Method and system for adjusting power of base station, computer equipment and readable storage medium

Abstract

The invention discloses a method and a system for adjusting power of a base station, computer equipment and a readable storage medium, and relates to the technical field of communication. The method for adjusting the power of the base station comprises the following steps: acquiring a user traffic predicted value; and determining the current coverage radius of the base station. And determining target power according to the user flow predicted value and the current coverage radius of the base station. And adjusting the transmitting power of the base station to the target power. In the invention, the base station can dynamically adjust the transmitting power based on the predicted value of the user traffic of the base station and the current coverage radius of the base station, thereby optimizing signal coverage and network performance. Flexible response to user requirements is realized from data collection, model establishment, real-time monitoring, power adjustment and feedback optimization.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a method for adjusting base station power, a system for adjusting base station power, a computer device and a readable storage medium. Background Art

[0002] Wireless signal propagation is affected by many factors such as terrain, buildings and climate, so base stations need to dynamically adjust the transmission power according to the actual situation to ensure signal coverage and quality. It is precisely because of the complexity of the wireless communication environment, the scarcity of spectrum resources, the need for energy saving and the impact of network optimization on user experience that adjusting base station power has become an important technical means in the field of mobile communications.

[0003] In addition, as the demand for mobile communications grows, proper power control can reduce signal interference, improve spectrum utilization, and reduce energy consumption, thereby reducing operating costs.

[0004] Currently, methods for adjusting base station power include: methods for adjusting base station power based on information feedback of channel status and methods for power control by collaboration of multiple base stations. Methods for adjusting base station transmit power based on information feedback of channel status, i.e., base stations use channel state information (CSI) fed back by users to adjust base station transmit power, which can better cope with multipath propagation and rapid fading. Methods for power control by collaboration of multiple base stations, i.e., multiple base stations coordinate with each other to adjust their respective transmit powers according to the interference between each other, so as to optimize the overall network.

[0005] The above method for adjusting the base station power is to adjust the power according to the specific situation of each user or according to the situation of the base station. The purpose is to ensure that the user signal strength is good or the base station interference is small. The goal is relatively single and not flexible enough. Summary of the invention

[0006] The technical problem to be solved by the present invention is that the method for adjusting the base station power in the prior art is to adjust the power according to the specific situation of each user or according to the situation of the base station, the purpose of which is to ensure that the user signal strength is good or the base station interference is small, the goal is relatively single and not flexible enough.

[0007] In view of the above-mentioned deficiencies of the prior art, the following solutions are provided:

[0008] In a first aspect, the present invention provides a method for adjusting base station power, the method for adjusting base station power comprising: obtaining a user traffic prediction value, determining a current coverage radius of the base station, determining a target power according to the user traffic prediction value and the current coverage radius of the base station, and adjusting the transmission power of the base station to the target power.

[0009] Optionally, obtaining the user traffic prediction value includes: obtaining user traffic data of the base station in a recent first preset time period. And, obtaining a predicted value of user traffic of the base station in a future second preset time period based on the user traffic data of the base station in the recent first preset time period and a user traffic prediction model. The user traffic prediction model is obtained based on historical user traffic data of the base station and a neural network algorithm.

[0010] Optionally, the method for adjusting the base station power further includes: obtaining historical user traffic data of the base station, performing data cleaning and preprocessing on the historical user traffic data of the base station to obtain preprocessed historical data, and obtaining a user traffic prediction model based on the preprocessed historical data and a neural network algorithm.

[0011] Optionally, obtaining a user traffic prediction model based on the preprocessed historical data and the neural network algorithm includes: preparing a training set and a test set based on the preprocessed historical data. Constructing a long short-term memory network LSTM model. Training the LSTM model based on the training set to obtain a trained LSTM model. And, evaluating the trained LSTM model based on the test set, and adjusting the model parameters of the trained LSTM model based on the evaluation results to obtain a user traffic prediction model.

[0012] Optionally, determining the current coverage radius of the base station includes: obtaining measurement report data from at least one sampling point. Determining at least one first sampling point according to the measurement report data from at least one sampling point. Obtaining the timing advance parameter TA value of each first sampling point in the at least one first sampling point respectively. Determining the distance between the base station and each first sampling point in the at least one first sampling point according to the TA value of each first sampling point in the at least one first sampling point and the distance coefficient corresponding to each first sampling point in the at least one first sampling point respectively. And, determining the current coverage radius of the base station according to the distance between the base station and each first sampling point in the at least one first sampling point. Wherein, at least one sampling point comes from at least one terminal under the base station. The reference signal received power of the first sampling point is within a first preset range. The distance coefficient corresponding to each first sampling point in the at least one first sampling point is obtained from a network specification.

[0013] Optionally, determining the current coverage radius of the base station according to the distance between the base station and each of the at least one first sampling point includes: determining the current coverage radius of the base station according to the distance between the base station and each of the at least one first sampling point. Calculate the current coverage radius R of the base station i . Where i is the number of the base station, N is the total number of the first sampling points in the at least one first sampling point, and d n is the distance between the base station and the nth first sampling point in the at least one first sampling point, d n=TA n ×ζ n TA n is the TA value of the nth first sampling point in at least one first sampling point, ζ n is a distance coefficient corresponding to the nth first sampling point in the at least one first sampling point, where n is a positive integer and the value range of n is 1≤n≤N.

[0014] Optionally, the target power is determined according to the user traffic prediction value and the current coverage radius of the base station, including: obtaining the current transmit power of the base station, the maximum transmit power of the base station, the minimum transmit power of the base station, the user traffic threshold of the base station, and the target coverage radius of the base station. The power adjustment reference value of the base station is determined according to the current transmit power of the base station, the user traffic threshold of the base station, the user traffic prediction value, the target coverage radius of the base station, and the current coverage radius of the base station. The value range of the target power is determined according to the power adjustment reference value, the maximum transmit power of the base station, and the minimum transmit power of the base station. And, the target power is determined according to the value range of the target power. Among them, the user traffic threshold is obtained according to the user traffic historical data of the base station. The target coverage radius of the base station is preset. The target power is the maximum value in the value range of the target power.

[0015] Optionally, determining the power adjustment reference value of the base station according to the current transmission power of the base station, the user flow threshold of the base station, the user flow prediction value, the target coverage radius of the base station and the current coverage radius of the base station includes: Calculate the power adjustment reference value P of the base station i '. Where i is the number of the base station, P i0 is the current transmission power of the base station, β1 and β2 are weight coefficients, T is the user flow threshold of the base station, and F i (t) is the predicted value of user traffic, R ta is the target coverage radius of the base station, R i is the current coverage radius of the base station.

[0016] Optionally, determining a target power value range according to the power adjustment reference value, the maximum transmit power of the base station, and the minimum transmit power of the base station includes: taking integer values ​​for m in the multiple value range, and according to P mi =P i '+m×Δp calculates multiple power adjustment values ​​P mi .according to Calculate multiple power optimization values ​​Z mi And, the target power value range is determined according to the multiple power optimization values, the maximum transmission power of the base station and the minimum transmission power of the base station. Where i is the number of the base station, P i' is the power adjustment reference value, Δp is the preset power increment, m is the increment multiple, m is an integer multiple ranging from [M1, M2], M1 and M2 are both integers, and M1 is the maximum value of the increment multiple m, and M2 is the minimum value of the increment multiple m. J is the total number of users currently served by the base station, C mij The power regulation value is P mi The signal strength of the base station to the jth user under the condition of G ij is the gain factor from the base station to the jth user, d ij is the distance between the base station and the jth user, and γ is the path loss exponent. is the interference weight coefficient. K is the total number of neighboring base stations of the base station. Interference(mi,k) is the power adjustment value P mi The interference between the base station and the kth neighboring base station in the case of G ki is the gain factor from the kth neighboring base station to the base station, d ik is the distance between the base station and its kth neighboring base station, F Inter The value range of the target power includes at least one power optimization value between the maximum transmission power of the base station and the minimum transmission power of the base station among the multiple power optimization values.

