Method and device for adjusting pitch angle of base station based on time sequence, and electronic equipment

Abstract

The invention discloses a method and a device for adjusting a pitch angle of a base station based on a time sequence, and electronic equipment. The method comprises the steps that a first data set of a first base station in a first time period is acquired, the network quality of the first base station is smaller than a preset threshold value, and the first data set comprises network performance parameters of the first base station; a target data set most similar to the first data set is determined from second data sets under each pitch angle in the multiple pitch angles, the second data sets are data sets obtained after data sets corresponding to second base stations are sequenced according to the time sequence, the number of the second base stations is multiple, and the network quality of the second base stations is larger than or equal to a preset threshold value; and adjusting the pitch angle of the first base station according to the target pitch angle corresponding to the target data set. The technical problem that the base station pitch angle optimization method in the related technology needs manual adjustment and cannot automatically adjust the base station pitch angle according to the network change is solved.

Description

Technical Field

[0001] The present application relates to the field of communications, and in particular to a method, device and electronic equipment for adjusting the elevation angle of a base station based on a time series. Background Art

[0002] In wireless network optimization, adjusting the base station pitch angle will directly affect the signal quality of the base station. A reasonable pitch angle can improve the user's call quality and Internet access rate, and effectively control the coverage of the base station. If the pitch angle is set improperly, the stability of calls and Internet access will be reduced, and problems such as disconnection and noise will occur during calls.

[0003] Due to the characteristics of the frequency band of the 5G network, the spacing between 5G base stations is closer than that of 3G and 4G base stations. The slight movement of the user group will change the coverage range of the base station, so the base station pitch angle needs to be adjusted synchronously, especially in scenes such as scenic spots and transportation hubs. When there are fewer users, the pitch angle needs to be raised to ensure signal coverage and diversion. When there are more users, the pitch angle needs to be lowered to ensure the network quality and stability of users near the base station. The optimization method of the base station pitch angle in the related technology requires manual adjustment, and it is impossible to automatically adjust the base station pitch angle according to network changes.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present application provide a method, device and electronic device for adjusting the base station pitch angle based on a time series, so as to at least solve the technical problem that the optimization method of the base station pitch angle in the related art requires manual adjustment and cannot automatically adjust the base station pitch angle according to network changes.

[0006] According to one aspect of an embodiment of the present application, a method for adjusting the elevation angle of a base station based on a time series is provided, comprising: obtaining a first data set of a first base station within a first time period, wherein the network quality of the first base station is less than a preset threshold, and the first data set includes network performance parameters of the first base station; determining a target data set that is most similar to the first data set from a second data set at each elevation angle of a plurality of elevation angles, wherein the second data set is a data set corresponding to a second base station sorted according to a time series, there are multiple second base stations, and the second base stations are base stations whose network quality is greater than or equal to the preset threshold; and adjusting the elevation angle of the first base station according to the target elevation angle corresponding to the target data set.

[0007] Optionally, the second data set at each elevation angle among multiple elevation angles is determined in the following manner: determine a first elevation angle, wherein the first elevation angle is any one of the multiple elevation angles; obtain an original data set of each second base station among multiple second base stations at the first elevation angle, wherein the data in the original data set includes at least one of the following: antenna height, number of user access, user access distance, base station load, and connection rate; perform dimensionality reduction processing on the original data set, and sort it according to time series to obtain a third data set; perform weighted processing on each data in the third data set to obtain a second data set of each second base station at the first elevation angle.

[0008] Optionally, the original data set is subjected to dimensionality reduction processing, including: standardizing the data in the original data set to obtain a standard data set; determining a covariance matrix corresponding to the standard data set, wherein the covariance matrix is ​​used to represent the linear relationship between the data in the standardized data set; determining the eigenvalues ​​and eigenvectors of the covariance matrix, wherein the eigenvalues ​​are used to represent the degree of variation of the data in the direction of the eigenvector; sorting the eigenvalues ​​in descending order, and selecting the eigenvectors corresponding to the first K eigenvalues ​​as principal components, wherein K is a positive integer; and projecting the data in the standard data set onto the principal components to obtain a fourth data set after dimensionality reduction.

[0009] Optionally, weighted processing is performed on each data in the third data set, including: determining the weight of each data in the third data set, and determining the observation value of each data in the third data set at different times, wherein the weight decreases from near to far in time series; and processing each data in the third data set based on the observation value and weight of each data in the third data set at different times.

