Base station load conversion method, device and electronic equipment

Abstract

The present application discloses a method, device and electronic device for converting base station load. The method includes: obtaining base station data related to the data transmission rate of the base station, wherein the base station data includes base station load data and base station index data; determining the correlation between the base station transmission rate and the base station data; determining the characteristic value required to construct the objective function based on the correlation, wherein the objective function is used to determine the relationship between the base station transmission rate and the base station load data; iteratively tuning the objective function to determine the load conversion parameters, and determining the load conversion model based on the load conversion parameters. The present application solves the technical problem that the traditional base station load conversion relies on expert experience evaluation, which has low efficiency and poor accuracy.

Description

Technical Field

[0001] The present application relates to the field of mobile communications, and in particular to a method, device and electronic equipment for converting base station loads. Background Art

[0002] After years of construction, the overall coverage of 5G mobile networks has been improved. The energy consumption of 5G single stations has increased significantly compared to 4G, and the average power consumption is 3.5 times that of 4G. Based on the load conversion of base stations with different configurations, the coordinated energy saving of wireless network 4 / 5G base stations is carried out, the 4G load after the 5G base station is shut down for energy saving is predicted, and the 5G is selectively shut down for energy saving. Improving the energy saving efficiency of 5G is of great significance to improving the operating efficiency of operators. As for how to convert the load of base stations, the industry currently relies mainly on expert experience, which has problems of low efficiency and poor accuracy.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present application provide a method, device and electronic device for converting a base station load, so as to at least solve the technical problem that traditional base station load conversion relies on expert experience evaluation, which has low efficiency and poor accuracy.

[0005] According to one aspect of an embodiment of the present application, a method for converting a base station load is provided, comprising: obtaining base station data related to the data transmission rate of the base station, wherein the base station data includes base station load data and base station index data; determining the correlation between the base station transmission rate and the base station data; based on the correlation, determining the characteristic values ​​required to construct an objective function, wherein the objective function is used to determine the relationship between the base station transmission rate and the base station load data; iteratively tuning the objective function to determine the load conversion parameters, and determining the load conversion model based on the load conversion parameters.

[0006] Optionally, before obtaining base station data related to the data transmission rate of the base station, the method also includes: processing missing values ​​in the base station data, including: when the base station data is discrete data, using the mode of the discrete data to fill the data; when the base station data is continuous data, using the mean of the continuous data to fill the data.

[0007] Optionally, before obtaining base station data related to the data transmission rate of the base station, the method also includes: processing abnormal values ​​in the base station data, including: obtaining a first quantile and a second quantile, wherein the first quantile is smaller than the second quantile; filling data in the base station data that is smaller than or equal to the first quantile with data corresponding to the first quantile; filling data in the base station data that is greater than or equal to the second quantile with data corresponding to the second quantile; and filling abnormal values ​​in the base station data with base station data of the same type.

[0008] Optionally, determining the correlation between the base station transmission rate and the base station data includes: determining a first correlation between the base station transmission rate and the base station load data, wherein the first correlation is determined by the base station transmission rate, the average value of the base station transmission rate, the base station load data, and the average value of the base station load data; determining a second correlation between the base station transmission rate and the base station index data, wherein the second correlation is determined by the base station transmission rate, the average value of the base station transmission rate, the base station index data, and the average value of the base station index data.

[0009] Optionally, based on the correlation, the characteristic values ​​required to construct the objective function are determined, including: obtaining a first threshold corresponding to the first correlation, and obtaining a second threshold corresponding to the second correlation; determining the base station load data corresponding to when the first correlation is greater than the first threshold as the target base station load data; determining the base station index data corresponding to when the second correlation is greater than the second threshold as the target base station index data; based on the target base station load data and the target base station index data, determine the characteristic values ​​required for the objective function.

