CN116264706A - 5G base station layout evaluation model training method, equipment and storage medium - Google Patents
5G base station layout evaluation model training method, equipment and storage medium Download PDFInfo
- Publication number
- CN116264706A CN116264706A CN202111531352.6A CN202111531352A CN116264706A CN 116264706 A CN116264706 A CN 116264706A CN 202111531352 A CN202111531352 A CN 202111531352A CN 116264706 A CN116264706 A CN 116264706A
- Authority
- CN
- China
- Prior art keywords
- data
- base station
- training
- grid
- network resource
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/06—Testing, supervising or monitoring using simulated traffic
-
- 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)
- Monitoring And Testing Of Transmission In General (AREA)
Abstract
The application provides a 5G base station layout evaluation model training method, equipment and a storage medium. The method comprises the following steps: acquiring network resource data of a 4G base station and grid data thereof, wherein the network resource data comprises one or more of the following: bandwidth, resource utilization, number of connection users, voice traffic, domain flow, average coverage distance of cells, user download rate, 5G base station layout data of the 4G base station; the grid data includes one or more of: grid 4G traffic, grid user data, number of grid 4G terminals, number of grid sites, 4G base station coverage data; and training the network resource data and the grid data by adopting a decision tree algorithm to obtain a 5G base station layout evaluation model. The 5G base station layout evaluation model can evaluate whether to build the 5G base station, and the accuracy of the 5G base station building is improved.
Description
Technical Field
The application relates to the technical field of communication, in particular to a 5G base station layout evaluation model training method, equipment and a storage medium.
Background
With the rapid development of mobile communication technology, the demand for 5G networks is also increasing. However, because the network construction cost of 5G is about 2 to 3 times that of 4G, the construction accuracy of 5G base station needs to be improved to realize the construction of a low-cost and well-covered 5G network.
In the traditional precision evaluation method, more single stations are evaluated after network construction is completed, and stations with lower precision are required to be optimized or moved by putting in cost again, so that the precision of 5G base station construction is lower, and the construction cost is wasted.
Disclosure of Invention
The application provides a 5G base station layout evaluation model training method, equipment and a storage medium, which are used for solving the problem of lower construction accuracy of a 5G base station.
In a first aspect, the present application provides a 5G base station deployment evaluation model training method, including:
acquiring network resource data of a 4G base station and grid data thereof, wherein the network resource data comprises one or more of the following: bandwidth, resource utilization, number of connection users, voice traffic, domain flow, average coverage distance of cells, user download rate, 5G base station layout data of the 4G base station; the grid data includes one or more of the following: grid 4G traffic, grid user data, number of grid 4G terminals, number of grid sites, 4G base station coverage data;
and training the network resource data and the grid data by adopting a decision tree algorithm to obtain a 5G base station layout evaluation model.
In a second aspect, the present application provides a 5G base station deployment evaluation model training device, including:
the acquisition module is used for acquiring network resource data of the 4G base station and grid data thereof, wherein the network resource data comprises one or more of the following: bandwidth, resource utilization, number of connection users, voice traffic, domain flow, average coverage distance of cells, user download rate, 5G base station layout data of the 4G base station; the grid data includes one or more of the following: grid 4G traffic, grid user data, number of grid 4G terminals, number of grid sites, 4G base station coverage data;
and the training module is used for training the network resource data and the grid data thereof by adopting a decision tree algorithm to obtain a 5G base station layout evaluation model.
In a third aspect, the present application provides a 5G base station deployment evaluation model training device, including: a processor, a memory storing code therein, the processor executing the code stored in the memory to perform the 5G base station deployment assessment model training method as in the first aspect.
In a fourth aspect, the present application provides a computer-readable storage medium having stored therein computer-executable instructions which, when executed by a processor, are configured to implement the 5G base station layout evaluation model training method according to any one of the first aspects.
According to the 5G base station layout evaluation model training method, network resource data and grid data of the 4G base station are obtained, a decision tree algorithm is adopted to train the network resource data and the grid data, and a 5G base station layout evaluation model capable of predicting whether to build the 5G base station is obtained. When the 5G base station is constructed, the 5G base station layout evaluation model can be utilized for prediction. And 5G base stations are arranged according to the prediction result of the evaluation model, so that the construction accuracy of the 5G base stations is improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.
