CN115413026A

CN115413026A - Base station selection method, system, equipment and storage medium based on clustering algorithm

Info

Publication number: CN115413026A
Application number: CN202211072662.0A
Authority: CN
Inventors: 封静娴; 杨涛; 熊尚坤; 杜国宇
Original assignee: China Telecom Corp Ltd
Current assignee: China Telecom Corp Ltd
Priority date: 2022-09-02
Filing date: 2022-09-02
Publication date: 2022-11-29

Abstract

The invention provides a base station selection method, a system, equipment and a storage medium based on a clustering algorithm, wherein the method comprises the following steps: presetting the number h of base stations of each group in an initial base station set of a target to be positioned, arranging and combining the initial base stations, respectively obtaining corresponding positioning coordinates, and establishing a positioning coordinate set; sequentially clustering the positioning coordinate set based on the cluster number k, and then carrying out classification accuracy evaluation to obtain the optimal cluster number k; and matching the coordinate mean value of the cluster with the maximum cluster positioning coordinate number with the nearest positioning coordinate in the cluster with the optimal cluster number k, and obtaining the positioning coordinate of the target to be positioned and the corresponding positioning base station combination according to the positioning coordinate. The invention can select the realization scheme with proper number and position from the alternative base station, and improves the precision and accuracy of the 5G positioning coordinate while improving the utilization rate of the network element resources with the positioning management function.

Description

Base station selection method, system, equipment and storage medium based on clustering algorithm

Technical Field

The invention relates to the field of communication positioning, in particular to a base station selection method, a system, equipment and a storage medium based on a clustering algorithm.

Background

Because 5G communication is characterized by high speed, low time delay, large connection and the like, key technologies thereof include large-scale antenna arrays, ultra-dense networking, novel multiple access, full spectrum access, novel network architecture and the like, in continuous standard evolution, 5G itself also adds a high-precision positioning function, such as industrial AGV, asset tracking and the like, especially indoor precise positioning, which can not be used by satellite positioning, and LTE and WiFi positioning technologies are not precise (which currently have bluetooth AOA, UWB and other technologies for high-precision positioning indoors).

In the 5G positioning, a reference signal is measured by a measured terminal, a measurement result is calculated by a Location Management Function (LMF), and the LMF calculates position information of the measured terminal according to stored known base station position information. According to the positioning principle, the two-dimensional positioning needs at least 3 positioning base stations to complete position calculation, but in practical application, a large number of base stations are generally measured, and a large amount of redundant base station information exists, so that the calculation amount is large and the resource waste of LMF is caused if a large amount of base station data is calculated; if only 3 base stations are selected for calculation, the accuracy is not enough, and a large error is generated in positioning.

Therefore, how to select a proper number of base stations with proper positions from the alternative base stations is an important problem to be solved, the accuracy and the precision of subsequent positioning coordinates are determined, and the method has important value for local or limited area positioning and division of positioning areas.

In view of this, the invention provides a base station selection method, system, device and storage medium based on a clustering algorithm.

It is to be noted that the information disclosed in the above background section is only for enhancement of understanding of the background of the invention and therefore may include information that does not constitute prior art that is already known to a person of ordinary skill in the art.

Disclosure of Invention

Aiming at the problems in the prior art, the invention aims to provide a base station selection method, a system, equipment and a storage medium based on a clustering algorithm, overcomes the difficulty in the prior art, can select an implementation scheme with proper number and position from alternative base stations, and improves the precision and the accuracy of a 5G positioning coordinate while improving the utilization rate of network element resources with a positioning management function.

The embodiment of the invention provides a base station selection method based on a clustering algorithm, which comprises the following steps:

presetting the number h of base stations in each group in an initial base station set of a target to be positioned, wherein h is more than or equal to 3, arranging and combining the initial base stations, respectively obtaining corresponding positioning coordinates, and establishing a positioning coordinate set;

sequentially clustering the positioning coordinate set based on the cluster number k, and then performing classification accuracy evaluation to obtain the optimal cluster number k;

and matching the coordinate mean value of the cluster with the maximum cluster positioning coordinate number with the nearest positioning coordinate in the cluster with the optimal cluster number k, and obtaining the positioning coordinate of the target to be positioned and the corresponding positioning base station combination according to the positioning coordinate.

Preferably, the method further includes, before the initial base station set of the target to be positioned is established, presetting the number h of base stations in each group, where h is greater than or equal to 3, arranging and combining the initial base stations, and obtaining corresponding positioning coordinates respectively, and further including the following steps:

obtaining an initial base station set based on the position of a target to be positioned, filtering isolated base stations in the initial base station set according to the strength of a reference signal of the initial base station by adopting an isolated forest algorithm, and obtaining a positioning coordinate and a corresponding positioning base station combination if a redundant base station does not exist; if the redundant base station still exists, the subsequent steps are executed.

Preferably, in the initial base station set of the target to be positioned, the number h of base stations in each group is preset, h is greater than or equal to 3, the initial base stations are arranged and combined, corresponding positioning coordinates are respectively obtained, and a positioning coordinate set is established, including:

based on the preset number h of base stations in each group, the value range of the number of the base stations is [3,M ], and corresponding initial base stations are obtained according to different values of the number h of the base stations for permutation and combination;

obtaining the sum W of the permutation and combination types obtained by different base station numbers h;

and each permutation and combination obtains a positioning coordinate based on the target to be positioned, and establishes a mapping relation between the positioning coordinate and the permutation and combination.