[0010] Optionally, each data in the third data set is processed according to the observation value and weight of each data in the third data set at different times, including: weighted sum calculation of the observation value and weight of each data in the third data set at different times to obtain a first numerical value; obtaining a moving average window size; determining the weight sum of each data in the third data set within the moving average window size; and performing a quotient operation on the first numerical value and the weight sum.

[0011] Optionally, after obtaining the first data set of the first base station in the first time period, the method also includes: performing dimensionality reduction processing on the first data set and sorting it according to time series to obtain a fifth data set; performing weighted processing on each data in the fifth data set to obtain a sixth data set of the first base station in the first time period.

[0012] Optionally, determining a target data set that is most similar to the first data set from the second data set at each pitch angle among multiple pitch angles includes: performing difference calculations on each data in the second data set at each pitch angle and the data at the corresponding position in the sixth data set to obtain a first difference value set; squaring and summing each value in the first difference value set to obtain a first sum value; performing a square root operation on the first sum value to obtain a distance value set between the second data set at each pitch angle and the sixth data set; and determining the data set corresponding to the minimum value in the distance value set as the target data set that is most similar to the first data set.

[0013] According to another aspect of an embodiment of the present application, a device for adjusting the elevation angle of a base station based on a time series is also provided, including: an acquisition module, used to acquire a first data set of a first base station within a first time period, wherein the network quality of the first base station is less than a preset threshold, and the first data set includes network performance parameters of the first base station; a determination module, used to determine a target data set that is most similar to the first data set from a second data set at each elevation angle of a plurality of elevation angles, wherein the second data set is a data set corresponding to a second base station sorted according to a time series, there are multiple second base stations, and the second base stations are base stations whose network quality is greater than or equal to the preset threshold; an adjustment module, used to adjust the elevation angle of the first base station according to the target elevation angle corresponding to the target data set.

[0014] According to another aspect of the embodiments 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 a first data set of a first base station within a first time period, wherein the network quality of the first base station is less than a preset threshold, and the first data set includes network performance parameters of the first base station; determining a target data set that is most similar to the first data set from a second data set at each elevation angle of a plurality of elevation angles, wherein the second data set is a data set corresponding to a second base station sorted in time series, there are multiple second base stations, and the second base stations are base stations whose network quality is greater than or equal to the preset threshold; adjusting the elevation angle of the first base station according to the target elevation angle corresponding to the target data set.

[0015] According to another aspect of an embodiment of the present application, a non-volatile storage medium is also provided, which includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the above-mentioned time series-based base station pitch angle adjustment method by running the computer program.

[0016] According to another aspect of the embodiments of the present application, a computer program product is provided, including computer instructions, which, when executed by a processor, implement the above-mentioned method for adjusting the base station elevation angle based on time series.

[0017] In an embodiment of the present application, a first data set of a first base station in a first time period is obtained, wherein the network quality of the first base station is less than a preset threshold, and the first data set includes network performance parameters of the first base station; a target data set that is most similar to the first data set is determined from a second data set at each elevation angle of a plurality of elevation angles, wherein the second data set is a data set corresponding to a second base station sorted in time series, there are multiple second base stations, and the second base stations are base stations whose network quality is greater than or equal to a preset threshold; the elevation angle of the first base station is adjusted according to the target elevation angle corresponding to the target data set, thereby achieving the purpose of automatically optimizing the elevation angle of the base station, thereby achieving the technical effect of improving the efficiency of optimizing the network performance of the base station, and further solving the technical problem that the optimization method of the base station elevation angle in the related technology requires manual adjustment and cannot automatically adjust the base station elevation angle according to network changes. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] 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:

[0019] Figure 1 It is a hardware structure block diagram of a computer terminal for implementing a method for adjusting a base station elevation angle based on a time series according to an embodiment of the present application;

[0020] Figure 2 is a flow chart of a method for adjusting a base station elevation angle based on a time series according to an embodiment of the present application;

[0021] Figure 3 It is the data distribution map of good and poor network quality in the entire data set;

[0022] Figure 4 The distribution of each elevation angle area is obtained by adjusting the base station elevation angle based on the time series;

[0023] Figure 5 It is a structural diagram of a base station elevation angle adjustment device based on time series according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] 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.

[0025] 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.

[0026] First, some nouns or terms that appear in the process of explaining the embodiments of the present application are subject to the following explanations:

[0027] Base station pitch angle: refers to the angle between the antenna and the pole. Adjusting the base station pitch angle is an important part of network optimization. By adjusting the pitch angle through the remote system, the signal coverage and propagation effect of the antenna can be optimized, and the communication quality can be improved.

