Intelligent metasurface channel optimization method and system based on beam forming algorithm

Abstract

The invention discloses an intelligent metasurface channel optimization method and system based on a beam forming algorithm, and relates to the technical field of intelligent metasurfaces, and the method comprises the steps: collecting real-time environment data, monitoring channel state data, and evaluating the influence of the environment and the channel state on a signal; evaluating the gain strategy of the intelligent metasurface, and evaluating the performance of the current beam forming strategy by combining the influence of the environment and the channel state on the signal; and calculating an optimal beam forming parameter by using a gradient descent method to realize channel optimization. According to the method, through comprehensive utilization of real-time environment monitoring, channel state evaluation, an advanced data analysis technology and a mathematical optimization method, dynamic adjustment and real-time optimization of intelligent metasurface channel optimization are achieved, efficient and stable operation of a communication system in a complex environment is ensured, the speed and reliability of data transmission are remarkably improved, and the method is suitable for popularization and application. The invention provides a more efficient, flexible and adaptive beam forming strategy optimization method, and the performance of a wireless communication system is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent super surface, and in particular to an intelligent super surface channel optimization method and system based on a beamforming algorithm. Background Art

[0002] With the development of wireless communication technology, from the initial analog signals to today's digital signal processing, and then to the recent 5G and upcoming 6G communication technologies, each leap has brought significant improvements in communication speed, stability and capacity; Intelligent metasurfaces use their fine control over electromagnetic waves to achieve precise control over the reflection and refraction of incident waves, thereby optimizing the signal propagation path and enhancing the quality of signal reception. Beamforming technology, which enables concentrated emission or reception of signals in a specific direction, can effectively improve signal transmission efficiency and reduce interference. Both have brought about significant improvements in communication speed and stability. Although smart metasurfaces and beamforming technologies have made certain progress in theory and experiment, traditional beamforming technology has limited effect when dealing with complex multipath propagation and dynamic obstacles, making it difficult to achieve efficient channel optimization and failing to make full use of real-time environmental data and channel state information, resulting in poor results of its gain strategy in practical applications. Summary of the invention

[0003] In view of the problems existing in the above-mentioned existing intelligent metasurface channel optimization method and system based on beamforming algorithm, the present invention is proposed.

[0004] Therefore, the problem to be solved by the present invention is that traditional beamforming technology has limited effect when dealing with complex multipath propagation and dynamic obstacles, it is difficult to achieve efficient channel optimization, and it fails to make full use of real-time environmental data and channel state information, resulting in its gain strategy being poorly effective in practical applications.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: an intelligent metasurface channel optimization method and system based on a beamforming algorithm, which includes collecting real-time environmental data and monitoring channel status data, using Fourier transform and wavelet transform to extract frequency domain features and time-frequency features, and calculating the comprehensive evaluation value of the environment and channel status on the signal; based on the maximum gain target and considering the attenuation changes of the pitch angle and the azimuth angle, the corresponding azimuth and pitch angle combination is used as a gain strategy, combined with the comprehensive evaluation value of the environment and channel status on the signal, and the current beamforming strategy is evaluated according to the attenuation of different wavelength signals on the transmission path; using the gradient descent method to calculate the optimal beamforming parameters to achieve channel optimization.

[0006] As a preferred solution of the intelligent metasurface channel optimization method and system based on the beamforming algorithm described in the present invention, the collection of real-time environment and monitoring of channel status data includes using sensors to collect signal source data, multipath propagation data, user mobility data and network usage data, and implementing end-to-end encryption on the transmitted data, and using a secure communication protocol for data transmission.

