Signal optimization method and system for wireless transmission equipment

Abstract

The invention provides a signal optimization method and system for wireless transmission equipment, and relates to the technical field of wireless communication, and the method comprises the steps: constructing a movement track prediction model, and carrying out the prediction processing of communication state parameters through the movement track prediction model, and obtaining a speed sequence and a position track; performing conjugate gradient optimization and dynamic step length adjustment on the speed sequence, and further performing dynamic phase compensation on the position trajectory by the optimized and adjusted speed sequence to obtain a trajectory compensation parameter; sparse compressed sensing is carried out on communication signals of the wireless transmission equipment to obtain a sparse coefficient matrix, and a power distribution vector is determined based on the sparse coefficient matrix and the track compensation parameters; and determining a communication evaluation value according to the signal to interference plus noise ratio change and the power distribution vector of the wireless transmission equipment, and optimizing and updating the power control parameter of the wireless transmission equipment based on the communication evaluation value, thereby realizing the dynamic power control of the mobile Internet of Things terminal based on prediction compensation so as to improve the stability of signal optimization.

Description

Technical Field

[0001] The present application relates to the field of wireless communication technology, and more specifically, to a signal optimization method and system for wireless transmission equipment. Background Art

[0002] With the rapid development of mobile communication technology and Internet of Things technology, wireless communication has become the mainstream means of information transmission and is widely used in scenarios such as smart terminals, industrial control, and Internet of Vehicles. The core of wireless communication is to transmit signals in space through electromagnetic waves to achieve information exchange between devices. Its performance is affected by many factors such as channel conditions, terminal mobility, and interference intensity.

[0003] Wireless transmission equipment is a fundamental component of wireless communication systems, and its signal optimization methods are directly related to the stability and communication quality of data transmission. Current signal optimization methods are mostly based on real-time channel estimation and static parameter adjustment, adjusting the transmission power, modulation method, or channel coding strategy to improve signal quality. However, traditional methods rely on feedback from the current channel state and lack a mechanism to predict future channel changes. This makes it difficult to cope with channel fluctuations caused by the high-speed movement of mobile IoT terminals, and they lack the ability to accurately compensate for trajectory changes. Most existing power control methods for mobile IoT terminals still use fixed weights or open-loop adjustment methods, which are unable to make fine dynamic adjustments based on real-time channel characteristics, interference conditions, and signal sparsity. Therefore, how to implement dynamic power control for mobile IoT terminals based on prediction compensation to improve the stability of signal optimization is a difficult problem facing the industry. Summary of the Invention

[0004] The present application provides a signal optimization method and system for wireless transmission equipment, which can realize dynamic power control of mobile Internet of Things terminals based on prediction compensation to improve the stability of signal optimization.

[0005] In a first aspect, the present application provides a signal optimization method and system for a wireless transmission device, the signal optimization method comprising the following steps:

[0006] Obtain the communication status parameters of wireless transmission equipment and build a movement trajectory prediction model;

[0007] The communication state parameters are predicted by the mobile trajectory prediction model to obtain a speed sequence and a position trajectory during signal transmission;

[0008] performing conjugate gradient optimization and dynamic step size adjustment on the velocity sequence to obtain an optimized and adjusted velocity sequence, and then performing dynamic phase compensation on the position trajectory based on the optimized and adjusted velocity sequence to obtain a trajectory compensation parameter;

[0009] collecting a communication signal of a wireless transmission device, performing sparse compressed sensing on the communication signal to obtain a sparse coefficient matrix, and determining a power allocation vector of the wireless transmission device based on the sparse coefficient matrix and the trajectory compensation parameter;

[0010] A communication evaluation value is determined according to a signal to interference noise ratio change of the wireless transmission device and the power allocation vector, and a power control parameter of the wireless transmission device is optimized and updated based on the communication evaluation value.

[0011] In this embodiment, the wireless transmission device is a mobile Internet of Things terminal.

[0012] In this embodiment, historical communication data of a wireless transmission device is acquired, and a movement trajectory prediction model based on a long short-term memory network is constructed based on the historical communication data.

[0013] In this embodiment, the communication state parameters are predicted by the mobile trajectory prediction model to obtain the speed sequence and position trajectory during signal transmission, specifically including:

[0014] The movement trajectory prediction model obtains a speed sequence during signal transmission by performing time sequence recursion on the communication state parameters;

[0015] The movement trajectory prediction model obtains the position trajectory during signal transmission by performing position prediction on the communication state parameters.

[0016] In this embodiment, the speed sequence is subjected to conjugate gradient optimization and dynamic step size adjustment to obtain the optimized and adjusted speed sequence, which specifically includes:

[0017] Using a conjugate gradient optimization algorithm to perform gradient optimization on the velocity sequence to obtain a gradient optimized sequence;

[0018] The gradient optimization sequence is subjected to step-size adjustment based on a Riemannian manifold to obtain an optimized and adjusted velocity sequence.

