CN111385818A - Method, device and equipment for optimizing wireless network parameters - Google Patents
Method, device and equipment for optimizing wireless network parameters Download PDFInfo
- Publication number
- CN111385818A CN111385818A CN201811622369.0A CN201811622369A CN111385818A CN 111385818 A CN111385818 A CN 111385818A CN 201811622369 A CN201811622369 A CN 201811622369A CN 111385818 A CN111385818 A CN 111385818A
- Authority
- CN
- China
- Prior art keywords
- cell
- wireless network
- determining
- network parameters
- parameters
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/02—Arrangements for optimising operational condition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/02—Traffic management, e.g. flow control or congestion control
- H04W28/06—Optimizing the usage of the radio link, e.g. header compression, information sizing, discarding information
-
- 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)
- Mobile Radio Communication Systems (AREA)
Abstract
The embodiment of the application provides a method, a device and equipment for optimizing wireless network parameters, wherein the method comprises the following steps: classifying wireless network parameters to determine a plurality of classification groups; analyzing each classification group in the plurality of classification groups and the feature label of the corresponding cell; classifying the plurality of cells by using the plurality of feature labels as training data by using an unsupervised learning algorithm; and determining at least one weak cell in the same category, and optimizing wireless network parameters corresponding to the at least one weak cell. In the application, the characteristic label of district is established according to the wireless network parameter that needs optimize, classify the district according to the characteristic label, corrected current general "relatively poor district" to "good district" study parameter setting mode, make the study of district parameter take place in the district of the same type, can obviously promote wireless network parameter optimization's degree of accuracy, science and high efficiency, reduction cost of labor that can great degree, promotion wireless network quality and user's perception.
Description
Technical Field
The present invention relates to the field of wireless technologies, and in particular, to a method, an apparatus, a device, and a computer storage medium for optimizing wireless network parameters.
Background
In recent years, with the development of wireless communication technology and the popularization of intelligent terminals, the traffic of terminal users is increased explosively, the number of communication stations for supporting mobile users is increased, and a wireless network is more complex than ever, so that higher requirements are provided for the optimization of wireless network parameters, and a wireless network parameter optimization method which can sufficiently cope with the severe situation needs to be found.
At present, the wireless network parameter optimization method mainly adopts a method that an operator manually adjusts wireless network parameters according to the running condition of wireless network indexes, and has strong subjectivity; secondly, there is a method for optimizing parameters according to parameter values of cells with good network operation indexes, but the types of the cells are not distinguished, so that the optimization efficiency is low; the method has certain complexity in the process of acquiring and analyzing data, and the manual operation efficiency is low.
Therefore, it is necessary to provide a more reasonable optimization scheme for wireless network parameters, so that the optimization efficiency is improved and the labor cost is reduced.
Disclosure of Invention
The embodiment of the application provides a method, a device, equipment and a computer storage medium for optimizing wireless network parameters, which can improve the efficiency, scientificity and efficiency of wireless network parameter optimization, and improve the quality and user experience of a wireless network while greatly reducing labor cost.
In a first aspect, an embodiment of the present application provides a method for optimizing a wireless network parameter, where the method may include:
classifying wireless network parameters to determine a plurality of classification groups;
analyzing each classification group in the plurality of classification groups and the feature label of the corresponding cell;
classifying the plurality of cells by using the plurality of feature labels as training data by using an unsupervised learning algorithm;
determining at least one weak cell in the same category, and optimizing wireless network parameters corresponding to the at least one weak cell, wherein the weak cell is a cell in the same category, and the wireless network parameters of the weak cell meet a first preset condition.
In the method, the characteristic label of the cell is established according to the wireless network parameters to be optimized, and the universality of the establishing method can be widely applied to the optimization of various parameters; the cells are classified according to the feature labels, the conventional general method for setting learning parameters from poor cells to good cells is corrected, the learning of cell parameters occurs in the cells of the same type, and the method for optimizing the wireless network parameters by applying machine learning is more scientific and reasonable. Meanwhile, the accuracy, scientificity and high efficiency of wireless network parameter optimization can be obviously improved, the labor cost can be greatly reduced, and the quality of a wireless network and the user perception are improved.
In a possible implementation manner, after the step of analyzing each classification group in the plurality of classification groups and the feature tag of the corresponding cell, "the method may further include:
and distinguishing the feature tags of the cells, and determining at least one of a category type feature tag and a numerical type feature tag.
In another possible embodiment, the method may further include: and carrying out standardization processing on the numerical characteristic label.