[0007] As a preferred solution of the intelligent metasurface channel optimization method and system based on the beamforming algorithm described in the present invention, wherein: the use of Fourier transform and wavelet transform to extract frequency domain features and time-frequency features, and the calculation of the comprehensive evaluation value of the signal by the environment and channel state include preprocessing, removing noise, removing outliers, and normalizing the data; Feature extraction is performed from the normalized data, using Fourier transform and wavelet transform to extract frequency domain features and time-frequency features. The Fourier transform is expressed as:

[0008]

[0009] Where f is the frequency of the signal, is the frequency domain representation of frequency f, j is the imaginary unit, A represents the signal amplification, is the phase of the signal, t represents time, Indicates the electromagnetic wave signal strength; The wavelet transform is expressed as:

[0010] in Represents the wavelet mother function, expressed as:

[0011] in is the scale parameter, a and b are the scale factor and location parameter of the wavelet transformation, respectively. represents the wavelet transform coefficient; Integrate feature data:

[0012] in and is the weight parameter, Represents feature data, is the frequency domain representation of frequency f, represents the wavelet transform coefficient; Use the integrated feature data To evaluate the impact of environment and channel conditions on specific wavelengths The influence of is expressed as:

[0013] in, It represents the comprehensive evaluation value of the environment and channel status for the wavelength λ. is an adjustment factor, is the attenuation coefficient, Represents feature data.

[0014] As a preferred solution of the intelligent metasurface channel optimization method and system based on the beamforming algorithm of the present invention, wherein: based on the maximum gain target and considering the attenuation changes of the pitch angle and the azimuth angle, the corresponding azimuth angle and the pitch angle are combined as the gain strategy, and the comprehensive evaluation value of the signal is combined with the environment and the channel state. The current beamforming strategy is evaluated according to the attenuation of different wavelength signals on the transmission path, including: Obtained based on various environmental data and monitoring channel status , using the gain function of the smart metasurface To evaluate the azimuth of the smart metasurface and pitch angle Gain under Gain function of smart metasurface It is expressed as:

[0015] in Represent the direction angle and elevation angle of the i-th channel respectively, is the basic gain, which indicates the gain value when the beam is facing the target direction. is a positive integer, Indicates gain with pitch angle Deviation from reference point The change of decay Represents the center position of the pitch angle, is a normal number, Represents the gain value of the azimuth angle and elevation angle of the i-th channel; The performance index R of evaluating the current beamforming strategy is:

[0016] in and Represent the starting and ending wavelengths of the frequency band respectively. is the material property-dependent absorption coefficient, refers to the degree of signal attenuation, K represents the number of different channels considered, i represents the iteration variable, is the weight of the ith channel, is the noise power, represents the transmit power of the ith channel, R represents the performance index, Indicates the gain value of the azimuth and elevation angle of the i-th channel.

[0017] As a preferred solution of the intelligent metasurface channel optimization method and system based on the beamforming algorithm described in the present invention, wherein: the use of the gradient descent method to calculate the optimal beamforming parameters includes: Combined with Python, use the gradient descent method to iterate and calculate the current and Down The gradient of , select the initial set of parameters As a starting point for iteration; In each iteration, the parameters are updated according to the direction of the gradient and the selected learning rate α; The iterative update step is expressed as:

[0018]

[0019] Where k is the number of iterations, is the learning rate, Represent the direction angle and elevation angle of the i-th channel respectively, and denote the direction angles of the kth and k+1th iterations of the i-th channel, respectively. and denote the pitch angles of the kth and k+1th iterations of the i-th channel, respectively. represents partial derivative; Repeat the iterative update step and calculate the change in R in two consecutive iterations ,exist Less than threshold Stop iteration when Take the final iteration and as the optimal value.

[0020] As a preferred solution of the intelligent metasurface channel optimization method and system based on beamforming algorithm described in the present invention, wherein: the channel optimization includes: and The optimal value is substituted into the control system of the intelligent metasurface, and the control system is used to adjust the electronic properties of the tiny structural units on the metasurface to change the phase of the reflected wave, form a specific beam direction, and achieve channel optimization.

[0021] As a preferred solution of the intelligent metasurface channel optimization method and system based on the beamforming algorithm described in the present invention, the collection of signal source data, multipath propagation data, user mobility data and network usage data also includes collecting the location, size, shape, material, dynamic vehicle and pedestrian movement data, signal strength, signal-to-noise ratio, bit error rate, arrival time, arrival angle and path loss of multipath signals, location of user equipment, transfer speed, real-time traffic and load data of the network.

