Base station load adjustment method and apparatus, electronic device, and computer readable medium

Abstract

Embodiments of the application disclose a base station load adjustment method and device, electronic equipment and a computer readable medium. The method comprises: during a UAV cluster aggregation operation, obtaining base station data of an Internet of Things base station in communication connection with a UAV in a UAV cluster; preprocessing the base station data to obtain preprocessed data; inputting the preprocessed data into a pre-trained base station load value prediction model to predict a load value of the Internet of Things base station by using the base station load value prediction model; determining a load solution based on the load value and executing the load solution to adjust the load of the Internet of Things base station. The embodiments solve the problem of network congestion during the UAV cluster aggregation operation and improve the adjustment efficiency and accuracy of the load of the Internet of Things base station.

Description

Technical Field

[0001] This application relates to the field of computer technology, specifically to base station load adjustment methods, apparatus, electronic devices, and computer-readable media. Background Technology

[0002] In scenarios where drone swarms operate in clusters, multiple drones move rapidly at low altitudes. To avoid network congestion, there are higher requirements for the rapid balancing and adjustment of the load on IoT base stations.

[0003] In existing technologies, load optimization and adjustment of IoT base stations mainly rely on manual modification of various base station parameters, which is inefficient and prone to errors. Summary of the Invention

[0004] This application provides a base station load adjustment method, apparatus, electronic device, and computer-readable medium to address the technical problems existing in the prior art.

[0005] In a first aspect, embodiments of this application provide a base station load adjustment method, the method comprising: during a drone swarm aggregation operation, acquiring base station data of an Internet of Things (IoT) base station that is communicatively connected to drones in the drone swarm; preprocessing the base station data to obtain preprocessed data; inputting the preprocessed data into a pre-trained base station load value prediction model, and predicting the load value of the IoT base station through the base station load value prediction model; determining a load solution based on the load value, and executing the load solution to adjust the load of the IoT base station.

[0006] Secondly, embodiments of this application provide a base station load adjustment device, which includes: an acquisition unit, configured to acquire base station data of an Internet of Things (IoT) base station that is communicatively connected to the drones in the drone swarm during a drone swarm aggregation operation; a preprocessing unit, configured to preprocess the base station data to obtain preprocessed data; a processing unit, configured to input the preprocessed data into a pre-trained base station load value prediction model to obtain the load value of the IoT base station; and an execution unit, configured to determine a load solution based on the load value and execute the load solution to adjust the load of the IoT base station.

[0007] Thirdly, embodiments of this application provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any embodiment of the first aspect.

[0008] Fourthly, embodiments of this application provide a computer-readable medium having a computer program stored thereon that, when executed by a processor, implements the method as described in any embodiment of the first aspect.

[0009] The base station load adjustment method, apparatus, electronic device, and computer-readable medium provided in this application acquire base station data of IoT base stations communicating with drones in the drone swarm during drone swarm aggregation operations. The base station data is then preprocessed to obtain preprocessed data. This preprocessed data is then input into a pre-trained base station load prediction model, which predicts the load value of the IoT base station. Finally, based on the load value, a load solution is determined and executed to adjust the load of the IoT base station. Therefore, this method can automatically predict the load value of the IoT base station using base station data and a base station load prediction model during drone swarm aggregation operations, and automatically determine a load solution and perform load optimization adjustments based on a composite value. This solves problems such as network congestion during drone swarm aggregation operations, ensuring stable network operation and improving communication quality. Furthermore, by eliminating the need for manual load optimization adjustments based on experience, it improves the efficiency and accuracy of load adjustment. Attached Figure Description

[0010] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0011] Figure 1 This is a flowchart of an embodiment of the base station load adjustment method of this application;

[0012] Figure 2 This is a schematic diagram of the base station load value prediction model of the base station load adjustment method of this application;

[0013] Figure 3 This is a schematic diagram of one embodiment of the base station load adjustment device of this application;

[0014] Figure 4 This is a schematic diagram of the structure of an electronic device used to implement the embodiments of this application. Detailed Implementation

[0015] All actions involving the acquisition of signals, information, or data in this application are carried out in accordance with the relevant data protection laws and policies of the country where the application is located, and with the authorization of the owner of the relevant device.

[0016] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.