In another possible implementation manner, the step of classifying the plurality of cells by using the plurality of feature labels as training data through the unsupervised learning algorithm may specifically include:
determining a cell to be clustered; classifying the cells to be clustered by using the class type feature tags, and determining a cell group to be clustered; and carrying out hierarchical clustering on the cell group to be clustered, and dividing the plurality of cells to be clustered into at least one type of cells.
In another possible implementation manner, the step of "classifying the wireless network parameters and determining a plurality of classification groups" may specifically include:
and classifying the wireless network parameters according to the functions of the wireless network parameters, and determining a plurality of classification groups, wherein the classification groups are related to the operation quality of the cell.
In another possible implementation, after the step of classifying the wireless network parameters and determining a plurality of classification groups, the method may further include: determining an operation index of the cell according to the plurality of classification groups; and selecting a cell corresponding to at least one operation index meeting a second preset condition according to the operation index.
In another possible implementation manner, before the step of "determining at least one weak cell in the same category and optimizing the radio network parameter corresponding to the at least one weak cell", the method may further include:
performing index condition check on the classified cells corresponding to each class to determine a check result;
and determining a weak cell and a strong cell in the same category according to the operation index and the checking result, wherein the strong cell is a cell in the same category, and the wireless network parameter of the strong cell does not meet the first preset condition.
In another possible implementation, the step of determining the weak cell and the strong cell in the same category according to the operation index and the checking result may specifically include:
when the operation index reaches a cell corresponding to a preset threshold value, determining the cell as a strong cell;
and when the operation index does not reach the cell corresponding to the preset threshold value, determining the cell as a weak cell.
In another possible implementation, the step of determining at least one weak cell in the same category and optimizing the radio network parameter corresponding to the at least one weak cell may specifically include: determining the category of at least one weak cell; and optimizing the wireless network parameters corresponding to at least one weak cell according to the mode of the wireless network parameters corresponding to the category.
In yet another possible implementation manner, the "classification group" is divided according to the category corresponding to the wireless network parameter; the classification group may include at least one of: coverage class parameters, handover class parameters, reselection class parameters, capacity management class parameters, quality class parameters, and interoperability class parameters.
In a second aspect, an embodiment of the present application provides an apparatus for optimizing a wireless network parameter, where the apparatus may include:
the classification module is used for classifying the wireless network parameters and determining a plurality of classification groups;
the analysis module is used for analyzing each classification group in the plurality of classification groups and the feature label of the corresponding cell;
the processing module is used for classifying the cells by using the feature labels as training data through an unsupervised learning algorithm;
and the optimization module is used for determining at least one weak cell in the same category and optimizing the wireless network parameters corresponding to the at least one weak cell, wherein the weak cell is a cell in which the wireless network parameters meet a first preset condition in the same category.
In the method, the characteristic label of the cell is established according to the wireless network parameters to be optimized, and the universality of the establishing method can be widely applied to the optimization of various parameters; the cells are classified according to the feature labels, the conventional general method for setting learning parameters from poor cells to good cells is corrected, the learning of cell parameters occurs in the cells of the same type, and the method for optimizing the wireless network parameters by applying machine learning is more scientific and reasonable. Meanwhile, the accuracy, scientificity and high efficiency of wireless network parameter optimization can be obviously improved, the labor cost can be greatly reduced, and the quality of a wireless network and the user perception are improved.
In a third aspect, an embodiment of the present application provides an apparatus for optimizing wireless network parameters, where the apparatus includes a processor and a memory storing computer program instructions;
the processor, when executing the computer program instructions, implements a method of optimizing a wireless network parameter as in any of the first aspect.
In a fourth aspect, embodiments of the present application provide a computer-readable storage medium, which includes instructions that, when executed on a computer, cause the computer to perform the method for optimizing the parameters of the wireless network according to any one of the first aspect.
In a fifth aspect, embodiments of the present application provide a computer program product containing instructions, which when run on a computer, cause the computer to perform the method for optimizing a parameter of a wireless network according to any one of the first aspect.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments of the present application will be briefly described below, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of a method for optimizing wireless network parameters according to an embodiment of the present application;
fig. 2 is a flowchart of a specific method for optimizing wireless network parameters according to an embodiment of the present application;
fig. 3 is a flowchart of cell feature tag normalization according to an embodiment of the present application;
fig. 4 is a flowchart of unsupervised machine learning cell clustering according to an embodiment of the present application;
FIG. 5 is a schematic diagram of a hierarchical clustering link structure provided by an embodiment of the present application;
FIG. 6 is a schematic diagram of a hierarchical structure of a hierarchical cluster according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of an apparatus for optimizing wireless network parameters according to an embodiment of the present application;
fig. 8 is a schematic structural diagram of an apparatus for optimizing wireless network parameters according to an embodiment of the present application.