[0022] Another object of the present invention is to provide a system for an intelligent metasurface channel optimization method based on a beamforming algorithm, comprising: The environmental data collection module is responsible for collecting environmental information, and the data processing submodule converts this information into a format that can be used for subsequent calculations; Data processing and analysis module, which pre-processes and analyzes the collected data; The environment and channel status assessment module uses an algorithm model to assess the environment and channel status; The beamforming parameter optimization module iteratively calculates the optimal beamforming parameters based on the environment and channel status evaluation results and extracts The optimal value of , including the performance verification submodule; The intelligent metasurface control module adjusts the tiny structural units on the intelligent metasurface according to the received parameters, changes the phase of the reflected wave, and forms a specific beam direction.

[0023] A computer device comprises: a memory and a processor; when the processor executes the computer program, the steps of an intelligent metasurface channel optimization method based on a beamforming algorithm are performed.

[0024] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of an intelligent metasurface channel optimization method based on a beamforming algorithm.

[0025] The beneficial effects of the present invention are as follows: by collecting and preprocessing data, and accurately analyzing the real-time environment and channel status, the signal transmission efficiency is significantly improved and the communication quality is optimized. The gain function of the intelligent metasurface is used to evaluate the gain at different azimuth and elevation angles, and the performance of the current beamforming strategy is further evaluated. The gradient descent method is used for iterative calculation to accurately calculate the optimal beamforming parameters, and the goal of channel optimization is achieved. By comprehensively utilizing real-time environmental monitoring, channel status evaluation, advanced data analysis technology and mathematical optimization methods, dynamic adjustment and real-time optimization of intelligent metasurface channel optimization are achieved, ensuring the efficient and stable operation of the communication system in a complex environment, significantly improving the rate and reliability of data transmission, and providing a more efficient, flexible and adaptive beamforming strategy optimization method, which significantly improves the performance of the wireless communication system. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0027] Figure 1 Schematic diagram of the flow of the intelligent metasurface channel optimization method based on the beamforming algorithm.

[0028] Figure 2 Schematic diagram of the structure of the intelligent metasurface channel optimization system based on the beamforming algorithm. DETAILED DESCRIPTION

[0029] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings.

[0030] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0031] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0032] Example 1

[0033] Reference Figure 1 , which is the first embodiment of the present invention, and provides an intelligent metasurface channel optimization method based on a beamforming algorithm. The intelligent metasurface channel optimization method based on a beamforming algorithm includes: S1: Collect real-time environmental data and monitor channel status data, use Fourier transform and wavelet transform to extract frequency domain features and time-frequency features, and calculate the comprehensive evaluation value of the environment and channel status on the signal; Preferably, collecting real-time environment and monitoring channel status data includes using sensors to collect signal source data, multipath propagation data, user mobility data and network usage data, and implementing end-to-end encryption on transmission data, using a secure communication protocol for data transmission.

[0034] By using high-precision sensors to collect data on the surrounding environment and channel status in real time, the beamforming strategy of the smart metasurface is provided with real-time and accurate environmental adaptability information. This real-time data collection and processing capability significantly improves the efficiency and accuracy of channel optimization, ensuring the stability of communication quality in complex environments. By implementing end-to-end encryption on transmitted data and using secure communication protocols, while ensuring communication efficiency and channel optimization, it also greatly enhances data security and privacy protection, which is particularly important for the current growing network security threats, especially in scenarios involving the transmission of sensitive information.

