Uplink power adjustment method, apparatus and device, and computer storage medium

Abstract

The invention discloses an uplink power adjustment method, apparatus and device, and a computer storage medium, and relates to the technical field of satellite communication. The method comprises the following steps: acquiring a signal transmission data sequence before a first moment; determining a weight of the signal transmission data according to the network quality parameter of the signal transmission data and a preset network quality parameter, and determining a first feature data sequence based on the signal transmission data and the corresponding weight; determining first signal transmission data sent to the satellite by the terminal at the corresponding second moment according to the corresponding relation between the feature data sequence and the signal transmission data sent to the satellite by the terminal at the target time; determining second signal transmission data corresponding to an uplink parameter influencing a network quality parameter according to the first signal transmission data; calculating predicted power based on the second signal transmission data; and adjusting the uplink power according to the predicted power. According to the embodiment of the invention, the influence of signal data transmission time on uplink power adjustment is reduced, and the real-time performance of uplink power adjustment is improved.

Description

Technical Field

[0001] The present application belongs to the field of satellite communication technology, and in particular, relates to a method, device, equipment and computer storage medium for uplink power adjustment. Background Art

[0002] With the development of satellite communication technology, how to control the uplink power of the terminal to transmit signals to the satellite and better play the advantages of satellite communication has become the primary problem that each manufacturer has to solve.

[0003] In the prior art, when adjusting the uplink power, the uplink power is often adjusted based on the downlink signal transmission data sent by the received satellite to the terminal. However, since it takes a certain amount of time for data to be sent from the satellite to the terminal, the uplink power adjustment of the terminal based on the signal transmission data obtained in the previous period has a lag, resulting in poor real-time performance of the uplink power adjustment. Summary of the invention

[0004] The embodiments of the present application provide a method, apparatus, device and computer storage medium for adjusting uplink power to solve the problem of poor real-time performance of uplink power adjustment in the prior art.

[0005] In a first aspect, an embodiment of the present application provides a method for adjusting uplink power, the method comprising:

[0006] Acquire a signal transmission data sequence sent by the satellite to the terminal before the first moment;

[0007] Determine the weight of the signal transmission data according to the network quality parameter of the signal transmission data in the signal transmission data sequence and the preset network quality parameter, and determine the first feature data sequence based on the signal transmission data and the weight corresponding to the signal transmission data;

[0008] Input the first characteristic data sequence into the characteristic prediction model, and determine the first signal transmission data sent by the satellite to the terminal at the second moment corresponding to the first characteristic data sequence through the correspondence between the characteristic data sequence in the characteristic prediction model and the signal transmission data sent by the satellite to the terminal at the target time; wherein the previous moment of the second moment is the first moment;

[0009] Determine, according to the first signal transmission data, second signal transmission data corresponding to the uplink parameter affecting the network quality parameter;

[0010] Inputting the second signal transmission data into the power prediction model, and calculating the predicted power based on the second signal transmission data by the power prediction model;

[0011] The uplink power is adjusted according to the predicted power.

[0012] In a second aspect, an embodiment of the present application provides a device for adjusting uplink power, the device comprising:

[0013] An acquisition module, used for acquiring a signal transmission data sequence sent by the satellite to the terminal before the first moment;

[0014] a determination module, configured to determine the weight of the signal transmission data according to the network quality parameter of the signal transmission data in the signal transmission data sequence and the preset network quality parameter, and determine the first feature data sequence based on the signal transmission data and the weight corresponding to the signal transmission data;

[0015] The determination module is further used to input the first characteristic data sequence into the characteristic prediction model, and determine the first signal transmission data sent by the satellite to the terminal at the second moment corresponding to the first characteristic data sequence through the correspondence between the characteristic data sequence in the characteristic prediction model and the signal transmission data sent by the satellite to the terminal at the target time; wherein the previous moment of the second moment is the first moment;

[0016] The determination module is further used to determine the second signal transmission data corresponding to the uplink parameter affecting the network quality parameter according to the first signal transmission data;

[0017] A calculation module, used for inputting the second signal transmission data into the power prediction model, and calculating the predicted power based on the second signal transmission data through the power prediction model;

[0018] The adjustment module is used to adjust the uplink power according to the predicted power.

[0019] In a third aspect, an embodiment of the present application provides a terminal device, which includes: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, the method for uplink power adjustment as in the first aspect is implemented.

[0020] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having computer program instructions stored thereon. When the computer program instructions are executed by a processor, the method for uplink power adjustment as in the first aspect is implemented.

[0021] In a fifth aspect, an embodiment of the present application provides a computer program product. When instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the method for uplink power adjustment as in the first aspect.