Detailed Description
Features and exemplary embodiments of various aspects of the present application will be described in detail below, and in order to make objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application. It will be apparent to one skilled in the art that the present application may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present application by illustrating examples thereof.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
For the convenience of understanding the content related to the present application, the method for optimizing the wireless network parameters related to the present application will be described in detail with reference to fig. 1.
Fig. 1 is a flowchart of a method for optimizing wireless network parameters according to an embodiment of the present application.
As shown in fig. 1, the method may specifically include S110-S140:
first, S110: and classifying the wireless network parameters to determine a plurality of classification groups.
Specifically, the wireless network parameters are classified according to the functions of the wireless network parameters, and a plurality of classification groups are determined, wherein the classification groups are related to the operation quality of the cell. The classification group is divided according to the classification corresponding to the wireless network parameters; the taxonomic group includes at least one of: coverage class parameters, handover class parameters, reselection class parameters, capacity management class parameters, quality class parameters, and interoperability class parameters.
In a possible embodiment, after this step, the method may further include: determining an operation index of the cell according to the plurality of classification groups; and selecting a cell corresponding to at least one operation index meeting a second preset condition according to the operation index.
Secondly, S120: each of the plurality of classification groups is analyzed for a characteristic label of the corresponding cell.
Specifically, after the step S120, the method may further include: and distinguishing the feature tags of the cells, and determining at least one of a category type feature tag and a numerical type feature tag. And standardizing each classified group according to the numerical characteristic label.
Then, S130: and classifying the plurality of cells by using the plurality of feature labels as training data by using an unsupervised learning algorithm.
Specifically, based on S120, this step may specifically include: determining a cell to be clustered; classifying the cells to be clustered by using the class type feature tags, and determining a cell group to be clustered; and carrying out hierarchical clustering on the cell group to be clustered, and dividing the plurality of cells to be clustered into at least one type of cells.
Finally, S140: and determining at least one weak cell in the same category, and optimizing wireless network parameters corresponding to the at least one weak cell. The weak cell is a cell in which the wireless network parameters in the same category meet a first preset condition.
Specifically, in a possible embodiment, this step may be preceded by: performing index condition check on the classified cells corresponding to each class to determine a check result; and determining a weak cell and a strong cell in the same category according to the operation index and the checking result, wherein the strong cell is a cell in the same category, and the wireless network parameter of the strong cell does not meet the first preset condition. When the operation index reaches a cell corresponding to a preset threshold value, determining the cell as a strong cell; and when the operation index does not reach the cell corresponding to the preset threshold value, determining the cell as a weak cell.
In one possible embodiment, S140 may specifically include: determining the category of at least one weak cell; and optimizing the wireless network parameters corresponding to at least one weak cell according to the mode of the wireless network parameters corresponding to the category.
It should be noted that supervised learning means that for each observed predictor variable value x1, x2 …, there is a corresponding y1, y2 … observed value corresponding to it; unsupervised learning presents a more challenging scenario, namely that only x1, x2 … are known for all observations, and the corresponding y1, y2 … are not known.
In summary, the method provided by the embodiment of the application can improve the efficiency, scientificity and high efficiency of wireless network parameter optimization, and improve the quality and the user experience of the wireless network while greatly reducing the labor cost.
The method of FIG. 1 is described in detail below with reference to the following examples.
Fig. 2 is a flowchart of a method for optimizing wireless network parameters according to an embodiment of the present application.
As shown in fig. 2, the method in fig. 1 is further refined, and may specifically include S210-S250, first, (based on S110) S210: classifying the wireless network parameters according to the functions of the wireless network parameters, and determining cell operation indexes which are influenced by the setting of the wireless network parameters in each class; (based on S120) S220: analyzing the feature labels of the related cells for each type of wireless network parameters, (based on S120) S230: standardizing the feature labels of the cells; next, (based on S130) S240: according to the parameters (or classification groups) to be optimized, the cell feature labels corresponding to the parameters (or classification groups) are used as training data, hierarchical clustering is carried out on the cells (hierarchical clustering algorithm), the algorithm is a tree-shaped unsupervised machine learning method from leaves to a trunk, all individuals are firstly used as different classes, and then each individual is combined step by step according to Euclidean distance); (based on S140) S250: all cells are divided into a plurality of classes, and the cells with poor cell operation indexes corresponding to the wireless network parameters in the cells of the same class learn the wireless network parameter setting method to the cells with good indexes. To achieve optimization of wireless network parameters.