Fig. 1 is a schematic diagram of an application scenario of a 5G base station layout evaluation model provided in an embodiment of the present application;
fig. 2 is a flowchart of a training method of a 5G base station deployment evaluation model according to an embodiment of the present application;
fig. 3 is a flowchart of a training data generating method according to an embodiment of the present application;
fig. 4 is a flowchart of a method for constructing a 5G base station deployment evaluation model according to an embodiment of the present application;
fig. 5 is a second flowchart of a training method of a 5G base station deployment evaluation model according to an embodiment of the present application;
FIG. 6 is a schematic diagram of a decision tree model according to an embodiment of the present disclosure;
fig. 7 is a schematic diagram of a training device for a 5G base station deployment evaluation model according to an embodiment of the present application;
fig. 8 is a second schematic diagram of a training device for a 5G base station layout evaluation model according to an embodiment of the present application.
Specific embodiments thereof have been shown by way of example in the drawings and will herein be described in more detail. These drawings and the written description are not intended to limit the scope of the inventive concepts in any way, but to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application as detailed in the accompanying claims.
In the prior art, 5G base station deployment is mainly evaluated by the following aspects: single station performance: after the network is built, counting the number of users, traffic and resource use conditions of a single station through KPI (Key Performance Indication, key performance index), calculating an investment recovery period, and evaluating the building accuracy of the 5G base station; MR (Measurement Report ) data: after the network is built, evaluating the building accuracy of the 5G base station by analyzing MR data such as network coverage, user access level, user position and the like; wireless link: after the network is built, analyzing a TA (Timing Advance) value through KPI, analyzing a wireless link of a single cell, and evaluating the building accuracy of a 5G base station; user feedback conditions: after the network is built, user complaints, such as sporadic complaints, regional complaints and business complaints, are counted, the layout of the wireless base stations in the complaint area, the antenna hanging height, the antenna azimuth angle, the antenna pitch angle and the like are checked, the user reflects the real network conditions, and the building accuracy of the 5G base stations is evaluated. However, since the general user does not have professional network knowledge, detailed network information cannot be fed back, which makes evaluation of network accuracy difficult.
Based on the evaluation of the dimension, the evaluation can be carried out only after the network is built and the 5G terminal is replaced by a user on a large scale, the hysteresis of the evaluation is large, and the extraction index analysis of each base station by inputting large human resources is needed, so that the user complaints are visited back by example and the construction accuracy of each base station is determined by combining with the field test. For sites with lower precision, site optimization or relocation is required by putting cost again, and wasteful network investment cannot be made up.
The application provides a training method for a 5G base station layout evaluation model, which is used for acquiring network resource data and grid data of a 4G base station, and training the network resource data and the grid data by adopting a decision tree algorithm to obtain the 5G base station layout evaluation model. And 5G base stations are arranged according to the prediction result of the evaluation model, so that the construction accuracy of the 5G base stations is improved.
Fig. 1 is a schematic diagram of an application scenario of a 5G base station layout evaluation model provided in an embodiment of the present application, where, as shown in fig. 1, when network resource data such as voice traffic, PS domain traffic, RPC connection user number, bandwidth, and cell tie coverage distance, and grid data thereof are input to the 5G base station layout evaluation model, the 5G base station layout evaluation model may output a result of whether to construct the 5G base station.
The following describes the technical solutions of the present application and how the technical solutions of the present application solve the above technical problems in detail with specific embodiments. The following embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.
Fig. 2 is a flowchart of a 5G base station layout evaluation model training method provided in an embodiment of the present application, where an execution subject of the method may be a 5G base station layout evaluation model training device. The 5G base station layout evaluation model training device can be any device with a data processing function, such as a computer and the like. The method in this embodiment may be implemented by software, hardware, or a combination of software and hardware. As shown in fig. 2, the method may include:
s201: acquiring network resource data of a 4G base station and grid data thereof, wherein the network resource data comprises one or more of the following: bandwidth, resource utilization, number of connection users, voice traffic, domain flow, average coverage distance of cells, user download rate, 5G base station layout data of the 4G base station; the grid data includes one or more of the following: grid 4G traffic, grid user data, number of grid 4G terminals, number of grid sites, 4G base station coverage data.