[0035] Furthermore, Fourier transform and wavelet transform are used to extract frequency domain features and time-frequency features, and the comprehensive evaluation value of the environment and channel status on the signal is calculated, including preprocessing, noise removal, outlier removal, and data normalization; Feature extraction is performed from the normalized data, using Fourier transform and wavelet transform to extract frequency domain features and time-frequency features. The Fourier transform is expressed as:

[0036]

[0037] Where f is the frequency of the signal, is the frequency domain representation, j is the imaginary unit, A represents the signal amplitude, is the phase of the signal, t represents time, Indicates the electromagnetic wave signal strength; The wavelet transform is expressed as:

[0038] in Represents the wavelet mother function, expressed as:

[0039] in is the scale parameter, a and b are the scale factor and location parameter of the wavelet transformation, respectively. represents the wavelet transform coefficient; Integrate feature data:

[0040] in Represents feature data, is the frequency domain representation of frequency f, represents the wavelet transform coefficients, and is the weight parameter, using the training set, using the mean square error loss function to calculate the difference between the actual label and the actual label, using the Adam optimizer for gradient descent optimization, and updating and Two weights, if the calculated loss no longer decreases significantly during the continuous iteration, the iterative output weight is stopped; Use the integrated feature data To evaluate the impact of environment and channel conditions on specific wavelengths The influence of is expressed as:

[0041] in Represents feature data, It represents the comprehensive evaluation value of the environment and channel status for the wavelength λ. is an adjustment factor, is the attenuation coefficient, the mean square error loss function is defined based on the experimental data, the computational loss between the experimental data is calculated, and the gradient descent optimization algorithm is used to update If the model loss no longer decreases significantly during the continuous iteration, the iteration output is stopped. , using typical signal attenuation data based on historical data, determine the attenuation coefficient.

[0042] By extracting frequency domain features and time-frequency features from normalized data through Fourier transform and wavelet transform, we can obtain comprehensive information about the environment and channel status, including but not limited to background noise levels, multipath effects caused by obstacles, etc., and comprehensively evaluate the impact of the environment and channel status on the signal wavelength. The frequency domain features help to identify the main frequency components of the signal, while the time-frequency features provide dynamic information about the signal changing over time. These features are crucial for analyzing the propagation characteristics of the signal and the impact of the environment and channel on the signal. They can be used to establish a more accurate environment and channel status model to provide support for the dynamic adjustment of the intelligent metasurface, thereby optimizing the signal transmission path and quality and achieving high-efficiency and low-interference communication, so as to optimize the beamforming strategy in the subsequent steps and achieve the effect of dynamic optimization of the channel, making the signal evaluation more detailed and comprehensive, accurately capturing the key influencing factors in signal transmission, and helping to dynamically adjust the metasurface structure to adapt to environmental changes and optimize the signal propagation effect.

[0043] Furthermore, the collection of signal source data, multipath propagation data, user mobility data and network usage data also includes collecting the location, size, shape, material of obstacle objects, dynamic vehicle and pedestrian movement data, signal strength, signal-to-noise ratio, bit error rate, arrival time, arrival angle and path loss of multipath signals, location of user equipment, transfer speed, real-time traffic and load data of the network.

[0044] By collecting various environmental data and channel data, it is convenient to implement dynamic channel optimization strategies based on environmental changes, thereby enhancing the flexibility of the system. By analyzing network usage data, resources can be reasonably scheduled to avoid network congestion, and the overall transmission efficiency of the network and user experience can be improved. Taking into account the characteristics of obstacles and dynamic factors such as vehicles and pedestrian movement, effective channel optimization can be achieved in complex and changeable communication environments, which can not only improve the performance of wireless communication systems, but also adapt to the ever-changing communication environment and user needs.

[0045] S2: Based on the maximum gain target and considering the attenuation changes of the elevation angle and azimuth angle, the corresponding azimuth angle and elevation angle combination is used as the gain strategy. Combined with the comprehensive evaluation value of the signal by the environment and channel status, the current beamforming strategy is evaluated according to the attenuation of different wavelength signals on the transmission path. Furthermore, based on the maximum gain target and considering the attenuation changes of the elevation angle and azimuth angle, the corresponding azimuth angle and elevation angle combination is used as the gain strategy. Combined with the comprehensive evaluation value of the signal by the environment and channel status, the current beamforming strategy is evaluated according to the attenuation of different wavelength signals on the transmission path. The strategies include: Obtained based on various environmental data and monitoring channel status , using the gain function of the smart metasurface To evaluate the azimuth of the smart metasurface and pitch angle Gain under By real-time monitoring of environmental data and channel status information and combining it with the characteristics of the smart metasurface, this method can optimize the channel in a detailed and dynamic manner. Through real-time evaluation of the environment and channel status, the control system of the smart metasurface can respond quickly to environmental changes.

