Intelligent power mining method and system for 4G and 5G common radio remote unit

Abstract

The invention relates to the technical field of mobile communication, and particularly discloses a 4G and 5G common remote radio unit power-oriented intelligent mining method and system, and the method comprises the steps: obtaining remote radio unit data of a 4G cell and a 5G cell, and building a database; performing data preprocessing on the data in the database by using a Z-score standardization method; clustering each data feature item according to a DBSCAN algorithm; according to a random forest algorithm and based on a clustering result, power potential tapping and refined distribution model construction are realized; and according to the power potential tapping and fine distribution model, determining power rising and falling amplitude values of the 4G cell and the 5G cell. According to the application, data processing, association, business rules and intelligent algorithms are organically connected in series, full mining and fine distribution of 4G and 5G common radio remote unit power are realized, optimization work development is accurately guided, and the solving efficiency of 4G and 5G high load, weak coverage, high interference and other problems caused by a power problem is improved.

Description

Technical Field

[0001] The present invention relates to the field of mobile communication technologies, and in particular to a method and system for intelligent mining of power of 4G and 5G common radio remote units. Background Art

[0002] With the continuous expansion of 4G and 5G network scale, network operation and maintenance costs are rising. On the other hand, during the large-scale network construction stage, factors such as wireless environment, user distribution, and business demands are not perfect and real-time. In order to meet user perception needs and stabilize network quality, the power of base station radio remote units will be reserved to varying degrees. Currently, mobile operators are continuously working to reduce costs and increase efficiency, making full use of existing resources, and maintaining both user perception stability and network service quality. The full utilization and exploration of the power of radio remote units serves as a support point for reducing costs and increasing efficiency, achieving full utilization of resources and continuous stability of user perception.

[0003] At present, the main idea for power mining of 4G and 5G shared remote radio units is to improve 4G coverage and maintain stable 5G coverage. The power increase or decrease is determined based on the comprehensive judgment of 4G and 5G weak coverage, uplink interference and utilization indicators. This work requires professional optimization personnel to regularly extract MR data, northbound performance data, drive test data, and remote radio unit information of equipment manufacturers, and then perform complex correlation calculations to confirm and implement solutions. This method and process have the following problems:

[0004] (1) Data collection is difficult: It involves MR data, northbound performance data, drive test data, and radio remote unit information from various manufacturers. It involves many interfaces and data types. Manual collection is time-consuming and difficult.

[0005] (2) Manual calculation is difficult: Calculation needs to be based on the association of multiple categories of data and there are many restrictions that need to be considered. The relevant personnel need to have professional business knowledge and processing capabilities, which is difficult and cannot meet the timeliness requirements.

[0006] (3) The degree of fit between the calculation results and the actual situation cannot be quantified: the results of the correlation calculation cannot be confirmed as the optimal solution and may require multiple attempts.

[0007] Therefore, how to solve the problems in the prior art such as high difficulty in data collection, great difficulty in manual calculation and inability to quantify the degree of fit between calculation results and actual conditions is a technical problem that needs to be solved urgently by those skilled in the art. Summary of the invention

[0008] To achieve the purpose of the present invention, the present application provides a method for intelligently mining power of 4G and 5G common radio remote units, comprising:

[0009] Obtain the remote radio unit data of 4G cells and 5G cells and establish a database;

[0010] Using the Z-score standardization method to preprocess the data in the database;

[0011] Cluster the feature items of each data according to the DBSCAN algorithm;

[0012] According to the random forest algorithm and based on the clustering results, power potential tapping and refined allocation model construction are realized;

[0013] According to the power potential tapping and refined allocation model, the power increase and decrease range values ​​of the 4G cell and the 5G cell are determined.

[0014] In some specific embodiments, the data in the database include: 4G cell and 5G cell engineering parameters, 4G MR coverage and 5G MR coverage, radio remote unit configuration, 4G wireless performance and 5G wireless performance.

[0015] In some specific embodiments, the data preprocessing includes:

[0016] Perform data correlation integration, data repair and data standardization on 5G MR coverage, 5G wireless performance, radio remote unit configuration, 4G cell engineering parameters, 4G MR coverage and 4G wireless performance.