Preferably, the preset number h of base stations in each group is based on a value range of [3,M ], and the obtaining of the corresponding initial base stations according to different values of the number h of base stations for permutation and combination includes:

wherein M represents the total number of initial base stations; p represents the total number of isolated base stations filtered.

Preferably, the sequentially clustering the positioning coordinate set based on the cluster number k, and then performing classification fitness evaluation to obtain the optimal cluster number k includes:

selecting a first initial clustering center in the positioning coordinate set according to the density peak value;

calculating the distance from each of the rest positioning coordinates in the positioning coordinate set to the initial clustering center and the sum of the distances;

taking the positioning coordinate farthest from the initial clustering center as a next initial clustering center, wherein the value range of the cluster number k is [2,T ], and allocating each positioning coordinate to the nearest cluster; t is the minimum natural number of the root-cutting result which is larger than W;

and carrying out classification certainty evaluation on the clustering results, selecting the clustering result with the best evaluation result as a final clustering result through iteration, and regarding the value of the cluster number k corresponding to the final clustering result as the optimal cluster number.

Preferably, the selecting a first initial cluster center in the positioning coordinate set according to the density peak includes:

obtaining local density formula location

ρ _i The representation takes the point i as the center of a circle and includes the preset radius d _c The number of points in the circle of (d) _ij To locate the distance between the j point and the i point in the coordinate set, χ (x) represents that the distance to the data object i is smaller than the preset radius d _c When x is the number of data objects<0, then x (x) =1, and when x is larger than or equal to 0, then x (x) =0;

and taking the positioning coordinate with the maximum local density as a first initial clustering center.

Preferably, the performing classification fitness evaluation on the clustering result, iteratively selecting the clustering result with the best evaluation result as a final clustering result, and regarding a value of the cluster number k corresponding to the final clustering result as an optimal cluster number includes:

the evaluation index DBI is evaluated through a clustering algorithm,

wherein, avg (C) _i ) Is C _i Mean Euclidean distance of class sample to its class center, avg (C) _j ) Is C _j Mean Euclidean distance of class sample to class center, d _cen (u _i ,u _j ) Is the C _i And C _j Class center euclidean distance of a class;

when the DBI value is smaller, the dispersion degree is lower, and the clustering result is better;

iteration is carried out through each round of k = k +1, and evaluation results of the number k of the clusters under different values are obtained;

and when k = T, selecting the clustering result with the best evaluation result as a final clustering result, and taking the value of the cluster number k corresponding to the final clustering result as the optimal cluster number.

Preferably, in the cluster according to the optimal cluster number k, the coordinate mean of the cluster with the largest cluster positioning coordinate number matches a nearest positioning coordinate, and the positioning coordinate of the target to be positioned and the corresponding positioning base station combination obtained according to the positioning coordinate include:

clustering according to the number of the optimal clusters, and selecting the cluster with the largest number of positioning coordinates in the clusters as the optimal cluster;

obtaining the average value of all positioning coordinates in the optimal cluster;

and taking the positioning coordinate closest to the average value as the positioning coordinate of the target to be positioned.

Preferably, in the cluster according to the optimal cluster number k, the coordinate mean of the cluster with the largest cluster positioning coordinate number matches a nearest positioning coordinate, and the positioning coordinate of the target to be positioned and the corresponding positioning base station combination obtained according to the positioning coordinate further include:

and obtaining the permutation and combination of the initial base station corresponding to the positioning coordinate according to the mapping relation.

The embodiment of the present invention further provides a base station selection system based on a clustering algorithm, which is used for implementing the base station selection method based on the clustering algorithm, and the base station selection system based on the clustering algorithm includes:

the method comprises the following steps that a permutation and combination module presets the number h of base stations in each group in an initial base station set of a target to be positioned, wherein h is more than or equal to 3, permutation and combination are carried out on the initial base stations, corresponding positioning coordinates are obtained respectively, and a positioning coordinate set is established;

the coordinate clustering module is used for sequentially clustering the positioning coordinate set based on the cluster number k and then carrying out classification accuracy evaluation to obtain the optimal cluster number k;

and the positioning coordinate module is used for matching the coordinate mean value of the cluster with the largest cluster positioning coordinate quantity with the nearest positioning coordinate according to the cluster with the optimal cluster quantity k, and obtaining the positioning coordinate of the target to be positioned and the corresponding positioning base station combination according to the positioning coordinate.

The embodiment of the present invention further provides a base station selection device based on a clustering algorithm, including:

a processor;

a memory having stored therein executable instructions of the processor;

wherein the processor is configured to perform the steps of the clustering algorithm based base station selection method described above via execution of the executable instructions.

Embodiments of the present invention also provide a computer-readable storage medium for storing a program, which when executed implements the steps of the above-mentioned clustering algorithm-based base station selection method.

The invention aims to provide a base station selection method, a system, equipment and a storage medium based on a clustering algorithm, which can select a proper number and position from alternative base stations, improve the utilization rate of network element resources with a positioning management function, and improve the precision and accuracy of a 5G positioning coordinate.

Drawings

Other features, objects and advantages of the present invention will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, with reference to the accompanying drawings.

Fig. 1 is a flow chart of a base station selection method based on a clustering algorithm of the present invention.

Fig. 2 is a schematic flowchart of step S120 in the embodiment of the base station selection method based on the clustering algorithm in the present invention.

Fig. 3 is a schematic flowchart of step S130 in the embodiment of the method for selecting a base station based on a clustering algorithm according to the present invention.

Fig. 4 is a schematic flowchart of step S140 in the embodiment of the base station selection method based on the clustering algorithm in the present invention.