[0028] In the related technology, only when the number of access users or the user locations change significantly, resulting in a sudden drop or serious deterioration of the related network quality, is the base station elevation angle adjusted through manual analysis. This method cannot automatically adjust the base station elevation angle according to network changes, so there is a lag in the timely optimization of the current network quality.

[0029] In order to solve the problems existing in the related art, the embodiment of the present application provides a method for adjusting the base station pitch angle based on a time series, which can be run on Figure 1 In the computer terminal shown, the computer terminal is described below.

[0030] The method for adjusting the base station elevation angle based on time series 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 for implementing a method for adjusting the base station elevation angle based on a time series is shown. Figure 1As shown, the computer terminal 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 connected via a wired and / or wireless network. In addition, it may also include: a display, a keyboard, a cursor control device, 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, and a BUS bus. Those skilled in the art can understand 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 shown.

[0031] 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. 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).

[0032] 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 method for adjusting the base station elevation angle based on time series 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, the method for adjusting the base station elevation angle based on time series is realized. 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.

[0033] 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 module 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 module 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0034] 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 .

[0035] It should be noted that, in some optional embodiments, the above Figure 1 The computer terminal 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 computer terminal described above.

[0036] In the above-mentioned operating environment, an embodiment of the present application provides an embodiment of a method for adjusting the pitch angle of a base station based on a time series. 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.

[0037] Figure 2 is a flow chart of a method for adjusting the elevation angle of a base station based on a time series according to an embodiment of the present application, such as Figure 2 As shown, the method comprises the following steps:

[0038] Step S202: Acquire a first data set of a first base station in a first time period, wherein the network quality of the first base station is less than a preset threshold, and the first data set includes network performance parameters of the first base station.

[0039] In the above step S202, the selected first base station is a base station with poor network quality. For example, a base station with a network quality less than a preset threshold is determined as the first base station, and the first base station may be a 5G high-frequency base station. Network quality generally refers to the performance of the services provided by the base station in multiple aspects, including but not limited to signal strength, data transmission speed, delay, packet loss rate, etc. In an optional embodiment, when at least one of the above network quality data is less than the corresponding preset threshold, the network quality of the base station is determined to be poor. In another optional embodiment, when each of the above network quality data is less than the corresponding threshold, the network quality of the base station is determined to be poor. The first data set includes network performance parameters of the first base station, and the network performance parameters may include, for example, antenna height, number of user accesses, user access distance, base station load, connection rate, etc. The above first time period may be a time series, for example, 1 hour, half an hour, etc., by collecting the base station elevation angle data in the time series, and after data processing, the optimal elevation angle to be adjusted to the base station is determined by the model.

[0040] Step S204, determining a target data set that is most similar to the first data set from a second data set at each pitch angle among multiple pitch angles, wherein the second data set is a data set corresponding to a second base station sorted in time series, there are multiple second base stations, and the second base stations are base stations whose network quality is greater than or equal to a preset threshold.

[0041] In the above step S204, the elevation angle can represent different signal propagation paths or coverage areas, and the data set at each elevation angle reflects the specific performance of the base station network at that angle. In an embodiment of the present application, the multiple elevation angles may, for example, include elevation angles from -3° to 15°, and the step size may be 1°, including a total of 18 elevation angles. In other embodiments, the minimum value in the value range of the multiple pitch angles may be less than -3°, the maximum value in the value range may be greater than 15°, and the step size may be less than 1° or greater than 1°, which is not limited here.

[0042] In an embodiment of the present application, each second base station at each elevation angle corresponds to a second data set. When there are multiple second base stations, there are multiple second data sets. The second base station is a base station with excellent network quality. For example, a base station with a network quality greater than or equal to a preset threshold is determined as a second base station, and the second base station can be a 5G high-frequency base station. In an optional embodiment, when each of the above network quality data (such as signal strength, data transmission speed, delay, packet loss rate) is greater than or equal to a preset threshold, it is determined that the network quality of the base station is excellent and can be used as a second base station. By analyzing the second data set sorted in time series, the trend of base station network performance over time can be obtained, and the target data set that is most similar to the first data set can be determined, so that the pitch angle of the first base station is adjusted more accurately according to the target elevation angle corresponding to the target data set.

[0043] Step S206: adjusting the elevation angle of the first base station according to the target elevation angle corresponding to the target data set.