[0022] The embodiment of the present application provides a method, device, equipment and computer storage medium for adjusting uplink power. The method first obtains a signal transmission data sequence sent by a satellite to a terminal before a first moment, and provides raw data input for subsequent adjustment of uplink power. A first feature data sequence is determined based on the signal transmission data and the weight corresponding to the signal transmission data. The importance of feature parameters that have a greater impact on network quality can be characterized by weight allocation, thereby improving the representativeness of feature data. The data of the next moment of the acquired historical signal transmission data is predicted by a feature prediction model, providing a basis for the prediction and adjustment of uplink power. The data corresponding to the uplink parameters related to uplink power predicted at the first moment is determined by the relationship between the network quality parameter and the uplink parameter, and the key data affecting the uplink power adjustment can be obtained. The second signal transmission data is input into the power prediction model, the predicted power is calculated based on the second signal transmission data by the power prediction model, and the uplink power is adjusted according to the predicted power. The uplink power is adjusted using the predicted power, providing a time advance for the uplink power adjustment, which helps to reduce the impact of transmission delay on the uplink power adjustment. The embodiment of the present application predicts the data of the next time period through the acquired signal transmission data, and adjusts the power according to the predicted data, and adjusts the uplink power according to the predicted value, thereby reducing the impact of the signal data transmission time on the uplink power adjustment and improving the real-time performance of the uplink power adjustment. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0024] Figure 1 It is a flowchart of the method for uplink power adjustment provided in an embodiment of the present application;

[0025] Figure 2 It is a flowchart of a method for determining first signal transmission data provided in an embodiment of the present application;

[0026] Figure 3 is a flowchart of a method for determining second signal transmission data provided by an embodiment of the present application;

[0027] Figure 4 It is a flowchart of a method for determining predicted power provided in an embodiment of the present application;

[0028] Figure 5 It is a flowchart of a conventional uplink power adjustment method provided in an embodiment of the present application;

[0029] Figure 6It is a structural diagram of an uplink power adjustment device provided in an embodiment of the present application;

[0030] Figure 7 It is a schematic diagram of the structure of the terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0031] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0032] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0033] The prior art usually relies on receiving downlink signal transmission data sent from the satellite to the terminal when adjusting the uplink power. The basic logic of this process is to evaluate the current channel status by analyzing various parameters in the downlink signal transmission process, such as signal strength, bit error rate, etc., and adjust the uplink transmission power of the terminal accordingly to ensure the quality and efficiency of signal transmission. However, this method faces a significant challenge in practical applications, namely the delay of data transmission. Due to the long distance between the satellite and the terminal, it takes a certain propagation time for the signal to be sent from the satellite to the terminal. This means that when the terminal receives the downlink signal transmission data for adjusting the uplink power, these data actually reflect the channel status of the previous period. Therefore, the uplink power adjustment based on these data inevitably has a lag. This lag may cause the adjustment of the uplink power to be unable to adapt to the changes in the current channel in a timely manner, especially when the channel status fluctuates rapidly, the adjustment of the uplink power may appear particularly lagging and inaccurate.

[0034] In order to solve the existing technology, the embodiment of the present application provides a method, device, equipment and computer storage medium for uplink power adjustment. The method first obtains the signal transmission data sequence sent by the satellite to the terminal before the first moment, and provides the original data input for the subsequent uplink power adjustment. The first characteristic data sequence is determined based on the signal transmission data and the weight corresponding to the signal transmission data. The importance of the characteristic parameters that have a greater impact on the network quality can be characterized by the weight allocation, which improves the representativeness of the characteristic data. The data of the next moment of the acquired historical signal transmission data is predicted by the characteristic prediction model to provide a basis for the prediction and adjustment of the uplink power. The data corresponding to the uplink parameters related to the uplink power predicted at the first moment is determined by the relationship between the network quality parameter and the uplink parameter, and the key data affecting the uplink power adjustment can be obtained. The second signal transmission data is input into the power prediction model, the predicted power is calculated based on the second signal transmission data by the power prediction model, and the uplink power is adjusted according to the predicted power. The uplink power is adjusted using the predicted power, which provides a time advance for the uplink power adjustment, which helps to reduce the impact of the transmission delay on the uplink power adjustment. The embodiment of the present application predicts the data of the next time period through the acquired signal transmission data, and adjusts the power according to the predicted data, and adjusts the uplink power according to the predicted value, thereby reducing the impact of the signal data transmission time on the uplink power adjustment and improving the real-time performance of the uplink power adjustment.

[0035] The following describes the uplink power adjustment method provided in the embodiment of the present application in conjunction with the accompanying drawings.

[0036] Figure 1 FIG. 1 is a flow chart showing a method for adjusting uplink power provided by an embodiment of the present application. Figure 1 As shown, the method may include the following steps: S101 to S106.

[0037] S101, obtaining a signal transmission data sequence sent by a satellite to a terminal before a first moment.

[0038] Among them, the first moment is the time point for obtaining the signal transmission data sequence sent by the satellite to the terminal; the signal transmission data sequence is a time period of a preset time length before the first moment, and the time period includes the first moment, and the collected downlink data sent by the satellite to the terminal is a sequence constructed in chronological order.

[0039] In some embodiments, when acquiring a signal transmission data sequence, the full amount of signal transmission data within a time window as long as possible is acquired, wherein the time window is the time period of the signal transmission data acquired before the first moment, and the full amount means that the signal transmission data within the time window is complete and not truncated or lost. Short-term data may not reflect long-term change trends. Through data from a long time window, the change trend of signal transmission data can be better identified, and abnormal signal changes can be more easily discovered. Acquiring full data can ensure the accuracy and reliability of the analysis results.