[0046] Gain function of smart metasurface It is expressed as:

[0047] in Represent the direction angle and elevation angle of the i-th channel respectively, is the basic gain, which indicates the gain value when the beam is facing the target direction. is a positive integer, Indicates gain with pitch angle Deviation from reference point The change of decay Represents the center position of the pitch angle, is a normal number, Represents the gain value of the azimuth angle and elevation angle of the i-th channel; By adjusting The beamforming strategy can be changed based on maximizing the gain function The goal is to use the gradient descent algorithm to calculate the gradient gain and update the parameters If the calculated gradient changes are no longer obvious during the continuous iteration, the iteration is stopped and the output update parameters are output. , by changing , control the emission direction of the reflected signal to focus it on the target receiver or avoid interference, thereby optimizing the reflection efficiency of the smart metasurface, and can use quantum optimization algorithms (such as quantum annealing, QAOA, etc.) to optimize parameters, thereby achieving ultra-high-speed channel optimization, which can effectively explore and optimize the beamforming strategy of the smart metasurface, achieve simultaneous optimization of signals in different frequency bands, and improve the performance of the overall communication system.

[0048] The performance index R of evaluating the current beamforming strategy is:

[0049] in and Represent the starting and ending wavelengths of the frequency band respectively. is the absorption coefficient related to material properties, reflecting the absorption capacity of the smart metasurface to signals of different wavelengths. refers to the degree of signal attenuation, K represents the number of different channels considered, i represents the iteration variable, is the weight of the ith channel. The historical average gain of each channel is determined based on the historical number and normalized as the weight of the corresponding channel. is the noise power, represents the transmit power of the ith channel, R represents the performance index, Indicates the gain value of the azimuth and elevation angle of the i-th channel.

[0050] R is a comprehensive evaluation function for wavelength λ by comprehensively considering the environment and channel status and gain function ,The overall impact of beamforming strategies on environmental adaptability, signal adjustment capability and communication efficiency are integrated in the calculation.

[0051] By dynamically optimizing the channel, this method can effectively resist environmental interference and signal attenuation, enhance the system's adaptability to adverse conditions, and improve the robustness of the communication system. The comprehensive evaluation results obtained through calculation use integral and logarithmic functions to increase complexity and academicity, and also include the concepts of exponential functions and normalization. It can accurately understand how the environment and channel status affect signal propagation. Combined with the analysis of the collected data, the gain function of the intelligent metasurface is used to evaluate its gain effect at different azimuth and elevation angles, which provides a basis for the adjustment of the beamforming strategy, realizes the refined control of the intelligent metasurface and the optimization of its reflection characteristics, and then effectively optimizes signals in different frequency bands.

[0052] S3: Use the gradient descent method to calculate the optimal beamforming parameters and achieve channel optimization; Furthermore, the use of the gradient descent method to calculate the optimal beamforming parameters includes: Combined with Python, use the gradient descent method to iterate and calculate the current and Down The gradient of , select the initial set of parameters As a starting point for iteration; By choosing an initial set of parameters As the starting point of iteration, it can provide a reasonable starting point for the algorithm, which is conducive to accelerating the convergence speed, avoiding falling into the local optimal solution as much as possible, and reducing the number of iterations required to reach the optimal solution.