[0017] In a second aspect, the present invention provides a system for adjusting base station power, the system for adjusting base station power includes a user traffic prediction value acquisition module, a current radius determination module, a target power determination module and a power adjustment module. Among them, the user traffic prediction value acquisition module is configured to: obtain a user traffic prediction value. The current radius determination module is configured to: determine the current coverage radius of the base station. The target power determination module is configured to: determine the target power according to the user traffic prediction value and the current coverage radius of the base station. The power adjustment module is configured to: adjust the transmission power of the base station to the target power.

[0018] In a third aspect, the present invention provides a computer device, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor runs the computer program stored in the memory, the processor executes the above-mentioned method for adjusting base station power.

[0019] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the processor executes the above-mentioned method for adjusting base station power.

[0020] The method, system, computer device and readable storage medium for adjusting base station power provided by the present invention enable the base station to dynamically adjust the transmission power based on the predicted value of the base station user traffic and the current coverage radius of the base station, thereby optimizing signal coverage and network performance. From data collection to model building, real-time monitoring, to power adjustment and feedback optimization, a flexible response to user needs is achieved. Dynamic power adjustment can also improve user experience, especially in areas with high user density, where dynamic power adjustment can ensure that call quality does not decline due to insufficient signals. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A flow chart of a method for adjusting base station power in an embodiment of the present invention;

[0022] Figure 2 A flowchart of another method for adjusting base station power in an embodiment of the present invention;

[0023] Figure 3 A flowchart of another method for adjusting base station power in an embodiment of the present invention;

[0024] Figure 4 A flowchart of another method for adjusting base station power in an embodiment of the present invention;

[0025] Figure 5 A flowchart of another method for adjusting base station power in an embodiment of the present invention;

[0026] Figure 6 A flowchart of another method for adjusting base station power in an embodiment of the present invention;

[0027] Figure 7 A flowchart of another method for adjusting base station power in an embodiment of the present invention;

[0028] Figure 8 A flowchart of a method for adjusting base station power in an example of an embodiment of the present invention;

[0029] Fig. 9 A structural diagram of a system for adjusting base station power in an embodiment of the present invention;

[0030] Fig.10 A structural diagram of another system for adjusting base station power in an embodiment of the present invention;

[0031] Fig.11 The structure diagram of another system for adjusting base station power in an embodiment of the present invention. DETAILED DESCRIPTION

[0032] In order to enable those skilled in the art to better understand the technical solution of the present invention, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0033] It should be understood that the specific embodiments and drawings described herein are only used to explain the present invention rather than to limit the present invention.

[0034] It can be understood that, in the absence of conflict, the various embodiments of the present invention and the various features in the embodiments can be combined with each other.

[0035] It can be understood that, for the convenience of description, the drawings of the present invention only show the parts related to the present invention, while the parts irrelevant to the present invention are not shown in the drawings.

[0036] It can be understood that each unit or module involved in the embodiments of the present invention may correspond to only one physical structure, or may be composed of multiple physical structures, or multiple units or modules may be integrated into one physical structure.

[0037] It can be understood that, without conflict, the functions and steps marked in the flowcharts and block diagrams of the present invention may occur in an order different from that marked in the drawings.

[0038] It is understood that the flowcharts and block diagrams of the present invention illustrate the possible architectures, functions, and operations of the systems, devices, equipment, and methods according to the various embodiments of the present invention. Each box in the flowchart or block diagram may represent a unit, module, program segment, or code, which contains executable instructions for implementing the specified functions. Moreover, each box or combination of boxes in the block diagram and flowchart may be implemented by a hardware-based system that implements the specified functions, or may be implemented by a combination of hardware and computer instructions.

[0039] It can be understood that the units and modules involved in the embodiments of the present invention can be implemented by software or hardware. For example, the units and modules can be located in a processor.

[0040] An embodiment of the present invention provides a method for adjusting base station power, such as Figure 1 As shown, the method for adjusting base station power includes steps 101 to 104.

[0041] Step 101: Obtain user traffic prediction value.

[0042] Exemplarily, methods for obtaining a user traffic prediction value of a base station may include prediction methods based on historical data (e.g., time series analysis method, moving average method), prediction methods based on machine learning and deep learning (e.g., linear regression, artificial neural network, Transformer model), prediction methods based on scenario analysis (e.g., methods based on regional feature analysis, methods based on activity and event driven), and prediction methods based on scenario analysis (e.g., methods based on network topology analysis and methods for modeling user behavior).

[0043] In some embodiments, Figure 2 As shown, the implementation method of step 101 includes step 201 and step 202.

[0044] Step 201: Obtain user traffic data of a base station in a recent first preset time period.

[0045] It can be understood that the length of the first preset time period can be set according to the specific application scenario. For example, the first preset time period can be one week, one month or several months.

[0046] Exemplarily, the user traffic data of the base station in the most recent first preset time period includes data such as the number of access users per hour and data usage of the base station in the most recent first preset time period. The time characteristics of the data (e.g., date, day of the week, holidays, etc.) can be recorded to capture the periodic fluctuations of user traffic.

[0047] Step 202: Obtain a predicted value of user traffic of the base station in a future second preset time period based on user traffic data of the base station in a recent first preset time period and a user traffic prediction model.

[0048] In step 202, the user traffic prediction model is obtained based on the user traffic history data of the base station and the neural network algorithm.

[0049] It can be understood that the user traffic data in the most recent first preset time period is used as input to predict the user traffic of the base station in the future second preset time period. The prediction result is obtained each time and can be used as input data for the next prediction. Through this cycle, multi-step prediction can be achieved.

[0050] In some embodiments, Figure 3 As shown, the method for adjusting base station power also includes steps 301 to 303.

[0051] Step 301: Obtain user traffic history data of a base station.

[0052] It can be understood that in step 301, when the historical data of the user traffic of the base station covers a large span (for example, several months), it can be convenient for the subsequent model to learn the periodicity and trend.

[0053] Step 302: Clean and preprocess the user traffic history data of the base station to obtain preprocessed history data.

[0054] It can be understood that step 302 can check whether there are missing values ​​and abnormal values ​​in the user traffic history data of the base station. For missing values, you can choose to interpolate to fill or delete the missing part. Arrange the data in chronological order to ensure that the timestamps are aligned. Normalize or standardize the traffic data so that the model can learn better. For example, the user traffic history data of the base station can be normalized by formula (1) to scale the user traffic history data of the base station to the interval [0, 1].

[0055]

[0056] In formula (1), X is the historical traffic data of a user of the base station, X nor is the normalized historical data of user traffic of a certain base station, X max is the maximum value in the historical data of user traffic of the base station, X min It is the minimum value in the historical user traffic data of the base station.

[0057] Step 303: Obtain a user traffic prediction model based on the preprocessed historical data and the neural network algorithm.

[0058] In some embodiments, Figure 4 As shown, the processing method of step 303 includes steps 401 to 404.

[0059] Step 401: Create a training set and a test set based on the preprocessed historical data.

[0060] It can be understood that the preprocessed historical data can be divided into a training set and a test set in chronological order. For example, the preprocessed historical data within the last month can be used as a test set, and the preprocessed historical data before the last month can be used as a training set.

[0061] For example, the ratio of the training set to the test set may be 8:2 or 7:3.

[0062] Step 402: Build an LSTM model.