[0040] In some embodiments, the signal transmission data may include time data, signal strength data, base station transmission power data, ephemeris data, and other data.

[0041] By acquiring a signal transmission data sequence sent by the satellite to the terminal before a first moment to be predicted, and using the signal transmission data sequence as subsequent input to predict the signal transmission data sent by the satellite to the terminal at the next moment after the first moment.

[0042] S102, determining the weight of the signal transmission data according to the network quality parameter of the signal transmission data in the signal transmission data sequence and the preset network quality parameter, and determining a first feature data sequence based on the signal transmission data and the weight corresponding to the signal transmission data.

[0043] Among them, the network quality parameter is an indicator for measuring network performance, the preset network quality parameter is a pre-selected parameter that affects the network quality, for example, it may include parameters such as signal strength, signal-to-noise ratio, transmission delay and spectrum efficiency; the weight is a numerical value assigned to the signal transmission data according to the network quality parameter of the signal transmission data, indicating the degree of influence of each signal transmission data on the network quality; the first characteristic data sequence is a data sequence containing data that affects the network quality.

[0044] By assigning corresponding weights to different signal transmission data and adjusting the signal transmission data sequence based on the weights, the transmission data that has an impact on the network quality can be made more prominent in the first feature data sequence.

[0045] S103, inputting the first characteristic data sequence into the characteristic prediction model, and determining the first signal transmission data sent by the satellite to the terminal at the second moment corresponding to the first characteristic data sequence through the correspondence between the characteristic data sequence in the characteristic prediction model and the signal transmission data sent by the satellite to the terminal at the target time; wherein the previous moment of the second moment is the first moment.

[0046] The second moment is the next moment of the moment of acquiring the signal transmission data, the first signal transmission data is the first characteristic data generated based on the signal transmission data acquired before the first moment, and the transmission data affecting the network quality is predicted at the second moment.

[0047] In some embodiments, after the first feature data sequence is input into the feature prediction model, the feature prediction model can calculate the first signal transmission data corresponding to the first feature data sequence based on the correspondence formula between the feature data sequence and the signal transmission data sent by the target time satellite to the terminal, wherein the correspondence formula can be set according to actual needs.

[0048] In some embodiments, after the first feature data is input into the feature prediction model, the feature prediction model can also perform feature extraction on the first feature data sequence using a convolution operation according to the convolutional neural network in the feature prediction model and a pre-trained convolution kernel, and perform weighted summation on the extracted features according to the fully connected layer and preset model parameters to obtain the first signal transmission data.

[0049] Using the feature prediction model, we can more accurately predict the signal transmission data that the satellite will send to the terminal at the next moment. By predicting the signal transmission data at the next moment and using it as the basis for analysis and adjustment, we can optimize network performance and satellite communication service quality.

[0050] S104: Determine second signal transmission data corresponding to an uplink parameter affecting a network quality parameter according to the first signal transmission data.

[0051] Among them, the second signal transmission data is data corresponding to the uplink parameters, the uplink parameters are parameters that affect the uplink quality, and can also include path loss formula parameters, which are set according to actual needs.

[0052] In some embodiments, the uplink parameters may specifically include parameters such as satellite base station transmission power, signal strength received by the terminal, rain attenuation, fast attenuation, slow attenuation, interference, thermal noise and user equipment (UE) noise.

[0053] In some embodiments, when determining the second signal transmission data based on the first signal transmission data, when the parameters corresponding to the second signal transmission data are the same as the parameters corresponding to the first signal transmission data, the first transmission data is used as the second transmission data; when there is a corresponding relationship between the parameters corresponding to the second signal transmission data and the parameters corresponding to the first signal transmission data, the second signal transmission data is calculated through the corresponding relationship.

[0054] In one example, when the parameter corresponding to the first signal transmission data and the parameter corresponding to the second signal transmission data are both signal strengths, the signal strength data in the first signal transmission data is used as the signal strength data in the second signal transmission data.

[0055] In an example, when the parameters corresponding to the first signal transmission data are satellite transmission power, terminal reception power and signal wavelength, and the parameter corresponding to the second signal transmission data is propagation distance, the propagation distance is calculated by the relationship between satellite transmission power, terminal reception power and propagation distance, and the formula can be expressed as:

[0056]

[0057] Among them, d is the propagation distance, λ is the signal wavelength, pr is the received power, and pt is the transmitted power.

[0058] By calculating the second signal transmission data through the first signal transmission data, the predicted data having an impact on the uplink power can be obtained. Through precise calculation and corresponding relationship, the second signal transmission data can be predicted and determined more accurately, thereby improving the prediction accuracy.

[0059] S105: input the second signal transmission data into a power prediction model, and calculate the predicted power based on the second signal transmission data through the power prediction model.

[0060] In some embodiments, after the second signal transmission data is input into the power prediction model, the second signal transmission data can be subjected to feature extraction using a convolution operation according to the convolutional neural network in the power prediction model and a pre-trained convolution kernel, and the extracted features are weighted and summed according to the fully connected layer and preset model parameters to obtain predicted power.