[0017] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0018] Please refer to Figure 1 This document illustrates a flowchart 100 of an embodiment of the base station load adjustment method according to this application. This base station load adjustment method can be applied to various electronic devices with data processing capabilities. For example, such electronic devices may include, but are not limited to, servers, tablet computers, laptops, handheld computers, and desktop computers. The processor in the aforementioned electronic device can be the executing entity of the base station load adjustment method.

[0019] The base station load adjustment method includes the following steps:

[0020] Step 101: During the drone swarm aggregation operation, acquire base station data from the IoT base station that communicates with the drones in the drone swarm.

[0021] In this embodiment, during the drone swarm aggregation operation, the entity executing the base station load adjustment method can obtain base station data from the IoT base station that is communicatively connected to the drones in the drone swarm. This base station data may include current and historical data from the IoT base station.

[0022] In some optional implementations of this embodiment, the base station data includes service data and network environment data. The service data includes, but is not limited to, at least one of the following: historical load data, real-time network traffic data, number of users, and user service habit data. The network environment data includes, but is not limited to, at least one of the following: network frequency band, network standard, and surrounding base station operation data.

[0023] Step 102: Preprocess the base station data to obtain preprocessed data.

[0024] In this embodiment, base station data can be preprocessed to obtain preprocessed data, ensuring data validity and consistency, and facilitating subsequent data processing and analysis. The aforementioned processing may include, but is not limited to, at least one of the following: deduplication, cleaning, correction, normalization, etc.

[0025] In some optional implementations of this embodiment, the following steps can be followed:

[0026] First, the base station data is inspected to identify problematic data, including invalid data and erroneous data. For example, invalid data may include, but is not limited to, unwanted data, missing value data, and data generated during base station malfunctions. Erroneous data refers to data with errors that can be corrected. For instance, if the RSRP (Reference Signal Receiving Power) / SINR (Signal to Interference plus Noise Ratio) value on the wireless side is abnormal, a base station malfunction can be considered, and the base station data from this period can be deleted as invalid data.

[0027] Then, erroneous data in the base station data is corrected, and invalid data is deleted to obtain valid data. Valid data may include the data after correcting the erroneous data, as well as other data in the aforementioned base station data excluding the problematic data.

[0028] Finally, the valid data is normalized to obtain preprocessed data. Specifically, the valid data can first be centered by minimization, and then scaled according to the range (i.e., the maximum value minus the minimum value) so that the valid data is converged to the numerical range [0,1].

[0029] Preprocessing base station data in the above manner can improve the validity and consistency of the data, facilitating subsequent data processing and analysis.

[0030] Step 103: Input the preprocessed data into the pre-trained base station load prediction model, and predict the load value of the IoT base station through the base station load prediction model.

[0031] In this embodiment, the aforementioned execution entity may store a pre-trained base station load prediction model. The base station load prediction model can be pre-trained using machine learning methods. The basic model structure used to train the base station load prediction model can be a neural network, etc. The base station load prediction model can be used to predict the load value of a base station based on base station data. Here, preprocessed data can be input into the pre-trained base station load prediction model to predict the load value of the IoT base station.

[0032] In some optional implementations of this embodiment, the aforementioned base station load prediction model can be trained through the following steps: First, acquire historical base station data and historical actual load values ​​of IoT base stations communicating with the drones during a historical demonstration of the drone swarm; then, preprocess the historical base station data to obtain sample data; finally, use the historical actual load values ​​as labels for the sample data, and train the basic prediction model using the sample data to obtain the base station load prediction model. The acquisition and preprocessing of historical base station data can be found in the steps described above, and will not be repeated here.

[0033] During training, sample data can be input into the base prediction model one by one to obtain the predicted loading values ​​output by the base prediction model. Then, based on the labels corresponding to the predicted results and the input sample data, the loss value can be determined. This loss value is the value of the loss function, a non-negative real-valued function used to characterize the difference between the detection result and the true result. Generally, the smaller the loss value, the better the robustness of the model. The loss function can be set according to actual needs; for example, it can be set to the cross-entropy loss function. Then, the parameters of the base prediction model can be updated using this loss value. Thus, each time sample data is input, the parameters of the base prediction model can be updated based on the loss value corresponding to that sample data until training is complete. In practice, training completion can be determined in several ways. For example, training completion can be determined when the accuracy of the prediction results output by the base prediction model reaches a preset value (e.g., 99%). Another example is training completion if the number of training iterations of the base prediction model equals a preset number. Yet another example is training completion when the loss value of the base prediction model converges. Here, once the basic prediction model has been trained, it can be determined as the base station load value prediction model.