[0019] In this embodiment, dynamic phase compensation is performed on the position trajectory using the optimized and adjusted velocity sequence to obtain trajectory compensation parameters, specifically including:

[0020] Discretize the optimized and adjusted speed sequence to obtain instantaneous speeds at different transmission time points;

[0021] Constructing a phase drift model based on the transmission time point through all instantaneous velocities and the position trajectories;

[0022] The phase drift model is optimized through conjugate gradient to obtain a phase compensation function, and then the trajectory compensation parameters are determined by the phase compensation function.

[0023] In this embodiment, the communication signal of the wireless transmission device is collected by a synchronous sampling circuit.

[0024] In this embodiment, performing sparse compressed sensing on the communication signal to obtain a sparse coefficient matrix specifically includes:

[0025] Performing a sliding window division process on the communication signal to obtain a plurality of time-continuous sub-signal segments;

[0026] Perform sparse basis transformation on each sub-signal segment to obtain a sparse domain;

[0027] Determining a sparse coefficient solution function by regression based on least absolute shrinkage and selection operators in the sparse domain;

[0028] The sparse coefficient solution function is iteratively optimized by using a back-propagation neural network through a gradient optimization algorithm to obtain multiple iteratively optimized sparse coefficients, and then a sparse coefficient matrix is constructed through all the iteratively optimized sparse coefficients.

[0029] In this embodiment, optimizing and updating the power control parameters of the wireless transmission device based on the communication evaluation value specifically includes:

[0030] Determining an allocation ratio of a power control parameter in a wireless transmission device according to the communication evaluation value;

[0031] The power control parameters of the wireless transmission device are iteratively updated according to the allocation ratio to obtain a power control instruction, and the signal optimization of the wireless transmission device is further achieved by the power control instruction.

[0032] In a second aspect, the present application provides a signal optimization system for a wireless transmission device, configured to execute a signal optimization method for a wireless transmission device, the signal optimization system comprising:

[0033] The state acquisition module is used to obtain the communication state parameters of the wireless transmission equipment and build a mobile trajectory prediction model;

[0034] A trajectory prediction module is used to predict the communication state parameters using the mobile trajectory prediction model to obtain a speed sequence and position trajectory during signal transmission;

[0035] a phase compensation module, configured to perform conjugate gradient optimization and dynamic step size adjustment on the velocity sequence to obtain an optimized and adjusted velocity sequence, and then perform dynamic phase compensation on the position trajectory based on the optimized and adjusted velocity sequence to obtain trajectory compensation parameters;

[0036] a signal processing module, configured to collect communication signals of a wireless transmission device, perform sparse compressed sensing on the communication signals to obtain a sparse coefficient matrix, and determine a power allocation vector of the wireless transmission device based on the sparse coefficient matrix and the trajectory compensation parameter;

[0037] The power control module is used to determine a communication evaluation value according to a change in the signal to interference and noise ratio of the wireless transmission device and the power allocation vector, and optimize and update the power control parameters of the wireless transmission device based on the communication evaluation value.

[0038] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects:

[0039] By acquiring the communication state parameters of the wireless transmission device, a mobile trajectory prediction model is constructed; the communication state parameters are predicted and processed by the mobile trajectory prediction model to obtain a speed sequence and a position trajectory during signal transmission; the speed sequence is subjected to conjugate gradient optimization and dynamic step size adjustment to obtain an optimized and adjusted speed sequence, and then the position trajectory is dynamically phase compensated by the optimized and adjusted speed sequence to obtain a trajectory compensation parameter; the communication signal of the wireless transmission device is collected, and sparse compressed sensing is performed on the communication signal to obtain a sparse coefficient matrix, and a power allocation vector of the wireless transmission device is determined based on the sparse coefficient matrix and the trajectory compensation parameter; a communication evaluation value is determined according to the signal-to-interference-noise ratio change of the wireless transmission device and the power allocation vector, and the power control parameters of the wireless transmission device are optimized and updated based on the communication evaluation value.

[0040] It can be seen that in this application, dynamic power control of mobile Internet of Things terminals based on prediction compensation can be realized. First, by obtaining the communication state parameters of the wireless transmission equipment and constructing a mobile trajectory prediction model, dynamic modeling of the position information and channel state of the mobile Internet of Things terminal in the future time slot can be realized; secondly, by processing the time series prediction of the communication state parameters through the mobile trajectory prediction model, the speed sequence and position trajectory at the moment of signal transmission are obtained, which can realize continuous tracking of the dynamic behavior of the terminal and prediction of the spatial path, and provide accurate time and space reference for subsequent phase adjustment and power control; and then by performing conjugate gradient optimization and dynamic step size adjustment on the speed sequence, the fitting accuracy and change smoothness of the trajectory prediction can be improved, and the optimized speed Dynamic phase compensation of sequence-guided signal trajectories can effectively solve the signal reflection path mismatch and phase drift problems caused by high-speed terminal movement. Then, by collecting the communication signals of wireless transmission equipment and introducing a sparse compressed sensing mechanism, key features can be extracted from high-dimensional communication data while ensuring the quality of signal reconstruction. A sparse coefficient matrix is formed, and the power allocation vector is solved by using the sparse coefficient matrix and trajectory compensation parameters. This can achieve collaborative power scheduling that combines signal characteristics and link status. Finally, by analyzing the changes in the signal-to-interference-noise ratio and the power allocation results, a communication evaluation value is constructed, and the power control parameters are jointly optimized and updated, thereby performing real-time adaptive adjustment of the power of the wireless transmission equipment to achieve signal quality optimization.