In order to more accurately estimate the layout of the 5G base station, network resource data and corresponding grid data are collected to serve as input data of a 5G base station layout evaluation model. The network resource data may generally collect bandwidth of the 4G base station, PRB (Physical Resource Block ) resource utilization, RRC (Radio Resource Control ) connection user number, PS (Packet Switch) domain traffic (GB), cell average coverage distance, user download rate, and 5G base station layout data; the mesh data may include: grid 4G traffic, grid user data, number of grid 4G terminals, number of grid sites, 4G base station coverage data. The grid user data may include the number of grid young people, the grid young people duty ratio, the number of grid 2I2C users, and the like.
The network resource data and the grid data of the acquired 4G base station can be acquired through a network resource management platform, a user information management platform and the like.
S202: and training the network resource data and the grid data by adopting a decision tree algorithm to obtain a 5G base station layout evaluation model.
After the network resource data and the grid data of the 4G base station are acquired, the acquired data can be further subjected to operations such as data cleaning and standardization processing. Further, a decision tree algorithm may be employed to construct the assessment model. Decision trees are a classification method by which training data is trained to construct decision tree models. The decision tree model is in a tree structure and can be in a binary tree structure or a multi-fork tree structure. Each internal node in the tree structure represents a determination of an attribute, each branch represents an output of a determination result, and each leaf node represents a classification result.
After the 5G base station layout evaluation model is established, network resource data and grid data of the 4G base station corresponding to the site can be input into the 5G base station layout evaluation model, and the result of whether to establish the 5G base station is output through the 5G base station layout evaluation model.
The embodiment of the application provides a training method for a 5G base station layout evaluation model, which is used for acquiring network resource data and grid data of a 4G base station, and training the acquired network resource data and grid data by adopting a decision tree algorithm to obtain the 5G base station layout evaluation model. When whether a site can build a 5G base station needs to be evaluated, network resource data and grid data of the 4G base station corresponding to the site can be input into a 5G base station layout evaluation model, and the 5G base station layout evaluation model can output a result of whether the 5G base station is built or not, so that the accuracy of 5G base station building is improved, and the building cost is saved.
In the above embodiments, the training data needs to be generated in the network resource data and the mesh data thereof, and an embodiment is provided below to describe the process of generating the training data in detail.
Fig. 3 is a flowchart of a training data generating method provided in an embodiment of the present application, where a 5G base station layout evaluation model is obtained by training data, and the method specifically includes:
s301: non-numerical attribute data is extracted from the network resource data and its mesh data.
The network resource data and the grid data thereof comprise numerical attribute data and non-numerical attribute data, wherein the non-numerical attribute data can be character data, image data and other types of data. For example, the non-numerical attribute data may be 5G base station layout data, mainly including { Yes, no } two types.
S302: and carrying out numerical conversion on the non-numerical attribute data.
To facilitate training of the 5G base station layout evaluation model, when the non-numeric attribute data is the 5G base station layout data, the { Yes, no } may be digitized, e.g., converted to {0,1}.
S303: and carrying out distribution randomization and homogenization treatment on the data after the numerical conversion to generate training data.
In order to avoid the data of the 5G base station layout evaluation model being too centralized, namely the data of {0} or {1} is too centralized in a certain area, the data needs to be subjected to distribution randomization and homogenization treatment, so that the training of the 5G base station layout evaluation model is easier.
It should be noted that, in order to facilitate the training of the 5G base station layout evaluation model, after generating the training data, the training data needs to be standardized.
The embodiment of the application provides a training data generation method, which is used for facilitating training of a 5G base station layout evaluation model, extracting non-numerical attribute data from acquired network resource data and grid data of a 4G base station, and performing numerical conversion on the non-numerical attribute data. In order to avoid the excessive concentration of training data, the data subjected to data conversion is subjected to distributed randomization and homogenization treatment, so that training data for training a 5G base station layout evaluation model is obtained.
