107506956B (en) * 2017-06-12 2018-06-15 合肥工业大学 Based on improvement particle cluster algorithm supply chain production and transport coordinated dispatching method and system

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105426955A (en) * 2015-08-20 2016-03-23 武汉科技大学 Disturbance-based elite reverse learning particle swarm optimization implementation method
CN105530651A (en) * 2015-11-27 2016-04-27 南京邮电大学 Optimal base station layout method in wireless positioning system
CN106326188A (en) * 2016-08-31 2017-01-11 中国人民解放军信息工程大学 Task division system based on backward learning of radius particle swarm optimization and method thereof
WO2018072351A1 (en) * 2016-10-20 2018-04-26 北京工业大学 Method for optimizing support vector machine on basis of particle swarm optimization algorithm
KR20180085562A (en) * 2017-01-19 2018-07-27 금오공과대학교 산학협력단 Search and reconnaissance method by multiple drones using particle swarm algorithm
CN107145066A (en) * 2017-04-07 2017-09-08 北京科技大学 A kind of multi-parameters optimization method
CN108830372A (en) * 2018-06-08 2018-11-16 湖北工业大学 A kind of adaptive particle swarm optimization method of Traveling Salesman Problem
CN112217557A (en) * 2020-09-30 2021-01-12 哈尔滨工程大学 Marine dynamic network base station layout optimization method
AU2020102550A4 (en) * 2020-10-14 2020-12-24 Wuhan University The location optimization of 5G base stations (BSs) in urban outdoor area that considers signal blocking effect
CN112911705A (en) * 2021-02-02 2021-06-04 湖南大学 Bayesian iteration improved particle swarm optimization algorithm-based indoor positioning method
CN113645630A (en) * 2021-06-30 2021-11-12 北京邮电大学 Base station layout method and device, electronic equipment and storage medium
CN113534042A (en) * 2021-07-14 2021-10-22 深圳市微能信息科技有限公司 TDOA (time difference of arrival) positioning algorithm based on improved reverse learning cuckoo search

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
"基于进化算法的神经网络研究与优化";何明慧;《中国优秀硕士学位论文全文数据库信息科技辑》;20180815(第8期);14-18 *
"无人机编队时差定位时的空间布局分析";赵忠凯等;《应用科技》;20210315;第48卷(第2期);12-18 *
多点定位系统的布站方法研究;胥松寿;;河南科技(第07期);56-57 *
赵忠凯等."无人机编队时差定位时的空间布局分析".《应用科技》.2021,第48卷(第2期),12-18. *

Also Published As

Publication number Publication date
CN114599004A (en) 2022-06-07

Similar Documents

Publication Publication Date Title
CN110167138B (en) Station distribution optimization method of passive time difference positioning system based on improved wolf optimization algorithm
CN111836358B (en) Positioning method, electronic device, and computer-readable storage medium
CN108871353A (en) Road network map generation method, system, equipment and storage medium
CN111464938B (en) Positioning method, positioning device, electronic equipment and computer readable storage medium
CN110234085B (en) Indoor position fingerprint map generation method and system based on anti-migration network
CN112461230A (en) Robot repositioning method and device, robot and readable storage medium
CN109874146B (en) Method and device for predicting path loss
CN107113764A (en) The method and apparatus for improving artificial neural network positioning performance
CN111417066B (en) Positioning method, positioning device, electronic equipment and computer readable storage medium
CN114501530B (en) Method and device for determining antenna parameters based on deep reinforcement learning
CN114599004B (en) Base station layout method and device
CN116736219B (en) Passive TDOA-FDOA combined positioning and optimizing station arrangement method based on improved particle swarm algorithm
CN117241215A (en) Wireless sensor network distributed node cooperative positioning method based on graph neural network
Javed et al. Position Vectors Based Efficient Indoor Positioning System.
CN114397894B (en) Mobile robot target searching method imitating human memory
CN112887909B (en) Indoor positioning method based on Wi-Fi signals
CN117933519B (en) Road network optimization method and related device
CN114280583A (en) Laser radar positioning precision verification method and system under condition of no GPS signal
CN114173281A (en) Optimal layout method of beacon nodes of positioning system based on TOA (time of arrival) under indoor NLOS (non-line of sight) environment
CN110146903B (en) Particle swarm Beidou satellite selection method based on feedback adjustment of inertial weight
CN114390534A (en) Beam pattern determination method, beam pattern determination device, electronic equipment and storage medium
KR102613133B1 (en) Apparatus and method for deciding validity of camera pose using visual localization
CN114245436B (en) Unmanned aerial vehicle auxiliary mobile edge network clustering method and device
KR102616082B1 (en) Apparatus and method for deciding validity of camera pose using visual localization
CN117553807B (en) Automatic driving navigation method and system based on laser radar

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