[0063] It can be understood that the Long Short-Term Memory (LSTM) network is a special variant of the Recurrent Neural Network (RNN). At each time step, the LSTM unit receives the current input and the hidden state of the previous time step as input, and then controls the flow and update of information through the forget gate, input gate, and output gate. The forget gate determines which information in the memory unit of the previous time step needs to be forgotten, the input gate determines which information in the current input needs to be stored in the memory unit, and the output gate determines which information in the memory unit needs to be output to the hidden state and output of the current time step. LSTM introduces a gating mechanism that can effectively retain and transmit important information in long time series, overcoming the gradient vanishing or gradient exploding problems of traditional RNN when dealing with long-term dependency problems, thereby better capturing long-term dependencies in sequence data. Through the synergy of the forget gate, input gate, and output gate, LSTM can flexibly control the forgetting, updating, and output of information according to the characteristics of the input data and task requirements, thereby better adapting to different sequence data and tasks. The application areas of LSTM include natural language processing, speech recognition, time series prediction, and video analysis.

[0064] Exemplarily, the LSTM model can be built using Keras or PyTorch.

[0065] Step 403: Train the LSTM model according to the training set to obtain a trained LSTM model.

[0066] Exemplarily, before training, you first need to prepare input data and labels, for example, create input data X and corresponding labels Y according to the set number of time steps (e.g., 7 days). For each time window, the preprocessed historical data of the previous 7 days is used as input, and the preprocessed historical data of the next day is used as the prediction target.

[0067] Step 404: Evaluate the trained LSTM model according to the test set, and adjust the model parameters of the trained LSTM model according to the evaluation results to obtain a user traffic prediction model.

[0068] For example, the data of the test set can be used as input to the trained LSTM model, and the mean square error (MSE) or root mean square error (RMSE) can be used to evaluate the prediction effect of the model, and the prediction results of the model can be compared with the actual data. For example, a time series chart can be drawn to visually check the prediction effect. According to the evaluation results, the model parameters can be adjusted to minimize the error between the prediction results and the actual data, and finally a user traffic prediction model can be obtained.

[0069] It can be understood that if normalization or standardization is performed in step 401, the predicted value of user traffic of the base station in the future second preset time period obtained in step 202 needs to be reversely transformed to be restored to the actual traffic value.

[0070] After obtaining the user traffic prediction model through steps 401 to 404, the user traffic prediction model can be used to predict the future user traffic of the base station. The prediction result can be used to formulate the base station power adjustment strategy to improve the network service quality and user experience.

[0071] Step 102: Determine the current coverage radius of the base station.

[0072] In some embodiments, Figure 5 The implementation method of step 102 includes steps 501 to 505.

[0073] Step 501: Acquire measurement report data from at least one sampling point.

[0074] In step 501, at least one sampling point comes from at least one terminal under a base station.

[0075] It can be understood that the sampling point refers to the location point or time point where various parameters of the wireless signal (such as signal strength, signal quality, frequency, etc.) are collected according to certain rules and time intervals during the measurement of the wireless communication network. The terminal (such as a mobile phone) is an important device for generating measurement reports. It will collect data according to the rules set by the system during the movement, and the location where these data are collected forms the sampling point. For example, in the Long Term Evolution (LTE) network, the terminal will regularly measure the Reference Signal Receiving Power (RSRP) and Reference Signal Received Quality (RSRQ) of the serving cell and the neighboring cell, and report these measurement results as sampling point data to the network. The terminal is a tool for collecting sampling point data, and the data collection of each sampling point is related to the location and measurement time of the terminal.

[0076] It is understandable that a terminal can generate multiple sampling points. For example, when a mobile phone moves from one cell to another, it will measure the signal at different locations (such as at certain distances or time intervals), and each measurement corresponds to a sampling point. Moreover, different terminals may also generate different sampling point data at the same location. At the same time, the measurement report usually pays more attention to the signal parameters at the sampling point rather than the characteristics of the terminal itself (such as terminal model, color, etc.), but some capabilities of the terminal (such as supported frequency bands, maximum transmit power, etc.) may affect the collection range and accuracy of the sampling point data.

[0077] It can be understood that the base station requires all mobile terminals connected to the base station to periodically report measurement data, and the measurement data reported at each sampling point contains a large amount of data, including sampling point timing advance parameter (Timing Advance, TA), RSRP of the serving base station, RSRQ of the serving base station, neighboring base station information, RSRP of the neighboring base station, etc. Taking base station i as an example, an example of the measurement report received by base station i is shown in Table 1.

[0078] Table 1 Example of measurement report received by base station i

[0079]

[0080]

[0081] Step 502: Determine at least one first sampling point according to measurement report data from at least one sampling point.

[0082] In step 502, the reference signal received power at the first sampling point is within a first preset range.

[0083] Exemplarily, the first preset range may be a narrower range, for example, the first preset range may be an interval [-105dBm, -100dBm], that is, the reference signal received power at the first sampling point is within the interval [-105dBm, -100dBm]. Alternatively, the first preset range may also be a first preset value, that is, the reference signal received power at the first sampling point is a first preset value. For example, the first preset value is -150dBm.

[0084] It can be understood that the first preset range is used as a screening condition, for example, the sampling point where the RSRP is within the first preset range is used as the first sampling point, and the coverage boundary of the base station can be determined. This screening condition ensures that the selected first sampling point has sufficient signal strength and excludes areas with weak signals, which may not belong to the effective coverage range of the base station. By screening out the sampling points where the RSRP is within the first preset range, the sample points of the coverage boundary of the base station can be obtained, which are used to calculate the current coverage radius of the base station.

[0085] Step 503: Obtain the TA value of each first sampling point in at least one first sampling point.

[0086] It can be understood that, as shown in Table 1, the TA value is used to represent the relative distance between the user equipment and the base station. The larger the TA value, the farther the distance between the user equipment and the base station is. The TA value can estimate the distance from the device to the base station within a certain accuracy. When the TA value takes different values, the distance from the corresponding terminal to the base station is also different. Each sampling point will have a specific TA value, such as 1, 3, 5, 8, etc.

[0087] Step 504: Determine the distance between the base station and each first sampling point in the at least one first sampling point according to the TA value of each first sampling point in the at least one first sampling point and the distance coefficient corresponding to each first sampling point in the at least one first sampling point.

[0088] In step 504, a distance coefficient corresponding to each first sampling point in the at least one first sampling point is obtained from a network specification.

[0089] Exemplarily, the distance d between the base station and the nth first sampling point in at least one first sampling point can be calculated according to formula (2): n .

[0090] d n =TA n ×ζ n (2)

[0091] In formula (2), TA n is the TA value of the nth first sampling point in at least one first sampling point, ζ n is a distance coefficient corresponding to an nth first sampling point in the at least one first sampling point, n is a positive integer and a value range of n is 1≤n≤N, and N is a total number of the at least one first sampling point.

[0092] It can be understood that the distance coefficient is determined by the network configuration and can be obtained from the network specification. The unit of the TA value is usually a time slice (e.g., symbol period), and the actual distance corresponding to each time slice can be obtained from the network specification. For example, in the 4th Generation Mobile Communication Technology (4G) network, the distance coefficient corresponding to a TA value is approximately 78 meters. If the TA value in a certain sampling point is 5, the distance from the sampling point to the base station is 78*5=390 meters.

[0093] In the fifth generation mobile communication technology (5th-Generation Mobile Communication Technology, 5G), it is a little more complicated. As shown in Table 2, in 5G, the distance coefficient corresponding to the TA value depends on the subcarrier spacing adopted. The subcarrier can be 15KHz, 30KHz, 60KHz, and 120KHz. As shown in the following table, if the 5G subcarrier is 15Khz, then when the TA value is 1, the distance from the sampling point to the base station is 78 meters. If the 5G subcarrier is 30Khz, then when the TA value is 1, the distance from the sampling point to the base station is 39 meters, which is half of 78.