[0061] In some embodiments, the power prediction model may be a MobileNet neural network model, which takes depthwise separable convolution as the core and splits the standardized convolution into depthwise convolution and pointwise convolution.

[0062] Since the second signal transmission data is predicted data, by predicting the power through the second signal transmission data, possible power requirements can be known in advance, thereby performing effective power control.

[0063] S106: Adjust the uplink power according to the predicted power.

[0064] First, the signal transmission data sequence sent by the satellite to the terminal before the first moment is obtained to provide the original data input for the subsequent adjustment of the uplink power. The first characteristic data sequence is determined based on the signal transmission data and the weight corresponding to the signal transmission data. The importance of the characteristic parameters that have a greater impact on the network quality can be characterized through the weight allocation, which improves the representativeness of the characteristic data. The data of the next moment of the acquired historical signal transmission data is predicted by the characteristic prediction model to provide a basis for the prediction and adjustment of the uplink power. The data corresponding to the uplink parameters related to the uplink power predicted at the first moment is determined by the relationship between the network quality parameters and the uplink parameters, and the key data affecting the uplink power adjustment can be obtained. The second signal transmission data is input into the power prediction model, and the predicted power is calculated based on the second signal transmission data through the power prediction model, and the uplink power is adjusted according to the predicted power. The uplink power is adjusted using the predicted power, which provides a time advance for the uplink power adjustment, which helps to reduce the impact of transmission delay on the uplink power adjustment. The embodiment of the present application predicts the data of the next time period through the acquired signal transmission data, and adjusts the power according to the predicted data, and adjusts the uplink power according to the predicted value, thereby reducing the impact of the signal data transmission time on the uplink power adjustment and improving the real-time performance of the uplink power adjustment.

[0065] In one embodiment, the acquired signal transmission data includes at least time, signal strength, base station transmission power and ephemeris time, and the acquired signal transmission data sequence is shown in Table 1.

[0066] Table 1 Signal transmission data sequence

[0067] time Signal Strength Base station transmission power Ephemeris … 1 R1 WT1 f(x1) … 2 R2 WT2 f(x2) … 3 R3 WT3 f(x3) … 4 R4 WT4 f(x4) … 5 R5 WT5 f(x5) … 6 R6 WT6 f(x6) … … … … … …

[0068] In some embodiments, determining the weight of the signal transmission data according to the network quality parameter of the signal transmission data in the signal transmission data sequence and the preset network quality parameter may include:

[0069] In the case where the network quality parameter to which the signal transmission data belongs is a preset network quality parameter, the weight is a first weight;

[0070] When the network quality parameter to which the signal transmission data belongs is not a preset network quality parameter, the weight is a second weight.

[0071] By assigning different weights to signal transmission data that meets preset network quality parameters and distinguishing between first weights and second weights, different weights can be assigned to different types of data more accurately, which helps to improve the accuracy and reliability of prediction.

[0072] In one example, determining the first feature data sequence based on the signal transmission data and the weight corresponding to the signal transmission data may include:

[0073] Convert the acquired signal transmission data sequence into matrix form:

[0074]

[0075] Among them, R n is the signal strength at the nth time, WT n is the base station transmission power at the nth time, f(x n ) is the ephemeris of the nth time.

[0076] The signal transmission data is assigned values ​​according to the weights corresponding to the signal transmission data to obtain the first characteristic data sequence. The formula can be expressed as:

[0077]

[0078] Among them, X (1) is the first feature data sequence, P RANn is the weight of the signal transmission data at the nth time, X n is the nth signal transmission data, P is the weight corresponding to the signal transmission data, and L1 is the preset network quality parameter.

[0079] The data matrix corresponding to the first feature data sequence can be:

[0080]

[0081] in, is the weighted signal strength at the nth time, is the weighted base station transmission power at the nth time, f(x n ) 1 is the weighted ephemeris at the nth time.

[0082] In some embodiments, Figure 2 As shown, determining the first signal transmission data sent by the satellite to the terminal at the second moment corresponding to the first feature data sequence through the correspondence between the feature data sequence in the feature prediction model and the signal transmission data sent by the satellite to the terminal at the target time can include: S201 to S204.

[0083] S201, calculating the sum of each signal transmission data in the first feature data sequence and the signal transmission data at the previous moment by using a feature prediction model to obtain a data sequence of target signal transmission data;

[0084] S202, calculating the change amount of adjacent target signal transmission data in the data sequence, and the weighted change amount of adjacent target signal transmission data after weighting;

[0085] S203, determining the correspondence between the characteristic data sequence and the signal transmission data sent by the satellite to the terminal at the target time based on the variation and the weighted variation, and the model parameters;

[0086] S204: Determine first signal transmission data based on the corresponding relationship.

[0087] By calculating the change amount and weighted change amount, the dynamic changes of signal transmission data can be captured more accurately, providing richer information for prediction. By building a feature prediction model, the regularity and correlation in historical data can be used to improve the accuracy of prediction.