[0053] In each iteration, the parameters are updated according to the direction of the gradient and the selected learning rate α; The iterative update step is expressed as:

[0054]

[0055] Where k is the number of iterations, is the learning rate, Represent the direction angle and elevation angle of the i-th channel respectively, and denote the direction angles of the kth and k+1th iterations of the i-th channel, respectively. and denote the pitch angles of the kth and k+1th iterations of the i-th channel, respectively. represents partial derivative; The learning rate α is used to control the step size of parameter updates, and the parameters are adjusted in the opposite direction of the gradient, aiming to gradually reduce the value of the objective function R until the minimum or local minimum is found. In this way, the parameters are continuously iterated to achieve the optimization goal, so that the algorithm can effectively approach the global optimal solution or a good local optimal solution.

[0056] Repeat the iterative update step and calculate the change in R in two consecutive iterations ,exist Less than threshold Stop iteration when Iteration Threshold The setting is to define the condition for the algorithm to stop, that is, when the parameter update amount is less than When the threshold is reached, it can be considered that the algorithm has converged to the optimal solution or the local optimal solution, and further iterative improvements will no longer be significant, which avoids unnecessary calculations, improves the efficiency of the algorithm, and achieves the effect of continuously iteratively optimizing parameters to achieve the optimization goal.

[0057] Take the final iteration and as the optimal value.

[0058] The gradient descent algorithm can significantly reduce the amount of calculation and the demand for computing resources by guiding the adjustment of parameters. At the same time, it allows the parameters to be quickly recalculated and adjusted when the environment or network status changes to adapt to new channel conditions, thereby enhancing the system's ability to adapt to dynamic and complex environments. By optimizing the beamforming parameters to achieve the optimal channel state, the signal transmission power consumption can be effectively reduced and the energy efficiency ratio can be improved.

[0059] Furthermore, channel optimization includes converting the calculated and The optimal value is substituted into the control system of the intelligent metasurface, and the control system is used to adjust the electronic properties of the tiny structural units on the metasurface to change the phase of the reflected wave, form a specific beam direction, and achieve channel optimization.

[0060] By calculating the and The optimal value is substituted into the control system of the intelligent metasurface to achieve the effect of accurately controlling the electronic properties of the tiny structural units on the intelligent metasurface and changing the phase of the reflected wave, so that the signal attenuation and interference originally caused by the multipath effect are effectively suppressed, the useful signal is enhanced, the channel capacity is increased, and the communication system can support a higher data transmission rate. By dynamically optimizing the channel, the signal can bypass obstacles or directly reflect to a distant place or blind area, thereby expanding the effective coverage range of the communication system and realizing channel optimization in complex environments.

[0061] In order to better illustrate the beneficial effects of the intelligent metasurface channel optimization method based on the beamforming algorithm, this embodiment also provides a specific parameter implementation method, which is as follows: 1. Experimental setup Using intelligent metasurface, the channel units K are configured to be 100, and each channel unit can adjust the corresponding and ; Obstacles were set up in the environment to simulate the multipath effect, and the test scene was an indoor conference hall (with an area of ​​about 20 m × 30 m); The data acquisition device includes a transmitter and a receiver, using the 5 GHz wireless frequency band; Ambient noise power ; Wavelength range: arrive ; Material absorption coefficient ; Initial transmit power ; And perform weight initialization assignment ; Determine the comprehensive evaluation value of wavelength λ based on experimental data ; 2. Initial state calculation Measure the channel capacity C and wavelength attenuation integral before optimization, and calculate the initialization performance index It is expressed as:

[0062]

[0063]

[0064] ; represents the initial performance index; 3. Optimize angle configuration Random initial allocation and , using the base gain , and set the learning rate ; Optimize using gradient descent and , expressed as: ； ; Repeat the iterative update step and calculate the change in R in two consecutive iterations ,exist Less than threshold Stop iteration when After 100 iterations, the optimal gain is ; Based on the phase angle change value with the greatest gain, the value is applied to the configuration of the reflected wave phase controller, and the phase angle change value is used as a phase compensation value for channel measurement; and recalculate , and recalculate the channel capacity C based on the optimized angle configuration, expressed as: Calculation based on wavelength attenuation reduction ;

[0065] ; Represents the performance index after optimization; By comparing the R value calculation results before and after optimization, it can be shown that the channel capacity item is significantly optimized and improved. After optimization, the performance index was significantly optimized and improved , which verifies that the useful signal can be enhanced by adjusting the angle and phase of the reflector unit. The improvement reflects the enhanced effective transmission of the overall signal after path optimization. Although the R value is small, the channel capacity is significantly improved, reflecting a more efficient signal transmission and optimization effect in a complex environment.