[0017] In some specific embodiments, it also includes: performing power intelligent mining and feature information allocation on the data after the data preprocessing, determining the segmentation boundary of each feature information, and using the segmentation boundary as the interval threshold for splitting leaf nodes during random forest training.

[0018] In some specific embodiments, the intelligent power potential tapping and refined power allocation include:

[0019] For any type of data after the data preprocessing, determine the index value after standardization as a standard point, and calculate the density space of the standard point;

[0020] Determine whether the standard point is a core point, if so, create a class around it, otherwise, mark it as a peripheral point;

[0021] Traverse all points in this type of data, and establish density-direct and density-reachable points into a class according to the density space;

[0022] Repeat the above steps until all preprocessed data are in the class or marked as peripheral points.

[0023] In some specific embodiments, the intelligent power potential tapping and refined power allocation also include: determining the optimal power configuration of 4G and 5G shared radio frequency remote units under specific scenarios, wireless environments, and network structures through a random forest algorithm.

[0024] In some specific embodiments, it also includes:

[0025] The information of the cells in the existing network that share the 4G and 5G radio remote units and have power margin is input into the power potential tapping and refined allocation model, and the corresponding power increase and decrease amplitude values ​​of the 4G cells and 5G cells are output.

[0026] To achieve the same invention purpose, the present application also provides a system for intelligent power mining of 4G and 5G common radio remote units, including:

[0027] Database establishment module: used to obtain the radio remote unit data of 4G cells and 5G cells and establish a database;

[0028] Data preprocessing module: used for preprocessing the data in the database using the Z-score standardization method;

[0029] Data classification module: used to cluster the feature items of each data according to the DBSCAN algorithm;

[0030] Model building module: used to realize power potential tapping and refined allocation model building based on random forest algorithm and clustering results;

[0031] Result output module: used to determine the power increase and decrease amplitude values ​​of the 4G cell and the 5G cell according to the power potential tapping and refined allocation model.

[0032] A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the above-mentioned method for intelligent power mining of 4G and 5G common radio remote units.

[0033] A device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the above-mentioned method for intelligent power mining of 4G and 5G common radio remote units.

[0034] Beneficial effects of the above technical solution:

[0035] This application organically connects data processing, association, business rules and intelligent algorithms to fully explore and finely allocate the power of 4G and 5G common radio remote units, accurately guide the optimization work, and improve the efficiency of solving problems such as 4G and 5G high load, weak coverage, high interference, etc. caused by power issues. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0037] Figure 1 A flow chart of a method for intelligent power mining of 4G and 5G common radio remote units provided by an embodiment of the present invention;

[0038] Figure 2 A schematic diagram of the structure of a system for intelligent power mining of 4G and 5G common radio remote units provided by an embodiment of the present invention;

[0039] Figure 3 A schematic diagram of data association integration of a method for intelligent mining of 4G and 5G common radio remote unit power provided by an embodiment of the present invention;

[0040] Figure 4 A schematic diagram of data standardization of a method for intelligent mining of 4G and 5G common radio remote unit power provided by an embodiment of the present invention;

[0041] Figure 5 A schematic diagram of a random forest training process for a method for intelligent mining of 4G and 5G common radio remote unit power provided by an embodiment of the present invention;

[0042] Figure 6 A schematic diagram of the structure of a device for intelligent power mining of 4G and 5G common radio remote units provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0043] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0044] Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar symbols throughout represent the same or similar elements or elements with the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0045] Embodiment 1

[0046] An embodiment of the present invention provides a method for intelligently mining power of 4G and 5G common radio remote units, referring to Figure 1 As shown, including:

[0047] Step S1: Acquire the radio remote unit data of the 4G cell and the 5G cell, and establish a database.

[0048] In a specific embodiment of the present invention, the data in the database includes: 4G cell and 5G cell engineering parameters, 4G MR coverage and 5G MR coverage, radio remote unit configuration, 4G wireless performance and 5G wireless performance.

[0049] Step S2: Use the Z-score standardization method to perform data preprocessing on the data in the database.

[0050] In a specific embodiment of the present invention, the data preprocessing includes:

[0051] Perform data correlation integration, data repair and data standardization on 5G MR coverage, 5G wireless performance, radio remote unit configuration, 4G cell engineering parameters, 4G MR coverage and 4G wireless performance.