[0094] Table 2 Relationship between TA and distance in 5G technology

[0095] Subcarrier spacing TA accuracy (seconds) TA distance (m) 15 16×64×Tc 78 30 16×32×Tc 39 60 16×16×Tc 19.5 120 16×8×Tc 10

[0096] In Table 2, chip time (Tc) is a basic time unit in the Global System for Mobile Communications (GSM) system.

[0097] Step 505: Determine the current coverage radius of the base station according to the distance between the base station and each first sampling point in at least one first sampling point.

[0098] In some embodiments, the implementation method of step 505 includes: calculating the current coverage radius R of the fixed base station according to formula (3): i .

[0099]

[0100] In formula (3), i is the number of the base station.

[0101] It can be understood that after obtaining the distance between each first sampling point in at least one first sampling point and the base station, the average distance between each first sampling point in at least one first sampling point and the base station i can be calculated according to the distance between each first sampling point in at least one first sampling point and the base station i to obtain the current coverage radius of the base station, that is, the current coverage radius R of the base station i can be calculated according to formula (3) i .

[0102] It is understandable that, since the position of the terminal is mobile, the position of each first sampling point in at least one first sampling point will also change, and the wireless channel environment will also change (for example, a car suddenly comes or it rains, which will affect the signal). The position of the sampling point that meets the RSRP and is within the first preset range will change in different time periods. Therefore, the current coverage radius R of base station i i In fact, it changes dynamically.

[0103] Step 103: Determine the target power according to the user traffic prediction value and the current coverage radius of the base station.

[0104] In some embodiments, Figure 6 As shown, the implementation method of step 103 includes steps 601 to 604.

[0105] Step 601: Obtain the current transmission power of the base station, the maximum transmission power of the base station, the minimum transmission power of the base station, the user flow threshold of the base station, and the target coverage radius of the base station.

[0106] In step 601, the user flow threshold is obtained based on the user flow history data of the base station. The target coverage radius of the base station is preset.

[0107] It can be understood that the normal carrying capacity of user traffic can be analyzed based on the historical data of user traffic of the base station, and the user traffic threshold T of the base station can be set. i When (t) exceeds the user traffic threshold T of the base station, it means that the base station's transmission power needs to be reduced to reduce the base station load and meet the needs of most users.

[0108] For example, the user traffic threshold T of the base station is set to the 80% quantile of the user traffic historical data of the base station, that is, the user traffic historical data of the base station are arranged in ascending order, and a value T is found such that at least 80% of the data in the user traffic historical data of the base station is less than or equal to T, and at least 20% of the data in the user traffic historical data of the base station is greater than or equal to T.

[0109] Understandably, an ideal target coverage radius R can be set taTo determine the target coverage range of the base station under normal circumstances, if the current coverage radius of the base station (i.e. the real-time coverage radius of the base station) R i Smaller than the target coverage radius R ta , indicating that user devices are more concentrated, the base station power can be increased accordingly, increasing the coverage range and improving the base station utilization rate. If the current coverage radius of the base station is R i Obviously larger than the target coverage radius R ta , it is necessary to reduce the base station power to ensure the signal quality in the coverage area.

[0110] Therefore, the user traffic threshold T of the base station and the target coverage radius R can be ta Serves as a reference feature for base station power adjustment.

[0111] Step 602: Determine a power adjustment reference value of the base station according to the current transmission power of the base station, the user traffic threshold of the base station, the user traffic prediction value, the target coverage radius of the base station and the current coverage radius of the base station.

[0112] In some embodiments, the implementation method of step 602 includes: calculating the power adjustment reference value P of the base station according to formula (4): i '.

[0113]

[0114] In formula (4), i is the number of the base station, P i0 is the current transmission power of base station i, β1 and β2 are weight coefficients, T is the user flow threshold of base station i, F i (t) is the predicted value of user traffic, R ta is the target coverage radius of base station i, R i is the current coverage radius of base station i.

[0115] It is understandable that when the user traffic prediction value F i (t) When the user traffic threshold T of the base station is exceeded, it indicates that the base station load is high and the base station power needs to be reduced to make the signals of some users worse, reduce the consumption of base station resources, and ensure the user experience of the remaining users. i 9t) is lower than the user flow threshold T of the base station, it means that the base station is currently lightly loaded and the base station power can be increased to improve the user signal, thus increasing the user flow. In formula (4), The increment of user traffic is normalized into a relative change to ensure consistent sensitivity to traffic demands of different orders of magnitude.

[0116] It can be understood that when the current coverage radius R of the base station i Smaller than the target coverage radius R of the base station ta, it means that the power needs to be increased to expand the coverage of the base station. On the contrary, when the current coverage radius of the base station is R i Greater than the target coverage radius R of the base station ta When , it means that the power needs to be reduced to reduce the coverage of the base station and ensure the user experience. In formula (4), The coverage radius adjustment of base station i is normalized to ensure that the adjustment effect is proportional to the degree of deviation.

[0117] It can be understood that the weight coefficients β1 and β2 are respectively used to balance the influence weight of the user traffic demand and the coverage radius of the base station in the power adjustment.

[0118] Step 603: Determine a value range of the target power according to the power adjustment reference value, the maximum transmit power of the base station, and the minimum transmit power of the base station.

[0119] In some embodiments, Figure 7 As shown, the implementation of step 603 includes steps 701 to 703.

[0120] Step 701: Calculate and obtain multiple power adjustment values.

[0121] In the multiple value range, m is taken as integer values ​​in turn, and multiple power adjustment values ​​P are calculated according to formula (5): mi .

[0122] P mi =P i '+m×Δp (5)

[0123] In formula (5), i is the number of the base station, P i ' is the power regulation reference value, Δp is the preset power increment, m is the increment multiple, the multiple value range is the interval [M1, M2], M1 and M2 are both integers, and M1 is the maximum value of the increment multiple m, and M2 is the minimum value of the increment multiple m. Exemplarily, the power increment Δp can be preset according to the actual application scenario, for example, the power increment Δp can be 0.1.

[0124] It can be understood that multiple power adjustment values ​​P can be obtained by assigning m multiple times. mi M1 and M2 can be negative integers, 0 or positive integers, respectively, and can be set according to the actual application scenario and actual needs. In other words, m can be a positive integer or a negative integer, or 0. For example, when m = 2, the power adjustment value P 2i It is equivalent to the power regulation reference value P i ' plus a 2-fold power increment Δp. When m = -3, the power adjustment value P -3i It is equivalent to the power regulation reference value P i' minus 3 times the power increment Δp. When m = 0, the power adjustment value P 0i It is equivalent to the power regulation reference value P i '.

[0125] Step 702: Calculate and obtain multiple power optimization values.

[0126] According to formula (6), multiple power optimization values ​​Z can be calculated mi .

[0127]

[0128] In formula (6), i is the number of the base station, J is the total number of users currently served by the base station, and C mij The power regulation value is P mi The signal strength of the base station to the jth user under the condition of G ij is the gain factor from the base station to the jth user, d ij is the distance between the base station and the jth user, and γ is the path loss exponent. is the interference weight coefficient.

[0129] Understandably, C. mij The signal strength from base station i to user j depends on the power and distance. If the base station power is too small, the base station signal strength received by the user will be very poor, resulting in a poor user experience. The gain factor G from the base station to the jth user ij Depending on antenna characteristics and user's geographical location, G ij It can be estimated from the network configuration file or the directivity of the antenna. The distance d between the base station and the jth user ij It can be determined by the user's location information. The path loss exponent γ indicates the attenuation of signal propagation and can be adjusted according to different environments (such as cities, suburbs, indoors, etc.). In different environments, the path loss exponent γ will be different. In urban environments, the value is usually 3.5 to 4. In suburban or rural areas, it may be lower, and the path loss exponent γ is close to 2.