It should be noted that different types of wireless network parameters affect different cell operation indexes, have different cell feature labels, and perform different cell classifications, and objects (i.e., cells) learned by cells with poor operation indexes are also different, and these objects will change with changes of parameters (or classification groups) to be optimized, so the method provided by the embodiment of the present application has universality and flexibility.
The following is a detailed description of the above-mentioned matters:
based on S210: namely parameter classification and operation index mapping.
Specifically, in the communication system, the number of wireless network parameters in a cell is large, and the wireless network parameters can be classified according to the function of the parameters, and the cell operation indexes that are correspondingly influenced by the setting values of the parameters can be found.
First, the parameters are classified according to their role, for example: coverage class parameters, handover class parameters, reselection class parameters, capacity management class parameters, quality class parameters, interoperability class parameters, and the like. The purpose of classifying the parameters is to optimize the parameters in a targeted manner by using a machine learning method.
Secondly, the cell operation index affected by the radio parameter is, for example: determining a cell operation index set influenced by each type of parameter, selecting the first n indexes (n is generally 4, but can be determined according to actual conditions, n is a positive integer) with the most obvious parameter influence, and using the operation indexes to judge 'a cell with good index' and 'a cell with poor index' in S250. It should be noted that the n index may be expressed as a second preset condition, that is, the first n indexes with the most significant parameter influence are selected to satisfy the second preset condition.
It should be noted that the influence of the radio parameters on the cell network operation index is communication service knowledge, a set of influences of all parameter classes on the cell network operation index is not described in detail herein, and only the coverage class parameters are taken as an example for description, hereinafter, the steps corresponding to the coverage class parameters are also taken as an example for describing a general method for optimizing the whole radio network parameters in detail, and the parameters of other classes can be fully expanded according to the method.
Finally, the cell operation index influenced by the coverage class parameter, for example: the signal strength > -110 decibel-milliwatt (dBm) sampling point occupation ratio, the LTE Reference Signal Receiving Quality (RSRQ) less-5 sampling point occupation ratio (RSRQ is the reference signal receiving quality), the wireless connection rate, the LTE service disconnection rate and the like are used as the coverage influencing indexes.
Based on the following steps of 220: i.e. the definition of the cell characteristics label.
Specifically, the corresponding parameter setting criteria of cells of different characteristics should be different. For example: the transmission power parameters of the coverage class need to be optimized, and it is obviously unreasonable that a cell with a station height of 20 meters learns the transmission power parameter setting from a cell with a station height of 100 meters; for another example, it is also unreasonable to learn the parameter setting value from a cell with 5 neighboring cells to a cell with 50 neighboring cells, if the same-frequency handover hysteresis parameter of the handover class needs to be optimized. Therefore, for optimization of various parameters, feature labels of cells need to be defined, and cells with different features need to be distinguished, so that parameter learning between cells is more reasonable.
Corresponding cell feature labels are defined according to different parameter classes, taking the cell feature label covering the class parameters as an example, the parameters of other classes can be used as reference.
First, a cell feature label of a coverage class parameter, wherein the cell feature of the coverage class parameter is a series of objective factors that can affect the cell coverage and cannot be easily adjusted, such as: such as station height, antenna downtilt angle, cell band type, etc.
A. Standing height: normally, the higher the station, the farther and wider the coverage.
B. Downward inclination angle of the antenna: normally, the larger the antenna downtilt angle, the closer the coverage distance.
C. Station spacing: the inter-site distance reflects the density of sites around the cell.
D. Cell frequency band type: different frequency bands have large difference in propagation loss, and different frequency bands use different scenes.
Based on the ratio of 230: i.e. cell signature tag standardization.
Specifically, as shown in fig. 3, the cell signatures obtained in S220 are classified into category signatures and numerical signatures, and normalization processing is performed on the numerical signatures.
First, feature labels differentiate the type or class of the type variable response event, for example: male and female, A, B and C; a numerical variable is a variable of a numerical measure. Take the cell feature label of the coverage class parameter as an example:
the category profile may include: cell band type.
The numeric signature may include: at least one of a station height, an antenna downtilt angle, or a station spacing.
Second, the numeric signature is normalized. The normalization is to map the value of the numerical characteristic label to a standard normal distribution with the mean value of 0 and the standard deviation of 1, and aims to eliminate the excessive influence of the label with a larger value and a larger variance on the subsequent clustering model fitting. For example: the value of the antenna downward inclination angle is approximately 3-15 degrees, the value of the station height is approximately 10-80 meters, the value of the station spacing is 50-1000 meters, and the influence of each label on the clustering model is seriously uneven if standardization is not carried out.