[0034] In some optional implementations of this embodiment, the base prediction model includes a Multilayer Perceptron (MLP). A Multilayer Perceptron is a feedforward neural network consisting of multiple neuron layers, each connected to neurons in the preceding and following layers. It is a widely used artificial neural network model used to solve machine learning tasks such as classification, regression, and pattern recognition.

[0035] In some optional implementations of this embodiment, the base station load prediction model includes an input layer, at least one hidden layer, and an output layer. For example, considering a model with only one hidden layer, see [link to relevant documentation]. Figure 2The input layer is the starting point of the base station load prediction model, responsible for receiving external input information, i.e., the preprocessed data mentioned above, and converting it into processable data. The input layer can also adjust the number of neurons and their connections according to the specific task requirements. The output layer is the endpoint of the base station load prediction model, used to transform the final processing result into an understandable format. The hidden layer is the core part of the base station load prediction model, used for information transmission and computation within the model. Each hidden layer consists of multiple neurons, each receiving input from the previous layer, performing nonlinear and linear transformations on it, and passing the computation result as output to the next layer. Through this computational process, the base station load prediction model can learn the complex features of the input data and make predictions based on these features.

[0036] Predicting the load value of IoT base stations using a base station load prediction model includes the following steps:

[0037] The first step is to output the preprocessed data to the first hidden layer of at least one of the above hidden layers through the input layer.

[0038] The second step involves performing linear and non-linear processing on the data output from the previous layer through each of the at least one hidden layer to obtain intermediate data.

[0039] The above linear processing procedure is illustrated in the following formula:

[0040]

[0041] Among them, c i The connection strength between neurons is represented by weights, where the magnitude of the weights indicates the likelihood of a connection. i This represents the bias. The bias is set to ensure correct classification, that is, to ensure that the output value calculated from the input cannot be arbitrarily activated. i This is for factor loss compensation. i This is the preprocessed data. z is the intermediate vector matrix obtained after linear processing of the hidden layer.

[0042] The above nonlinear processing can be performed using an activation function. For example, see the Sigmoid function below:

[0043]

[0044] By introducing nonlinear factors, the base station load prediction model can arbitrarily approximate any nonlinear function, utilizing properties such as monotonically increasing and inverse functions monotonically increasing.

[0045] This explanation uses the second layer, or first hidden layer, of the base station load prediction model as an example. Assume this hidden layer has three neurons, and the outputs of these three neurons can be denoted as follows: The calculation formula is as follows:

[0046]

[0047]

[0048]

[0049] Where x1, x2, and x3 are preprocessed data, The intermediate data output after linear processing of the three neurons mentioned above are respectively. These are the biases corresponding to the three neurons mentioned above. These are the factor loss compensations for the three neurons mentioned above. These are the connection strength weights between the three neurons mentioned above and the three neurons in the previous layer.

[0050] And so on. Assuming there are m neurons in layer n-1, then the output of the j-th neuron in layer n... See below:

[0051]

[0052] in, This is the output of the i-th neuron in the (n-1)-th layer. This refers to the intermediate data output after linear processing of the j-th neuron in the n-th layer. This is the bias corresponding to the j-th neuron in the n-th layer. For factor loss compensation corresponding to the j-th neuron in the n-th layer, denoted as the connection strength weight between the j-th neuron in the n-th layer and the i-th neuron in the (n-1)-th layer, where m and n are both positive integers and e is a natural constant.

[0053] The third step involves processing the intermediate data output from the last hidden layer of at least one hidden layer through the output layer to obtain the load value of the IoT base station. Here, the intermediate data output from the last hidden layer can be processed by the output layer, such as performing numerical range conversion, to obtain the load value of the IoT base station.

[0054] The base station load prediction model with the above structure can learn the complex characteristics of the input data and make accurate predictions of the load value of IoT base stations based on these characteristics.

[0055] Step 104: Based on the load value, determine the load solution and execute the load solution to adjust the load of the IoT base station.