[0130] In formula (6), K is the total number of neighboring base stations of the base station, and Interference(mi,k) is the power adjustment value P mi The interference between the base station and the kth neighboring base station in the case of G ki is the gain factor from the kth neighboring base station to the base station, d ik is the distance between the base station and its kth neighboring base station, F Inter It is an interference factor.

[0131] It can be understood that Interference(mi,k) is the power adjustment value P mi In the case of interference between a base station and its kth neighboring base station, if the base stations use the same frequency, they will cause mutual interference, resulting in a decrease in base station performance (for example, rate). Therefore, when the power of a base station is too large, its coverage will invade the coverage of other base stations, resulting in increased interference. Therefore, when adjusting the power, the interference between base stations must be taken into account. The distance d between a base station and its kth neighboring base station is ik It can also be obtained based on the neighboring station information recorded locally by the base station. ki is the gain factor from the kth neighboring base station to the base station, which can be calculated according to formula (7).

[0132] G ki =G tx ×G rx (7)

[0133] In formula (7), G tx is the base station’s transmitting antenna gain, G rx is the base station’s receiving antenna gain, G tx and G rx can be obtained from the technical documentation or network configuration file of the base station. Therefore, when the transmitting antenna gain G of the base station is obtained, tx and the base station’s receiving antenna gain G rx Then, the gain factor G from the kth neighboring base station to the base station can be calculated by formula (7): ki .

[0134] Understandably, the interference factor F Inter Reflects the degree of spectrum overlap and interference level between base stations. Generally speaking, the interference factor F Inter The value of is usually adjusted based on the following factors:

[0135] Frequency overlap: Base stations using the same frequency resources will cause stronger interference to other base stations, especially in areas close to the base stations.

[0136] Adjacent channel interference: If there is no complete overlap of spectrum resources between base stations, but adjacent frequency bands are used, interference may also occur. Adjacent channel interference is usually low, but it still needs to be considered.

[0137] Co-channel interference: If two base stations use the same frequency resources, the interference factor F Inter Higher, usually set to a value of 1 or higher.

[0138] Adjacent frequency interference: If the base station uses the adjacent frequency band, the interference factor F Inter The value of is low, for example, the interference factor F InterIt will usually be less than 1 and is usually set between 0.1 and 0.5.

[0139] It can be understood that each time the increment multiple m is assigned a value, a power adjustment value P is calculated according to formula (5): mi , we can get a power optimization value Z according to formula (6) mi , in this way, multiple power optimization values ​​can be obtained.

[0140] Step 703: Determine a value range of the target power according to multiple power optimization values, the maximum transmit power of the base station, and the minimum transmit power of the base station.

[0141] In step 703, the value range of the target power includes at least one power optimization value among the multiple power optimization values ​​that is between the maximum transmission power of the base station and the minimum transmission power of the base station.

[0142] It can be understood that the maximum transmission power of the base station and the minimum transmission power of the base station are respectively inherent parameters of the base station. Therefore, the value range of the target power needs to be within the maximum transmission power of the base station and the minimum transmission power of the base station. Thus, at least one power optimization value between the maximum transmission power of the base station and the minimum transmission power of the base station can be determined from multiple power optimization values ​​as the value range of the target power.

[0143] Step 604: Determine the target power according to the value range of the target power.

[0144] In step 604, the target power is the maximum value in the value range of the target power.

[0145] It can be understood that taking the maximum value from the target power value range as the target power can balance the user signal strength and base station interference while ensuring signal strength and coverage, and avoid causing excessive interference between each other in the area overlapping with the coverage range of adjacent base stations.

[0146] Step 104: Adjust the transmission power of the base station to the target power.

[0147] Exemplarily, the transmit power of the base station may be adjusted by adjusting a power control parameter, a channel parameter or a system parameter.

[0148] In summary, the base station can dynamically adjust the transmission power based on the predicted value of the base station user traffic and the current coverage radius of the base station, thereby optimizing signal coverage and network performance. From data collection to model building, real-time monitoring, to power adjustment and feedback optimization, a flexible response to user needs is achieved.

[0149] A method for adjusting base station power provided by an embodiment of the present invention is described below by taking an example.

[0150] like Figure 8 As shown, this example includes steps 801 to 804.

[0151] 801: Data Collection and Initialization

[0152] Objective: To establish an accurate prediction model for base station user traffic and a baseline for the current network status.

[0153] 1. Determine the initial parameters of the base station: record the initial transmission power P of each base station i0 , Coverage radius R i , measurement report (Measurement Report, MR) of the base station.

[0154] How to determine the coverage radius? It can be based on the MR data of the base station.

[0155] MR is the measurement data that the base station requires all mobile terminals to report regularly. Each sampling point (i.e., the measurement data reported regularly by the mobile terminal) contains a large amount of complete MR data, including TA, serving base station RSRP (reference signal received power, which refers to signal strength and measures the quality of cell signals), RSRQ, neighboring base station information, neighboring base station signal strength and other information, as shown in Table 1.

[0156] Table 1 Example of measurement report received by base station i

[0157]

[0158] In Table 1, the TA value is used to indicate the relative distance between the user equipment and the base station. The larger the TA value, the farther the distance between the user equipment and the base station is. The TA value can estimate the distance between the device and the base station within a certain accuracy. When the TA value is different, the distance between the corresponding terminal and the base station is also different. Each sampling point will have a specific TA value, such as 1, 3, 5, 8, etc.

[0159] RSRP represents the signal strength received from the base station. A screening condition is set, that is, the sampling point where RSRP is equal to the first preset value (for example, -105dBm) as the coverage limit. This screening condition ensures that the selected sampling points have sufficient signal strength and excludes areas with weak signals, which may not belong to the effective coverage range of the base station. By screening out the sampling points where RSRP is equal to -105dBm, the sample points of the base station coverage limit can be obtained, which are used to further calculate the coverage radius R of the base station. i , the specific process is as follows:

[0160] First, the TA value of each sampling point where RSRP is equal to -105 dBm (i.e., the first sampling point) is converted into an actual distance. The specific formula may vary depending on the network configuration, but generally, formula (2) can be used for estimation.

[0161] d n =TA n ×ζ n (2)

[0162] For the description of formula (2), reference may be made to the relevant description in the above embodiment, which will not be repeated here.

[0163] The distance coefficient is determined by the network configuration. The unit of TA value is usually time slice (such as symbol period). The actual distance corresponding to each time slice can be obtained from the network specification. For example, in the 4G network, the distance coefficient of a TA value is about 78 meters. If the TA value in a certain sampling point is 5, the distance from the sampling point to the base station is 78*5=390 meters. It is a little more complicated in 5G.

[0164] As shown in Table 2, in 5G, the distance coefficient corresponding to the TA value depends on the subcarrier spacing adopted. The subcarrier can be 15KHz, 30KHz, 60KHz, and 120KHz. As shown in the following table, if the 5G subcarrier is 15Khz, then when the TA value is 1, the distance from the sampling point to the base station is 78 meters. If the 5G subcarrier is 30Khz, then when the TA value is 1, the distance from the sampling point to the base station is 39 meters, which is half of 78.

[0165] Table 2 Relationship between TA and distance in 5G technology

[0166] Subcarrier spacing TA accuracy (seconds) TA distance (m) 15 16×64×Tc 78 30 16×32×Tc 39 60 16×16×Tc 19.5 120 16×8×Tc 10

[0167] The TA value of each filtered sampling point (i.e., the first sampling point) is converted into a relative distance to obtain a series of distance values. Using all the distances of the filtered sampling points, the average distance of these points to the base station is calculated, as shown in formula (3):

[0168]

[0169] For the description of formula (3), reference may be made to the relevant description in the above embodiment, which will not be repeated here.