[0044] Through the above steps S202 to S206, the purpose of automatically optimizing the base station elevation angle is achieved, thereby achieving the technical effect of improving the efficiency of base station network performance optimization, and further solving the technical problem that the optimization method of the base station elevation angle in the related art requires manual adjustment and cannot automatically adjust the base station elevation angle according to network changes. The following is an explanation.

[0045] In step S204 of the above-mentioned time series-based base station elevation angle adjustment method, the second data set at each elevation angle of multiple elevation angles is determined in the following manner: determine a first elevation angle, wherein the first elevation angle is any one of the multiple elevation angles; obtain an original data set of each second base station among multiple second base stations at the first elevation angle, wherein the data in the original data set includes at least one of the following: antenna height, number of user access, user access distance, base station load, and connection rate; perform dimensionality reduction processing on the original data set, and then sort it according to the time series to obtain a third data set; perform weighted processing on each data in the third data set to obtain a second data set of each second base station at the first elevation angle.

[0046] In the above steps, the original data set is subjected to dimensionality reduction processing, including: standardizing the data in the original data set to obtain a standard data set; determining the covariance matrix corresponding to the standard data set, wherein the covariance matrix is ​​used to represent the linear relationship between the data in the standardized data set; determining the eigenvalues ​​and eigenvectors of the covariance matrix, wherein the eigenvalues ​​are used to represent the degree of variation of the data in the direction of the eigenvector; sorting the eigenvalues ​​in descending order, and selecting the eigenvectors corresponding to the first K eigenvalues ​​as principal components, wherein K is a positive integer; and projecting the data in the standard data set onto the principal components to obtain a fourth data set after dimensionality reduction.

[0047] In the above steps, weighted processing is performed on each data in the third data set, including: determining the weight of each data in the third data set, and determining the observation value of each data in the third data set at different times, wherein the weight decreases from near to far according to the time series; and processing each data in the third data set according to the observation value and weight of each data in the third data set at different times.

[0048] In the above steps, each data in the third data set is processed according to the observation value and weight of each data in the third data set at different times, including: weighted sum calculation of the observation value and weight of each data in the third data set at different times to obtain a first value; obtaining a moving average window size; determining the weight sum of each data in the third data set within the moving average window size; and performing a quotient operation on the first value and the weight sum.

[0049] In the embodiment of the present application, the first pitch angle may be, for example, any pitch angle between -3° and 15°. The above steps are explained below using the first pitch angle of -3° as an example. After obtaining the first pitch angle of -3°, an original data set of the second base station at the first pitch angle is selected. The data in the original data set may include, for example: antenna height, number of user accesses, user access distance, base station load, connection rate, etc., and {k1, k2, k3, ..., ka} may be used to represent the original data set.

[0050] After obtaining the original data set, since there are many types of data in the original data set and some of them are correlated, such as the correlation between the number of user accesses and the base station load, there is redundant information in the original data set, that is, the data overlaps or repeats when expressing certain features. Therefore, it is necessary to reduce the dimension of the original data set, for example, the principal component analysis (PCA) algorithm can be used for dimension reduction. By selecting the most important principal component of the repeated features and reducing the dimension of the data, while retaining most of the information in the original data, the amount of calculation can also be reduced. After the original data set is reduced in dimension, the fourth data set {x1, x2, x3, ..., xb} is generated.

[0051] Specifically, when using the PCA algorithm to reduce the dimensionality of the original data set, since PCA is sensitive to the scale of the data, and different features in the original data set (such as antenna height, number of user access, etc.) may have different units and magnitudes, it is usually necessary to first standardize the data in the original data set to convert it into a unified standard form. Standardization is usually achieved by subtracting the mean of each feature value and dividing it by the standard deviation to obtain a standard data set. The mean of the standardized data is 0 and the standard deviation is 1, which allows fair comparison between different features.