[0066] Example 2 Reference Figure 2 , which is the second embodiment of the present invention, and which is different from the previous embodiment, provides a system for an intelligent metasurface channel optimization method based on a beamforming algorithm, including: The environmental data collection module is responsible for collecting environmental information, including obstacle location, size, shape, material, dynamic vehicle and pedestrian data, as well as signal strength, signal-to-noise ratio and bit error rate. The data processing submodule converts this information into a format that can be used for subsequent calculations. Data processing and analysis module, which pre-processes and analyzes the collected data; The environment and channel status assessment module uses an algorithm model to assess the environment and channel status; The beamforming parameter optimization module iteratively calculates the optimal beamforming parameters based on the environment and channel status evaluation results and extracts The optimal value of , including the performance verification submodule; The intelligent metasurface control module adjusts the tiny structural units on the intelligent metasurface according to the received parameters, changes the phase of the reflected wave, and forms a specific beam direction.

[0067] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0068] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0069] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0070] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit with a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit with a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0071] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An intelligent metasurface channel optimization method based on a beamforming algorithm, characterized in that: include, Collect real-time environmental data and monitor channel status data, use Fourier transform and wavelet transform to extract frequency domain features and time-frequency features, and calculate the comprehensive evaluation value of the environment and channel status on the signal; Based on the maximum gain target and considering the attenuation changes of the elevation angle and azimuth angle, the corresponding azimuth angle and elevation angle combination is used as the gain strategy. Combined with the comprehensive evaluation value of the signal by the environment and channel status, the current beamforming strategy is evaluated according to the attenuation of different wavelength signals on the transmission path. The gradient descent method is used to calculate the optimal beamforming parameters and achieve channel optimization.

2. The intelligent metasurface channel optimization method based on beamforming algorithm as claimed in claim 1, characterized in that: The collecting of real-time environment and monitoring channel status data includes using sensors to collect signal source data, multipath propagation data, user mobility data and network usage data, and implementing end encryption on the transmission data, and using a secure communication protocol for data transmission.

3. The intelligent metasurface channel optimization method based on beamforming algorithm as claimed in claim 2, characterized in that: The method uses Fourier transform and wavelet transform to extract frequency domain features and time-frequency features, and calculates the comprehensive evaluation value of the signal by the environment and channel state, including preprocessing, removing noise, removing outliers, and normalizing the data; Feature extraction is performed from the normalized data, using Fourier transform and wavelet transform to extract frequency domain features and time-frequency features. The Fourier transform is expressed as: ， ， Where f is the frequency of the signal, is the frequency domain representation, j is the imaginary unit, A represents the signal amplitude, is the phase of the signal, t represents time, Indicates the electromagnetic wave signal strength; The wavelet transform is expressed as: ， in Represents the wavelet mother function, expressed as: ， in is the scale parameter, a and b are the scale factor and location parameter of the wavelet transformation, respectively. represents the wavelet transform coefficient, t represents time, Indicates the electromagnetic wave signal strength; Integrate feature data: ， in and is the weight parameter, Represents feature data, is the frequency domain representation of frequency f, represents the wavelet transform coefficient; Use the integrated feature data To evaluate the impact of environment and channel conditions on specific wavelengths The influence of is expressed as: ， in, It represents the comprehensive evaluation value of the environment and channel status for the wavelength λ. is an adjustment factor, is the attenuation coefficient, Represents feature data.