[0041] To sum up, the technical solution adopted in this application can realize dynamic power control of mobile Internet of Things terminals based on predictive compensation to improve the stability of signal optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0043] Figure 1 This is a flow chart of a signal optimization method for a wireless transmission device provided by the present application;

[0044] Figure 2 is an exemplary flow chart for determining a velocity sequence and position trajectory during signal transmission according to the present application;

[0045] Figure 3 is an exemplary flow chart for determining trajectory compensation parameters provided by the present application;

[0046] Figure 4It is a module structure diagram of the signal optimization system provided by this application. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0048] An embodiment of the present application provides a signal optimization method and system for wireless transmission equipment. The core of the method and system is to construct a mobile trajectory prediction model by acquiring communication state parameters of the wireless transmission equipment; predict and process the communication state parameters using the mobile trajectory prediction model to obtain a speed sequence and position trajectory during signal transmission; perform conjugate gradient optimization and dynamic step size adjustment on the speed sequence to obtain an optimized and adjusted speed sequence, and then perform dynamic phase compensation on the position trajectory using the optimized and adjusted speed sequence to obtain trajectory compensation parameters; collect the communication signal of the wireless transmission equipment, perform sparse compressed sensing on the communication signal to obtain a sparse coefficient matrix, and determine the power allocation vector of the wireless transmission equipment based on the sparse coefficient matrix and the trajectory compensation parameters; determine a communication evaluation value based on the signal-to-interference-noise ratio change of the wireless transmission equipment and the power allocation vector, and optimize and update the power control parameters of the wireless transmission equipment based on the communication evaluation value.

[0049] Example 1: In order to better understand the above technical solution, the following will be combined with the accompanying drawings and specific implementation methods to describe the above technical solution in detail. Figure 1 As shown in FIG, this figure is an exemplary flow chart of a signal optimization method for a wireless transmission device according to this embodiment of the present application, and the signal optimization method includes the following steps:

[0050] In step S1, the communication state parameters of the wireless transmission device are obtained and a movement trajectory prediction model is constructed.

[0051] In specific implementation, communication status parameters can be collected in real time through a communication module deployed in the wireless transmission equipment. The communication status parameters include: position information, speed data and channel status. The channel status includes channel gain and channel signal-to-noise ratio. The communication module is an information collection and transmission component deployed in the wireless transmission equipment. The communication module includes: a radio frequency unit, a baseband processing unit, a protocol control unit and an interface conversion unit. It should be noted that the radio frequency unit is used to complete the transmission and reception of wireless signals and can support multiple communication standards such as 4G, 5G and WiFi. The baseband processing unit is used to perform baseband layer processing such as modulation, channel estimation, and signal synchronization on the collected signals. The protocol control unit is used to execute logical operations such as communication protocol status maintenance, data frame parsing, and connection management to ensure effective interaction of control information during the communication process. The interface conversion unit is used to realize data adaptation and interconnection between the communication module and other functional modules. The interface conversion unit includes standard interfaces such as SPI, I2C, UART, and USB.

[0052] In this embodiment, historical communication data of a wireless transmission device is acquired, and a movement trajectory prediction model based on a long short-term memory network is constructed based on the historical communication data.

[0053] In specific implementation, the historical communication data of the wireless transmission device can be obtained through the communication records of the wireless transmission device. The historical communication data includes the device position, moving speed, historical channel gain and channel signal-to-noise ratio of the historical communication, and the device position and moving speed of the historical communication are used as training samples based on the long short-term memory network (LSTM). The training samples can be sampled through the sliding window algorithm, and the loss function in the training process can select the mean square error, which is conducive to improving the robustness to outliers; by using the communication state parameters as the model input, the moving speed and device position can be predicted.

[0054] It should be noted that the wireless transmission equipment in this application is a mobile Internet of Things terminal. A mobile Internet of Things terminal refers to a communication terminal with wireless communication capabilities, motion properties and distributed collaborative characteristics. It is often deployed in mobile Internet of Things scenarios such as vehicle-mounted systems, drones, smart wearables and portable industrial equipment. The mobile Internet of Things terminal has the characteristics of fast channel state changes, strong link dynamics, and complex environmental interference. In addition, the prediction of mobile speed and device position through LSTM in this application is conducive to capturing the nonlinear trends and periodic changes in the motion trajectory of wireless transmission equipment, and is suitable for trajectory prediction tasks of mobile Internet of Things terminals in complex scenarios.