[0010] Optionally, the objective function is iteratively tuned, including: constructing a selection matrix based on base station configuration data, wherein the base station configuration data includes at least a wireless standard, a channel bandwidth and an antenna configuration, and the selection matrix is ​​used to classify the base station data; determining a first matrix and a second matrix, wherein the first matrix is ​​determined by the base station transmission rate, and the second matrix is ​​determined by the target base station load data and the target base station index data; determining a third matrix based on the first matrix, the second matrix and the selection matrix, wherein the third matrix is ​​determined by characteristic parameters, which are parameters corresponding to the target base station load data and the target base station index data; iteratively tuning the objective function according to a gradient descent algorithm to obtain load conversion parameters corresponding to the third matrix when the objective function takes a minimum value.

[0011] Optionally, a load conversion model is determined based on the load conversion parameters, including: determining a base station rate model based on the load conversion parameters, wherein the base station rate model is used to represent the relationship between the base station transmission rate based on the base station configuration data and the base station load data; determining a load conversion model based on the base station rate model, wherein the load conversion model is used to represent the relationship between the base station configuration data and the base station load data.

[0012] According to another aspect of an embodiment of the present application, a base station load conversion device is also provided, including: an acquisition module, used to acquire base station data related to the data transmission rate of the base station, wherein the base station data includes base station load data and base station index data; a first determination module, used to determine the correlation between the base station transmission rate and the base station data; a second determination module, used to determine the characteristic values ​​required to construct an objective function based on the correlation, wherein the objective function is used to determine the relationship between the base station transmission rate and the base station load data; a third determination module, used to iteratively tune the objective function, determine the load conversion parameters, and determine the load conversion model based on the load conversion parameters.

[0013] According to another aspect of the embodiment of the present application, there is also provided an electronic device, including: a memory for storing program instructions; a processor, connected to the memory, for executing program instructions to implement the following functions: obtaining base station data related to the data transmission rate of the base station, wherein the base station data includes base station load data and base station index data; determining the correlation between the base station transmission rate and the base station data; based on the correlation, determining the characteristic values ​​required to construct an objective function, wherein the objective function is used to determine the relationship between the base station transmission rate and the base station load data; iteratively tuning the objective function to determine the load conversion parameters, and determining the load conversion model based on the load conversion parameters.

[0014] According to another aspect of the embodiment of the present application, a non-volatile storage medium is also provided, which includes a stored program, wherein when the program is running, the device where the non-volatile storage medium is located is controlled to execute the above-mentioned base station load conversion method.

[0015] In an embodiment of the present application, by acquiring base station data related to the data transmission rate of the base station, wherein the base station data includes base station load data and base station index data; determining the correlation between the base station transmission rate and the base station data; determining the characteristic values ​​required for constructing the objective function based on the correlation, wherein the objective function is used to determine the relationship between the base station transmission rate and the base station load data; iteratively tuning the objective function to determine the load conversion parameters, thereby achieving the purpose of determining the load conversion model based on the load conversion parameters, thereby achieving the technical effect of improving the accuracy of base station conversion, and further solving the technical problem that traditional base station load conversion relies on expert experience evaluation, with low efficiency and poor accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0017] Figure 1It is a hardware structure block diagram of a computer terminal (or electronic device) for implementing a base station load conversion method according to an embodiment of the present application;

[0018] Figure 2 is a flow chart of a base station load conversion method according to an embodiment of the present application;

[0019] Figure 3a is a flow chart of iterative tuning of a model according to an embodiment of the present application;

[0020] Figure 3b It is a flow chart of establishing a wireless network base station load conversion model based on base station configuration according to an embodiment of the present application;

[0021] Figure 3c is a schematic diagram of the correlation between a base station transmission rate and base station data according to an embodiment of the present application;

[0022] Figure 4 It is a structural diagram of a base station load conversion device according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] In the related art, based on expert experience, the load conversion coefficients of base stations with different configurations are determined by tracking the loads of base stations with different configurations for a long time. For example, the empirical value of the conversion coefficient between the utilization rate of 5G PRB (i.e., physical resource block) and the utilization rate of 4G PRB is 5. The advantage of using expert experience to determine the base station load conversion coefficient is that it is simple and fast, but the disadvantage is that the conversion method is relatively rough, resulting in large errors. In order to solve the problems of low efficiency and poor accuracy in traditional base station load conversion relying on expert experience evaluation, the embodiments of the present application provide corresponding solutions, which are described in detail below.