The above-mentioned standardization process involved:
1) calculating a numerical characteristic label mean value mu;
2) calculating a numerical characteristic label standard deviation delta;
3) the normalized value Xnew ═ (X- μ)/δ was calculated
And respectively standardizing X (station height), antenna downward inclination angle or station spacing by using the coverage parameters as classes.
Based on the following steps of 240: as shown in fig. 4, for the cells to be clustered, the cells are classified through the class-type feature labels obtained in S230, and then the numerical-type feature labels of each classified cell set are subjected to unsupervised machine learning by using a hierarchical clustering algorithm, so that all the cells to be clustered are finally classified.
Specifically, first, cells are to be clustered. The cells to be clustered are required to be included in the wireless network except special scene cells (such as high-speed rail coverage cells and high-speed cells) and VIP coverage cells, and the accuracy of the model can be improved due to the fact that the sample capacity is increased.
Second, class-type feature labels are classified. And classifying the cells to be clustered by using the class type feature labels obtained in the step S230. Taking the classification of the class type feature tags covering the class parameters as an example, the cell frequency band types include three types: the method comprises the steps that D frequency bands, E frequency bands and F frequency bands are used for dividing cells to be clustered into three types, namely the cells to be clustered of the D frequency bands, the cells to be clustered of the E frequency bands and the cells to be clustered of the F frequency bands.
Next, the numeric feature labels are hierarchically clustered. And carrying out hierarchical clustering on each group formed after classifying the class type feature tags, taking numerical feature tag hierarchical clustering covering class parameters as an example, forming a D-frequency band cell to be clustered, an E-frequency band cell to be clustered and an F-frequency band cell to be clustered after classifying the class type feature tags, carrying out numerical feature tag hierarchical clustering on the three classes respectively, and finally, dividing all the cells to be clustered into N classes.
For example, the following steps are carried out: selecting the numerical characteristic label data of the 72 cells in the D frequency band to specifically show hierarchical clustering:
firstly, hierarchical clustering: realized by R language, the parameter method is set as average, and 72 cells are gradually connected together by using a mean clustering connection method.
Average ═ hcclust (dist (numerical signature), method ═ average ")
Fig. 5 is a schematic diagram illustrating a hierarchical clustering of corresponding D-band 72 cells according to numerical characteristic label data.
Second, the layers were separated. Specifically, the links (links) generated in the "hierarchical clustering" are specifically divided to determine the class to which each cell specifically belongs. Let s be the number of samples, the total number of layers is determined by the following formula:
layer (sqrt (s)), where floor is rounded down and sqrt is the square root.
Since the example 72 samples are layer 8, the 72D-band cells are classified into 8 types according to their association (link): the method is realized in R language: cutree (hc. complete, 8). As shown in fig. 6, a hierarchical schematic diagram of hierarchical clustering for D-band 72 cells is shown, where 20 cells such as cell (cell)1 and cell 2 are classified into class 1, and cells 39, 43, 44, and 45 are classified into class 8.
Based on the following 250: the method comprises the steps of obtaining operation index mapping by S210, setting an index normal value threshold, obtaining classification of all cells by S240, checking the index normal condition of each cell type, wherein the cell with all indexes reaching the normal value threshold is a 'good cell', the cell with the index not reaching the standard (namely the cell meeting a first preset condition) is a 'poor cell', parameters of the 'poor cell' need to be optimized, and the adjustment value of the parameters is the mode of the parameter setting value of the 'good cell' of the same type (wherein the mode is the value with the largest occurrence frequency in a group of data).
In summary, the method provided by the embodiment of the present application makes up for the deficiency of the existing wireless network parameter optimization method. Firstly, the method establishes a feature label of a cell according to wireless network parameters to be optimized, establishes the universality of the method from the step, and can be widely applied to the optimization of various parameters; then, the cells are classified according to the feature labels, the existing general method for setting learning parameters from 'poor cells' to 'good cells' is corrected, the learning of cell parameters occurs in the cells of the same type, and the method for optimizing the wireless network parameters by applying machine learning is more scientific and reasonable; finally, the similar method for learning parameter setting from 'poor cells' to 'good cells' is more objective and efficient than the traditional method for mining network parameter setting through manual judgment of operators and optimizing parameters. Therefore, the method provided by the embodiment of the application is used for optimizing the wireless network parameters, so that the accuracy, scientificity and high efficiency of the wireless network parameter optimization can be obviously improved, the labor cost can be greatly reduced, and the quality of the wireless network and the user perception are improved.