[0055] In step S2, the communication state parameters are predicted by the mobile trajectory prediction model to obtain a speed sequence and position trajectory during signal transmission;

[0056] Preferably, in this embodiment, reference Figure 2 As shown in the figure, this figure is an exemplary flow chart of determining the speed sequence and position trajectory during signal transmission in an embodiment of the present application. In this embodiment, the communication state parameters are predicted by the mobile trajectory prediction model to obtain the speed sequence and position trajectory during signal transmission, which can be specifically implemented by the following steps:

[0057] First, in step S21, the movement trajectory prediction model obtains the speed sequence during signal transmission by performing time sequence recursion on the communication state parameters;

[0058] Then, in step S22, the movement trajectory prediction model performs position prediction on the communication state parameters to obtain the position trajectory during signal transmission.

[0059] In specific implementation, first, the communication state parameters can be constructed as labeled multidimensional time series samples in chronological order, and the multidimensional time series samples can be input into the mobile trajectory prediction model for training and inference. It should be noted that, in this embodiment, the mobile trajectory prediction model adopts a dual-channel structure, one channel is used to process the speed prediction task, and the other channel is used to process the position prediction task; in the speed prediction channel, the historical speed value, channel attenuation change rate and acceleration information in the communication state parameters are used as input features, and the state evolution trend is extracted through the time recursive mechanism of the long short-term memory network (LSTM), and multiple speed prediction values are predicted, and then a sequence composed of all speed prediction values in chronological order is used as a speed sequence; in the position prediction channel, LSTM is combined with the change pattern of the historical trajectory, and the LSTM performs sequence prediction to output the position trajectory.

[0060] It should be noted that the speed sequence refers to the set of predicted speed values of the mobile Internet of Things terminal at continuous time points during the future signal transmission process, and each item in the speed sequence corresponds to the linear speed at a moment; the position trajectory refers to the predicted position path of the mobile Internet of Things terminal in space corresponding to multiple future transmission time slots. The position trajectory is used to guide the reflection path design, phase compensation direction selection and interference avoidance. The speed sequence and position trajectory in this application are the two core output forms of the prediction results and together constitute the basic data source for power regulation, which is conducive to the realization of feedforward resource allocation and closed-loop optimization control.

[0061] In step S3, the velocity sequence is subjected to conjugate gradient optimization and dynamic step size adjustment to obtain an optimized and adjusted velocity sequence, and then the position trajectory is subjected to dynamic phase compensation based on the optimized and adjusted velocity sequence to obtain trajectory compensation parameters;

[0062] In this embodiment, the speed sequence is subjected to conjugate gradient optimization and dynamic step size adjustment to obtain the optimized and adjusted speed sequence, which can be specifically obtained in the following manner, namely:

[0063] Using a conjugate gradient optimization algorithm to perform gradient optimization on the velocity sequence to obtain a gradient optimized sequence;

[0064] The gradient optimization sequence is subjected to step-size adjustment based on a Riemannian manifold to obtain an optimized and adjusted velocity sequence.

[0065] In the specific implementation, first, the conjugate gradient optimization algorithm is used to perform first-order gradient optimization on the speed sequence, and the optimized speed sequence is used as the gradient optimization sequence, wherein the conjugate gradient optimization algorithm can achieve a faster convergence rate and improve the numerical stability of the predicted speed vector by constructing the linear independence between the gradient of the objective function and the search direction of the previous round. Preferably, the speed component can be introduced in each iteration to normalize the speed sequence, which is beneficial to improve the computational efficiency and avoid local convergence. There is no limitation here; then, the speed sequence after gradient optimization is subjected to dynamic step adjustment processing based on Riemann manifold, that is, the speed sequence optimization problem is mapped to the The projected image is projected into the complex circular manifold structure, and each velocity point is used as a unit modulus complex vector for spatial constraint. Through the adaptive step size adjustment strategy on the Riemann manifold, the optimal projection is performed while keeping the norm of the unit modulus complex vector constant to ensure the convergence performance of the optimization path in the non-Euclidean space. Preferably, the dynamic step size adjustment can be implemented by the power method initial estimation and local reconstruction search, so that the step size adjustment process has stronger adaptability, which is not limited here. It should be noted that in this application, the optimized and adjusted velocity sequence is obtained by the combined processing of the above-mentioned conjugate gradient optimization and Riemann manifold step size adjustment, which provides a smooth velocity input for the subsequent trajectory phase compensation model.

[0066] It should be noted that the conjugate gradient optimization in this application refers to a fast-converging first-order optimization method in a multivariable space with orthogonality between search directions as a constraint, which is conducive to processing large-scale continuous variables; Riemannian manifold step size adjustment refers to variable-scale optimization in a constrained space with nonlinear geometric structure to dynamically adjust the search step size to balance stability and accuracy.