[0026] The base station load conversion method embodiment provided in the embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 The hardware structure block diagram of a computer terminal (or electronic device) for implementing a base station load conversion method is shown. Figure 1 As shown, the computer terminal 10 (or electronic device 10) may include one or more (102a, 102b, ..., 102n are used to illustrate) processors (the processor may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission module 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0027] It should be noted that the one or more processors and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10 (or electronic device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0028] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the load conversion method of the base station in the embodiment of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, realizing the above-mentioned base station load conversion method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0029] The transmission module 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0030] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or electronic device).

[0031] It should be noted that, in some optional embodiments, the above Figure 1 The computer device (or electronic device) shown may include hardware elements (including circuits), software elements (including computer code stored on a computer-readable medium), or a combination of hardware elements and software elements. It should be noted that Figure 1 This is merely one example of a particular embodiment and is intended to illustrate the types of components that may be present in the above-described computer device (or electronic device).

[0032] In the above-mentioned operating environment, an embodiment of the present application provides an embodiment of a base station load conversion method. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0033] Figure 2is a flow chart of a base station load conversion method according to an embodiment of the present application, such as Figure 2 As shown, the method comprises the following steps:

[0034] Step S202, acquiring base station data related to the data transmission rate of the base station, wherein the base station data includes base station load data and base station index data.

[0035] In the above step S202, load data and index data related to the base station transmission rate are obtained through the wireless base station PM data. The above base station index data include RRC connection success rate, switching success rate, signal coverage rate, disconnection rate and other index data. The base station data in this step is the base station data obtained after preprocessing. The preprocessing includes processing missing values ​​of the original data and processing abnormal values ​​in the original data.

[0036] Step S204: determine the correlation between the base station transmission rate and the base station data.

[0037] In the above step S204, for example, the Pearson correlation coefficient may be used to calculate the correlation between the base station transmission rate and the base station load data and the base station index data.

[0038] Step S206, determining the characteristic value required for constructing the objective function according to the correlation, wherein the objective function is used to determine the relationship between the base station transmission rate and the base station load data;

[0039] Step S208, iteratively tune the objective function to determine the load conversion parameters, and determine the load conversion model based on the load conversion parameters.

[0040] In step S202 of the above-mentioned base station load conversion method, before obtaining the base station data related to the data transmission rate of the base station, the following two preprocessing processes are specifically included: 1) Processing the missing values ​​in the base station data, specifically including: when the base station data is discrete data, using the mode of the discrete data for data filling; when the base station data is continuous data, using the mean of the continuous data for data filling; the missing values ​​of important variables are backfilled through modeling prediction, and the base station data with serious attribute missing are discarded. 2) Processing the abnormal values ​​in the base station data, including: obtaining the first quantile and the second quantile, wherein the first quantile is less than the second quantile; filling the data in the base station data that is less than or equal to the first quantile with the data corresponding to the first quantile; filling the data in the base station data that is greater than or equal to the second quantile with the data corresponding to the second quantile; filling the abnormal values ​​in the base station data with the same type of base station data. Specifically, for outliers in base station data, for example, the cap method can be used to backfill base station data that is less than or equal to the first quantile with the value of the first quantile, for example, the first quantile can be 3%, and base station data that is greater than or equal to the second quantile can be backfilled with the value of the second quantile, for example, the second quantile can be 97%; when the value of the base station data is an outlier such as null, the same type of base station data is used to fill it.

[0041] In step S204 of the above-mentioned base station load conversion method, the correlation between the base station transmission rate and the base station data is determined, which specifically includes the following steps: determining a first correlation between the base station transmission rate and the base station load data, wherein the first correlation is determined by the base station transmission rate, the average value of the base station transmission rate, the base station load data and the average value of the base station load data; determining a second correlation between the base station transmission rate and the base station index data, wherein the second correlation is determined by the base station transmission rate, the average value of the base station transmission rate, the base station index data and the average value of the base station index data.