Fig. 7 is a schematic structural diagram of an apparatus for optimizing wireless network parameters according to an embodiment of the present application.
As shown in fig. 7, the apparatus 70 may specifically include:
a classification module 701, configured to classify a wireless network parameter and determine a plurality of classification groups;
an analysis module 702, configured to analyze each of the plurality of classification groups for a feature tag of a corresponding cell;
a processing module 703, configured to use an unsupervised learning algorithm to classify multiple cells by using multiple feature labels as training data;
an optimizing module 704, configured to determine at least one weak cell in the same category, and optimize a wireless network parameter corresponding to the at least one weak cell, where the weak cell is a cell in the same category where the wireless network parameter meets a first preset condition.
The classification module 701 may further be configured to perform feature tag differentiation on feature tags of the cells, and determine at least one of a category-type feature tag and a numerical-type feature tag.
The processing module 703 may also be configured to normalize the numeric signature. Determining a cell to be clustered; classifying the cells to be clustered by using the class type feature tags, and determining a cell group to be clustered; and carrying out hierarchical clustering on the cell group to be clustered, and dividing the plurality of cells to be clustered into at least one type of cells.
The classification module 701 may also be configured to classify the wireless network parameters according to the function of the wireless network parameters, and determine a plurality of classification groups, where the plurality of classification groups are related to the operation quality of the cell.
The processing module 703 may be further configured to determine an operation index of the cell according to the plurality of classification groups; and selecting a cell corresponding to at least one operation index meeting a second preset condition according to the operation index.
The optimizing module 704 may be further configured to perform index condition check on the cell corresponding to each classified class, and determine a check result; and determining a weak cell and a strong cell in the same category according to the operation index and the checking result, wherein the strong cell is a cell in the same category, and the wireless network parameter of the strong cell does not meet the first preset condition. When the operation index reaches a cell corresponding to a preset threshold value, determining the cell as a strong cell; and when the operation index does not reach the cell corresponding to the preset threshold value, determining the cell as a weak cell. Determining the category of at least one weak cell; and optimizing the wireless network parameters corresponding to at least one weak cell according to the mode of the wireless network parameters corresponding to the category.
It should be noted that the above-mentioned related classification groups are classified according to the corresponding categories of the wireless network parameters; wherein the classification group may include at least one of: coverage class parameters, handover class parameters, reselection class parameters, capacity management class parameters, quality class parameters, and interoperability class parameters.
Fig. 8 is a schematic structural diagram of an apparatus for optimizing wireless network parameters according to an embodiment of the present application.
As shown in fig. 8, the apparatus may include a processor 801 and a memory 802 that stores computer program instructions.
Specifically, the processor 801 may include a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.
The processor 801 reads and executes the computer program instructions stored in the memory 802 to implement the wireless network parameter optimization device in any of the above embodiments.
The transceiver 803 is mainly used for implementing communication between at least two of the modules, apparatuses, units, clients, or servers in the embodiments of the present invention.
In one example, the device may also include a bus 804. As shown in fig. 8, the processor 801, the memory 802, and the transceiver 803 are connected via a bus 804 to complete communication with each other.
In addition, in combination with the method for optimizing wireless network parameters in the foregoing embodiments, the embodiments of the present application may provide a computer storage medium to implement. The computer storage medium having computer program instructions stored thereon; the computer program instructions, when executed by a processor, implement a method for optimizing a wireless network parameter as in any of the above embodiments.
It is to be understood that the present application is not limited to the particular arrangements and instrumentality described above and shown in the attached drawings. A detailed description of known methods is omitted herein for the sake of brevity. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present application are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications, and additions or change the order between the steps after comprehending the spirit of the present application.
The functional blocks shown in the above structural block diagrams may be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, plug-in, function card, or the like. When implemented in software, the elements of the present application 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 by a data signal carried in a carrier wave over a transmission medium or a communication link. A "machine-readable medium" may include any medium that can store or transfer information. Examples of a machine-readable medium include electronic circuits, semiconductor memory devices, ROM, flash memory, Erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, Radio Frequency (RF) links, and so forth. The code segments may be downloaded via computer networks such as the internet, intranet, etc.
It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, may be performed in an order different from the order in the embodiments, or may be performed simultaneously.
As will be apparent to those skilled in the art, for convenience and brevity of description, the specific working processes of the systems, modules and units described above may refer to corresponding processes in the foregoing method embodiments, and are not described herein again. It should be understood that the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present application, and these modifications or substitutions should be covered within the scope of the present application.