4. The intelligent metasurface channel optimization method based on beamforming algorithm as claimed in claim 3, characterized in that: The method based on the maximum gain target and taking into account the attenuation changes of the elevation angle and the azimuth angle, combining the corresponding azimuth angle and the elevation angle as the gain strategy, combining the comprehensive evaluation value of the signal by the environment and the channel state, and evaluating the current beamforming strategy according to the attenuation of different wavelength signals on the transmission path includes: Obtained based on various environmental data and monitoring channel status , using the gain function of the smart metasurface To evaluate the azimuth of the smart metasurface and pitch angle Gain under Gain function of smart metasurface It is expressed as: ， in Represent the direction angle and elevation angle of the i-th channel respectively, is the basic gain, which indicates the gain value when the beam is facing the target direction. is a positive integer, Indicates gain with pitch angle Deviation from reference point The change of decay Represents the center position of the pitch angle, is a normal number, Represents the gain value of the azimuth angle and elevation angle of the i-th channel; The performance index R of evaluating the current beamforming strategy is: ， in and Represent the starting and ending wavelengths of the frequency band respectively. is the material property-dependent absorption coefficient, refers to the degree of signal attenuation, K represents the number of different channels considered, i represents the iteration variable, is the weight of the ith channel, is the noise power, represents the transmit power of the ith channel, R represents the performance index, Indicates the gain value of the azimuth and elevation angle of the i-th channel.

5. The intelligent metasurface channel optimization method based on beamforming algorithm as claimed in claim 4, characterized in that: The method of using the gradient descent method to calculate the optimal beamforming parameters includes: Combined with Python, use the gradient descent method to iterate and calculate the current and Down The gradient of , select the initial set of parameters As a starting point for iteration; In each iteration, the parameters are updated according to the direction of the gradient and the selected learning rate α; The iterative update step is expressed as: ， ， Where k is the number of iterations, is the learning rate, Represent the direction angle and elevation angle of the i-th channel respectively, and denote the direction angles of the kth and k+1th iterations of the i-th channel, respectively. and denote the pitch angles of the kth and k+1th iterations of the i-th channel, respectively. represents partial derivative; Repeat the iterative update step and calculate the change in R in two consecutive iterations ,exist Less than threshold Stop iteration when Take the final iteration and as the optimal value.

6. The intelligent metasurface channel optimization method based on beamforming algorithm as claimed in claim 5, characterized in that: The channel optimization includes: and The optimal value is substituted into the control system of the intelligent metasurface, and the control system is used to adjust the electronic properties of the tiny structural units on the metasurface to change the phase of the reflected wave, form a specific beam direction, and achieve channel optimization.

7. The intelligent metasurface channel optimization method based on beamforming algorithm according to claim 6, characterized in that: The collection of signal source data, multipath propagation data, user mobility data and network usage data also includes collecting the location, size, shape, material, dynamic vehicle and pedestrian movement data, signal strength, signal-to-noise ratio, bit error rate, arrival time, arrival angle and path loss of multipath signals, location of user equipment, transfer speed, real-time traffic and load data of the network.

8. A system based on the intelligent metasurface channel optimization method based on the beamforming algorithm according to any one of claims 1 to 7, characterized in that: include, The environmental data collection module is responsible for collecting environmental information, and the data processing submodule converts this information into a format that can be used for subsequent calculations; Data processing and analysis module, which pre-processes and analyzes the collected data; The environment and channel status assessment module uses an algorithm model to assess the environment and channel status; The beamforming parameter optimization module iteratively calculates the optimal beamforming parameters based on the environment and channel status evaluation results and extracts The optimal value of , including the performance verification submodule; The intelligent metasurface control module adjusts the tiny structural units on the intelligent metasurface according to the received parameters, changes the phase of the reflected wave, and forms a specific beam direction.

9. A computer device comprising: A memory and a processor; the memory stores a computer program, characterized in that: when the processor executes the computer program, the steps of the intelligent metasurface channel optimization method based on the beamforming algorithm described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the intelligent metasurface channel optimization method based on a beamforming algorithm described in any one of claims 1 to 7 are implemented.

Images