[0067] Preferably, in this embodiment, reference Figure 3 As shown in FIG. 1 , this figure is an exemplary flow chart for determining trajectory compensation parameters in an embodiment of the present application. In this embodiment, the position trajectory is dynamically phase compensated by the optimized and adjusted velocity sequence, and the trajectory compensation parameters can be obtained by the following steps:

[0068] First, in step S31, the optimized and adjusted speed sequence is discretized to obtain instantaneous speeds at different transmission time points;

[0069] Then, in step S32, a phase drift model based on the transmission time point is constructed through all instantaneous velocities and the position trajectory;

[0070] Finally, in step S33, the phase drift model is optimized through conjugate gradient to obtain a phase compensation function, and then the trajectory compensation parameters are determined by the phase compensation function.

[0071] In a specific implementation, first, the optimized and adjusted speed sequence is discretized, that is, the optimized speed sequence is sampled at equal intervals to obtain the instantaneous speed at multiple transmission time points. This discretization process can align the time slot structure of the communication system to ensure that each speed point strictly corresponds to a specific transmission period, thereby improving the time accuracy of the compensation control. Then, based on the instantaneous speed at each time point and the corresponding predicted position trajectory, a phase drift model based on the transmission time point is constructed. In actual implementation, a visual matching algorithm can be used to map the speed vector to the spatial path to establish a time label, thereby forming a joint evolution model of speed and position. This evolution model is then used as a phase drift model based on the transmission time point, which can represent the phase offset phenomenon caused by signal path perturbations. Finally, the conjugate gradient optimization algorithm is used to numerically solve the phase drift model, and the solution is solved using the minimization of phase error as the objective function. The solution result is then used as the phase compensation function, which is discretized at the time slot level to extract the phase control amount corresponding to each time point, and then the set of all phase control amounts is used as the trajectory compensation parameter.

[0072] It should be noted that the phase drift model in this application is a time function model constructed based on the Doppler frequency shift in wireless transmission, which is used to describe the phase change trend in the signal propagation path; the phase compensation function is a continuous phase correction solution obtained by a numerical optimization algorithm, which is differentiable and controllable; the trajectory compensation parameter is a set of executable instructions suitable for the intelligent reflecting surface (IRS) after the phase compensation function is discretized, which is beneficial to improving the coherence performance of the signal reflection path in high-speed dynamic scenarios, wherein the IRS is an element surface composed of several micro-surface elements, which can control the phase of the incident signal. The wireless transmission device in this application includes the IRS module, which is beneficial to transmission optimization through signal position.

[0073] In step S4, a communication signal of the wireless transmission device is collected, sparse compressed sensing is performed on the communication signal to obtain a sparse coefficient matrix, and a power allocation vector of the wireless transmission device is determined based on the sparse coefficient matrix and the trajectory compensation parameter;

[0074] It should be noted that in this application, the communication signal of the wireless transmission device is collected through a synchronous sampling circuit, wherein the synchronous sampling circuit includes a high-precision analog-to-digital converter (ADC), a sampling controller and a cache module, which can convert the communication signal into a digital signal code to ensure the time synchronization and data integrity of the sampling. In specific implementation, the synchronous sampling circuit can be triggered and controlled by an external reference clock source, and the sampling frequency can be dynamically configured according to the current system bandwidth, which is conducive to high-fidelity sampling of the signal.

[0075] In this embodiment, sparse compressed sensing is performed on the communication signal to obtain a sparse coefficient matrix, which can be specifically obtained in the following manner, namely:

[0076] Performing a sliding window division process on the communication signal to obtain a plurality of time-continuous sub-signal segments;

[0077] Perform sparse basis transformation on each sub-signal segment to obtain a sparse domain;

[0078] Determining a sparse coefficient solution function by regression based on least absolute shrinkage and selection operators in the sparse domain;

[0079] The sparse coefficient solution function is iteratively optimized by using a back-propagation neural network through a gradient optimization algorithm to obtain multiple iteratively optimized sparse coefficients, and then a sparse coefficient matrix is constructed through all the iteratively optimized sparse coefficients.

[0080] In the specific implementation, first, the collected original communication signal is divided into a sliding window according to the time axis, and the entire continuous signal is divided into multiple sub-signal segments with the same length and overlap. Preferably, the sliding window length can be set to an integer multiple of multiple symbol periods, and the step size is set according to the time slot structure of the communication protocol, which can ensure that the divided sub-signal segments have sufficient time domain locality, which is not limited here; secondly, a sparse basis transform is performed on each sub-signal segment, and the sub-signal segment is mapped from the time domain or frequency domain to the sparse domain, wherein the sparse basis can be selected from wavelet transform and discrete cosine transform, which is conducive to enhancing the concentrated expression of signal features in the sparse domain; then, in the sparse domain, based on the least absolute shrinkage and selection operator regression algorithm (LAS LASSO (Lass Array Sparse Object Streaming) is used to construct a sparse coefficient solution function, and the solution result is used as the sparse coefficient solution function. Among them, LASSO initializes the solution function of each sub-signal segment to a zero vector by introducing a norm regularization term. The norm regularization term is used to perform fitting optimization with the transformed sparse vector and the original signal residual as the objective function, which can effectively compress coefficient redundancy. Finally, the sparse coefficient solution function is iteratively trained using a back-propagation neural network. During the training process, the gradient update path and learning rate parameters are dynamically adjusted through the Adam optimizer to improve the solution accuracy and convergence efficiency. The result of each iterative training round is used as the sparse coefficient, and the sparse coefficients obtained from all sub-signal segments are arranged in chronological order to construct a sparse coefficient matrix.