[0052] The covariance matrix is ​​an important statistic used to represent the linear relationship between the data in the standardized data set. Each element in the matrix is ​​the covariance between two variables. The covariance is used to measure whether the two variables change in the same direction or in the opposite direction during the change process, and the degree of change. For the standard data set, the covariance matrix reflects the correlation between different features. Eigenvalues ​​and eigenvectors are concepts in linear algebra, and they play a key role in matrix analysis and dimensionality reduction. The eigenvalue represents the degree of variation (or energy) of the data in the direction of the eigenvector, while the eigenvector is the direction with the largest variation in the data set. In dimensionality reduction, the eigenvalues ​​and eigenvectors of the covariance matrix are used to determine the main variation direction of the data. By sorting the eigenvalues, for example, in order from large to small, the most important variation direction in the data can be identified. Selecting the eigenvectors corresponding to the first K largest eigenvalues ​​as the principal components means that the information in the most important K directions in the data is retained, while other less important directions are ignored. The choice of K depends on the required degree of dimensionality reduction and the characteristics of the data. The last step is to project the standardized data onto the selected principal components. This can be achieved, for example, by calculating the projection length of the data in each principal component direction. The result of the projection is a new data set with a dimension of K (i.e., the number of principal components selected), which is much lower than the dimension of the original data. This reduced-dimensional data set (i.e., the fourth data set) retains the most critical information in the original data while reducing the complexity and computational cost of the data. The fourth data set can be represented by {x1, x2, x3, …, xk}.

[0053] After dimensionality reduction, sort by time series to obtain the third data set. For example, the fourth data set can be arranged in chronological order according to the hourly granularity to integrate into a time series data set, that is, the third data set mentioned above. The third data set is the data sequence of the second base station over a period of time, and then weighted calculation is performed using the weighted moving average method, so that the weights of recent observations are larger and the weights of long-term observations are smaller. In this way, the time series data (that is, the second data set mentioned above) of the changing characteristics of the relevant data of the second base station with excellent network quality can be obtained according to the importance of time granularity. The formula is as follows:

[0054]

[0055] Among them, x1 t is the observed value of data x1 in the third data set at time t, w i Yes x1 t-i+1 The corresponding weight, n is the window size of the moving average, that is, how many data points in the past are considered to calculate the average value, and the obtained Y1 t+1 It is represented by the best characteristic data of the second base station with good network quality in the recent period of time, which can be represented by Y1, that is, the data in the second data set. t +w2x1 t-1 +…+w n x1 t-n+1 represents the first value, w1+w2+…+w n represents the above weight sum.

[0056] Similarly, the variation characteristics of other data in the second data set can be obtained. The second data set obtained by the second base station at an elevation angle of -3° can be expressed as Y(-3)={Y1, Y2, Y3, ..., Yk}.

[0057] By repeating the above steps, other second data sets corresponding to the second base station at multiple elevation angles can be obtained. For example, Y(-2), Y(-1), Y..., Y(15) can be obtained through the above process.

[0058] The data of important features are selected from the above-obtained data sets, and brought into the training set, test set and validation set. The important features are weighted in combination with the base station elevation angle and expert experience, and the bagging model is used for training. By adjusting the values ​​of the data set, the overfitting phenomenon is reduced and the model availability is improved, thereby obtaining the target model for prediction. For example, for a training set of m samples, it is divided into m sample sampling sets 1, m sample sampling sets 2, ..., m sample sampling sets T by random sampling. Each sampling set is used to train a weak learner. When there are T sampling sets and T weak learners, the T weak learners are combined into a strong learner through a combination strategy to better predict the optimal elevation angle of the base station.

[0059] By building a system that automatically learns the elevation angles and data change characteristics of base stations with good network quality, and generates a network model at each elevation angle, for base stations with poor network quality, by analyzing relevant feature data, the recommended base station elevation angle is generated through the network model and automatically adjusted by the system to solve the current problem that the base station elevation angle optimization has a lag and requires manual adjustment.

[0060] In step S202 of the above-mentioned method for adjusting the base station elevation angle based on time series, after obtaining the first data set of the first base station in the first time period, the method also includes: performing dimensionality reduction processing on the first data set and sorting it according to the time series to obtain a fifth data set; performing weighted processing on each data in the fifth data set to obtain a sixth data set of the first base station in the first time period.

[0061] In the embodiment of the present application, the dimension reduction and weighted processing method of the first data set corresponding to the first base station is the same as the dimension reduction processing method of the original data set of the second base station, which will not be repeated here.

[0062] In step S204 of the above-mentioned time series-based method for adjusting the base station elevation angle, a target data set that is most similar to the first data set is determined from the second data set at each elevation angle among the multiple elevation angles, including: performing difference calculations on each data in the second data set at each elevation angle and the data at the corresponding position in the sixth data set to obtain a first difference value set; performing square operations on each value in the first difference value set and summing them to obtain a first sum value; performing square root operations on the first sum value to obtain a distance value set between the second data set at each elevation angle and the sixth data set; and determining the data set corresponding to the minimum value in the distance value set as the target data set that is most similar to the first data set.