[0088] In some embodiments, the sum of each signal transmission data in the first characteristic data sequence and the signal transmission data at the previous moment is calculated to obtain a data sequence of the target signal transmission data. The formula may be:

[0089]

[0090] Among them, X (2) Transmit data for the target signal, P RANn is the weight of the signal transmission data at the nth time, X n is the nth signal transmission data, P is the weight corresponding to the signal transmission data, and L1 is the preset network quality parameter.

[0091] The data sequence corresponding to the target signal transmission data can be:

[0092]

[0093] in, is the accumulated weighted signal strength at the nth time, is the accumulated weighted base station transmission power at the nth time, f(x n ) 2 is the accumulated weighted ephemeris at the nth time.

[0094] In one example, the target signal transmission data at the first time is the first signal transmission data in the first feature data sequence, the target signal transmission data at the second time is the sum of the first signal transmission data and the second signal transmission data in the first feature data sequence, the target signal transmission data at the third time is the sum of the first signal transmission data, the second signal transmission data, and the third signal transmission data in the first feature data sequence, and so on.

[0095] In some embodiments, before calculating the change in adjacent target signal transmission data in the data sequence, the method may further include:

[0096] sequentially calculating ratios of adjacent target signal transmission data;

[0097] In the case where the ratio does not fall within the set range, target update data is determined according to preset transformation parameters, and adjacent target signal transmission data is updated according to the target update data.

[0098] In some embodiments, the ratio formula may be:

[0099]

[0100] Among them, λ is the ratio, X k Transmit data for the target signal, X k-1 The data of the target signal at the last moment of transmission.

[0101] The range formula can be set to:

[0102]

[0103] Among them, λ is the ratio and n is the number of data in the sequence.

[0104] The target update data is determined according to the preset transformation parameters. The formula is:

[0105] Y k =X k +c, X=[R,W,f(x),···], c∈C, k=0,1,2,3,···

[0106] Among them, X k Transmit data for the target signal, Y k is the target update data, c is the preset transformation parameter, and C is the preset transformation parameter set.

[0107] In some embodiments, Figure 3 As shown, determining the correspondence between the characteristic data sequence and the signal transmission data sent by the satellite to the terminal at the target time based on the variation and the weighted variation, as well as the model parameters, may include: S301 to S303.

[0108] S301, generating a difference matrix based on the variation;

[0109] S302, generating a weighted matrix according to the weighted variation;

[0110] S303, determining second signal transmission data according to the difference matrix, the weighting matrix and the model parameters.

[0111] By calculating the difference of the accumulated data to convert the data into a number series with an exponential growth law, and determining the second signal transmission data according to the number series, accurate prediction of future trends can be achieved.

[0112] In some embodiments, a difference matrix is ​​generated based on the variation, and the formula may be:

[0113]

[0114] Among them, X′ k is the difference, Transmit data for the target signal, The data of the target signal at the last moment of transmission.

[0115] The weighted matrix is ​​generated according to the weighted change. The formula can be:

[0116]

[0117] Among them, Z k is the weighted change, α is the preset weight parameter, and its value range is between (0, 1).

[0118] In some embodiments, the second signal transmission data is determined according to the difference matrix, the weighting matrix and the model parameters, and the formula may be:

[0119]

[0120] Among them, a is the development coefficient, which characterizes the trend of eigenvalue change, b is the grayscale action, which characterizes the eigenvalue of the grayscale prediction model, and t is the time, which characterizes the eigenvalue of the grayscale prediction model.

[0121] Assumptions And construct the following solution matrix:

[0122]

[0123] Obviously, D = uH, then we can get u = (B T B) -1 B T , in summary, the solution is:

[0124]

[0125] X(k+1)=X (2) (k+1)-X (2) (k), X=[R,W,f(x),···]

[0126] Among them, X(k+1) is the characteristic data of the next moment, a is the development coefficient, and b is the grayscale action amount.

[0127] In some embodiments, Figure 4 As shown, the power prediction model extracts features from the second feature data, and determines the predicted power according to the extracted features and preset weight parameters, which may include: S401 to S403.

[0128] S401, performing weighted summation on corresponding second signal transmission data according to a plurality of first preset convolution kernels of a power prediction model to obtain a first target feature;

[0129] S402, performing dimensionality reduction processing on the first target feature according to a second preset convolution kernel of the power prediction model to obtain a second target feature;

[0130] S403: Input the second target feature into the fully connected layer of the power prediction model, perform weighted summation on the second target feature according to a preset weight parameter, and obtain the predicted power corresponding to the second target feature.

[0131] The convolution operation is decomposed into two parts: depthwise convolution and pointwise convolution. In the depthwise convolution stage, each input channel is convolved independently with a convolution kernel, thereby reducing the number of convolution kernels. In the pointwise convolution stage, feature combination and mixing between channels are performed, further reducing parameters and improving overall computational efficiency.