[0042] In the embodiment of the present application, the Pearson correlation coefficient is used to determine the correlation between the base station transmission rate and the base station data, and the following Pearson correlation coefficient formula can be used:

[0043]

[0044] In the above formula, r represents the correlation coefficient, and its value range is [-1,1]. The higher the correlation, the closer its corresponding correlation coefficient is to 1. i Indicates the base station transmission rate corresponding to different base station data, X represents the average base station transmission rate, Y i represents base station data, including base station load data and base station index data, Y represents the average value of base station data, n represents the number of base station data, when calculating the first correlation, r represents the correlation coefficient between the base station transmission rate and the base station load data, Yi represents the base station load data. When calculating the second correlation, r represents the correlation coefficient between the base station transmission rate and the base station index data. Y i The first correlation and the second correlation are determined according to the above formula.

[0045] In step S206 of the above-mentioned base station load conversion method, the characteristic values ​​required for constructing the objective function are determined based on the correlation, which specifically includes the following steps: obtaining a first threshold corresponding to the first correlation, and obtaining a second threshold corresponding to the second correlation; determining the base station load data corresponding to when the first correlation is greater than the first threshold as the target base station load data; determining the base station index data corresponding to when the second correlation is greater than the second threshold as the target base station index data; determining the characteristic values ​​required for the objective function based on the target base station load data and the target base station index data.

[0046] In an embodiment of the present application, when the first correlation is greater than the first threshold and the second correlation is greater than the second threshold, it can be considered that the corresponding base station load data and base station index data have a high correlation with the base station transmission frequency. For example, the first threshold can be set to 0.6 and the second threshold can be set to 0.7. It should be noted that the first threshold and the second threshold can be set to the same or different, and can be set according to actual conditions, and are not limited here. Based on the determined target base station load data and target base station index data, the characteristic values ​​required for the objective function are constructed.

[0047] In step S208 of the above-mentioned base station load conversion method, the objective function is iteratively tuned, specifically including the following steps: constructing a selection matrix based on the base station configuration data, wherein the base station configuration data at least includes the wireless standard, channel bandwidth and antenna configuration, and the selection matrix is ​​used to classify the base station data; determining a first matrix and a second matrix, wherein the first matrix is ​​determined by the base station transmission rate, and the second matrix is ​​determined by the target base station load data and the target base station index data; determining a third matrix based on the first matrix, the second matrix and the selection matrix, wherein the third matrix is ​​determined by characteristic parameters, which are parameters corresponding to the target base station load data and the target base station index data; iteratively tuning the objective function according to the gradient descent algorithm to obtain the load conversion parameters corresponding to the third matrix when the objective function takes the minimum value.

[0048] In an embodiment of the present application, a selection matrix E is introduced based on business needs for sample classification, which refers to the classification of base station data in the embodiment of the present application; based on the target base station load data and the target base station index data, the target base station load data and the target base station index data are selected as the target data with the highest correlation with the base station transmission rate. For example, the target data may be PRB utilization. A second matrix is ​​constructed based on the PRB utilization. Based on the gradient descent algorithm, the feature parameters are iteratively learned to obtain the optimal parameter combination (with the minimum loss function).

[0049] Specifically, the algorithm formula corresponding to the above process is: Y=TR(XBE), where TR represents the matrix diagonal value, the matrix Y is composed of the base station transmission rate, that is, the first matrix mentioned above, the matrix X is composed of the regression eigenvalues ​​(PRB utilization), the characteristic matrix B is composed of characteristic parameters, and the selection matrix E represents the sample classification based on configuration factors such as unrestricted, channel bandwidth and antenna configuration.

[0050] Assuming that the selection matrix E based on the base station configuration data divides the m base station data into α categories, the expressions of the matrices in Y=TR(XBE) are as follows:

[0051]

[0052]

[0053]

[0054]

[0055] In the above matrix, the values ​​in the E matrix are 1 or 0. Each column has only one value of 1, and the others are 0. 1 represents the category to which the data belongs. Based on the classified samples or data to be audited, the feature matrix B is calculated by reverse iteration.