[0052] Specifically, data association integration refers to Figure 3 As shown, data repair mainly solves two main problems of the indicator data involved in this method: abnormal data and null value data. For abnormal data (exceeding the normal range), the method of direct deletion is adopted, and for null value data, the median (median filling can avoid the impact of large or small data) filling method is adopted.

[0053] Actual range of indicators involved:

[0054] Indicator name Indicator range 5GMR Coverage 0～100％ 5G uplink interference level -140~0dBm 5GPRB Utilization 0～100％ 5G downlink low CQI ratio 0～100％ 5GTA 0～∞ Uplink weak coverage ratio 0～100％ Remote radio unit power margin 0～520 4GMR Coverage 0～100％ 4G uplink interference level -140~0dBm 4GPRB Utilization 0～100％ 4G downlink low CQI ratio 0～100％ 4GTA 0～∞ Uplink weak coverage ratio 0～100％

[0055] In order to unify the comparison standards and ensure the reliability of the results, the original variables need to be processed before analyzing the data to achieve data standardization. Figure 4 The data shown in this paper converts the original data into dimensionless and magnitude-independent standardized values, eliminating the impact of different attributes between different indicators, making the results more comparable. This method uses the Z-score standardization method to process the data, and its conversion function is as follows:

[0056]

[0057] Among them, x represents the original value of a certain indicator, x mean Represents the mean of an indicator, x std Represents an indicator.

[0058] In a specific embodiment of the present invention, power intelligent mining and feature information allocation are performed on the data after data preprocessing, the segmentation boundary of each feature information is determined, and the segmentation boundary is used as the interval threshold for splitting leaf nodes during random forest training.

[0059] Step S3: Cluster the feature items of each data according to the DBSCAN algorithm.

[0060] In a specific embodiment of the present invention, step S3 includes:

[0061] Step S31: for any type of data after the data preprocessing, determine the index value after standardization as a standard point, and calculate the density space of the standard point;

[0062] Step S32: Determine whether the standard point is a core point, if so, create a class around it, otherwise, mark it as a peripheral point;

[0063] Step S33: traverse all points in this type of data, and establish density-direct and density-reachable points into a class according to the density space;

[0064] Step S34: Repeat steps S31 to S33 until all pre-processed data are in the class or marked as peripheral points.

[0065] Specifically, the DBSCAN algorithm clusters each feature to obtain the interval boundary of each feature index. The interval boundary is the leaf node of the random forest training split. The DBSCAN algorithm needs to determine two parameters first:

[0066] (1) Epsilon: The radius of the neighborhood around a point (the radius has different meanings for different clustering objects in different application scenarios).

[0067] (2)minPts: The minimum number of points contained in the neighboring area.

[0068] Combined with the above, the steps of DBSCAN clustering in this method are as follows: (assuming epsilon and minPts are known)

[0069] 1. For any indicator in this method, select a point (normalized indicator value) and calculate its NBHD (p, epsilon) (density space) to determine whether it is a core point. If so, create a class around the point, otherwise, set it as a peripheral point.

[0070] 2. Traverse the other points until a class is established. Add directly-reachable points to the class, and then add density-reachable points. If a point marked as peripheral is added, change its status to edge point.

[0071] 3. Repeat steps 1 and 2 until all points are in the class (core points or edge points) or are peripheral points. Output the upper and lower thresholds of each clustered category, adjust the parameters multiple times to obtain the local optimal solution as the final result, and this result is used as the basis for the leaf node bifurcation in the random forest training process.

[0072] For the data preprocessed in step S2, the DBSCAN clustering algorithm is used to select scenarios, 5GMR coverage, 5G uplink interference level, 5GPRB utilization, 5G downlink low CQI ratio, 5GTA, 5G uplink weak coverage ratio, RF remote unit power margin, 4GMR coverage, 4G uplink interference level, 4GPRB utilization, 4G downlink low CQI ratio, 4GTA, 4G uplink weak coverage ratio as feature information for intelligent power mining and allocation, determine the segmentation boundary of each feature information, and use the division result as the interval threshold for splitting leaf nodes during subsequent random forest training.

[0073] In a specific embodiment of the present invention, step S3 also includes: determining the optimal power configuration of the 4G and 5G common radio remote units under specific scenarios, wireless environments, and network structures through a random forest algorithm.