[0081] It should be noted that the sparse coefficient matrix in this application refers to the multi-dimensional combination structure of the sparse representation results obtained by optimization in the compressed sensing reconstruction process. Each column of the matrix corresponds to the sparse coefficient of a sub-signal segment, which is used to characterize the energy distribution and disturbance characteristics of the signal in the frequency domain or sparse domain. Among them, by introducing neural networks, the model's dependence on channel state feedback can be greatly reduced, and the system's generalization ability in highly dynamic mobile Internet of Things scenarios can be enhanced.

[0082] In this embodiment, the power allocation vector of the wireless transmission device is determined based on the sparse coefficient matrix and the trajectory compensation parameter in the following manner:

[0083] Determining a sparsity index of each sub-signal segment in the sparse coefficient matrix;

[0084] Determining an output power factor using the sparsity index and the trajectory compensation parameter;

[0085] The power factor is normalized to obtain a power allocation vector.

[0086] In the specific implementation, first, the sparse coefficient vector corresponding to each sub-signal segment in the sparse coefficient matrix is subjected to structural feature analysis by a sparse structure analysis algorithm to obtain a sparsity index, wherein, for each sparse vector, the sparse structure analysis algorithm uses L0 norm to count non-zero coefficients to measure the sparsity level, and the sparse structure analysis algorithm uses L1 norm to calculate the sum of sparse vector amplitudes to estimate the energy distribution, and the sparse structure analysis algorithm uses the ratio of the mean of non-zero coefficients to the standard deviation of the vector amplitude as a sparsity index to reflect whether the signal energy is concentrated or distributed. Then, the trajectory compensation parameter sequence is differentiated and normalized to extract the compensation change amplitude between adjacent time points. The sparsity index and the compensation strength index are standardized respectively to make their numerical ranges consistent. Fusion weights are set for the two types of indicators based on the system experience parameters. The power factor of each sub-signal segment is obtained by weighted summation. The power factor refers to the vector reflecting the power priority that should be allocated to the signal segment. Finally, all power factors are summed and normalized to the total power distribution ratio. The product of the total power distribution ratio and the power factor is then used as the power allocation vector.

[0087] It should be noted that the power allocation vector in this application refers to a joint changing indicator that adapts to signal complexity and mobility status. The power allocation vector can realize a refined and adaptive power control strategy in dynamic scenarios. By fusing the sparse coefficient matrix and trajectory compensation parameters, it can achieve fine energy control in highly dynamic scenarios and improve the overall link steady-state communication performance.

[0088] In step S5, a communication evaluation value is determined according to the signal to interference and noise ratio change of the wireless transmission device and the power allocation vector, and the power control parameters of the wireless transmission device are optimized and updated based on the communication evaluation value.

[0089] In this embodiment, the communication evaluation value may be determined based on the signal-to-interference-and-noise ratio change of the wireless transmission device and the power allocation vector in the following manner:

[0090] Obtain information on signal-to-interference-and-noise ratio changes of wireless transmission equipment during communication, and determine interference signal-to-noise ratio fluctuations in different time periods in combination with the power allocation vector;

[0091] A steady-state estimation error index is determined based on the interference signal-to-noise ratio fluctuation, and a communication evaluation value is further determined based on the steady-state estimation error index.

[0092] In a specific implementation, first, information on the signal-to-interference-and-noise ratio (SINR) change of the device during the communication process is obtained through a link measurement module of the wireless transmission device. The link measurement module can periodically collect actual received power, interference power, and background noise level in each time period or transmission cycle to construct signal-to-interference-and-noise ratio time series data. Preferably, a sliding time window mechanism can be used to organize the signal-to-interference-and-noise ratio data to obtain interference signal-to-noise ratio fluctuations. Then, a target SINR reference range is preset based on experience, and the absolute value of the difference between the target SINR reference range and the interference signal-to-noise ratio fluctuation is calculated. The average of all absolute values is used as a steady-state estimation error indicator. Then, an empirical weight coefficient is determined based on historical experience. The communication evaluation value is obtained by weighted aggregation calculation using the empirical weight coefficient corresponding to the error amplitude, fluctuation duration, and energy consumption ratio.

[0093] It should be noted that the communication evaluation value in this application refers to a link performance evaluation index calculated based on the actual signal-to-interference-and-noise ratio (SINR) fluctuations measured by the wireless transmission equipment during the communication process and the power allocation strategy, which is used to comprehensively reflect the communication quality stability, interference adaptability and energy consumption efficiency in the current time slot or time period. The communication evaluation value is usually composed of multiple sub-indicators, including the signal-to-interference-and-noise ratio deviation amplitude, fluctuation duration, and transmission performance under unit power, etc., and is weighted and fused through empirical weights, so as to have adaptive adjustment capabilities under different operating environments.