[0056] Figure 3a The flowchart for iterative tuning of the model is shown in Figure 3a In the method, a selection matrix is ​​constructed according to the unrestricted type, channel bandwidth and antenna configuration in the base station configuration data. The regression algorithm is selected for modeling based on the base station configuration data. The formula used by the algorithm, namely Y=TR(XBE), is constructed according to the selected base station data and the selection matrix. The model is iteratively tuned through the gradient descent algorithm to output the final load conversion parameters.

[0057] In step S208 of the above-mentioned base station load conversion method, a load conversion model is determined based on the load conversion parameters, including: determining a base station rate model based on the load conversion parameters, wherein the base station rate model is used to represent the relationship between the base station transmission rate based on the base station configuration data and the base station load data; determining a load conversion model based on the base station rate model, wherein the load conversion model is used to represent the relationship between the base station configuration data and the base station load data.

[0058] In the embodiment of the present application, the table corresponding to the base station rate model is as follows:

[0059]

[0060]

[0061] In the above table, a and b are the values ​​in the load conversion parameters.

[0062] In the embodiment of the present application, a load conversion model under different equipment configurations is established according to the base station rate model. The table corresponding to the load conversion model is as follows:

[0063]

[0064] Figure 3b is a flow chart of establishing a wireless network base station load conversion model based on base station configuration according to an embodiment of the present application, such as Figure 3b As shown, step 301 is to collect and preprocess the power data of all base stations, specifically including cleaning and normalizing outliers, missing values, etc.; step 302 is to screen the relevant features of base station rate modeling, specifically through the Pearson correlation coefficient, to screen the modeling features; step 303 is to apply the regression algorithm based on the base station configuration data to select modeling and tuning, specifically including constructing a selection matrix, generating a model based on the regression algorithm, and tuning the model based on the gradient descent algorithm; step 304 is to establish a conversion model based on the base station configuration data and the base station load data.

[0065] The embodiment of the present application builds a load conversion model based on the selection regression algorithm of base station configuration data, and outputs the relationship between base station rate and load by constructing a sample selection matrix and sample classification modeling. The associated base station rate model is established under different equipment configurations. It has strong versatility and is adaptable to all equipment in the entire network. It also has the advantages of good accuracy and high efficiency, which solves the problems of traditional base station load conversion relying on expert experience evaluation, low efficiency and poor accuracy.

[0066] The following is an example of the contents in the embodiments of the present application:

[0067] The correlation between the base station transmission rate (RLC_BYTE) and various influencing factors is calculated through the Pearson correlation coefficient; see Figure 3c It can be seen that the resource utilization rate (PRB_RATE) has the highest correlation with the base station rate (RLC_BYTE), with a correlation coefficient of 0.8. Therefore, the resource utilization rate is selected as the modeling feature.

[0068] The following table shows the sample data after preprocessing, including:

[0069]

[0070]

[0071] The samples are divided into n categories based on the base station configuration data, and each matrix is ​​expressed as:

[0072]

[0073]

[0074]

[0075]

[0076] Based on Y=TR(XBE), the characteristic matrix B is calculated and the relationship between base station rate and load is established. As shown in the following table:

[0077]

[0078] Associate the base station rate model and establish the load conversion model under different base station configuration data, as shown in the following table:

[0079]

[0080] Example of using the load conversion table: Assuming that the 5G AAU load of the 5G-100M-8TR configuration is 10%, according to the above table, the 4G RRU load converted to the 4G-20M-2T2R configuration is 39%.

[0081] Figure 4 is a structural diagram of a base station load conversion device according to an embodiment of the present application, such as Figure 4 As shown, the device comprises:

[0082] An acquisition module 402 is used to acquire base station data related to the data transmission rate of the base station, wherein the base station data includes base station load data and base station index data;

[0083] A first determination module 404, configured to determine the correlation between the base station transmission rate and the base station data;

[0084] A second determination module 406 is used to determine the characteristic value required to construct the objective function according to the correlation, wherein the objective function is used to determine the relationship between the base station transmission rate and the base station load data;

[0085] The third determination module 408 is used to iteratively tune the objective function, determine the load conversion parameters, and determine the load conversion model according to the load conversion parameters.