The training data provided in the above embodiment is trained to obtain a 5G base station deployment evaluation model, and an embodiment is provided below to describe a process of constructing the 5G base station deployment evaluation model.
Fig. 4 is a flowchart of a method for constructing a 5G base station deployment evaluation model according to an embodiment of the present application, where the method may include:
s401: the training data is divided into training set data and test set data.
Because the constructed 5G base station layout evaluation model needs to be verified, training data needs to be divided into training set data and test set data. The training set data are used for constructing a 5G base station layout evaluation model, and the test set data are used for verifying training results. When the training data is divided, the ratio of the training set data and the test set data may be determined, and the ratio of the training set data and the test set data may be 8-2, 7-3, 6-4, 5-5, etc. The training data may be divided into training set data and test set data according to a determined ratio.
The training data can be divided in a random division manner.
S402: training the training set data by adopting a decision tree algorithm, and verifying the training result by adopting the test set data.
Training the training set data by adopting a decision tree algorithm to obtain a 5G base station layout evaluation model, wherein the 5G base station layout evaluation model can predict whether a 5G base station is built at a certain site.
Before the training result is verified by adopting the test set data, an index for measuring whether the training result is accurate needs to be defined, wherein the index can be an error between a predicted result and a real result of a 5G base station layout evaluation model. In an implementation scenario where it is evaluated whether to establish a 5G base station, the index may be defined as 5%. When the error between the predicted result and the real result of the 5G base station layout evaluation model is within 5%, the predicted result of the 5G base station layout evaluation model is determined to be accurate.
The embodiment of the application provides a 5G base station layout evaluation model construction method, which divides acquired training data into training set data and test set data according to a certain proportion. Training the training set data by adopting a decision tree algorithm to obtain a 5G base station layout evaluation model, wherein the training result can be verified by the test set data. When the training result is accurate, the 5G base station layout evaluation model can evaluate whether to build the 5G base station according to the network resource data and the grid data of the existing 4G base station, so that the accuracy of the 5G base station building is improved.
On the basis of the above embodiments, a specific embodiment is provided below to describe in detail a training method and an application process of the 5G base station deployment evaluation model.
Fig. 5 is a flowchart second of a 5G base station layout evaluation model training method provided in an embodiment of the present application, where an execution subject of the method may be a 5G base station layout evaluation model training device, specifically as follows:
s501: and acquiring network resource data and grid data of the 4G base station.
Network data of the 4G base station and corresponding grid data can be extracted through a network resource management platform, a user information management platform and the like. Wherein the network data comprises: bandwidth of the 4G base station, PRB resource utilization rate, RRC connection user number, voLTE voice traffic Erl, PS domain traffic (GB), cell average coverage distance, user download rate and 5G base station layout data; the mesh data includes: grid 4G traffic (MB), grid user data, number of grid 4G terminals, number of grid sites, 4G base station coverage data. The grid user data may include the number of grid young people, the grid young people duty ratio, the number of grid 2I2C users, and the like.
S502: and cleaning the network resource data and the grid data thereof.
Because the grid resource data and the grid data thereof may have problems of including 'none', null values or attributes including more non-numerical attribute data, the acquired data may be cleaned before generating the training data.
In one implementation scenario, when the data contains "none", or a null value, this can be resolved by deleting the row data and the null value where "none" is located.
In another implementation scenario, when more non-numeric attribute data is included in an attribute, the non-numeric data needs to be mapped into a certain numeric category data as shown in table 1. The discretization operation is mainly used for solving the problem of model accuracy distortion caused by overlarge sample deviation in classification. Through label discretization, more classifications are added, so that the sample number difference is smaller, and the prediction accuracy and the actual coincidence are ensured.
Table 1 4g base station grid resource data and grid data thereof
The non-numerical attribute data may include belonging grid attribute data and 4G base station coverage data. Wherein, the belonging grid attribute data can comprise four category values, namely a very high value grid, a high potential grid and an unfocused grid. And checking the number of class values contained in the belonging grid attribute data and mapping the class values into data classes. In one scenario, the number of category values contained in the grid attribute data may be as follows: there are 4405 high-value grids, 613 high-value grids, 492 high-potential grids, and 64 unfocused grids.