[0063] In an embodiment of the present application, the first data set is subjected to dimensionality reduction and weighting processing to obtain a sixth data set, and the sixth data set can be represented by Z = {Z1, Z2, Z3, ..., Zk}. For each second data set, for example, taking the second data set as Y(-3) = {Y1, Y2, Y3, ..., Yk} as an example, a difference is calculated between each data in the second data set and the data at the corresponding position in the sixth data set to obtain a first difference value set; each value in the first difference set is squared and summed to obtain a first sum value; the first sum value is squared to obtain a distance value set between the second data set and the sixth data set at each pitch angle. Specifically, any distance value in the distance value set can be calculated by the following formula:

[0064]

[0065] Among them, L(x, y) is the Euclidean distance calculation method in KNN, and L(x, y) represents any distance value in the distance value set. After calculating the distance values ​​of the data in all the second data sets with the data in the sixth data set according to the above formula, a distance value set can be obtained, and the second data set corresponding to the minimum value in the distance value set is determined as the target data set, and the elevation angle of the first base station is adjusted according to the elevation angle corresponding to the target data set.

[0066] Figure 3is the data distribution diagram of good and poor network quality in the entire data set, Figure 4 The distribution of each pitch angle area is obtained through the adjustment method of the base station pitch angle based on time series. The closest distance of each difference point can be determined by the Euclidean distance formula under the KNN model. The model has high accuracy because it can divide the data more accurately in real time. For base stations with poor network quality, the recommended adjustment value is sent to the system based on the recommended pitch angle information generated by the system, and the system completes the automatic adjustment.

[0067] Figure 5 is a structural diagram of a base station elevation angle adjustment device based on time series according to an embodiment of the present application, such as Figure 5 As shown, the device comprises:

[0068] An acquisition module 30 is configured to acquire a first data set of a first base station in a first time period, wherein the network quality of the first base station is less than a preset threshold, and the first data set includes a network performance parameter of the first base station;

[0069] A determination module 32 is used to determine a target data set that is most similar to the first data set from a second data set at each pitch angle of the multiple pitch angles, wherein the second data set is a data set corresponding to a second base station sorted in time series, there are multiple second base stations, and the second base stations are base stations whose network quality is greater than or equal to a preset threshold;

[0070] The adjustment module 34 is configured to adjust the elevation angle of the first base station according to the target elevation angle corresponding to the target data set.

[0071] In the determination module in the above-mentioned time series-based base station elevation angle adjustment device, the determination module is also used to determine a second data set at each of the multiple elevation angles. Specifically, the second data set at each of the multiple elevation angles is determined in the following manner: determine a first elevation angle, wherein the first elevation angle is any one of the multiple elevation angles; obtain an original data set of each second base station among the multiple second base stations at the first elevation angle, wherein the data in the original data set includes at least one of the following: antenna height, number of user access, user access distance, base station load, and connection rate; perform dimensionality reduction processing on the original data set, and sort it according to the time series to obtain a third data set; perform weighted processing on each data in the third data set to obtain a second data set of each second base station at the first elevation angle.

[0072] In the determination module in the above-mentioned time series-based base station pitch angle adjustment device, the determination module is also used to standardize the data in the original data set to obtain a standard data set; determine the covariance matrix corresponding to the standard data set, wherein the covariance matrix is ​​used to represent the linear relationship between the data in the standardized data set; determine the eigenvalues ​​and eigenvectors of the covariance matrix, wherein the eigenvalues ​​are used to represent the degree of variation of the data in the direction of the eigenvector; sort the eigenvalues ​​in descending order, and select the eigenvectors corresponding to the first K eigenvalues ​​as principal components, wherein K is a positive integer; and project the data in the standard data set onto the principal components to obtain a fourth data set after dimensionality reduction.

[0073] In the determination module in the above-mentioned time series-based base station pitch angle adjustment device, the determination module is also used to determine the weight of each data in the third data set, and to determine the observation value of each data in the third data set at different times, wherein the weight decreases from near to far according to the time series; and each data in the third data set is processed according to the observation value and weight of each data in the third data set at different times.

[0074] In the determination module in the above-mentioned time series-based base station pitch angle adjustment device, the determination module is also used to perform weighted sum calculation on the observation value and weight of each data in the third data set at different times to obtain a first numerical value; obtain the moving average window size; determine the weight sum of each data in the third data set within the moving average window size; and perform a quotient operation on the first numerical value and the weight sum.