[0086] In the acquisition module in the above-mentioned base station load conversion device, before acquiring the base station data related to the data transmission rate of the base station, the device also includes: a processing module 401, which is used to process the missing values ​​in the base station data, including: when the base station data is discrete data, using the mode of the discrete data to fill the data; when the base station data is continuous data, using the mean of the continuous data to fill the data. The above-mentioned processing module is also used to acquire the base station data related to the data transmission rate of the base station, including: processing the missing values ​​in the base station data, including: when the base station data is discrete data, using the mode of the discrete data to fill the data; when the base station data is continuous data, using the mean of the continuous data to fill the data.

[0087] In the first determination module in the above-mentioned base station load conversion device, the correlation between the base station transmission rate and the base station data is determined, which specifically includes the following processes: determining the first correlation between the base station transmission rate and the base station load data, wherein the first correlation is determined by the base station transmission rate, the average value of the base station transmission rate, the base station load data and the average value of the base station load data; determining the second correlation between the base station transmission rate and the base station index data, wherein the second correlation is determined by the base station transmission rate, the average value of the base station transmission rate, the base station index data and the average value of the base station index data.

[0088] In the second determination module in the above-mentioned base station load conversion device, the characteristic values ​​required for constructing the objective function are determined based on the correlation, which specifically includes the following processes: obtaining a first threshold corresponding to the first correlation, and obtaining a second threshold corresponding to the second correlation; determining the base station load data corresponding to when the first correlation is greater than the first threshold as the target base station load data; determining the base station index data corresponding to when the second correlation is greater than the second threshold as the target base station index data; determining the characteristic values ​​required for the objective function based on the target base station load data and the target base station index data.

[0089] In the third determination module in the above-mentioned base station load conversion device, the objective function is iteratively tuned, which specifically includes the following processes: constructing a selection matrix based on the base station configuration data, wherein the base station configuration data at least includes the wireless standard, channel bandwidth and antenna configuration, and the selection matrix is ​​used to classify the base station data; determining a first matrix and a second matrix, wherein the first matrix is ​​determined by the base station transmission rate, and the second matrix is ​​determined by the target base station load data and the target base station index data; determining a third matrix based on the first matrix, the second matrix and the selection matrix, wherein the third matrix is ​​determined by characteristic parameters, and the characteristic parameters are parameters corresponding to the target base station load data and the target base station index data; iteratively tuning the objective function according to the gradient descent algorithm to obtain the load conversion parameters corresponding to the third matrix when the objective function takes the minimum value.

[0090] In the third determination module in the above-mentioned base station load conversion device, a load conversion model is determined based on the load conversion parameters, which specifically includes the following processes: based on the load conversion parameters, a base station rate model is determined, wherein the base station rate model is used to represent the relationship between the base station transmission rate based on the base station configuration data and the base station load data; based on the base station rate model, a load conversion model is determined, wherein the load conversion model is used to represent the relationship between the base station configuration data and the base station load data.

[0091] It should be noted that Figure 4 The base station load conversion device shown is used to perform Figure 2 The base station load conversion method shown in the figure, therefore the relevant explanations in the above base station load conversion method are also applicable to the base station load conversion device, and will not be repeated here.

[0092] An embodiment of the present application also provides a non-volatile storage medium, which includes a stored program, wherein when the program is running, the device where the non-volatile storage medium is located is controlled to execute the following base station load conversion method: obtain base station data related to the data transmission rate of the base station, wherein the base station data includes base station load data and base station index data; determine the correlation between the base station transmission rate and the base station data; based on the correlation, determine the characteristic values ​​required to construct an objective function, wherein the objective function is used to determine the relationship between the base station transmission rate and the base station load data; iteratively tune the objective function to determine the load conversion parameters, and determine the load conversion model based on the load conversion parameters.