The 4G base station coverage data may include a variety of scenarios for residences, school campuses, industrial parks, hospitals, and the like. And checking the category number contained in the 4G base station coverage data, and performing category mapping. In one scenario, the number of category categories included in the 4G base station coverage data is shown in table 2:
table 2 4g base station coverage data
The result obtained after the type mapping of the data belonging to the grid attribute and the 4G base station coverage data is shown in table 3.
Table 3 mapping processed data
S503: training data is generated in the network resource data and its mesh data.
The non-numerical attribute data { whether or not a 5G base station is installed } is separated out and used as tag data. Since these tag data mainly contain two types { yes, no } and { yes, no } needs to be converted into {0,1} in order to facilitate model training and learning, and other attribute columns may constitute training data.
In order to avoid that the training data used is too centralized, i.e. the data of yes or no is too centralized in a certain area, as shown in table 4. The training data may be distributed and randomized and homogenized, as shown in table 5, to better perform the model constructed.
TABLE 4 data distribution randomization and homogenization of data before treatment
TABLE 5 randomizing and homogenizing data distribution
S504: and (5) carrying out standardization processing on the training data.
The training data is standardized, and the training data can be placed in a set interval according to a proportion to generate dimensionless numerical data.
The training data is converted into dimensionless numerical data, unit limitation of the data can be removed, indexes of different units or orders of magnitude can be compared and weighted conveniently, and data of different sources are unified into a reference system.
After the data processing in the above steps, the results of the overall data are checked, and as shown in table 6, the maximum value and the minimum value thereof differ widely for each column of data. Since training of the model is unfavorable when the maximum value and the minimum value differ greatly, normalization processing can be performed on the digital data, and the code is as follows:
from sklearn import preprocessing
X_scaled＝preprocessing.scale(X)
table 6 normalized data
S505: the training data is divided into training set data and test set data.
After the training data is formed, the training data is further divided into training set data and test set data according to a certain proportion. The dividing ratio can be selected according to the actual data amount, for example, 8-2, 7-3, 6-4, 5-5 ratios can be selected. After determining the ratio of the training set data and the test set data, the training data may be divided into the training set data and the test set data according to the ratio. The 5G base station layout evaluation model is generated through training set data, and the testing set data are used for testing the accuracy and the error of the model so as to verify the effectiveness of the model. For example, in using 7-3 partitioning of training set data and test set data, the specific code implementation is as follows:
from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test＝train_test_split(X_scaled,y,test_size＝0.3,random_state＝7)
s506: and training the training set data by adopting a decision tree algorithm to obtain a 5G base station layout evaluation model.
And selecting a decision tree algorithm to construct a model. A decision tree (decision tree) is a tree structure (which may be a binary tree or a non-binary tree). Wherein each internal node represents a determination of an attribute, each branch represents an output of a determination result, and each leaf node represents a classification result. The decision making process using the decision tree is to start from the root node, test the corresponding characteristic attribute in the item to be classified, select the output branch according to the value until the leaf node is reached, and take the category stored by the leaf node as the decision result.
In the specific code implementation process, sklearn can be used to construct a decision tree model and judge the performance of the model on a tester. The parameter criterion in the model used measures the quality of classification, where "Gini" represents Gini input, split is the strategy that decides to select the classification in the node, "best" means the best classification is selected and max_depth represents the maximum depth of the tree. The choice of the maximum depth parameter is important for training the model. If too large, the model is prone to over-fitting, resulting in poor performance of the model on the training data.
from sklearn.tree import DecisionTreeClassifier
dtc＝DecisionTreeClassifier(criterion＝'gini',splitter＝'best',max_depth＝3)
dtc.fit(x_train,y_train)
S507: a measure is defined.
In the problem of predicting whether to establish the 5G base station, the prediction accuracy of the model is judged, and the error between the prediction result and the real result is calculated. For example, the measurement index may be defined as 5%, and when the error between the predicted result and the actual result is within 5%, the result obtained by the 5G base station layout evaluation model may be considered to be accurate.
S508: and verifying the training result by adopting the test set data.