[0075] In the acquisition module in the above-mentioned time series-based base station pitch angle adjustment device, the acquisition module is also used to perform dimensionality reduction processing on the first data set and sort it according to the time series to obtain the fifth data set; perform weighted processing on each data in the fifth data set to obtain the sixth data set of the first base station in the first time period.

[0076] In the determination module in the above-mentioned time series-based base station pitch angle adjustment device, the determination module is also used to perform difference calculation on each data in the second data set at each pitch angle and the data at the corresponding position in the sixth data set to obtain a first difference set; square each value in the first difference set and sum them to obtain a first sum value; perform square root operation on the first sum value to obtain a distance value set between the second data set at each pitch angle and the sixth data set; and determine the data set corresponding to the minimum value in the distance value set as the target data set that is most similar to the first data set.

[0077] Through the acquisition module 30, determination module 32, and adjustment module 34 in the above-mentioned time series-based base station pitch angle adjustment device, the purpose of automatically optimizing the base station pitch angle is achieved, thereby achieving the technical effect of improving the efficiency of base station network performance optimization, and further solving the technical problem that the optimization method of the base station pitch angle in the related technology requires manual adjustment and cannot automatically adjust the base station pitch angle according to network changes.

[0078] It should be noted that Figure 5 The time series-based base station elevation angle adjustment device is used to perform Figure 2 The method for adjusting the base station pitch angle based on a time series is shown, so the relevant explanations in the above method for adjusting the base station pitch angle based on a time series are also applicable to the device for adjusting the base station pitch angle based on a time series, and will not be repeated here.

[0079] An embodiment of the present application also provides an electronic device, which includes a memory and a processor, wherein the memory is used to store program instructions; the processor is connected to the memory, and is used to execute program instructions to implement the following functions: obtaining a first data set of a first base station in a first time period, wherein the network quality of the first base station is less than a preset threshold, and the first data set includes network performance parameters of the first base station; determining a target data set that is most similar to the first data set from a second data set at each elevation angle of multiple elevation angles, wherein the second data set is a data set corresponding to a second base station sorted in time series, there are multiple second base stations, and the second base stations are base stations whose network quality is greater than or equal to the preset threshold; adjusting the elevation angle of the first base station according to the target elevation angle corresponding to the target data set.

[0080] It should be noted that the above electronic equipment is used to execute Figure 2 The method for adjusting the base station pitch angle based on a time series is shown, so the relevant explanations in the above method for adjusting the base station pitch angle based on a time series are also applicable to the electronic device and will not be repeated here.

[0081] An embodiment of the present application also provides a non-volatile storage medium, which includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the following time series-based base station elevation angle adjustment method by running the computer program: obtaining a first data set of a first base station in a first time period, wherein the network quality of the first base station is less than a preset threshold, and the first data set includes network performance parameters of the first base station; determining a target data set that is most similar to the first data set from a second data set at each elevation angle of a plurality of elevation angles, wherein the second data set is a data set corresponding to a second base station sorted according to a time series, there are multiple second base stations, and the second base stations are base stations whose network quality is greater than or equal to the preset threshold; adjusting the elevation angle of the first base station according to the target elevation angle corresponding to the target data set.

[0082] It should be noted that the above non-volatile storage medium is used to execute Figure 2 The method for adjusting the base station pitch angle based on a time series is shown, so the relevant explanations in the above method for adjusting the base station pitch angle based on a time series are also applicable to the non-volatile storage medium, and will not be repeated here.

[0083] An embodiment of the present application also provides a computer program product, including computer instructions, which, when executed by a processor, implement the steps of the method for adjusting the base station elevation angle based on time series in each embodiment of the present application.

[0084] An embodiment of the present application further provides a computer program, which, when executed by a processor, implements the steps of the method for adjusting the base station elevation angle based on time series in each embodiment of the present application.

[0085] 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.

[0086] 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.

[0087] 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.

[0088] 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.

[0089] 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.

[0090] 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.

[0091] 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 adjusting the elevation angle of a base station based on a time series, characterized in that: include: Acquire a first data set of a first base station in a first time period, wherein the network quality of the first base station is less than a preset threshold, and the first data set includes a network performance parameter of the first base station; Determine a target data set that is most similar to the first data set from a second data set at each pitch angle among multiple pitch angles, wherein the second data set is a data set obtained by sorting data sets corresponding to a second base station in time series, there are multiple second base stations, and the second base stations are base stations whose network quality is greater than or equal to the preset threshold; The elevation angle of the first base station is adjusted according to the target elevation angle corresponding to the target data set.