[0056] In this embodiment, different load values ​​correspond to different base station load warning levels, and different base station load warning levels correspond to different load solutions. Load solutions may include, but are not limited to, at least one of the following: adjusting power parameters, switching thresholds, load balancing processing, radio frequency optimization processing or capacity expansion processing, building new IoT base stations, etc. The aforementioned execution entity can determine the base station load warning level based on the load value, thereby determining the load solution based on the base station load warning level, and executing the load solution to adjust the load of the IoT base station.

[0057] In some optional implementations of this embodiment, the following steps may be included:

[0058] When the load value is within the first numerical range, parameter optimization processing can be performed on the IoT base station. Parameter optimization processing includes at least one of the following: adjusting power parameters and switching thresholds. In practice, the first numerical range can be (-∞, 0.5], corresponding to a base station load warning level of 0.

[0059] When the load value falls within the second numerical range, load balancing can be performed on the IoT base station. In practice, the second numerical range can be (0.5, 0.7], corresponding to a base station load warning level of 1. Load balancing can be achieved through parameter tuning, for example, by switching the range or threshold of the cells covered by the IoT base station, thereby reducing the signal coverage area of ​​the IoT base station and reducing its load.

[0060] When the load value falls within the third numerical range, radio frequency (RF) optimization or capacity expansion can be performed on the IoT base station. In practice, the third numerical range can be (0.7, 0.9], corresponding to a base station load warning level of 2. RF optimization can be achieved by adjusting the IoT base station's antenna. By adjusting the antenna, the signal coverage area of ​​the IoT base station can be reduced, thereby decreasing the load on the IoT base station. Capacity expansion can be achieved by increasing the number of carriers in the IoT base station, for example, from one carrier to two carriers.

[0061] When the load value falls within the fourth value range, new IoT base stations can be built to distribute the load and resolve the aforementioned IoT base station load issue. In practice, the fourth value range can be (0.9, ∞), corresponding to a base station load warning level of 3.

[0062] The method provided in the above embodiments of this application acquires base station data from IoT base stations communicating with drones in the drone swarm during drone swarm aggregation operations; then preprocesses the base station data to obtain preprocessed data; subsequently, the preprocessed data is input into a pre-trained base station load prediction model to predict the load value of the IoT base station; finally, based on the load value, a load solution is determined and executed to adjust the load of the IoT base station. Therefore, this method can automatically predict the load value of the IoT base station using base station data and a base station load prediction model during drone swarm aggregation operations, and automatically determine a load solution and perform load optimization adjustments based on a composite value. This solves problems such as network congestion during drone swarm aggregation operations, ensures stable network operation, and improves communication quality; furthermore, it improves the efficiency and accuracy of load adjustment by eliminating the need for manual load optimization adjustments based on experience.

[0063] Further reference Figure 3 As an implementation of the methods shown in the above figures, this application provides an embodiment of a base station load adjustment device, which is similar to... Figure 1 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0064] like Figure 3 As shown, the base station load adjustment device 300 of this embodiment includes: an acquisition unit 301, used to acquire base station data of an IoT base station that is communicatively connected to the drones in the drone swarm during the drone swarm aggregation operation; a preprocessing unit 302, used to preprocess the base station data to obtain preprocessed data; a processing unit 303, used to input the preprocessed data into a pre-trained base station load value prediction model to obtain the load value of the IoT base station; and an execution unit 304, used to determine a load solution based on the load value and execute the load solution to adjust the load of the IoT base station.

[0065] In some optional implementations of this embodiment, the preprocessing unit 302 is further configured to: detect the base station data, determine problematic data in the base station data, the problematic data including invalid data and erroneous data; correct the erroneous data in the base station data and delete the invalid data in the base station data to obtain valid data; and normalize the valid data to obtain preprocessed data.

[0066] In some optional implementations of this embodiment, the execution unit 304 is further configured to: perform parameter optimization processing on the IoT base station when the load value is within a first numerical range, the parameter optimization processing including at least one of the following: adjusting power parameters, switching thresholds; perform load balancing processing on the IoT base station when the load value is within a second numerical range; perform radio frequency optimization processing or capacity expansion processing on the IoT base station when the load value is within a third numerical range; and build a new IoT base station when the load value is within a fourth numerical range.