And (3) obtaining the training accuracy of the model on the test set by using the defined measurement index, namely, the error of the predicted result and the real result of the model on the test data is less than 3%. Thus, the model is considered to yield an accurate from sklearn. Metrics import policy score
y_pre＝dtc.predict(x_test)
accuracy_score(y_test,y_pre)
In one implementation scenario, ten sets of data are selected on the test set, and the comparison of the predicted output value to the true value is shown below (where 1 represents the installation of a 5G base station and 0 represents no).
dtc.predict(x_test[:11])
array([0.，1.，1.，1.，0.，1.，1.，0.，0.，0.，0.])
y_test[:11]
array([0.，1.，1.，1.，0.，1.，1.，0.，0.，0.，0.])
For the established decision tree model, the tree_export_graphviz is utilized to output the specifically established decision tree result, as shown in fig. 6. Each internal node of the model in fig. 6 represents a judgment on an attribute, each branch represents an output of a judgment result, and each leaf node represents a classification result. Each node may include the following: a coefficient of kunity, the number of samples in a node, the number of samples per class, a high volume sample classification, etc. As shown in fig. 6, the characteristics of { VoLTE voice traffic Erl, PS domain traffic, RPC connection user number, bandwidth, cell average coverage distance } and the like have a large influence on the model performance, and the internal construction process of the decision tree model is largely constructed according to the characteristics, so that it can be considered that the characteristics of { VoLTE voice traffic Erl, PS domain traffic, RPC connection user number, bandwidth, cell average coverage distance } and the like have a large correlation with the final 5G base station construction judgment.
S509: application of 5G base station layout evaluation model
And importing the 4G network resource data related to the 5G base station to be built into a 5G base station layout evaluation model. The 4G network resource data includes 5 dimensions, such as { VoLTE voice traffic Erl, PS domain traffic, RPC connection user number, bandwidth, average coverage distance of cells }, and the model makes a judgment on whether the corresponding site is constructed or not, that is, whether the corresponding site is constructed or not. If the output result is yes, the 5G base station can be built, and if the output result is no, the building of the 5G base station of the station is suspended.
The embodiment of the application provides a training method for a 5G base station layout evaluation model, which comprises the steps of firstly acquiring 4G network resource data and grid data, cleaning and processing the acquired data to generate training data, and then carrying out standardization processing and normalization processing on the data. Dividing the processed training data into training set data and test set data according to a certain proportion, and training the training set data by adopting a decision tree algorithm to obtain a 5G base station layout evaluation model. The test set data may verify the training results. When the training result is accurate, the 5G base station layout evaluation model can evaluate whether the 5G base station can be built according to the network resource data and the grid data of the existing 4G base station, so that the accuracy of the 5G base station construction is improved, and the construction cost is saved.
Fig. 7 is a schematic diagram of a training device for a 5G base station layout evaluation model according to an embodiment of the present application, as shown in fig. 7, and the training device 700 for a 5G base station layout evaluation model according to the present embodiment may include an acquisition module 701 and a training module 702.
An acquiring module 701, configured to acquire network resource data of a 4G base station and mesh data thereof, where the network resource data includes one or more of the following: bandwidth, resource utilization, number of connection users, voice traffic, domain flow, average coverage distance of cells, user download rate, 5G base station layout data of the 4G base station; the grid data includes one or more of the following: grid 4G traffic, grid user data, number of grid 4G terminals, number of grid sites, 4G base station coverage data.
The training module 702 is configured to train the network resource data and the grid data thereof by using a decision tree algorithm, so as to obtain a 5G base station layout evaluation model.
The apparatus 700 of the present embodiment may be used to perform the method embodiment shown in fig. 2, and its implementation principle and technical effects are similar, and will not be described herein.
Fig. 8 is a second schematic diagram of a training device for a 5G base station layout evaluation model according to an embodiment of the present application, as shown in fig. 8, and a training device 800 for a 5G base station layout evaluation model according to an embodiment of the present application includes: a processor 801, and a memory 802, wherein the processor 801 and the memory 802 are connected by a bus 803.
In a specific implementation process, the memory 802 stores codes, and the processor 801 runs the codes stored in the memory 802 to execute the 5G base station layout evaluation model training method in the above method embodiment.