Fig. 5 is a flowchart of the detailed steps of the base station selection method based on the clustering algorithm according to the present invention.

Fig. 6, 7, 8 and 9 are schematic diagrams of steps and scenes for implementing the base station selection method based on the clustering algorithm.

Fig. 10 is a block diagram of a system for implementing the clustering algorithm-based base station selection method of the present invention.

Fig. 11 is a schematic block diagram of the permutation and combination module in the embodiment of the base station selection system based on the clustering algorithm of the present invention.

Fig. 12 is a schematic block diagram of a coordinate clustering module in an embodiment of a base station selection system based on a clustering algorithm according to the present invention.

Fig. 13 is a schematic block diagram of a location coordinate module in an embodiment of the clustering algorithm based base station selection system of the present invention.

Fig. 14 is a schematic diagram of a base station selection apparatus based on a clustering algorithm of the present invention.

Detailed Description

The following description of the embodiments of the present application is provided by way of specific examples, and other advantages and effects of the present application will be readily apparent to those skilled in the art from the disclosure herein. The present application is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present application. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.

Embodiments of the present application will be described in detail below with reference to the accompanying drawings so that those skilled in the art to which the present application pertains can easily carry out the present application. The present application may be embodied in many different forms and is not limited to the embodiments described herein.

Reference throughout this specification to "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," or the like, means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. Furthermore, the particular features, structures, materials, or characteristics shown may be combined in any suitable manner in any one or more embodiments or examples. Moreover, various embodiments or examples and features of different embodiments or examples presented in this application can be combined and combined by those skilled in the art without contradiction.

Furthermore, the terms "first", "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the expressions of the present application, "plurality" means two or more unless specifically defined otherwise.

In order to clearly explain the present application, components that are not related to the description are omitted, and the same reference numerals are given to the same or similar components throughout the specification.

Throughout the specification, when a device is referred to as being "connected" to another device, this includes not only the case of being "directly connected" but also the case of being "indirectly connected" with another element interposed therebetween. In addition, when a device "includes" a certain component, unless otherwise stated, the device does not exclude other components, but may include other components.

When a device is said to be "on" another device, this may be directly on the other device, but may be accompanied by other devices in between. When a device is said to be "directly on" another device, there are no other devices in between.

Although the terms first, second, etc. may be used herein to describe various elements in some instances, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, the first interface and the second interface are represented. Also, as used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context indicates otherwise. It will be further understood that the terms "comprises," "comprising," "includes" and/or "including," when used in this specification, specify the presence of stated features, steps, operations, elements, components, items, species, and/or groups, but do not preclude the presence, or addition of one or more other features, steps, operations, elements, components, items, species, and/or groups thereof. The terms "or" and/or "as used herein are to be construed as inclusive or meaning any one or any combination. Thus, "A, B or C" or "A, B and/or C" means "any of the following: a; b; c; a and B; a and C; b and C; A. b and C ". An exception to this definition will occur only when a combination of elements, functions, steps or operations are inherently mutually exclusive in some way.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used herein, the singular forms "a", "an" and "the" include plural forms as long as the words do not expressly indicate a contrary meaning. The terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, regions, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of other features, regions, integers, steps, operations, elements, components, and/or groups thereof.

Although not defined differently, including technical and scientific terms used herein, all terms have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. Terms defined in commonly used dictionaries are to be additionally interpreted as having meanings consistent with those of related art documents and the contents of the present prompts, and must not be excessively interpreted as having ideal or very formulaic meanings unless defined.

Fig. 1 is a flowchart of a base station selection method based on a clustering algorithm according to the present invention. As shown in fig. 1, the base station selection method based on the clustering algorithm of the present invention includes the following steps:

s120, presetting the number h of base stations in each group in an initial base station set of the target to be positioned, wherein h is more than or equal to 3, arranging and combining the initial base stations, respectively obtaining corresponding positioning coordinates, and establishing a positioning coordinate set.

And S130, sequentially clustering the positioning coordinate set based on the cluster number k, and then carrying out classification accuracy evaluation to obtain the optimal cluster number k.

And S140, matching the coordinate mean value of the cluster with the largest cluster positioning coordinate quantity with the nearest positioning coordinate in the cluster with the optimal cluster quantity k, and obtaining the positioning coordinate of the target to be positioned and the corresponding positioning base station combination according to the positioning coordinate.

The invention provides a base station selection optimization method aiming at 5G positioning. The method comprises the steps of firstly, eliminating edge base stations with lower measurement signals through an isolated forest algorithm; subsequently, a certain number of base stations are combined, the positioning result (positioning point) of each combination is calculated, the scattered positioning points obtain a clustering result by utilizing an improved K-Means + + algorithm, and finally, the base station combination is determined reversely according to the positioning points, so that the aim of selecting the optimal base station combination is fulfilled. The method can reversely select the base station combination based on the optimal positioning result from the viewpoint of reducing the positioning error, improves the indoor positioning precision, and has important value for local or limited area positioning and division of the positioning area.