[0170] In formula (3), the average distance R i It is the current coverage radius of the base station. Since the terminal is moving, the position of each first sampling point will also change, and the wireless channel environment will also change (for example, a car suddenly comes and it rains, which will affect the signal). The position of the sampling point that meets the RSRP equal to -105dBm in different time periods will change, so R iIt also changes dynamically.

[0171] 2. Establish a user traffic prediction model: Use a time series prediction model (such as LSTM) to model future user traffic and output the traffic prediction value F of each base station in a certain period of time in the future. i (t), use historical data when training the model and ensure that the model has good accuracy on the validation set.

[0172] To achieve the prediction of future user traffic based on the time series prediction model, this example follows the following specific steps to build and train the model. LSTM (Long Short-Term Memory Network) is a deep learning model that is particularly suitable for time series prediction tasks. The following are the detailed implementation steps:

[0173] Step 1: Prepare the data

[0174] Collect user traffic data: Collect historical user traffic data of base stations: Collect user traffic data of base stations in the past few months, including the number of access users per hour, data usage, etc. Record the time characteristics of the data (such as date, day of the week, holidays, etc.) to capture the periodic fluctuations of traffic. The data should have a certain time span (such as several months) so that the model can learn periodicity and trends.

[0175] Data cleaning and preprocessing: Check the data for missing values ​​and outliers. For missing values, you can choose to interpolate or delete the missing parts. Arrange the data in chronological order and ensure that the timestamps are aligned. Normalize or standardize the traffic data so that the model can learn better. For example, the data can be scaled to the range of [0,1] by formula (1).

[0176]

[0177] For the description of formula (1), reference may be made to the relevant description in the above embodiment, which will not be repeated here.

[0178] Then, the data is divided into training and test sets in chronological order, usually in a ratio of 80:20 or 70:30. For example, the data from the most recent month can be used as the test set, and the previous data can be used for training.

[0179] Step 2: Build LSTM model

[0180] 1. Model input format:

[0181] The input of the LSTM model is three-dimensional data with the shape of (batch size, time steps, features).

[0182] Batch size refers to the batch size, which refers to the number of data groups input in each training.

[0183] Time steps refers to the number of time steps used for prediction. For example, if you use the traffic data of the previous 7 days to predict the traffic on the 8th day, the Time steps is 7.

[0184] Features refers to the number of features, which is usually 1 in a single traffic prediction task.

[0185] 2. Model architecture: Use Keras or PyTorch to build an LSTM model. The following is a Keras sample code:

[0186] from tensorflow.keras.models import Sequential

[0187] from tensorflow.keras.layers import LSTM,Dense

[0188] model=Sequential()

[0189] model.add(LSTM(64,activation='relu',input_shape=(time_steps,features)))

[0190] model.add(Dense(1))

[0191] model.compile(optimizer='adam',loss='mse')

[0192] in,

[0193] LSTM(64) means using 64 LSTM units.

[0194] activation = 'relu' means the activation function is ReLU.

[0195] input_shape=(time_steps,features) specifies the shape of the input.

[0196] The output layer Dense(1) represents the prediction of a value (i.e. future traffic).

[0197] Step 3: Train the model

[0198] 1. Prepare input data and labels: Create input data X and corresponding labels Y according to the set number of time steps (for example, 7 days). For each time window, the previous 7 days of data are used as input, and the next day of data is used as the prediction target.

[0199] 2. Training model: Use the data in the training set to train the model:

[0200] model.fit(X_train,Y_train,epochs=50,batch_size=32,validation_split=0.1)

[0201] in,

[0202] epochs=50 means training for 50 cycles.

[0203] Batch_size=32 means that 32 sets of data are used for training each time.

[0204] validation_split=0.1 means using 10% of the data for validation.

[0205] Step 4: Model Evaluation

[0206] 1. Evaluate the model on the test set:

[0207] Input the test set data into the model to predict future traffic data.

[0208] The mean square error (MSE) or root mean square error (RMSE) is used to evaluate the prediction effect of the model. Some codes are as follows:

[0209] from sklearn.metrics import mean_squared_error

[0210] y_pred=model.predict(X_test)

[0211] mse=mean_squared_error(Y_test,y_pred)

[0212] 2. Visualize the prediction results: Compare the model's prediction results with the actual data and draw a time series chart to visually check the prediction effect.

[0213] Step 5: Predict future user traffic

[0214] 1. Future traffic prediction: Use the most recent traffic data as input to predict user traffic in future time periods. After each prediction of new data, the prediction results can be looped into the model to achieve multi-step prediction.

[0215] 2. Denormalization: If the data is normalized or standardized, the final prediction result should be transformed in reverse to restore it to the actual flow value.

[0216] Through the above steps, the LSTM model can be used to predict the future user traffic of the base station. The prediction results can be used to formulate the base station power adjustment strategy, thereby improving the network service quality and user experience.

[0217] 802: Setting adjustment strategy

[0218] Objective: To adjust base station power based on user traffic forecasts and real-time changes in coverage radius to optimize signal coverage and network performance.

[0219] Step 1: Set power adjustment threshold based on traffic prediction

[0220] Traffic prediction: Use time series models such as LSTM to predict future user traffic and output the traffic prediction value F for each base station in the future time period. i (t).

[0221] Set traffic threshold T: Analyze the normal carrying capacity of user traffic based on historical data and set a traffic threshold T to represent the traffic level that the base station can normally support. i When (t) exceeds the threshold, it indicates that the power needs to be reduced to reduce the base station load and meet user needs. For example, the flow threshold T is set to the 80% quantile of the historical flow.

[0222] Step 2: Dynamically monitor coverage radius

[0223] Calculation of coverage radius: As shown above, based on the TA parameter of each first sampling point in the MR data, the actual base station current coverage radius R is calculated. i .

[0224] Ideal coverage radius: Set an ideal target coverage radius as the target coverage range of the base station under normal circumstances.

[0225] Coverage radius change detection: If the real-time coverage radius (i.e. the current coverage radius of the base station) is R i Smaller than the target coverage radius R ta , indicating that user devices are more concentrated, the base station power can be increased accordingly, increasing the coverage range and improving the base station utilization rate. If the current coverage radius of the base station is R i Obviously larger than the target coverage radius R ta , it is necessary to reduce the base station power to ensure the signal quality in the coverage area.

[0226] Formula (4) is set as the power adjustment value of base station i in the future time period. The formula will be adjusted based on future traffic prediction, current coverage radius and target coverage radius.

[0227]

[0228] For the description of formula (4), reference may be made to the relevant description in the above embodiment, which will not be repeated here.

[0229] When the predicted flow F i (t) When it exceeds the threshold value T, it indicates that the base station load will be very high, and it is necessary to reduce the base station power to make the signals of some users worse, reduce the base station resource consumption, and ensure the user experience of the remaining users; when the traffic is lower than the threshold, it means that the base station load is currently light, and the base station power can be increased to make the user signal better, thereby increasing the traffic. Normalize the increment of user traffic to a relative change to ensure consistent sensitivity to traffic demands of different orders of magnitude. i Smaller than the target coverage radius R ta When the actual coverage radius R i Greater than the target coverage radius R ta When , it means reducing power and lowering the coverage of the base station to ensure user experience. The base station coverage radius adjustment is normalized to ensure that the adjustment effect is proportional to the degree of deviation. The weight coefficients β1 and β2 are used to balance the user traffic demand and the influence weight of the base station coverage radius in power adjustment.

[0230] 803: Setting the utility function of power adjustment to determine the appropriate power value for the base station.

[0231] The utility function of power adjustment is shown in formula (6).

[0232]

[0233] For the description of formula (6), reference may be made to the relevant description in the above embodiment, which will not be repeated here.

[0234] Therefore, after the base station adjusts the power, it needs to ensure that the utility function Z is maximized, that is, a balance is reached between the user signal strength and the interference of the base station, so that the base station increases the power when the user demand is large, while avoiding excessive interference in the overlapping area.