The specific implementation process of the processor 801 may refer to the above-mentioned method embodiment, and its implementation principle and technical effects are similar, and this embodiment will not be described herein again.
In the embodiment shown in fig. 8, it should be understood that the processor 801 may be a central processing unit (in english: central Processing Unit, abbreviated as CPU), or may be other general purpose processors, digital signal processors (in english: digital Signal Processor, abbreviated as DSP), application specific integrated circuits (in english: application Specific Integrated Circuit, abbreviated as ASIC), or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor for execution, or in a combination of hardware and software modules in a processor for execution.
The bus 803 may be an industry standard architecture (Industry Standard Architecture, ISA) bus, an external device interconnect (Peripheral Component, PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, among others. The bus 803 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, the bus 803 in the figures of the present application is not limited to only one bus or one type of bus.
The embodiment of the application provides a computer readable storage medium, wherein computer executable instructions are stored in the computer readable storage medium, and the computer executable instructions are used for realizing the method for training the base station layout evaluation model according to any of the method embodiments 5G when being executed by a processor.
The computer readable storage medium described above may be implemented by any type or combination of volatile or non-volatile Memory devices, such as static random access Memory (Static Random Access Memory, SRAM), electrically erasable programmable Read-Only Memory (EEPROM), erasable programmable Read-Only Memory (Erasable Programmable Read-Only Memory, EPROM), programmable Read-Only Memory (Programmable Read-Only Memory, PROM), read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk, or optical disk. A readable storage medium can be any available medium that can be accessed by a general purpose or special purpose computer.
An exemplary readable storage medium is coupled to the processor such the processor can read information from, and write information to, the readable storage medium. In the alternative, the readable storage medium may be integral to the processor. The processor and the readable storage medium may reside in an application specific integrated circuit (Application Specific Integrated Circuits, ASIC for short). The processor and the readable storage medium may reside as discrete components in a device.
The embodiment of the application provides a computer program product, which comprises a computer program, and the computer program realizes the 5G base station layout evaluation model training method provided by any embodiment of the application when being executed by a processor.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It is to be understood that the present application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (10)
1. The 5G base station layout evaluation model training method is characterized by comprising the following steps of:
acquiring network resource data of a 4G base station and grid data thereof, wherein the network resource data comprises one or more of the following: bandwidth, resource utilization, number of connection users, voice traffic, domain flow, average coverage distance of cells, user download rate, 5G base station layout data of the 4G base station; the grid data includes one or more of: grid 4G traffic, grid user data, number of grid 4G terminals, number of grid sites, 4G base station coverage data;
and training the network resource data and the grid data by adopting a decision tree algorithm to obtain a 5G base station layout evaluation model.
2. The method of claim 1, wherein prior to training the network resource data and its grid data using a decision tree algorithm, further comprising:
generating training data in the network resource data and the grid data thereof;
and carrying out standardization processing on the training data.
3. The method of claim 2, wherein normalizing the training data comprises:
scaling the training data to a set interval to generate dimensionless numerical data;
and carrying out normalization processing on the numerical data.
4. The method of claim 2, wherein generating training data in the network resource data and its grid data comprises:
extracting non-numerical attribute data from the network resource data and the grid data thereof;
performing numerical conversion on the non-numerical attribute data;
and carrying out distribution randomization and homogenization treatment on the data after the numerical conversion to generate the training data.
5. The method according to any one of claims 2-4, wherein training the network resource data and its grid data using a decision tree algorithm comprises:
dividing the training data into training set data and test set data;
training the training set data by adopting a decision tree algorithm, and verifying the training result by adopting the test set data.
6. The method of claim 5, wherein the dividing the training data into training set data and test set data comprises:
determining a ratio of the training set data and the test set data;
and dividing the training data into the training set data and the test set data according to the proportion.
7. The method of claim 1, wherein prior to training the network resource data and its grid data using a decision tree algorithm, further comprising:
and cleaning the network resource data and the grid data thereof.