[0067] In some optional implementations of this embodiment, the base station load prediction model includes an input layer, at least one hidden layer, and an output layer; the processing unit 303 is further configured to: output the preprocessed data to the first hidden layer among the at least one hidden layer through the input layer; for each hidden layer, perform linear and nonlinear processing on the data output by the previous layer in sequence through the hidden layer to obtain intermediate data; and process the intermediate data output by the last hidden layer among the at least one hidden layer through the output layer to obtain the load value of the IoT base station.

[0068] In some optional implementations of this embodiment, the base station load prediction model is trained through the following steps: acquiring historical base station data and historical actual load values ​​of IoT base stations communicating with the drones during historical aggregation operations; preprocessing the historical base station data to obtain sample data; using the historical actual load values ​​as labels for the sample data, and training the basic prediction model using the sample data to obtain the base station load prediction model.

[0069] In some optional implementations of this embodiment, the basic prediction model includes a multilayer perceptron.

[0070] In some optional implementations of this embodiment, the base station data includes service data and network environment data; the service data includes at least one of the following: historical load data, real-time network traffic data, number of users, and user service habit data; the network environment data includes at least one of the following: network frequency band, network standard, and surrounding base station operation data.

[0071] The apparatus provided in the above embodiments of this application acquires base station data from an IoT base station communicating with drones in the drone swarm during drone swarm aggregation operations. The base station data is then preprocessed to obtain preprocessed data. This preprocessed data is then input into a pre-trained base station load prediction model, which predicts the load value of the IoT base station. Finally, based on the load value, a load solution is determined and executed to adjust the load of the IoT base station. Therefore, this method can automatically predict the load value of the IoT base station using base station data and a base station load prediction model during drone swarm aggregation operations, and automatically determine a load solution and perform load optimization adjustments based on a composite value. This solves problems such as network congestion during drone swarm aggregation operations, ensuring stable network operation and improving communication quality. Furthermore, by eliminating the need for manual load optimization adjustments based on experience, it improves the efficiency and accuracy of load adjustment.

[0072] The following is for reference. Figure 4 It shows a schematic diagram of the structure of an electronic device used to implement some embodiments of this application. Figure 4 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this application.

[0073] like Figure 4 As shown, electronic device 400 may include a processing device (e.g., a central processing unit, a graphics processor, etc.) 401, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 402 or a program loaded from storage device 408 into random access memory (RAM) 403. RAM 403 also stores various programs and data required for the operation of electronic device 400. Processing device 401, ROM 402, and RAM 403 are interconnected via bus 404. Input / output (I / O) interface 405 is also connected to bus 404.

[0074] Typically, the following devices can be connected to I / O interface 405: input devices 406 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 407 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 408 including, for example, disks, hard disks, etc.; and communication devices 409. Communication device 409 allows electronic device 400 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 4 An electronic device 400 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 4Each box shown can represent a device or multiple devices as needed.

[0075] In particular, according to some embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 409, or installed from storage device 408, or installed from ROM 402. When the computer program is executed by processing device 401, it performs the functions defined above in the methods of some embodiments of this application.

[0076] It should be noted that the computer-readable medium described in some embodiments of this application may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In some embodiments of this application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0077] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol, such as HTTP (Hypertext Transfer Protocol), and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0078] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: acquire base station data from an IoT base station communicating with drones in the drone swarm during drone swarm aggregation operations; preprocess the base station data to obtain preprocessed data; input the preprocessed data into a pre-trained base station load prediction model to predict the load value of the IoT base station; and, based on the load value, determine a load solution and execute the load solution to adjust the load of the IoT base station.

[0079] Computer program code for performing operations of some embodiments of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++; and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, or it can be connected to an external computer (e.g., via the Internet using an Internet service provider), including local area networks (LANs) or wide area networks (WANs).

[0080] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0081] The units described in some embodiments of this application can be implemented in software or hardware. The described units can also be housed in a processor; for example, a processor may be described as including a first determining unit, a second determining unit, a selecting unit, and a third determining unit. The names of these units do not necessarily limit the specific unit itself.

[0082] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0083] The above description is merely a selection of preferred embodiments of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this application.