Claims (13)
1. A method for optimizing wireless network parameters, comprising:
classifying wireless network parameters to determine a plurality of classification groups;
analyzing each classification group in the plurality of classification groups and the feature label of the corresponding cell;
classifying the plurality of cells by using the plurality of feature labels as training data by using an unsupervised learning algorithm;
determining at least one weak cell in the same category, and optimizing wireless network parameters corresponding to the at least one weak cell, wherein the weak cell is a cell in the same category, and the wireless network parameters meet a first preset condition.
2. The method of claim 1, further comprising, after the step of analyzing the signature of the corresponding cell for each of the plurality of classification groups:
and distinguishing the feature tags of the cells, and determining at least one of a category type feature tag and a numerical type feature tag.
3. The method of claim 2, further comprising: and carrying out standardization processing on the numerical characteristic label.
4. The method according to any one of claims 1-3, wherein the classifying the plurality of cells using the unsupervised learning algorithm using the plurality of feature labels as training data comprises:
determining a cell to be clustered;
classifying the cells to be clustered by using class type feature tags, and determining a cell group to be clustered;
and performing hierarchical clustering on the cell group to be clustered, and dividing a plurality of cells to be clustered into at least one type of cells.
5. The method of claim 1, wherein the classifying the wireless network parameters and determining a plurality of classification groups comprises:
and classifying the wireless network parameters according to the functions of the wireless network parameters, and determining a plurality of classification groups, wherein the classification groups are related to the operation quality of the cell.
6. The method according to claim 1 or 5, wherein after the step of classifying the wireless network parameters and determining a plurality of classification groups, further comprising:
determining an operation index of the cell according to the plurality of classification groups;
and selecting a cell corresponding to at least one operation index meeting a second preset condition according to the operation index.
7. The method of claim 6, wherein before the step of determining at least one weak cell in the same category and optimizing radio network parameters corresponding to the at least one weak cell, the method further comprises:
performing index condition check on the classified cells corresponding to each class to determine a check result;
and determining a weak cell and a strong cell in the same category according to the operation index and the checking result, wherein the strong cell is a cell in the same category, and the wireless network parameter does not meet a first preset condition.
8. The method of claim 7, wherein the determining the weak cell and the strong cell in the same category according to the operation index and the checking result comprises:
when the operation index reaches a cell corresponding to a preset threshold value, determining the operation index as the strong cell;
and when the operation index does not reach the cell corresponding to the preset threshold value, determining the cell as the weak cell.
9. The method according to claim 7 or 8, wherein the determining at least one weak cell in the same category and optimizing the radio network parameter corresponding to the at least one weak cell comprises:
determining the category of the at least one weak cell;
and optimizing the wireless network parameters corresponding to the at least one weak cell according to the mode of the wireless network parameters corresponding to the category.
10. The method of claim 1, wherein the classification group is classified according to a class corresponding to the wireless network parameter; the taxonomic group includes at least one of: coverage class parameters, handover class parameters, reselection class parameters, capacity management class parameters, quality class parameters, and interoperability class parameters.
11. An apparatus for optimizing wireless network parameters, comprising:
the classification module is used for classifying the wireless network parameters and determining a plurality of classification groups;
an analysis module, configured to analyze each of the plurality of classification groups for a feature tag of a corresponding cell;
the processing module is used for classifying the cells by using the feature labels as training data through an unsupervised learning algorithm;
the optimization module is used for determining at least one weak cell in the same category and optimizing wireless network parameters corresponding to the at least one weak cell, wherein the weak cell is a cell in the same category, and the wireless network parameters meet a first preset condition.
12. An apparatus for optimizing wireless network parameters, the apparatus comprising: a processor and a memory storing computer program instructions;
the processor, when executing the computer program instructions, implements a method of optimizing wireless network parameters according to any one of claims 1-10.