[0093] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0094] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0095] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0096] 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 units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0097] 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. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0098] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0099] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for converting base station load, characterized in that: include: Acquire base station data related to the data transmission rate of the base station, wherein the base station data includes base station load data and base station index data; Determining a correlation between a base station transmission rate and the base station data; Determining, based on the correlation, a characteristic value required for constructing an objective function, wherein the objective function is used to determine a relationship between the base station transmission rate and the base station load data; Iteratively tuning the objective function to determine load conversion parameters, and determining a load conversion model based on the load conversion parameters; Determining the characteristic values ​​required for constructing the objective function based on the correlation includes: obtaining a first threshold corresponding to the first correlation, and obtaining a second threshold corresponding to the second correlation; determining the base station load data corresponding to when the first correlation is greater than the first threshold as the target base station load data; determining the base station index data corresponding to when the second correlation is greater than the second threshold as the target base station index data; determining the characteristic values ​​required for the objective function based on the target base station load data and the target base station index data; Iteratively tuning the objective function includes: constructing a selection matrix based on base station configuration data, wherein the base station configuration data at least includes a wireless standard, a channel bandwidth, and an antenna configuration, and the selection matrix is ​​used to classify the base station data; determining a first matrix and a second matrix, wherein the first matrix is ​​determined by the base station transmission rate, the second matrix is ​​determined by the target base station load data and the target base station index data, and the second matrix is ​​the eigenvalue required by the objective function; determining a third matrix based on the first matrix, the second matrix, and the selection matrix, wherein the third matrix is ​​determined by characteristic parameters, and the characteristic parameters are parameters corresponding to the target base station load data and the target base station index data; iteratively tuning the objective function based on a gradient descent algorithm to obtain a load conversion parameter corresponding to the third matrix when the objective function takes a minimum value; Among them, the first matrix, the second matrix, the selection matrix and the third matrix satisfy the following formula: Y= TR(XBE) , Y represents the first matrix, X represents the second matrix, B represents the third matrix, E represents the selection matrix, TR Represents taking the matrix diagonal value.

2. The method according to claim 1, characterized in that Before acquiring base station data related to the data transmission rate of the base station, the method further includes: Processing missing values ​​in the base station data includes: when the base station data is discrete data, using the mode of the discrete data to perform data filling; when the base station data is continuous data, using the mean of the continuous data to perform data filling.

3. The method according to claim 1, characterized in that Before acquiring base station data related to the data transmission rate of the base station, the method further includes: Processing the outliers in the base station data includes: obtaining a first quantile and a second quantile, wherein the first quantile is smaller than the second quantile; filling the data in the base station data that is smaller than or equal to the first quantile with the data corresponding to the first quantile; filling the data in the base station data that is greater than or equal to the second quantile with the data corresponding to the second quantile; and filling the outliers in the base station data with base station data of the same type.

4. The method according to claim 1, characterized in that Determining the correlation between the base station transmission rate and the base station data includes: Determine a first correlation between the base station transmission rate and the base station load data, wherein the first correlation is determined by the base station transmission rate, an average value of the base station transmission rate, the base station load data, and an average value of the base station load data; A second correlation between the base station transmission rate and the base station indicator data is determined, wherein the second correlation is determined by the base station transmission rate, an average value of the base station transmission rate, the base station indicator data, and an average value of the base station indicator data.

5. The method according to claim 1, characterized in that Determining a load conversion model according to the load conversion parameters includes: Determining a base station rate model according to the load conversion parameter, wherein the base station rate model is used to represent the relationship between the base station transmission rate based on the base station configuration data and the base station load data; A load conversion model is determined based on the base station rate model, wherein the load conversion model is used to represent the relationship between the base station configuration data and the base station load data.