Claims

1. A method for adjusting base station load, characterized in that, The method includes: During the drone swarm aggregation operation, base station data of the Internet of Things base station that is communicatively connected to the drones in the drone swarm is acquired; The base station data is preprocessed to obtain preprocessed data; The preprocessed data is input into a pre-trained base station load prediction model, and the load value of the IoT base station is predicted by the base station load prediction model. The base station load prediction model includes an input layer, at least one hidden layer, and an output layer. The parameters of the hidden layer include factor loss compensation. The base station load prediction model is a trained basic prediction model, and the basic prediction model includes a multilayer perceptron. Based on the load value, a load solution is determined and implemented to adjust the load of the IoT base station; Different load values ​​correspond to different base station load warning levels, and different base station load warning levels correspond to different load solutions. Determining the load solution based on the load value includes: When the load value is within a first numerical range, the IoT base station is subjected to parameter optimization processing, which includes at least one of the following: adjusting power parameters and switching thresholds; the corresponding base station load warning level is level 0. When the load value is within the second numerical range, load balancing is performed on the IoT base station; the corresponding base station load warning level is level 1. When the load value is within the third numerical range, the IoT base station undergoes radio frequency optimization or capacity expansion processing; the radio frequency optimization is achieved by adjusting the antenna of the IoT base station; the capacity expansion is achieved by increasing the carrier of the IoT base station; the corresponding base station load warning level is level 2. When the load value is within the fourth value range, a new IoT base station is built; the corresponding base station load warning level is level 3.

2. The method according to claim 1, characterized in that, The preprocessing of the base station data to obtain preprocessed data includes: The base station data is inspected to identify problematic data, including invalid data and erroneous data. The erroneous data in the base station data is corrected, and the invalid data in the base station data is deleted to obtain valid data; The valid data is normalized to obtain preprocessed data.

3. The method according to claim 1, characterized in that, The step of predicting the load value of the IoT base station using the base station load value prediction model includes: The preprocessed data is output to the first hidden layer of the at least one hidden layer through the input layer; For each of the at least one hidden layer, the data output from the previous layer is sequentially processed linearly and non-linearly through the hidden layer to obtain intermediate data. The intermediate data output by the last hidden layer in the at least one hidden layer is processed by the output layer to obtain the load value of the IoT base station.

4. The method according to claim 1, characterized in that, The base station load prediction model is trained through the following steps: Acquire historical base station data and historical actual load values ​​of IoT base stations that communicate with drones during historical drone swarm aggregation operations; The historical base station data is preprocessed to obtain sample data; The historical actual load value is used as the label for the sample data. The base prediction model is trained using the sample data to obtain the base station load value prediction model.

5. The method according to any one of claims 1-4, characterized in that, The base station data includes service data and network environment data; the service data includes at least one of the following: historical load data, real-time network traffic data, number of users, and user service habit data; the network environment data includes at least one of the following: network frequency band, network standard, and surrounding base station operation data.

6. A base station load adjustment device, characterized in that, The device includes: The acquisition unit is used to acquire base station data of the Internet of Things base station that is communicatively connected to the drones in the drone swarm during the drone swarm aggregation operation. A preprocessing unit is used to preprocess the base station data to obtain preprocessed data; A processing unit is used to input the preprocessed data into a pre-trained base station load prediction model to obtain the load value of the Internet of Things base station; the base station load prediction model includes an input layer, at least one hidden layer and an output layer, and the parameters of the hidden layer include factor loss compensation; the base station load prediction model is a trained basic prediction model, and the basic prediction model includes a multilayer perceptron. An execution unit is configured to determine a load solution based on the load value and execute the load solution to adjust the load of the IoT base station. Different load values ​​correspond to different base station load warning levels, and different base station load warning levels correspond to different load solutions. Determining a load solution based on the load value includes: when the load value is within a first numerical range, performing parameter optimization processing on the IoT base station, the parameter optimization processing including at least one of the following: adjusting power parameters, switching thresholds; the corresponding base station load warning level is level 0; when the load value is within a second numerical range, performing load balancing processing on the IoT base station; the corresponding base station load warning level is level 1; when the load value is within a third numerical range, performing radio frequency optimization processing or capacity expansion processing on the IoT base station; the radio frequency optimization processing is achieved by adjusting the antenna of the IoT base station; the capacity expansion processing is achieved by expanding the carrier of the IoT base station; the corresponding base station load warning level is level 2; when the load value is within a fourth numerical range, building a new IoT base station; the corresponding base station load warning level is level 3.

7. An electronic device, characterized in that, include: One or more processors; Storage device, on which one or more programs are stored, When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-5.

8. A computer-readable medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-5.

Images