8. A 5G base station deployment assessment model training device, comprising:
the system comprises an acquisition module, a network resource acquisition module and a network resource acquisition module, wherein the acquisition module is used for acquiring network resource data of a 4G base station and grid data thereof, and the network resource data comprises one or more of the following: bandwidth, resource utilization, number of connection users, voice traffic, domain flow, average coverage distance of cells, user download rate, 5G base station layout data of the 4G base station; the grid data includes one or more of: grid 4G traffic, grid user data, number of grid 4G terminals, number of grid sites, 4G base station coverage data;
and the training module is used for training the network resource data and the grid data thereof by adopting a decision tree algorithm to obtain a 5G base station layout evaluation model.
9. A 5G base station deployment evaluation model training device, comprising: a processor, a memory having code stored therein, the processor running the code stored in the memory to perform the 5G base station layout evaluation model training method of any of claims 1-7.
10. A computer readable storage medium having stored therein computer executable instructions which when executed by a processor are for implementing the 5G base station deployment assessment model training method according to any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111531352.6A CN116264706A (en) | 2021-12-15 | 2021-12-15 | 5G base station layout evaluation model training method, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111531352.6A CN116264706A (en) | 2021-12-15 | 2021-12-15 | 5G base station layout evaluation model training method, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116264706A true CN116264706A (en) | 2023-06-16 |
Family
ID=86723434
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111531352.6A Pending CN116264706A (en) | 2021-12-15 | 2021-12-15 | 5G base station layout evaluation model training method, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116264706A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117596156A (en) * | 2023-12-07 | 2024-02-23 | 机械工业仪器仪表综合技术经济研究所 | Construction method of evaluation model of industrial application 5G network |
-
2021
- 2021-12-15 CN CN202111531352.6A patent/CN116264706A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117596156A (en) * | 2023-12-07 | 2024-02-23 | 机械工业仪器仪表综合技术经济研究所 | Construction method of evaluation model of industrial application 5G network |
| CN117596156B (en) * | 2023-12-07 | 2024-05-07 | 机械工业仪器仪表综合技术经济研究所 | Construction method of evaluation model of industrial application 5G network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108563548B (en) | Abnormality detection method and apparatus | |
| CN109949290B (en) | Pavement crack detection method, device, equipment and storage medium | |
| CN105740991B (en) | Climate change prediction method and system based on improved BP neural network fitting of multiple climate modes | |
| García et al. | Calibration of an urban cellular automaton model by using statistical techniques and a genetic algorithm. Application to a small urban settlement of NW Spain | |
| CN110503565A (en) | Behaviorist risk recognition methods, system, equipment and readable storage medium storing program for executing | |
| US20140372172A1 (en) | Method and computer system to forecast economic time series of a region and computer program thereof | |
| CN112365007B (en) | Model parameter determining method, device, equipment and storage medium | |
| CN114066184A (en) | Area coverage assessment method and device and electronic equipment | |
| CN114374449A (en) | Interference source determination method, device, equipment and medium | |
| CN110348717B (en) | Base station value scoring method and device based on grid granularity | |
| CN116264706A (en) | 5G base station layout evaluation model training method, equipment and storage medium | |
| CN109995549B (en) | Method and device for evaluating flow value | |
| CN108734393A (en) | Matching process, user equipment, storage medium and the device of information of real estate | |
| CN110992230B (en) | Full-scale demographic method, device and server based on terminal signaling data | |
| CN112598326A (en) | Model iteration method and device, electronic equipment and storage medium | |
| CN112883267A (en) | Data heat degree statistical method and device based on deep learning | |
| CN113890833B (en) | Network coverage prediction method, device, equipment and storage medium | |
| CN112579847A (en) | Method and device for processing production data, storage medium and electronic equipment | |
| CN115203556A (en) | Score prediction model training method and device, electronic equipment and storage medium | |
| CN112929887B (en) | Method and device for setting room substation based on flow prediction and electronic equipment | |
| CN115967906A (en) | User resident position identification method, terminal, electronic device and storage medium | |
| CN113822464A (en) | User information processing method and device, electronic equipment and storage medium | |
| CN113076451B (en) | Abnormal behavior identification and risk model library establishment method and device and electronic equipment | |
| CN113256444A (en) | Low-voltage transformer area household transformation relation identification method and device | |
| CN116384779B (en) | Method, device and server for comprehensively cutting key index influence factors of on-orbit test |
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 |