[0074] Step S4: Implement power potential tapping and refinement allocation model construction according to the random forest algorithm and based on the clustering results.

[0075] In a specific embodiment of the present invention, step S4 includes:

[0076] The cell information of 4G and 5G cells in the existing network that share radio remote units and have power margin is input into the power potential tapping and refined allocation model, and the corresponding power increase and decrease amplitude values ​​of the 4G cells and 5G cells are output.

[0077] Specifically, first, select a 4G cell and a 5G cell of a common radio remote unit that meet the following conditions, the details are as follows:

[0078]

[0079]

[0080] The communities that meet the requirements in the above table are selected as potential tapping targets and divided into training sets for random forest training. Figure 3 As shown, the specific process is as follows:

[0081] 1. Based on the advantaged potential objects, sampling with replacement is adopted, and the number of plots sampled each time is less than the number of plots to be selected;

[0082] 2. Randomly select k features from all the features, and use these features to build a decision tree for the selected samples (using CART, all nodes can only be split into binary trees, but the same feature can be divided multiple times to ensure that the information is fully utilized. At the same time, the segmented boundary interval results of the feature information divided by the DBSCAN density clustering algorithm described in step 3 are used as the basis for judging the splitting of the random forest leaf nodes), where N features include 5GMR coverage, 5G uplink interference level, 5GPRB utilization, 5G downlink low CQI ratio, 5GTA, uplink weak coverage ratio, radio frequency remote unit power margin, 4GMR coverage, 4G uplink interference level, 4GPRB utilization, 4G downlink low CQI ratio, 4GTA, uplink weak coverage ratio, etc. Calculate the value k=log2N;

[0083] 3. Repeat the above two steps to train Y decision tree models respectively, generate multiple decision trees to form a random forest, and finally use the weighted voting method to obtain the result - that is, output the optimal power configuration of the 4G and 5G shared radio remote units under specific scenarios, wireless environments, and network structures.

[0084] Step S5: Determine the magnitude of the power increase or decrease of the 4G and 5G cells according to the power potential tapping and refined allocation model.

[0085] Specifically, according to the power potential tapping and refined allocation model, the cell information of 4G and 5G cells sharing the same radio remote unit and with power margin in the existing network is taken as input. After being processed by the model, the amplitude values ​​of power increase and decrease of the corresponding 4G cells and 5G cells are output.

[0086] This application organically connects data processing, association, business rules and intelligent algorithms to fully explore and finely allocate the power of 4G and 5G common radio remote units, accurately guide the optimization work, and improve the efficiency of solving problems such as 4G and 5G high load, weak coverage, high interference, etc. caused by power issues.

[0087] Embodiment 2

[0088] An embodiment of the present invention provides a system for intelligent mining of power of 4G and 5G common radio remote units, referring to Figure 2 As shown, including:

[0089] Database establishment module 10: used to obtain the radio remote unit data of 4G and 5G cells and establish a database;

[0090] Data preprocessing module 20: used to perform data preprocessing on the data in the database using a Z-score standardization method;

[0091] Data classification module 30: used to cluster the feature items of each data according to the DBSCAN algorithm;

[0092] Model building module 40: used to realize power potential tapping and refined allocation model building according to random forest algorithm and based on clustering results;

[0093] The result output module 50 is used to determine the amplitude values ​​of the power increase and decrease of the 4G and 5G cells according to the power potential tapping and refined allocation model.

[0094] In a specific embodiment of the present invention, the data in the database includes: 4G cell and 5G cell engineering parameters, 4GMR coverage and 5GMR coverage, radio remote unit configuration, 4G wireless performance and 5G wireless performance.

[0095] In a specific embodiment of the present invention, the data preprocessing includes:

[0096] Perform data correlation integration, data repair and data standardization on 5G MR coverage, 5G wireless performance, radio remote unit configuration, 4G cell engineering parameters, 4G MR coverage and 4G wireless performance.

[0097] In a specific embodiment of the present invention, it also includes: performing power intelligent mining and feature information allocation on the data after the data preprocessing, determining the segmentation boundary of each feature information, and using the segmentation boundary as the interval threshold for splitting leaf nodes during random forest training.