13. A computer storage medium having stored thereon computer program instructions which, when executed by a processor, implement the method of optimizing a wireless network parameter of any one of claims 1-10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811622369.0A CN111385818B (en) | 2018-12-28 | 2018-12-28 | Method, device and equipment for optimizing wireless network parameters |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811622369.0A CN111385818B (en) | 2018-12-28 | 2018-12-28 | Method, device and equipment for optimizing wireless network parameters |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111385818A true CN111385818A (en) | 2020-07-07 |
| CN111385818B CN111385818B (en) | 2023-04-14 |
Family
ID=71222175
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811622369.0A Active CN111385818B (en) | 2018-12-28 | 2018-12-28 | Method, device and equipment for optimizing wireless network parameters |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111385818B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101039490A (en) * | 2006-03-14 | 2007-09-19 | 中国电信股份有限公司 | Coverage analysis system and method for optimizing mobile communication system network |
| CN101287269A (en) * | 2008-04-22 | 2008-10-15 | 中国移动通信集团设计院有限公司 | Mobile communication network optimizing method, device and system |
| US20110090820A1 (en) * | 2009-10-16 | 2011-04-21 | Osama Hussein | Self-optimizing wireless network |
| CN102510564A (en) * | 2011-12-19 | 2012-06-20 | 清华大学 | Self-optimization method for improving concentrated clustering type self-organization network (SON) |
| CN104883278A (en) * | 2014-09-28 | 2015-09-02 | 北京匡恩网络科技有限责任公司 | Method for classifying network equipment by utilizing machine learning |
| US20160212633A1 (en) * | 2015-01-19 | 2016-07-21 | Jdsu Uk Limited | Techniques for dynamic network optimization using geolocation and network modeling |
-
2018
- 2018-12-28 CN CN201811622369.0A patent/CN111385818B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101039490A (en) * | 2006-03-14 | 2007-09-19 | 中国电信股份有限公司 | Coverage analysis system and method for optimizing mobile communication system network |
| CN101287269A (en) * | 2008-04-22 | 2008-10-15 | 中国移动通信集团设计院有限公司 | Mobile communication network optimizing method, device and system |
| US20110090820A1 (en) * | 2009-10-16 | 2011-04-21 | Osama Hussein | Self-optimizing wireless network |
| CN102510564A (en) * | 2011-12-19 | 2012-06-20 | 清华大学 | Self-optimization method for improving concentrated clustering type self-organization network (SON) |
| CN104883278A (en) * | 2014-09-28 | 2015-09-02 | 北京匡恩网络科技有限责任公司 | Method for classifying network equipment by utilizing machine learning |
| US20160212633A1 (en) * | 2015-01-19 | 2016-07-21 | Jdsu Uk Limited | Techniques for dynamic network optimization using geolocation and network modeling |
Non-Patent Citations (1)
| Title |
|---|
| 郭景赞等: "移动互联网业务无线特征识别及优化方法研究", 《邮电设计技术》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111385818B (en) | 2023-04-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112243249B (en) | LTE new access anchor point cell parameter configuration method and device under 5G NSA networking | |
| CN103716123A (en) | Method and system for identifying packet loss and error causes in sensor network | |
| CN109981234B (en) | Self-adaptive adjusting method, device, equipment and medium for double carriers and carrier aggregation | |
| CN109362092B (en) | Network parameter adjusting method, device, equipment and medium | |
| CN110705685A (en) | Neural network quantitative classification method and system | |
| CN110751278A (en) | Neural network bit quantization method and system | |
| CN110062393A (en) | A kind of network difference cell intelligent analysis method | |
| CN113660687B (en) | Network difference cell processing method, device, equipment and storage medium | |
| CN111385818B (en) | Method, device and equipment for optimizing wireless network parameters | |
| CN110753369B (en) | Method and device for detecting interrupt cell | |
| CN108900266A (en) | The cognition car networking frequency spectrum sensing method with FCM algorithm is chosen based on cooperative node | |
| CN110321930B (en) | Illegal broadcast signal classification method based on cyclic neural network | |
| CN111447655B (en) | Method, device, equipment and medium for accessing terminal to network | |
| CN104394543A (en) | Joint frequency spectrum sensing method based on Adaboost algorithm | |
| CN114828055A (en) | User service perception evaluation method, device, equipment, medium and program product | |
| CN109327854B (en) | Track user identification method and device | |
| CN115175252A (en) | System and method for distributing multimode cooperative communication service flow for V2G network | |
| CN109993388B (en) | Method, device, equipment and medium for judging cause of deteriorated cell | |
| CN114638465A (en) | Acquisition terminal network signal quality evaluation method based on secondary scoring | |
| CN114258093B (en) | Method and device for configuring switching configuration information | |
| CN111988252A (en) | Signal modulation mode identification method based on deep learning | |
| CN114268983A (en) | Shared information analysis method and device and electronic equipment | |
| CN114268394B (en) | Distributed network wireless spectrum intelligent sensing method based on data judgment | |
| CN117412315B (en) | Wireless communication network data optimization method based on data analysis | |
| Yan et al. | [Retracted] Defect Point Location Method of Civil Bridge Based on Internet of Things Wireless Communication |
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 |