[0235] How to use this utility function?

[0236] 1. Determine the adjusted power P in 802 i ', calculate Z i1 .

[0237] 2. Set ΔP, where ΔP is the power increment, for example 0.1. i Add ΔP to the ′, and calculate it as P 1i , calculate the corresponding Z 1i , in P 1i Add ΔP to the basis and calculate it as P 2i , calculate the corresponding Z 2i Repeat this process m1 times, and calculate Z each time according to formula (6) mi The value of m1 depends on the needs and can be set by yourself. i ′ minus ΔP, repeat the same process m2 times, and calculate Z each time according to formula (6) mi , the value of m2 depends on the needs and can be set by yourself. (Corresponding to the above embodiment, m is taken as integer values ​​in the multiple value range, and multiple power adjustment values ​​are calculated according to formula (5), wherein the multiple value range is the interval [M1, M2], M1 and M2 are both integers, and M1 is the maximum value of the incremental multiple m, and M2 is the minimum value of the incremental multiple m)

[0238] 3. The Z formed on top mi In the set, a maximum value is selected as the final adjusted power, that is, the target power.

[0239] It should be noted that the target power must not exceed the maximum transmit power and minimum transmit power of the base station.

[0240] 804: Real-time feedback and dynamic adjustment

[0241] Objective: To monitor user traffic and coverage radius in real time to ensure that adjustments are immediate and effective.

[0242] According to the network management system of the base station, the current user traffic, coverage radius and other data of each base station are collected. The user traffic prediction model is continuously trained and optimized based on the newly collected data, and the model parameters are continuously adjusted to improve the prediction accuracy of the model.

[0243] Ensure that the data is updated frequently enough (e.g., once every 10 minutes) to reflect the network status in a timely manner. If the traffic or coverage radius measured within a period (e.g., once every 10 minutes) deviates from the predicted value, recalculate F based on the new data. i (t) and R i , and perform power adjustment. After the power adjustment, the current transmit power parameters of the base station are updated and the new power value is recorded for subsequent monitoring.

[0244] Through the above steps, the base station can dynamically adjust the transmission power based on user traffic prediction and base station coverage, thereby optimizing signal coverage and network performance. This solution ensures the logical coherence of each step, from data collection to model building, real-time monitoring, power adjustment and feedback optimization, and realizes flexible response to user needs.

[0245] An embodiment of the present invention provides a system for adjusting base station power, such as Fig. 9 As shown, the system 900 for adjusting the base station power includes a user traffic prediction value acquisition module 901 , a current radius determination module 902 , a target power determination module 903 and a power adjustment module 904 .

[0246] The user traffic prediction value acquisition module 901 is configured to: acquire the user traffic prediction value.

[0247] In some embodiments, the user traffic prediction value acquisition module 901 is configured to: acquire user traffic data of the base station in the most recent first preset time period. And, acquire the predicted value of the user traffic of the base station in the future second preset time period based on the user traffic data of the base station in the most recent first preset time period and the user traffic prediction model. The user traffic prediction model is obtained based on the user traffic history data of the base station and the neural network algorithm.

[0248] In some embodiments, Fig.10 As shown, the base station power system 900 also includes a model acquisition module 905. The model acquisition module 905 is configured to: obtain user traffic history data of the base station. Perform data cleaning and preprocessing on the user traffic history data of the base station to obtain preprocessed history data. And, obtain a user traffic prediction model based on the preprocessed history data and a neural network algorithm.

[0249] In some embodiments, the model acquisition module 905 is configured to: create a training set and a test set based on the preprocessed historical data; construct a long short-term memory network LSTM model; train the LSTM model based on the training set to obtain a trained LSTM model; and evaluate the trained LSTM model based on the test set, and adjust the model parameters of the trained LSTM model based on the evaluation results to obtain a user traffic prediction model.

[0250] The current radius determination module 902 is configured to determine the current coverage radius of the base station.

[0251] In some embodiments, the current radius determination module 902 is configured to: obtain measurement report data from at least one sampling point. Determine at least one first sampling point according to the measurement report data from at least one sampling point. Obtain the TA value of each first sampling point in the at least one first sampling point respectively. Determine the distance between the base station and each first sampling point in the at least one first sampling point according to the TA value of each first sampling point in the at least one first sampling point and the distance coefficient corresponding to each first sampling point in the at least one first sampling point respectively. And, determine the current coverage radius of the base station according to the distance between the base station and each first sampling point in the at least one first sampling point. Wherein, at least one sampling point comes from at least one terminal under the base station. The reference signal received power of the first sampling point is within a first preset range. The distance coefficient corresponding to each first sampling point in the at least one first sampling point is obtained from a network specification.

[0252] In some embodiments, the current radius determination module 902 is configured to: Calculate the current coverage radius R of the base station i Wherein, N is the total number of first sampling points in at least one first sampling point, d n is the distance between the base station and the nth first sampling point in the at least one first sampling point, d n =TA n ×ζ n TA n is the TA value of the nth first sampling point in at least one first sampling point, ζ n is a distance coefficient corresponding to the nth first sampling point in the at least one first sampling point, where n is a positive integer and the value range of n is 1≤n≤N.

[0253] The target power determination module 903 is configured to determine the target power according to the user traffic prediction value and the current coverage radius of the base station.

[0254] In some embodiments, the target power determination module 903 is configured to: obtain the current transmit power of the base station, the maximum transmit power of the base station, the minimum transmit power of the base station, the user traffic threshold of the base station, and the target coverage radius of the base station. Determine the power adjustment reference value of the base station according to the current transmit power of the base station, the user traffic threshold of the base station, the user traffic prediction value, the target coverage radius of the base station, and the current coverage radius of the base station. Determine the value range of the target power according to the power adjustment reference value, the maximum transmit power of the base station, and the minimum transmit power of the base station. And, determine the target power according to the value range of the target power. Among them, the user traffic threshold is obtained based on the user traffic historical data of the base station. The target coverage radius of the base station is preset. The target power is the maximum value in the value range of the target power.

[0255] In some embodiments, the target power determination module 903 is configured as follows: according to Calculate the power adjustment reference value P of the base station i '. Among them, P i0 is the current transmission power of the base station, β1 and β2 are weight coefficients, T is the user flow threshold of the base station, and F i (t) is the predicted value of user traffic, R ta is the target coverage radius of the base station, R i is the current coverage radius of the base station.

[0256] In some embodiments, the target power determination module 903 is configured to: take integer values ​​for m in the multiple value range, and calculate the target power according to P. mi =P i '+m×Δp calculates multiple power adjustment values ​​P mi . according to Calculate multiple power optimization values ​​Z mi And, the target power value range is determined according to the multiple power optimization values, the maximum transmission power of the base station and the minimum transmission power of the base station. Where i is the number of the base station, P i ' is the power adjustment reference value, Δp is the preset power increment, m is the increment multiple, the multiple value range is the interval [M1, M2], M1 and M2 are both integers, and M1 is the maximum value of the increment multiple m, and M2 is the minimum value of the increment multiple m. J is the total number of users currently served by the base station, C mij The power regulation value is P mi The signal strength of the base station to the jth user under the condition of G ij is the gain factor from the base station to the jth user, d ij is the distance between the base station and the jth user, and γ is the path loss exponent. is the interference weight coefficient. K is the total number of neighboring base stations of the base station. Interference(mi,k) is the power adjustment value P mi The interference between the base station and the kth neighboring base station in the case of G ki is the gain factor from the kth neighboring base station to the base station, d ik is the distance between the base station and its kth neighboring base station, F Inter The value range of the target power includes at least one power optimization value between the maximum transmission power of the base station and the minimum transmission power of the base station among the multiple power optimization values.