2. The method according to claim 1, characterized in that The second data set at each of the plurality of elevation angles is determined by: Determine a first pitch angle, wherein the first pitch angle is any one of the multiple pitch angles; Acquire an original data set of each second base station in a plurality of second base stations at the first elevation angle, wherein the data in the original data set includes at least one of the following: antenna height, number of user accesses, user access distance, base station load, and connection rate; After performing dimensionality reduction processing on the original data set, the data set is sorted according to time series to obtain a third data set; Weighted processing is performed on each data in the third data set to obtain a second data set of each second base station at the first elevation angle.

3. The method according to claim 2, characterized in that Performing dimensionality reduction processing on the original data set includes: Standardizing the data in the original data set to obtain a standard data set; Determine a covariance matrix corresponding to the standard data set, wherein the covariance matrix is ​​used to represent the linear relationship between each data in the standardized data set; Determining the eigenvalues ​​and eigenvectors of the covariance matrix, wherein the eigenvalues ​​are used to represent the degree of variation of the data in the direction of the eigenvector; Sort the eigenvalues ​​in descending order, and select the eigenvectors corresponding to the first K eigenvalues ​​as principal components, where K is a positive integer; The data in the standard data set is projected onto the principal component to obtain a fourth data set after dimensionality reduction.

4. The method according to claim 2, characterized in that Performing weighted processing on each data in the third data set includes: Determine the weight of each data in the third data set, and determine the observation value of each data in the third data set at different times, wherein the weight decreases from near to far in time series; Each data in the third data set is processed according to the observation value and weight of each data in the third data set at different times.

5. The method according to claim 4, characterized in that Processing each data in the third data set according to the observation value and weight of each data in the third data set at different times, including: Performing weighted sum calculation on the observed value and weight of each data in the third data set at different times to obtain a first value; Get the moving average window size; Determine the sum of the weights of each data in the third data set within the moving average window size; A quotient operation is performed on the first value and the weight sum.

6. The method according to claim 1, characterized in that After acquiring the first data set of the first base station in the first time period, the method further includes: Performing dimensionality reduction processing on the first data set and sorting the data according to time series to obtain a fifth data set; Weighted processing is performed on each data in the fifth data set to obtain a sixth data set of the first base station in the first time period.

7. The method according to claim 6, characterized in that Determining a target data set that is most similar to the first data set from a second data set at each pitch angle of a plurality of pitch angles includes: Performing difference calculation on each data in the second data set at each pitch angle and the data at the corresponding position in the sixth data set to obtain a first difference set; Square each value in the first difference value set and sum them to obtain a first sum value; Performing a square root operation on the first sum value to obtain a distance value set between the second data set and the sixth data set at each pitch angle; The data set corresponding to the minimum value in the distance value set is determined as the target data set most similar to the first data set.

8. A device for adjusting the pitch angle of a base station based on a time series, characterized in that: include: An acquisition module, configured to acquire a first data set of a first base station in a first time period, wherein the network quality of the first base station is less than a preset threshold, and the first data set includes a network performance parameter of the first base station; a determination module, configured to determine a target data set that is most similar to the first data set from a second data set at each pitch angle among multiple pitch angles, wherein the second data set is a data set corresponding to a second base station sorted in time series, there are multiple second base stations, and the second base stations are base stations whose network quality is greater than or equal to the preset threshold; An adjustment module is used to adjust the elevation angle of the first base station according to the target elevation angle corresponding to the target data set.

9. 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: obtaining a first data set of a first base station in a first time period, wherein the network quality of the first base station is less than a preset threshold, and the first data set includes network performance parameters of the first base station; determining a target data set that is most similar to the first data set from a second data set at each elevation angle of a plurality of elevation angles, wherein the second data set is a data set corresponding to a second base station sorted in time series, there are multiple second base stations, and the second base stations are base stations whose network quality is greater than or equal to the preset threshold; and adjusting the elevation angle of the first base station according to the target elevation angle corresponding to the target data set.

10. A non-volatile storage medium, characterized in that: The non-volatile storage medium includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the method for adjusting the base station elevation angle based on time series as described in any one of claims 1 to 7 by running the computer program.

11. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by the processor, the method for adjusting the base station elevation angle based on time series described in any one of claims 1 to 7 is implemented.

Images