Fig. 2 is a schematic flowchart of step S120 in the embodiment of the base station selection method based on the clustering algorithm in the present invention. Fig. 3 is a schematic flowchart of step S130 in the embodiment of the base station selection method based on the clustering algorithm in the present invention. Fig. 4 is a schematic flowchart of step S140 in the embodiment of the base station selection method based on the clustering algorithm in the present invention. As shown in fig. 2 to 4, in the embodiment of fig. 1, on the basis of steps S120, S130, and S140, step S120 further includes step S110, step S120 is replaced by S121, S122, and S123, step S130 is replaced by S131, S132, S133, and S134, and step S140 is replaced by S141, S142, S143, and S144, and each step is explained below:

s110, obtaining an initial base station set based on the position of a target to be positioned, adopting an isolated forest algorithm, filtering isolated base stations in the initial base station set according to the strength of a reference signal of the initial base station, and if redundant base stations do not exist, obtaining positioning coordinates and a corresponding positioning base station combination; if the redundant base station still exists, the subsequent steps are executed. In this embodiment, more than three base stations in the filtered initial base station set are used as the determination conditions for the existence of the redundant base stations, and if less than or equal to three base stations, it is determined that no redundant base station exists, so as to directly output the positioning coordinates. The isolated forest algorithm is an Ensemble-based anomaly detection method, and therefore linear time complexity is achieved. And the precision is higher, and the speed is fast when processing big data, so the application range in the industry is wider at present. Common scenarios include: attack detection in network security, financial transaction fraud detection, disease detection, noise data filtering (data cleansing), and the like. Different algorithms are used for detecting different types of anomalies, and the isolated forest algorithm mainly aims at the anomaly points in the continuous structured data. The premise of using isolated forests is that outliers are defined as those "outliers that are easily isolated" -which can be understood as points that are sparsely distributed and are relatively far from the high density population. Statistically, if there are only sparsely distributed points in a region in the data space, the probability that the data point falls in the region is very low, and therefore, the points in the regions can be considered as abnormal, but not limited to this.

S121, based on the number h of base stations in each group, the value range of the number of the base stations is [3,M ], obtaining corresponding initial base stations for permutation and combination according to different values of the number h of the base stations, wherein,

wherein M represents the total number of initial base stations; p denotes the total number of isolated base stations filtered.

And S122, obtaining the sum W of the permutation and combination types obtained by different base station numbers h.

And S123, obtaining a positioning coordinate by each permutation and combination based on the target to be positioned, and establishing a mapping relation between the positioning coordinate and the permutation and combination.

S131, selecting a first initial clustering center in the positioning coordinate set according to the density peak value. Step S131, including: obtaining local density formula location

ρ _i Representing the center of a circle with point i as the center, includingAt a predetermined radius d _c The number of points in the circle of (d) _ij To locate the distance between the j point and the i point in the coordinate set, χ (x) represents that the distance to the data object i is less than the preset radius d _c When x is the number of data objects<0, then x (x) =1, and when x is larger than or equal to 0, then x (x) =0; the location coordinate with the highest local density is used as the first initial cluster center, but not limited thereto.

S132, calculating the distance from each of the rest positioning coordinates in the positioning coordinate set to the initial clustering center and the sum of the distances.

S133, taking the positioning coordinate farthest from the initial clustering center as the next initial clustering center, wherein the value range of the cluster number k is [2,T ], and distributing each positioning coordinate to the nearest cluster; t is the smallest natural number of the root-cutting result larger than W.

And S134, carrying out classification fitness evaluation on the clustering results, selecting the clustering result with the best evaluation result as a final clustering result through iteration, and taking the value of the number k of clusters corresponding to the final clustering result as the optimal cluster number. Step S134, including:

the evaluation index DBI is evaluated through a clustering algorithm,

and when k = T, selecting the clustering result with the best evaluation result as a final clustering result, and taking the value of the cluster number k corresponding to the final clustering result as the optimal cluster number. Davisonberg Ding Zhishu (DBI), also called classification accuracy index, is an index for evaluating the goodness of a clustering algorithm proposed by David L. Davis and Tang Nade. Bouldin, but not limited thereto.

And S141, clustering according to the number of the optimal clusters, and selecting the cluster with the largest number of the positioning coordinates in the clusters as the optimal cluster.

And S142, obtaining the average value of all the positioning coordinates in the optimal cluster.

And S143, taking the positioning coordinate closest to the average value as the positioning coordinate of the target to be positioned.

And S144, obtaining the permutation and combination of the initial base stations corresponding to the positioning coordinates according to the mapping relation.

The invention can remove the influence of the isolated base station on the clustering result through an isolated forest algorithm. The initial measurement result is used for preliminary screening, the distance between each base station and the target to be measured is long, the measurement result of the reference signal is low, and the positioning accuracy is affected. The isolated forest algorithm can quickly separate P base stations with sparse distribution through super-cutting.

The invention obtains clustering results and positioning coordinates based on an improved K-Means + + algorithm. The basic idea of selecting the initial seed point by the k-means + + algorithm is as follows: the initial cluster centers are as far apart from each other as possible. 1. A point is randomly selected from the input set of data points as a first cluster center ("seed point"). 2. For each point x in the data set, its distance D (x) from the nearest cluster center (referred to as the selected cluster center) is calculated. 3. Selecting a new data point as a new cluster center, wherein the selection principle is as follows: the point with a larger D (x) has a larger probability of being selected as the cluster center. 4. Repeat 2 and 3 until k cluster centers are selected. 5. The standard k-means algorithm is run with these k initial cluster centers.