[0132] The first target feature is obtained by performing weighted summation of multiple first preset convolutions and the corresponding second signal transmission data respectively, which is a deep convolution process. One channel of the deep convolution corresponds to one convolution kernel, which only changes the size of the feature map but does not change the number of channels of the feature map. The dimensionality reduction process of the first target feature according to the second preset convolution kernel is a point-by-point convolution process. The point-by-point convolution performs a convolution operation through a convolution kernel of size 1X1, which does not change the size of the feature map but only changes the number of channels of the feature map.

[0133] In one example, the input feature matrix size is H×W×N, the output feature matrix size is H×W×M, and the standard convolution kernel size is Z k ×Z k , then when conventional convolution is used, the amount of calculation can be expressed as Z k ×Z k ×N×M×H×W, while when using depth-wise separable convolution, the computational complexity of depth-wise convolution is Z k ×Z k ×N×H×W, the computational complexity of point-by-point convolution is N×M×H×W, and the total computational complexity is:

[0134] Z k ×Z k ×N×H×W+N×M×H×W

[0135] Comparing the two, we can get the ratio of the two:

[0136]

[0137] Therefore, the computational effort of the neural network is significantly reduced by using depthwise separable convolutions.

[0138] In some embodiments, before inputting the first feature data sequence into the feature prediction model, the method may further include:

[0139] Acquire training feature data sequence and training signal transmission data;

[0140] Input the training feature data sequence into the preset feature prediction model, and determine the training signal prediction data sent by the satellite to the terminal at the second moment corresponding to the training feature data sequence through the correspondence between the feature data sequence in the preset feature prediction model and the signal transmission data sent by the satellite to the terminal at the target time;

[0141] Determine a loss function value based on the training signal transmission data and the training signal prediction data;

[0142] When the difference between the training signal transmission data and the training signal prediction data is greater than the set threshold, the characteristic parameters are determined according to the loss function value and the preset characteristic prediction model is updated until the difference is less than or equal to the set threshold, and the updated preset characteristic parameters and the corresponding characteristic prediction model are obtained. The characteristic parameters are parameters corresponding to the corresponding relationship between the characteristic data sequence and the signal transmission data sent by the target time satellite to the terminal.

[0143] By training and updating the model, the model performance can be optimized according to the actual data and the accuracy of the prediction can be improved. The use of the loss function provides a quantitative optimization target for model training, which helps to reduce the prediction error.

[0144] In the prior art, the uplink transmission power is estimated based on the signal transmission quality, or based on the downlink quality estimation, or based on the uplink quality to adjust the uplink transmission power of the next period. Figure 6 As shown, the terminal sends a Physical Random Access Channel (PRACH) preamble to the base station. When the base station does not respond, the transmission power is increased. After the base station responds, it sends a transmission power control signal (TPC) through the Physical Downlink Control Channel (PDCCH) to control the uplink transmission power of the terminal in the next time period. The terminal selects the transmission power for the next time period based on TPC. They are all uplink power adjustment methods between the base station and the satellite, and there is no method for adjusting the uplink power when the terminal is directly connected to the satellite. The present application selects the output power according to the prediction model, which puts the decision-making power on the terminal side to a certain extent.

[0145] Figure 6 An uplink power adjustment device 600 provided in an embodiment of the present application is shown. Figure 6 As shown, the device may include:

[0146] An acquisition module 601 is used to acquire a signal transmission data sequence sent by a satellite to a terminal before a first moment;

[0147] A determination module 602, configured to determine the weight of the signal transmission data according to the network quality parameter of the signal transmission data in the signal transmission data sequence and a preset network quality parameter, and determine a first feature data sequence based on the signal transmission data and the weight corresponding to the signal transmission data;

[0148] The determination module 602 is further configured to input the first characteristic data sequence into a characteristic prediction model, and determine the first signal transmission data sent by the satellite to the terminal at a second moment corresponding to the first characteristic data sequence through the correspondence between the characteristic data sequence in the characteristic prediction model and the signal transmission data sent by the satellite to the terminal at the target time; wherein the previous moment of the second moment is the first moment;

[0149] The determination module 602 is further configured to determine, according to the first signal transmission data, second signal transmission data corresponding to an uplink parameter affecting a network quality parameter;

[0150] A calculation module 603, configured to input the second signal transmission data into a power prediction model, and calculate the predicted power based on the second signal transmission data through the power prediction model;

[0151] The adjustment module 604 is configured to adjust the uplink power according to the predicted power.

[0152] In some embodiments, the determination module 602 is further configured to, when the network quality parameter to which the signal transmission data belongs is the preset network quality parameter, the weight is a first weight;

[0153] The determination module 602 is further configured to, when the network quality parameter to which the signal transmission data belongs is not the preset network quality parameter, set the weight to a second weight.

[0154] In some embodiments, the calculation module 603 is further used to calculate the sum of each signal transmission data in the first feature data sequence and the signal transmission data at the previous moment through the feature prediction model to obtain a data sequence of target signal transmission data;

[0155] The calculation module 603 is further used to calculate the change amount of the transmission data of adjacent target signals in the data sequence, and the weighted change amount of the adjacent target signals after weighting;

[0156] The determination module 602 is further used to determine the correspondence between the characteristic data sequence and the signal transmission data sent by the satellite to the terminal at the target time based on the change amount and the weighted change amount and the model parameter;

[0157] The determination module 602 is further configured to determine the first signal transmission data based on the corresponding relationship.