[0094] In this embodiment, the power control parameters of the wireless transmission device are optimized and updated based on the communication evaluation value in the following manner:

[0095] Determining an allocation ratio of a power control parameter in a wireless transmission device according to the communication evaluation value;

[0096] The power control parameters of the wireless transmission device are iteratively updated according to the allocation ratio to obtain a power control instruction, and the signal optimization of the wireless transmission device is further achieved by the power control instruction.

[0097] In specific implementation, first, the communication evaluation value is used as the input of the objective function to analyze the performance of the current power configuration in terms of link stability and energy efficiency, and the allocation ratio of each power control parameter is determined based on the gradient information or change trend of the function; then, the weighted minimum mean square error algorithm can be used to perform multiple rounds of iterative solution of the objective optimization function under the conditions of satisfying the total power constraint and fairness restriction, and finally obtain a converged and stable parameter configuration result; finally, the updated power control parameters are encoded into corresponding power control instructions and sent to the controller of the wireless transmission equipment, which parses and executes the instructions to complete the dynamic adjustment of the transmission power, power amplifier gain or modulation strategy.

[0098] It should be noted that the power control parameters in this application may include: subcarrier transmission power, antenna gain coefficient, modulation order control factor, etc. Updating and optimizing the power control parameters is conducive to intelligent response of the link status; the power control instruction is the control data of the wireless transmission equipment, which can be sent to each module of the equipment through the software and hardware interface to realize actual control of physical resource allocation.

[0099] It can be seen that in this application, dynamic power control of mobile Internet of Things terminals based on prediction compensation can be realized. First, by obtaining the communication state parameters of the wireless transmission equipment and constructing a mobile trajectory prediction model, dynamic modeling of the position information and channel state of the mobile Internet of Things terminal in the future time slot can be realized; secondly, by processing the time series prediction of the communication state parameters through the mobile trajectory prediction model, the speed sequence and position trajectory at the moment of signal transmission are obtained, which can realize continuous tracking of the dynamic behavior of the terminal and prediction of the spatial path, and provide accurate time and space reference for subsequent phase adjustment and power control; and then by performing conjugate gradient optimization and dynamic step size adjustment on the speed sequence, the fitting accuracy and change smoothness of the trajectory prediction can be improved, and the optimized speed Dynamic phase compensation of sequence-guided signal trajectories can effectively solve the signal reflection path mismatch and phase drift problems caused by high-speed terminal movement. Then, by collecting the communication signals of wireless transmission equipment and introducing a sparse compressed sensing mechanism, key features can be extracted from high-dimensional communication data while ensuring the quality of signal reconstruction. A sparse coefficient matrix is formed, and the power allocation vector is solved by using the sparse coefficient matrix and trajectory compensation parameters. This can achieve collaborative power scheduling that combines signal characteristics and link status. Finally, by analyzing the changes in the signal-to-interference-noise ratio and the power allocation results, a communication evaluation value is constructed, and the power control parameters are jointly optimized and updated, thereby performing real-time adaptive adjustment of the power of the wireless transmission equipment to achieve signal quality optimization.

[0100] To sum up, the technical solution adopted in this application can realize dynamic power control of mobile Internet of Things terminals based on predictive compensation to improve the stability of signal optimization.

[0101] In the second embodiment, the present application provides a signal optimization system for wireless transmission equipment, referring to Figure 4 As shown, this figure is a module structure diagram of the signal optimization system shown in this embodiment of the present application, and the signal optimization system includes:

[0102] The state acquisition module 100 is used to obtain the communication state parameters of the wireless transmission device and build a movement trajectory prediction model;

[0103] The trajectory prediction module 200 is used to predict the communication state parameters using the mobile trajectory prediction model to obtain a speed sequence and a position trajectory during signal transmission;

[0104] a phase compensation module 300 for performing conjugate gradient optimization and dynamic step size adjustment on the velocity sequence to obtain an optimized and adjusted velocity sequence, and then performing dynamic phase compensation on the position trajectory based on the optimized and adjusted velocity sequence to obtain trajectory compensation parameters;

[0105] A signal processing module 400 is configured to collect communication signals of a wireless transmission device, perform sparse compressed sensing on the communication signals to obtain a sparse coefficient matrix, and determine a power allocation vector for the wireless transmission device based on the sparse coefficient matrix and the trajectory compensation parameters;

[0106] The power control module 500 is configured to determine a communication evaluation value according to a change in the signal to interference and noise ratio of the wireless transmission device and the power allocation vector, and optimize and update a power control parameter of the wireless transmission device based on the communication evaluation value.