In the present invention, first, candidate base stations are grouped into a plurality of base station combinations (common base station) of h (h variable) groups

Seed combinations) and calculating based on the measurement results of each combinationAnd (6) obtaining a positioning result, and forming a plurality of scattered positioning points. Then, initial point selection: and selecting a first initial clustering center according to a density peak value method to ensure that the first clustering center is generated in an integral core. Then, the cluster number is determined: the cluster number is in the range of

The first round is preset to be 2, and the number of clusters is increased progressively until reaching the upper limit along with the increase of the number of rounds of clustering. And selecting the remaining initial clustering centers by using the maximum distance sum criterion provided by K-Means + +. And finding a more proper clustering center through an iterative algorithm. And finally, evaluating the clustering result through the DBI evaluation index to obtain an evaluation result. And (5) repeating the steps (2) - (5), wherein the number of the clusters set in the step (3) is increased progressively, the clustering results corresponding to the number of the clusters are evaluated by using the step (5), the clustering results of different preset clusters are compared by using a DBI (database identity) evaluation method, and the clustering result with the best evaluation is selected.

And, the invention infers the base station according to the best positioning coordinate. According to the characteristic that the positioning result is generated around the real position, the cluster with the most coordinates in the clustering result is selected, the intra-class coordinate mean value is calculated, the coordinate closest to the coordinate mean value is selected as the final positioning coordinate, and the combination of the positioning base stations can be reversely deduced according to the coordinate, so that the selected base station is determined.

The base station selection method based on the clustering algorithm can select a scheme with proper number and position from alternative base stations, improves the precision and accuracy of the 5G positioning coordinate while improving the utilization rate of the network element resources with the positioning management function.

Fig. 5 is a flowchart of the detailed steps of the base station selection method based on the clustering algorithm according to the present invention. The specific steps of the base station selection method based on the clustering algorithm implemented by the template shown in fig. 5 include:

and determining the terminal to be positioned.

And obtaining an initial measurement result of the terminal to be positioned and positioning auxiliary data at the same time.

And generating initial positioning coordinates, removing isolated base stations by using an isolated forest algorithm, and judging whether the number of the remaining base stations is more than 3.

If the number of the terminal positioning coordinates is less than or equal to 3, directly outputting the initial positioning coordinates as the positioning coordinates of the terminal to be positioned.

And if the number of the isolated points is more than 3, clustering the positioning results after the isolated points are removed based on the density peak value and the K-Means + + algorithm. And evaluating the clustering quality through an internal effectiveness index DBI, and outputting a clustering result. And selecting the class with the most quantity as class C by recording the number of the internal fixed coordinates of each cluster. By calculating the mean value of the coordinates of class C

The coordinate closest thereto is selected as the final positioning coordinate. Thereby outputting the positioning coordinate of the terminal to be positioned and reversely deducing the base station combination according to the positioning coordinate.

Fig. 6, 7, 8 and 9 are schematic diagrams of steps and scenes for implementing the base station selection method based on the clustering algorithm. Referring to fig. 5, 6, 7, 8, and 9, in the present invention, a reference signal is measured by a measured terminal through 5G positioning, a measurement result is calculated by a Location Management Function (LMF), and the LMF calculates position information of the measured terminal 12 according to stored known base station position information. However, a large number of measured positioning base stations 11 exist, and a large amount of redundant base station information exists, for example, calculation of a large amount of base station data results in a large calculation amount and resource waste of the LMF; if only 3 base stations are selected for calculation, the accuracy is not enough, and a large error is generated in positioning. After the 5G positioning base station selection function is added:

step 1: the LMF performs screening based on initial reference signal measurements. And eliminating P isolated base stations 10 which are relatively far away from the target to be measured through an isolated forest algorithm (IForest). IForest mainly comprises two parts, a training phase and a testing phase.

A training stage: firstly, randomly selecting n sample points from a training data set, and putting the n sample points into a root node; secondly, randomly selecting a dimension and cutting in a data range; finally, the above steps are repeated until each node has only one data or reaches a preset height.

And (3) a testing stage: firstly, traversing each iTree by training data x; secondly, calculating the number of the layers of the tree where x falls; thirdly, calculating the average height of x in each tree; and finally, when the abnormal score s is larger than the set threshold and the signal intensity from the base station to the target to be measured is smaller than the average value of all the base stations, judging as an isolated point.

s(x,n)＝2^(-E(h(x))/c(n))

For example: the target to be measured can carry out data transmission with 10 nearby base stations (M1, M2, M3, M4, M5, M6, M7, M8, M9 and M10), and the signal strength of the target to be measured is [ -44-42-52-78-30-36-54-36-72-47] and the unit is dbm. The abnormal values of-78 and-72 in the one-dimensional array can be identified through an isolated forest algorithm, and then two isolated base stations (M4, M9) are removed, so that the positioning accuracy is prevented from being influenced.

And 2, step: and if the redundant base station still exists after the isolated base station is removed, continuing to execute the subsequent steps. First, a plurality of base station combinations are constructed, each combination comprising h (h is more than or equal to 3 and less than or equal to M) base stations. Traversal may obtain

Seed base station combination and corresponding

And (6) planting positioning results. Wherein M represents the total number of initial base stations; p represents the number of the eliminated base stations; h represents a group of h base stations, and a positioning point can be correspondingly calculated) (the combined positioning results 13 obtained in this step are coordinate points scattered in the positioning area, which are the sample sources of clustering in the subsequent steps).

For example: after 2 base stations are removed through the isolated forest, 8 candidate base stations (M1, M2, M3, M5, M6, M7, M8 and M10) are remained. Traversal may obtain

And each combination mode can obtain a corresponding positioning result.

And step 3: clustering was performed using a modified K-Means + + algorithm. The specific steps of the improved algorithm are as follows:

(1) And selecting a first initial clustering center according to the density peak value. Local density formula location

χ (x) denotes that the distance to data object i is less than the cutoff distance dist _c The number of data objects.