[0158] In some embodiments, the uplink power adjustment device 600 may further include:

[0159] A generating module, used for generating a difference matrix based on the variation;

[0160] A generating module is further used to generate a weighting matrix according to the weighted variation;

[0161] The determination module 602 is further configured to determine the second signal transmission data according to the difference matrix, the weighting matrix and the model parameters.

[0162] In some embodiments, the uplink power adjustment device 600 may further include:

[0163] A weighting module, used for performing weighted summation on the corresponding second signal transmission data according to a plurality of first preset convolution kernels of the power prediction model to obtain a first target feature;

[0164] A dimensionality reduction module, used for performing dimensionality reduction processing on the first target feature according to a second preset convolution kernel of the power prediction model to obtain a second target feature;

[0165] The weighting module is also used to input the second target feature into the fully connected layer of the power prediction model, perform weighted summation on the second target feature according to a preset weight parameter, and obtain the predicted power corresponding to the second target feature.

[0166] In some embodiments, the acquisition module 601 is further used to acquire a training feature data sequence and training signal transmission data;

[0167] The determination module 602 is further configured to input the training feature data sequence into a preset feature prediction model, and determine the training signal prediction data sent by the satellite to the terminal at the second moment corresponding to the training feature data sequence through the correspondence between the feature data sequence in the preset feature prediction model and the signal transmission data sent by the satellite to the terminal at the target time;

[0168] The determination module 602 is further configured to determine a loss function value according to the training signal transmission data and the training signal prediction data;

[0169] The determination module 602 is also used to determine the characteristic parameters and update the preset characteristic prediction model according to the loss function value when the difference between the training signal transmission data and the training signal prediction data is greater than a set threshold, until the difference is less than or equal to the set threshold, to obtain the updated preset characteristic parameters and the corresponding characteristic prediction model, wherein the characteristic parameters are parameters corresponding to the correspondence between the characteristic data sequence and the signal transmission data sent by the target time satellite to the terminal.

[0170] Figure 6 The various modules in the device shown can be implemented Figure 1 Each step in the above steps can achieve the corresponding technical effect, which will not be repeated here for the sake of brevity.

[0171] Figure 7 A schematic diagram of the hardware structure of a terminal device provided in an embodiment of the present application is shown.

[0172] The terminal device may include a processor 701 and a memory 702 storing computer program instructions.

[0173] Specifically, the processor 701 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0174] The memory 702 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 702 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In one example, the memory 702 may include a removable or non-removable (or fixed) medium, or the memory 702 is a non-volatile solid-state memory. The memory 702 may be inside or outside the integrated gateway disaster recovery device.

[0175] In one example, the memory 702 may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Thus, generally, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method for uplink power adjustment according to the present disclosure.

[0176] The processor 701 reads and executes the computer program instructions stored in the memory 702 to implement Figure 1 The uplink power adjustment method in the illustrated embodiment.

[0177] In one example, the terminal device may further include a communication interface 703 and a bus 704. Figure 7 As shown, the processor 701, the memory 702, and the communication interface 703 are connected via a bus 704 and communicate with each other.

[0178] The communication interface 703 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0179] Bus 704 includes hardware, software or both, and the components of terminal equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (Accelerated Graphics Port, AGP) or other graphics bus, enhanced industry standard architecture (Extended Industry Standard Architecture, EISA) bus, front side bus (Front Side Bus, FSB), Hyper Transport (Hyper Transport, HT) interconnection, industry standard architecture (Industry Standard Architecture, ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 704 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the application considers any suitable bus or interconnection.

[0180] In addition, in combination with the uplink power adjustment method in the above embodiment, the embodiment of the present application can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any uplink power adjustment method in the above embodiment is implemented.

[0181] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed, implements any one of the uplink power adjustment methods in the above embodiments.

[0182] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0183] The functional blocks shown in the structural block diagram described above can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), appropriate firmware, plug-in, function card, etc. When implemented in software, the elements of the present application are programs or text segments used to perform the required tasks. The program or text segment can be stored in a machine-readable medium, or transmitted on a transmission medium or communication link via a data signal carried in a carrier. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, read-only memory (Read-Only Memory, ROM), flash memory, erasable read-only memory (Erasable ReadOnly Memory, EROM), floppy disks, compact disc read-only memory (Compact Disc Read-Only Memory, CD-ROM), optical discs, hard disks, optical fiber media, radio frequency (Radio Frequency, RF) links, etc. The text segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0184] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0185] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0186] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A method for adjusting uplink power, characterized in that: include: Acquire a signal transmission data sequence sent by the satellite to the terminal before the first moment; Determine the weight of the signal transmission data according to the network quality parameter of the signal transmission data in the signal transmission data sequence and the preset network quality parameter, and determine the first feature data sequence based on the signal transmission data and the weight corresponding to the signal transmission data; Input the first characteristic data sequence into a characteristic prediction model, and determine the first signal transmission data sent by the satellite to the terminal at the second moment corresponding to the first characteristic data sequence through the correspondence between the characteristic data sequence in the characteristic prediction model and the signal transmission data sent by the satellite to the terminal at the target time; wherein the previous moment of the second moment is the first moment; Determine, according to the first signal transmission data, second signal transmission data corresponding to an uplink parameter affecting a network quality parameter; Inputting the second signal transmission data into a power prediction model, and calculating predicted power based on the second signal transmission data by using the power prediction model; The uplink power is adjusted according to the predicted power.