6. A base station load conversion device, characterized in that: include: An acquisition module, used to acquire base station data related to the data transmission rate of the base station, wherein the base station data includes base station load data and base station index data; A first determination module, used to determine the correlation between the base station transmission rate and the base station data; A second determination module is used to determine the characteristic value required to construct an objective function according to the correlation, wherein the objective function is used to determine the relationship between the base station transmission rate and the base station load data; A third determination module is used to iteratively tune the objective function to determine the load conversion parameters, and determine the load conversion model according to the load conversion parameters; The second determination module is further used to obtain a first threshold corresponding to the first correlation, and to obtain a second threshold corresponding to the second correlation; determine the base station load data corresponding to when the first correlation is greater than the first threshold as the target base station load data; determine the base station index data corresponding to when the second correlation is greater than the second threshold as the target base station index data; determine the characteristic value required by the objective function based on the target base station load data and the target base station index data; The third determination module is also used to construct a selection matrix based on base station configuration data, wherein the base station configuration data at least includes a wireless standard, a channel bandwidth and an antenna configuration, and the selection matrix is ​​used to classify the base station data; determine a first matrix and a second matrix, wherein the first matrix is ​​determined by the base station transmission rate, the second matrix is ​​determined by the target base station load data and the target base station index data, and the second matrix is ​​the eigenvalue required by the objective function; determine a third matrix based on the first matrix, the second matrix and the selection matrix, wherein the third matrix is ​​determined by characteristic parameters, and the characteristic parameters are parameters corresponding to the target base station load data and the target base station index data; iteratively tune the objective function according to the gradient descent algorithm to obtain the load conversion parameters corresponding to the third matrix when the objective function takes the minimum value; Among them, the first matrix, the second matrix, the selection matrix and the third matrix satisfy the following formula: Y= TR(XBE) , Y represents the first matrix, X represents the second matrix, B represents the third matrix, E represents the selection matrix, TR Represents taking the matrix diagonal value.

7. An electronic device, characterized in that: include: A memory for storing program instructions; A processor, connected to the memory, is used to execute program instructions to implement the following functions: obtain base station data related to the data transmission rate of the base station, wherein the base station data includes base station load data and base station index data; determine the correlation between the base station transmission rate and the base station data; determine the characteristic value required for constructing the objective function based on the correlation, wherein the objective function is used to determine the relationship between the base station transmission rate and the base station load data; iteratively tune the objective function to determine the load conversion parameter, and determine the load conversion model based on the load conversion parameter; determine the characteristic value required for constructing the objective function based on the correlation, including: obtaining a first threshold corresponding to a first correlation, and obtaining a second threshold corresponding to a second correlation; determining the base station load data corresponding to when the first correlation is greater than the first threshold as the target base station load data; determining the base station index data corresponding to when the second correlation is greater than the second threshold as the target base station index data; based on the target base station load data and the target base station index data , determine the eigenvalues ​​required for the objective function; iteratively tune the objective function, including: constructing a selection matrix based on base station configuration data, wherein the base station configuration data at least includes a wireless standard, a channel bandwidth, and an antenna configuration, and the selection matrix is ​​used to classify the base station data; determining a first matrix and a second matrix, wherein the first matrix is ​​determined by the base station transmission rate, the second matrix is ​​determined by the target base station load data and the target base station index data, and the second matrix is ​​the eigenvalue required for the objective function; determining a third matrix based on the first matrix, the second matrix, and the selection matrix, wherein the third matrix is ​​determined by characteristic parameters, and the characteristic parameters are parameters corresponding to the target base station load data and the target base station index data; iteratively tuning the objective function based on a gradient descent algorithm to obtain a load conversion parameter corresponding to the third matrix when the objective function takes a minimum value; wherein the first matrix, the second matrix, the selection matrix, and the third matrix satisfy the following formula: Y=TR(XBE) , Y represents the first matrix, X represents the second matrix, B represents the third matrix, E represents the selection matrix, TR Represents taking the matrix diagonal value.

8. A non-volatile storage medium, characterized in that: The non-volatile storage medium includes a stored program, wherein when the program is executed, the device where the non-volatile storage medium is located is controlled to execute the base station load conversion method described in any one of claims 1 to 5.

Images