(2) And calculating the sum of the distances from each coordinate point to the existing clustering center. And the coordinate with the largest value is selected as the next initial cluster center. (initial wheel of cluster number set to 2)

(3) And allocating each positioning result to a cluster with the highest similarity, and searching a reasonable clustering center through iteration.

(4) The clustering results were evaluated using a modified DBI method. Using the following formula

The clustering results in this range are evaluated.

After the first round of steps (2) - (4) is finished, the set cluster number is increased progressively (cluster number range)

) And (5) executing the steps (2) to (4) again, and outputting the clustering evaluation result DBI (i) of each round. And comparing each round of DBI (i), selecting the best evaluation result as a final clustering result, and taking the number of clusters corresponding to the round as the optimal cluster number.

For example: the total number of clusters is set to [2, 15] according to the positioning result of 219. And setting the number of clusters equal to 2 in the first round, executing an improved K-Means + + algorithm, and evaluating the clustering quality through DBI. Within the range of the cluster number, the above steps are executed again until the cluster number reaches 15. The minimum value of DBI in the evaluation results was assumed to be 0.5, and the number of clusters was 6. That is, when the number of clusters is 6, the clustering result is optimal.

And 4, step 4: and selecting the cluster with the maximum number of coordinates in the cluster as the optimal cluster according to the clustering result. Calculating the mean value of the coordinates in the class

The positioning coordinate closest to the average coordinate 15 is the final positioning coordinate 16, and the base station combination [ base station 141, base station 142, base station 143, base station 144 ] is reversely deduced based on the positioning result]。

For example: of the 6 clusters, the cluster having the largest number of coordinates within the cluster is selected as the optimal cluster. Suppose that the mean value of the intra-class coordinates is (15.74,20.23). And, of the 219 positioning results, the coordinate closest to the coordinate (15.74,20.23) is assumed to be (13,17). The final location coordinates are (13,17). Assuming that the positioning coordinates (13,17) are generated by four positioning base stations M1, M2, M5, and M6, the finally selected 5G positioning base stations are M1, M2, M5, and M6.

Compared with the prior art, the main advantages of the patent are as follows:

1. according to the scheme, the selection algorithm of the base station in the 5G positioning is designed, the optimal base station combination can be selected based on the initial measurement result, and the positioning precision is improved.

2. And (3) eliminating P isolated base stations relatively far away from the target to be measured according to the size of the reference signal measured for the first time by adopting an isolated forest algorithm (IForest), so as to avoid influencing the positioning accuracy.

3. And (3) obtaining a clustering result and a positioning coordinate by adopting an improved K-Means + + algorithm:

(1) The initial point selection is improved. And selecting the point with the maximum density peak value as an initial clustering point, wherein the maximum density indicates that the probability of the tested terminal at the position is maximum, so that the method is more reasonable than the random point selection.

(2) The k value selection is improved. In the scheme, the k value selection is not fixed, a DBI (database partitioning interface) evaluation method is introduced to evaluate the clustering result corresponding to each selected k value, and the final clustering result is determined according to the evaluation result.

(3) And generating a cluster sample point. This scheme can set up the combination of the base station of multiple quantity, and every combination can calculate a location result, a coordinate point promptly, consequently does not need base station number in the preset combination, and is more reasonable.

4. And reversely deducing the base station combination according to the clustering result and the positioning coordinate. The positioning coordinate point is selected according to the rule, and the point can correspond to one base station combination, so that the number and the position of the optimal base station combination can be determined.

The method aims at the practical problem that in 5G positioning, under the condition that a large number of redundant base stations exist, an LMF (location-based function) needs to solve in positioning calculation, and selects a proper positioning base station. And the number of the positioning base stations and the positions of the base stations are determined through the algorithm by removing isolated base stations and selecting the base stations by using a clustering algorithm, so that the positioning error caused by the subjectively determined number is avoided.

The method can be applied to local or limited area positioning in 5G positioning and division of positioning base stations in a positioning area, solves the problem of base station selection in the process of LMF position calculation, avoids positioning errors caused by subjective base station combination selection, and improves positioning accuracy and accuracy; and determining a positioning base station combination corresponding to the local positioning area, dividing the positioning area and determining a base station combination corresponding to a certain positioning area.

Fig. 10 is a block diagram of a system for implementing the clustering algorithm-based base station selection method of the present invention. As shown in fig. 10, the base station selection system based on clustering algorithm of the present invention includes but is not limited to:

and the permutation and combination module 52 presets the number h of base stations in each group in the initial base station set of the target to be positioned, wherein h is more than or equal to 3, permutes and combines the initial base stations, respectively obtains corresponding positioning coordinates, and establishes a positioning coordinate set.

And the coordinate clustering module 53 sequentially clusters the positioning coordinate set based on the cluster number k, and then performs classification accuracy evaluation to obtain the optimal cluster number k.

And the positioning coordinate module 54 matches the closest positioning coordinate with the coordinate mean of the cluster with the largest number of cluster positioning coordinates in the cluster with the optimal number k of clusters, and obtains the positioning coordinate of the target to be positioned and the corresponding positioning base station combination according to the positioning coordinate.

The implementation principle of the above modules is described in the related introduction of the clustering algorithm-based base station selection method, and will not be described herein again.

The base station selection system based on the clustering algorithm can select a proper number and position from the alternative base stations, improves the precision and accuracy of the 5G positioning coordinate while improving the utilization rate of the network element resources with the positioning management function.