[0098] In a specific embodiment of the present invention, the data classification module 30 is used to perform the following steps:

[0099] Step S31: for any type of data after the data preprocessing, determine the index value after standardization as a standard point, and calculate the density space of the standard point;

[0100] Step S32: Determine whether the standard point is a core point, if so, create a class around it, otherwise, mark it as a peripheral point;

[0101] Step S33: traverse all points in this type of data, and establish density-direct and density-reachable points into a class according to the density space;

[0102] Step S34: Repeat steps S31 to S33 until all pre-processed data are in the class or marked as peripheral points.

[0103] In a specific embodiment of the present invention, the data classification module 30 is also used to determine the optimal power configuration of 4G and 5G common radio remote units under specific scenarios, wireless environments, and network structures through a random forest algorithm.

[0104] In a specific embodiment of the present invention, the model building module 40 is used to perform the following steps:

[0105] The cell information of 4G and 5G cells in the existing network that share radio remote units and have power margin is input into the power potential tapping and refined allocation model, and the corresponding power increase and decrease amplitude values ​​of the 4G cells and 5G cells are output.

[0106] This application organically connects data processing, association, business rules and intelligent algorithms to fully explore and finely allocate the power of 4G and 5G common radio remote units, accurately guide the optimization work, and improve the efficiency of solving problems such as 4G and 5G high load, weak coverage, high interference, etc. caused by power issues.

[0107] Embodiment 3

[0108] Corresponding to the method embodiment, in the embodiment of the present invention, a device for intelligent mining of power of 4G and 5G common radio remote units, such as a terminal, a server, etc., is also provided. Among them, the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited to this.

[0109] An example of a hardware structure block diagram of a device for intelligent power mining of 4G and 5G common radio remote units provided by an embodiment of the present invention is shown in FIG. Figure 6 As shown, it may include:

[0110] Processor 1, communication interface 2, memory 3 and communication bus 4;

[0111] The processor 1, the communication interface 2, and the memory 3 communicate with each other via the communication bus 4;

[0112] Optionally, the communication interface 2 may be an interface of a communication module, such as an interface of a GSM module;

[0113] The processor 1 may be a central processing unit CPU, or an application-specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application.

[0114] The memory 3 may include a high-speed RAM memory, and may also include a non-volatile memory (non volatile memory), such as at least one disk memory.

[0115] The processor 1 is specifically used to execute the computer program stored in the memory 3 to perform the following steps:

[0116] Step S1: Obtaining the remote radio unit data of 4G and 5G cells and establishing a database;

[0117] Step S2: using the Z-score standardization method to perform data preprocessing on the data in the database;

[0118] Step S3: Intelligently tap the power potential and finely allocate the power for the radio remote units shared by 4G and 5G cells according to the DBSCAN clustering algorithm and the random forest algorithm;

[0119] Step S4: constructing a power potential tapping and refined allocation model according to the results of the power intelligent potential tapping and refined power allocation;

[0120] Step S5: Determine the magnitude of the power increase or decrease of the 4G and 5G cells according to the power potential tapping and refined allocation model.

[0121] The above-mentioned product can execute the method provided in the embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not described in detail in this embodiment, please refer to a method for intelligent power mining of 4G and 5G common radio remote units provided in the embodiment of the present invention.

[0122] Embodiment 4

[0123] In an embodiment of the present invention, a storage medium is further provided, which may store a program suitable for execution by a processor, wherein the program is used to perform the following steps:

[0124] Step S1: Obtaining the remote radio unit data of 4G and 5G cells and establishing a database;

[0125] Step S2: using the Z-score standardization method to perform data preprocessing on the data in the database;

[0126] Step S3: Intelligently tap the power potential and finely allocate the power for the radio remote units shared by the 4G cell and the 5G cell according to the DBSCAN clustering algorithm and the random forest algorithm;

[0127] Step S4: constructing a power potential tapping and refined allocation model according to the results of the power intelligent potential tapping and refined power allocation;

[0128] Step S5: Determine the power increase and decrease range values ​​of the 4G cell and the 5G cell according to the power potential tapping and refined allocation model.

[0129] Optionally, the detailed functions and extended functions of the program may refer to the above description.

[0130] The above product can execute the method provided by the embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not described in detail in this embodiment, please refer to the methods provided by other embodiments of the present invention.