2. The method for adjusting uplink power according to claim 1, characterized in that: The determining the weight of the signal transmission data according to the network quality parameter of the signal transmission data in the signal transmission data sequence and the preset network quality parameter comprises: In a case where the network quality parameter to which the signal transmission data belongs is the preset network quality parameter, the weight is a first weight; In a case where the network quality parameter to which the signal transmission data belongs is not the preset network quality parameter, the weight is a second weight.

3. The method for uplink power adjustment according to claim 1, characterized in that: The determining, based on the correspondence between the feature data sequence in the feature prediction model and the signal transmission data sent by the satellite to the terminal at the target time, the first signal transmission data sent by the satellite to the terminal at the second time corresponding to the first feature data sequence includes: The sum of each signal transmission data in the first feature data sequence and the signal transmission data at the previous moment is calculated by the feature prediction model to obtain a data sequence of target signal transmission data; Calculating the change amount of adjacent target signal transmission data in the data sequence and the weighted change amount of adjacent target signal transmission data after weighting; Determine the correspondence between the characteristic data sequence and the signal transmission data sent by the satellite to the terminal at the target time based on the variation and the weighted variation, as well as the model parameters; The first signal transmission data is determined based on the corresponding relationship.

4. The method for adjusting uplink power according to claim 3, characterized in that: The determining, based on the variation and the weighted variation, and the model parameters, of the corresponding relationship between the characteristic data sequence and the target time satellite sending signal transmission data to the terminal comprises: generating a difference matrix based on the variation; generating a weighting matrix according to the weighted variation; The second signal transmission data is determined according to the difference matrix, the weighting matrix and the model parameters.

5. The method for adjusting uplink power according to claim 1, characterized in that: The calculating the predicted power based on the second signal transmission data by using the power prediction model includes: Performing weighted summation on the corresponding second signal transmission data according to the plurality of first preset convolution kernels of the power prediction model to obtain a first target feature; Performing dimensionality reduction processing on the first target feature according to a second preset convolution kernel of the power prediction model to obtain a second target feature; The second target feature is input into the fully connected layer of the power prediction model, and the second target feature is weighted summed according to a preset weight parameter to obtain the predicted power corresponding to the second target feature.

6. The method for adjusting uplink power according to any one of claims 1 to 5, characterized in that: Before inputting the first feature data sequence into the feature prediction model, the method further includes: Acquire training feature data sequence and training signal transmission data; Input the training feature data sequence into a preset feature prediction model, and determine the training signal prediction data sent by the satellite to the terminal at the second moment corresponding to the training feature data sequence through the correspondence between the feature data sequence in the preset feature prediction model and the signal transmission data sent by the satellite to the terminal at the target time; Determine a loss function value according to the training signal transmission data and the training signal prediction data; When the difference between the training signal transmission data and the training signal prediction data is greater than a set threshold, the characteristic parameters are determined according to the loss function value and the preset characteristic prediction model is updated until the difference is less than or equal to the set threshold, thereby obtaining the updated preset characteristic parameters and the corresponding characteristic prediction model, wherein the characteristic parameters are parameters corresponding to the corresponding relationship between the characteristic data sequence and the signal transmission data sent by the target time satellite to the terminal.

7. An uplink power adjustment device, characterized in that: The device comprises: An acquisition module, used for acquiring a signal transmission data sequence sent by the satellite to the terminal before the first moment; a determination module, configured to determine the weight of the signal transmission data according to the network quality parameter of the signal transmission data in the signal transmission data sequence and a preset network quality parameter, and determine a first feature data sequence based on the signal transmission data and the weight corresponding to the signal transmission data; The determination module is further used to input the first characteristic data sequence into a characteristic prediction model, and determine the first signal transmission data sent by the satellite to the terminal at a second moment corresponding to the first characteristic data sequence through the correspondence between the characteristic data sequence in the characteristic prediction model and the signal transmission data sent by the satellite to the terminal at the target time; wherein the previous moment of the second moment is the first moment; The determination module is further used to determine, according to the first signal transmission data, second signal transmission data corresponding to the uplink parameter affecting the network quality parameter; a calculation module, configured to input the second signal transmission data into a power prediction model, and calculate the predicted power based on the second signal transmission data through the power prediction model; An adjustment module is used to adjust the uplink power according to the predicted power.

8. A terminal device, characterized in that: The device comprises: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, the method for uplink power adjustment according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the method for uplink power adjustment according to any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the method for uplink power adjustment as described in any one of claims 1-6.

Images