Fig. 11 is a schematic block diagram of the permutation and combination module in the embodiment of the base station selection system based on the clustering algorithm of the present invention. Fig. 12 is a schematic block diagram of a coordinate clustering module in an embodiment of a base station selection system based on a clustering algorithm according to the present invention. Fig. 13 is a schematic block diagram of a location coordinate module in an embodiment of the clustering algorithm based base station selection system of the present invention. Fig. 11 to 13 show that, on the basis of the embodiment of the apparatus in fig. 10, the base station selection system based on the clustering algorithm of the present invention further includes a module base station filtering module 51, and the arrangement combination module 52 is replaced by a base station grouping module 521, a category summing module 522, and a mapping relation module 523. The coordinate clustering module 53 is replaced by an initial clustering module 531, a distance calculation module 532, a coordinate assignment module 533, and an iterative clustering module 534. The location coordinates module 54 is replaced by an optimal clustering module 541, a coordinate averaging module 542, a coordinate location module 543, and a base station combination module 544, each of which is described below:

a base station filtering module 51 configured to obtain an initial base station set based on the position of the target to be positioned, filter isolated base stations in the initial base station set according to the strength of a reference signal of the initial base station by using an isolated forest algorithm, and obtain a positioning coordinate and a corresponding positioning base station combination if no redundant base station exists; and if the redundant base station still exists, executing the subsequent modules.

A base station grouping module 521 configured to obtain corresponding initial base stations for permutation and combination according to different values of the number h of base stations based on the number h of base stations in each preset group, where the number h of base stations is [3,M ],

A class summing module 522 configured to obtain a sum W of permutation and combination classes obtained by different numbers h of base stations;

the mapping relation module 523 is configured to obtain a positioning coordinate based on the target to be positioned for each permutation and combination, and establish a mapping relation between the positioning coordinate and the permutation and combination.

The initial clustering module 531 is configured to select a first initial clustering center in the positioning coordinate set according to the density peak; the method comprises the following steps: obtaining local density formula location

ρ _i The representation takes the point i as the center of a circle and includes a preset radius d _c The number of points in the circle of (d) _ij To locate the distance between the j point and the i point in the coordinate set, χ (x) represents that the distance to the data object i is less than the preset radius d _c When x is the number of data objects<0, then x (x) =1, and when x is larger than or equal to 0, then x (x) =0; and taking the positioning coordinate with the maximum local density as a first initial clustering center.

A distance calculation module 532 configured to calculate a distance from each of the remaining positioning coordinates in the positioning coordinate set to the initial cluster center and a sum of the distances;

a coordinate allocating module 533 configured to use the positioning coordinate farthest from the initial clustering center as a next initial clustering center, where a value range of the cluster number k is [2,T ], and allocate each positioning coordinate to a closest cluster; t is the minimum natural number of the root-cutting result which is larger than W;

the iterative clustering module 534 is configured to perform classification fitness evaluation on the clustering results, select the clustering result with the best evaluation result as the final clustering result through iteration, and regard the value of the cluster number k corresponding to the final clustering result as the optimal cluster number. The method comprises the following steps:

the evaluation index DBI is evaluated through a clustering algorithm,

wherein, avg (C) _i ) Is C _i Mean Euclidean distance of class sample to its class center, avg (C) _j ) Is C _j Mean Euclidean distance of class sample to its class center, d _cen (u _i ,u _j ) Is the C _i And C _j Class center Euclidean distance of a class;

and when k = T, selecting the clustering result with the best evaluation result (the clustering result with the minimum DBI value) as the final clustering result, and taking the value of the cluster number k corresponding to the final clustering result as the optimal cluster number.

And an optimal clustering module 541 configured to perform clustering according to the number of the optimal clusters, and select a cluster with the largest number of the positioning coordinates in the clusters as the optimal cluster.

A coordinate averaging module 542 configured to obtain an average of all location coordinates in the optimal cluster.

And the coordinate positioning module 543 is configured to use the positioning coordinate closest to the average value as the positioning coordinate of the target to be positioned.

And the base station combination module 544 is configured to obtain the permutation and combination of the initial base stations corresponding to the positioning coordinates according to the mapping relationship.

The implementation principle of the above steps is described in the related introduction of the clustering algorithm-based base station selection method, and will not be described herein again.

The embodiment of the invention also provides base station selection equipment based on the clustering algorithm, which comprises a processor. A memory having stored therein executable instructions of the processor. Wherein the processor is configured to perform the steps of the clustering algorithm based base station selection method via execution of executable instructions.

As shown above, the base station selection system based on the clustering algorithm according to the embodiment of the present invention can select an appropriate number and position from the candidate base stations, thereby improving the accuracy and precision of the 5G positioning coordinates while improving the utilization rate of the network element resources with the positioning management function.

As will be appreciated by one skilled in the art, aspects of the present invention may be embodied as a system, method or program product. Thus, various aspects of the invention may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" platform.

Fig. 14 is a schematic diagram of a base station selection apparatus based on a clustering algorithm of the present invention. An electronic device 600 according to this embodiment of the invention is described below with reference to fig. 14. The electronic device 600 shown in fig. 14 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.

As shown in fig. 14, the electronic device 600 is in the form of a general purpose computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one memory unit 620, a bus 630 connecting the different platform components (including the memory unit 620 and the processing unit 610), a display unit 640, etc.

Wherein the storage unit stores program code executable by the processing unit 610 to cause the processing unit 610 to perform steps according to various exemplary embodiments of the present invention described in the above-mentioned electronic prescription flow processing method section of the present specification. For example, processing unit 610 may perform the steps as shown in fig. 1.

The storage unit 620 may include readable media in the form of volatile memory units, such as a random access memory unit (RAM) 6201 and/or a cache memory unit 6202, and may further include a read-only memory unit (ROM) 6203.