[0107] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes 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, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0108] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, including a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0109] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

Claims

1. A signal optimization method for wireless transmission equipment, characterized in that: The signal optimization method comprises the following steps: Obtain the communication status parameters of wireless transmission equipment and build a movement trajectory prediction model; The communication state parameters are predicted by the mobile trajectory prediction model to obtain a speed sequence and a position trajectory during signal transmission; performing conjugate gradient optimization and dynamic step size adjustment on the velocity sequence to obtain an optimized and adjusted velocity sequence, and then performing dynamic phase compensation on the position trajectory based on the optimized and adjusted velocity sequence to obtain a trajectory compensation parameter; collecting a communication signal of a wireless transmission device, performing sparse compressed sensing on the communication signal to obtain a sparse coefficient matrix, and determining a power allocation vector of the wireless transmission device based on the sparse coefficient matrix and the trajectory compensation parameter; A communication evaluation value is determined according to a signal to interference noise ratio change of the wireless transmission device and the power allocation vector, and a power control parameter of the wireless transmission device is optimized and updated based on the communication evaluation value.

2. A signal optimization method for wireless transmission equipment according to claim 1, characterized in that: The wireless transmission device is a mobile Internet of Things terminal.

3. The signal optimization method for wireless transmission equipment according to claim 1, wherein: Acquire historical communication data of the wireless transmission device, and construct a movement trajectory prediction model based on a long short-term memory network based on the historical communication data.

4. The signal optimization method for wireless transmission equipment according to claim 1, wherein: Predicting the communication state parameters using the mobile trajectory prediction model to obtain the speed sequence and position trajectory during signal transmission specifically includes: The movement trajectory prediction model obtains a speed sequence during signal transmission by performing time sequence recursion on the communication state parameters; The movement trajectory prediction model obtains the position trajectory during signal transmission by performing position prediction on the communication state parameters.

5. The signal optimization method for wireless transmission equipment according to claim 1, wherein: The speed sequence is subjected to conjugate gradient optimization and dynamic step size adjustment to obtain an optimized and adjusted speed sequence, specifically comprising: Using a conjugate gradient optimization algorithm to perform gradient optimization on the velocity sequence to obtain a gradient optimized sequence; The gradient optimization sequence is subjected to step-size adjustment based on a Riemannian manifold to obtain an optimized and adjusted velocity sequence.

6. The signal optimization method for wireless transmission equipment according to claim 1, wherein: The position trajectory is subjected to dynamic phase compensation using the optimized and adjusted velocity sequence to obtain trajectory compensation parameters, specifically including: Discretize the optimized and adjusted speed sequence to obtain instantaneous speeds at different transmission time points; Constructing a phase drift model based on the transmission time point through all instantaneous velocities and the position trajectories; The phase drift model is optimized through conjugate gradient to obtain a phase compensation function, and then the trajectory compensation parameters are determined by the phase compensation function.

7. The signal optimization method for wireless transmission equipment according to claim 1, wherein: The communication signal of the wireless transmission device is collected through the synchronous sampling circuit.

8. The signal optimization method for wireless transmission equipment according to claim 1, wherein: Performing sparse compressed sensing on the communication signal to obtain a sparse coefficient matrix specifically includes: Performing a sliding window division process on the communication signal to obtain a plurality of time-continuous sub-signal segments; Perform sparse basis transformation on each sub-signal segment to obtain a sparse domain; Determining a sparse coefficient solution function by regression based on least absolute shrinkage and selection operators in the sparse domain; The sparse coefficient solution function is iteratively optimized by using a back-propagation neural network through a gradient optimization algorithm to obtain multiple iteratively optimized sparse coefficients, and then a sparse coefficient matrix is constructed through all the iteratively optimized sparse coefficients.

9. The signal optimization method for wireless transmission equipment according to claim 1, wherein: Optimizing and updating the power control parameters of the wireless transmission device based on the communication evaluation value specifically includes: Determining an allocation ratio of a power control parameter in a wireless transmission device according to the communication evaluation value; The power control parameters of the wireless transmission device are iteratively updated according to the allocation ratio to obtain a power control instruction, and the signal optimization of the wireless transmission device is further achieved by the power control instruction.

10. A signal optimization system for wireless transmission equipment, configured to execute a signal optimization method for wireless transmission equipment according to any one of claims 1 to 9, characterized in that: The signal optimization system comprises: The state acquisition module is used to obtain the communication state parameters of the wireless transmission equipment and build a mobile trajectory prediction model; A trajectory prediction module is used to predict the communication state parameters using the mobile trajectory prediction model to obtain a speed sequence and position trajectory during signal transmission; a phase compensation module, configured to perform conjugate gradient optimization and dynamic step size adjustment on the velocity sequence to obtain an optimized and adjusted velocity sequence, and then perform dynamic phase compensation on the position trajectory based on the optimized and adjusted velocity sequence to obtain trajectory compensation parameters; a signal processing module, configured to collect communication signals of a wireless transmission device, perform sparse compressed sensing on the communication signals to obtain a sparse coefficient matrix, and determine a power allocation vector of the wireless transmission device based on the sparse coefficient matrix and the trajectory compensation parameter; The power control module is used to determine a communication evaluation value according to a change in the signal to interference and noise ratio of the wireless transmission device and the power allocation vector, and optimize and update the power control parameters of the wireless transmission device based on the communication evaluation value.

Images