[0131] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0132] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0133] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0134] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0135] It should be understood that in the embodiments of the present application, the various embodiments and features can be combined with each other to solve the aforementioned technical problems.

[0136] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: USB flash drives, mobile hard drives, read-only memories (ROM, Read Only Memory), Random Access Memory (RAM), disks or CDs, etc. that can store program codes.

[0137] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0138] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0139] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referenced to each other. The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the functions in the process. Figure 1 A process or multiple processes and / or boxes Figure 1These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing terminal device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including an instruction device, which implements the functions specified in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device, so that a series of operation steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable terminal device provide for implementing the process in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps of the functions specified in one or more boxes. Although the preferred embodiments of the embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they know the basic creative concept. Therefore, the attached claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention. Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or terminal device including a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of more restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0140] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", "one specific embodiment" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

Claims

1. A method for intelligently mining power of 4G and 5G common radio remote units, characterized in that: include: Obtain the remote radio unit data of 4G cells and 5G cells and establish a database; Using the Z-score standardization method to preprocess the data in the database; Cluster the feature items of each data according to the DBSCAN algorithm; According to the random forest algorithm and based on the clustering results, power potential tapping and refined allocation model construction are realized; According to the power potential tapping and refined allocation model, the power increase and decrease range values ​​of the 4G cell and the 5G cell are determined.

2. The method for intelligent power mining of 4G and 5G common radio remote units according to claim 1 is characterized in that: The data in the database include: 4G cell and 5G cell engineering parameters, 4G MR coverage and 5G MR coverage, radio remote unit configuration, 4G wireless performance and 5G wireless performance.

3. The method for intelligent power mining of 4G and 5G common radio remote units according to claim 2 is characterized in that: The data preprocessing includes: Perform data correlation integration, data repair and data standardization on 5G MR coverage, 5G wireless performance, radio remote unit configuration, 4G cell engineering parameters, 4G MR coverage and 4G wireless performance.

4. The method for intelligent power mining of 4G and 5G common radio remote units according to claim 1, characterized in that: Also includes: Power intelligent mining and feature information allocation are performed on the data after the data preprocessing, the segmentation boundary of each feature information is determined, and the segmentation boundary is used as the interval threshold for splitting leaf nodes during random forest training.

5. The method for intelligent power mining of 4G and 5G common radio remote units according to claim 1, characterized in that: The intelligent power potential tapping and refined power allocation include: For any type of data after the data preprocessing, determine the index value after standardization as a standard point, and calculate the density space of the standard point; Determine whether the standard point is a core point, if so, create a class around it, otherwise, mark it as a peripheral point; Traverse all points in this type of data, and establish density-direct and density-reachable points into a class according to the density space; Repeat the above steps until all preprocessed data are in the class or marked as peripheral points.

6. The method for intelligent power mining of 4G and 5G common radio remote units according to claim 1, characterized in that: The intelligent power potential tapping and refined power allocation also include: determining the optimal power configuration of 4G and 5G shared radio remote units under specific scenarios, wireless environments, and network structures through a random forest algorithm.

7. The method for intelligent power mining of 4G and 5G common radio remote units according to claim 1, characterized in that: Also includes: The information of the cells in the existing network that share the 4G and 5G radio remote units and have power margin is input into the power potential tapping and refined allocation model, and the corresponding power increase and decrease amplitude values ​​of the 4G cells and 5G cells are output.

8. A system for intelligent power mining of 4G and 5G common radio remote units, characterized in that: include: Database establishment module: used to obtain the radio remote unit data of 4G cells and 5G cells and establish a database; Data preprocessing module: used for preprocessing the data in the database using the Z-score standardization method; Data classification module: used to cluster the feature items of each data according to the DBSCAN algorithm; Model building module: used to realize power potential tapping and refined allocation model building based on random forest algorithm and clustering results; Result output module: used to determine the power increase and decrease amplitude values ​​of the 4G cell and the 5G cell according to the power potential tapping and refined allocation model.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for intelligent power mining of 4G and 5G common radio remote units according to any one of claims 1 to 7 is implemented.

10. A device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements a method for intelligent power mining of 4G and 5G common radio remote units as described in any one of claims 1 to 7.

Images