[0257] The power adjustment module 904 is configured to adjust the transmission power of the base station to the target power.

[0258] The specific scheme and beneficial effects of a system for adjusting base station power provided by an embodiment of the present invention can be referred to the relevant description of a method for adjusting base station power provided by an embodiment of the present invention, and will not be repeated here.

[0259] An embodiment of the present invention provides a computer device, such as Fig.11 As shown, the computer device 1100 includes a memory 1101 and a processor 1102. The memory 1101 stores a computer program. When the processor 1102 runs the computer program stored in the memory 1101, the processor 1102 executes the above-mentioned method for adjusting base station power.

[0260] The specific solution and beneficial effects of a computer device provided by an embodiment of the present invention can be referred to the relevant description of a method for adjusting base station power provided by an embodiment of the present invention, which will not be repeated here.

[0261] An embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the processor executes the above-mentioned method for adjusting base station power.

[0262] The specific solution and beneficial effects of a computer-readable storage medium provided by an embodiment of the present invention can be referred to the relevant description of a method for adjusting base station power provided by an embodiment of the present invention, which will not be repeated here.

[0263] It is to be understood that the above embodiments are merely exemplary embodiments used to illustrate the principles of the present invention, but the present invention is not limited thereto. For those of ordinary skill in the art, various modifications and improvements can be made without departing from the spirit and essence of the present invention, and these modifications and improvements are also considered to be within the scope of protection of the present invention.

Claims

1. A method for adjusting base station power, characterized in that: include: Get user traffic forecast value; Determine the current coverage radius of the base station; Determine the target power according to the user traffic prediction value and the current coverage radius of the base station; as well as The transmit power of the base station is adjusted to the target power.

2. The method for adjusting base station power according to claim 1, characterized in that: The obtaining of the user traffic prediction value comprises: Acquiring user traffic data of the base station within a recent first preset time period; and The predicted value of the user traffic of the base station in a future second preset time period is obtained based on the user traffic data of the base station in the most recent first preset time period and a user traffic prediction model; the user traffic prediction model is obtained based on the user traffic historical data of the base station and a neural network algorithm.

3. The method for adjusting base station power according to claim 2, characterized in that: Also includes: Obtain user traffic history data of base stations; Performing data cleaning and preprocessing on the user traffic history data of the base station to obtain preprocessed history data; as well as The user traffic prediction model is obtained based on the preprocessed historical data and the neural network algorithm.

4. The method for adjusting base station power according to claim 3, characterized in that: The obtaining the user traffic prediction model according to the preprocessed historical data and the neural network algorithm includes: Creating a training set and a test set based on the preprocessed historical data; Build a long short-term memory network LSTM model; Training the LSTM model according to the training set to obtain a trained LSTM model; and The trained LSTM model is evaluated according to the test set, and the model parameters of the trained LSTM model are adjusted according to the evaluation results to obtain the user traffic prediction model.

5. The method for adjusting base station power according to claim 1, characterized in that: The determining the current coverage radius of the base station includes: Acquire measurement report data from at least one sampling point; the at least one sampling point is from at least one terminal under the base station; Determine at least one first sampling point according to the measurement report data from the at least one sampling point; the reference signal received power of the first sampling point is within a first preset range; Respectively obtain a timing advance parameter TA value of each first sampling point in the at least one first sampling point; determining a distance between a base station and each of the at least one first sampling points according to a TA value of each of the at least one first sampling point and a distance coefficient corresponding to each of the at least one first sampling point; the distance coefficient corresponding to each of the at least one first sampling point is obtained from a network specification; and The current coverage radius of the base station is determined according to the distance between the base station and each first sampling point of the at least one first sampling point.

6. The method for adjusting base station power according to claim 5, characterized in that: The determining the current coverage radius of the base station according to the distance between the base station and each of the at least one first sampling point comprises: according to Calculate the current coverage radius R of the base station i ; wherein i is the number of the base station, N is the total number of the first sampling points in the at least one first sampling point, d n is the distance between the base station and the nth first sampling point among the at least one first sampling point, d n =TA n ×ζ n TA n is the TA value of the nth first sampling point in the at least one first sampling point, ζ n is a distance coefficient corresponding to the nth first sampling point in the at least one first sampling point, where n is a positive integer and the value range of n is 1≤n≤N.

7. The method for adjusting base station power according to claim 1, characterized in that: The determining the target power according to the user traffic prediction value and the current coverage radius of the base station includes: Obtaining the current transmission power of the base station, the maximum transmission power of the base station, the minimum transmission power of the base station, the user flow threshold of the base station and the target coverage radius of the base station; the user flow threshold is obtained based on the user flow historical data of the base station; the target coverage radius of the base station is preset; Determine a power adjustment reference value of the base station according to a current transmit power of the base station, a user traffic threshold of the base station, a user traffic prediction value, a target coverage radius of the base station, and a current coverage radius of the base station; Determining a value range of the target power according to the power adjustment reference value, the maximum transmit power of the base station, and the minimum transmit power of the base station; and The target power is determined according to a value range of the target power; the target power is a maximum value in the value range of the target power.

8. The method for adjusting base station power according to claim 7, characterized in that: The determining the power adjustment reference value of the base station according to the current transmit power of the base station, the user traffic threshold of the base station, the user traffic prediction value, the target coverage radius of the base station and the current coverage radius of the base station includes: according to Calculate the power adjustment reference value P of the base station i '; where i is the number of the base station; P i0 is the current transmission power of the base station, β1 and β2 are weight coefficients, T is the user flow threshold of the base station, F i (t) is the user traffic prediction value, R ta is the target coverage radius of the base station, R i is the current coverage radius of the base station.

9. The method for adjusting base station power according to claim 7, characterized in that: The determining the value range of the target power according to the power adjustment reference value, the maximum transmit power of the base station, and the minimum transmit power of the base station includes: In the multiple value range, m is taken as integer value in turn, and according to P mi =P i '+m×Δp calculates multiple power adjustment values ​​P mi ; Where i is the number of the base station, P i ' is the power adjustment reference value, Δp is the preset power increment, m is the increment multiple, the multiple value range is the interval [M1, M2], M1 and M2 are both integers, and M1 is the maximum value of the increment multiple m, and M2 is the minimum value of the increment multiple m; according to Calculate multiple power optimization values ​​Z mi ; Where J is the total number of users currently served by the base station, C mij The power regulation value is P mi The signal strength of the base station to the jth user under the condition of G ij is the gain factor from the base station to the jth user, d ij is the distance between the base station and the jth user, γ is the path loss index; is the interference weight coefficient; K is the total number of neighboring base stations of the base station, and Interference(mi,k) is the power adjustment value P mi The interference value between the base station and the kth neighboring base station of the base station under the condition of G ki is the gain factor from the kth neighboring base station to the base station, d ik is the distance between the base station and its kth neighboring base station, F Inter is a confounding factor; and The value range of the target power is determined according to the multiple power optimization values, the maximum transmission power of the base station and the minimum transmission power of the base station; the value range of the target power includes at least one power optimization value among the multiple power optimization values ​​that is between the maximum transmission power of the base station and the minimum transmission power of the base station.

10. A system for adjusting base station power, characterized in that: include: A user traffic prediction value acquisition module is configured to: acquire a user traffic prediction value; A current radius determination module is configured to: determine a current coverage radius of a base station; A target power determination module, configured to: determine the target power according to the user traffic prediction value and the current coverage radius of the base station; and A power adjustment module is configured to: adjust the transmission power of the base station to the target power.

11. A computer device, characterized in that: The method comprises a memory and a processor, wherein a computer program is stored in the memory, and when the processor runs the computer program stored in the memory, the processor executes the method for adjusting base station power according to any one of claims 1 to 9.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the processor performs the method for adjusting base station power according to any one of claims 1 to 9.

Images