The memory unit 620 may also include a program/utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including, but not limited to: a processing system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.

Bus 630 may be one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

The electronic device 600 may also communicate with one or more external devices 700 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 600, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 600 to communicate with one or more other computing devices. Such communication may occur via an input/output (I/O) interface 650. Also, the electronic device 600 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the Internet) via the network adapter 660. The network adapter 660 may communicate with the other modules of the electronic device 600 via the bus 630. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms, to name a few.

The embodiment of the invention also provides a computer readable storage medium for storing a program, and the steps of the base station selection method based on the clustering algorithm are realized when the program is executed. In some possible embodiments, the aspects of the present invention may also be implemented in the form of a program product comprising program code for causing a terminal device to perform the steps according to various exemplary embodiments of the present invention described in the above-mentioned electronic prescription flow processing method section of this specification, when the program product is run on the terminal device.

As shown above, the base station selection system based on the clustering algorithm in this embodiment of the present invention can select an appropriate number and position from the candidate base stations, so as to improve the accuracy and precision of the 5G positioning coordinates while improving the utilization rate of the network element resources with the positioning management function.

The program product 800 for implementing the above method according to an embodiment of the present invention may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited in this regard and, in the present document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

A computer readable storage medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable storage medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for carrying out processes of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).

In summary, the present invention is directed to a method, a system, a device, and a storage medium for selecting a base station based on a clustering algorithm, which can select an appropriate number and position from alternative base stations, and improve the accuracy and precision of a 5G positioning coordinate while improving the utilization rate of network element resources with a positioning management function.

The foregoing is a further detailed description of the invention in connection with specific preferred embodiments and it is not intended to limit the invention to the specific embodiments described. For those skilled in the art to which the invention pertains, several simple deductions or substitutions can be made without departing from the spirit of the invention, and all shall be considered as belonging to the protection scope of the invention.

Claims

1. A base station selection method based on a clustering algorithm is characterized by comprising the following steps:

presetting the number h of base stations of each group in an initial base station set of a target to be positioned, wherein h is more than or equal to 3, arranging and combining the initial base stations, respectively obtaining corresponding positioning coordinates, and establishing a positioning coordinate set;

2. The method for selecting a base station based on a clustering algorithm according to claim 1, wherein the number h of base stations in each group is preset in the initial base station set of the target to be positioned, h is not less than 3, the initial base stations are arranged and combined, corresponding positioning coordinates are respectively obtained, and before the positioning coordinate set is established, the method further comprises the following steps:

3. The method for selecting a base station based on a clustering algorithm according to claim 2, wherein the number h of base stations in each group is preset in the initial base station set of the target to be positioned, h is greater than or equal to 3, the initial base stations are arranged and combined, corresponding positioning coordinates are respectively obtained, and a positioning coordinate set is established, comprising:

4. The method as claimed in claim 3, wherein the base station number h based on each group is preset, the value range of the base station number is [3,M ], and the obtaining of the corresponding initial base stations according to different values of the base station number h for permutation and combination includes:

5. The method for selecting a base station based on a clustering algorithm according to claim 2, wherein the clustering is performed on the positioning coordinate set in sequence based on the number k of clusters, and then the classification accuracy evaluation is performed to obtain the optimal number k of clusters, comprising:

taking the positioning coordinate farthest from the initial clustering center as the next initial clustering center, wherein the value range of the cluster number k is [2,T ], and allocating each positioning coordinate to the nearest cluster; t is the minimum natural number of the root-opening result larger than W;

6. The method of claim 5, wherein the selecting a first initial cluster center in the set of location coordinates according to a density peak comprises:

obtaining local density formula location

ρ _i The representation takes the point i as the center of a circle and includes a preset radius d _c The number of points in the circle of (d) _ij To locate the distance between the j point and the i point in the coordinate set, χ (x) represents that the distance to the data object i is less than the preset radius d _c When x is the number of data objects<0, then x (x) =1, and when x is larger than or equal to 0, then x (x) =0;

7. The method for selecting a base station based on a clustering algorithm according to claim 5, wherein the evaluating the classification suitability of the clustering result, iteratively selecting the clustering result with the best evaluation result as the final clustering result, and regarding the value of the cluster number k corresponding to the final clustering result as the optimal cluster number comprises:

the evaluation index DBI is evaluated through a clustering algorithm,

8. The method for selecting a base station based on a clustering algorithm according to claim 3, wherein in the clustering according to the optimal cluster number k, the coordinate mean of the cluster with the largest cluster positioning coordinate number matches the nearest positioning coordinate, and the combination of the positioning coordinate of the target to be positioned and the corresponding positioning base station obtained according to the positioning coordinate comprises:

9. The method for selecting a base station based on a clustering algorithm according to claim 8, wherein in the clustering according to the optimal cluster number k, the coordinate mean of the cluster with the largest number of in-cluster positioning coordinates matches the nearest positioning coordinate, and the positioning coordinates of the object to be positioned and the corresponding positioning base station combination obtained according to the positioning coordinates further comprises:

10. A system for selecting a base station based on a clustering algorithm, comprising:

11. A base station selection device based on a clustering algorithm, comprising:

a processor;

a memory having stored therein executable instructions of the processor;

wherein the processor is configured to perform the steps of the clustering algorithm based base station selection method of any one of claims 1 to 9 via execution of the executable instructions.

12. A computer-readable storage medium storing a program, which when executed by a processor performs the steps of the clustering algorithm based base station selection method of any one of claims 1 to 9.