Beam forming control method and system for 5G wireless communication antenna

Abstract

The invention discloses a beam forming control method and system for a 5G wireless communication antenna, and relates to the technical field of 5G wireless communication. The beam forming control method of the 5G wireless communication antenna comprises the following steps: S1, constructing a three-dimensional electromagnetic interference model by a three-dimensional perception pre-calibration method, and predicting an interference trend; s2, dividing an antenna coverage area into a core area and an edge area according to a partition weight optimization method; s3, adopting a blind area energy reconstruction method, monitoring signal intensity and attenuation, and identifying a communication blind area; s4, establishing a beam energy and terminal power consumption mapping model according to an energy efficiency dynamic matching method, and dynamically allocating main beam and sidelobe power; s5, a space-time coding anti-interference method is adopted, and same-frequency interference signals are eliminated through space-domain filtering; and S6, a track driving parameter migration method, constructing a dynamic response model, and realizing beam parameter migration adaptation. According to the invention, the problems of single channel, rigid adjustment and slow response in the prior art are solved.

Description

Technical Field

[0001] The present invention relates to the field of 5G wireless communication technologies, and specifically to a beamforming control method and system for 5G wireless communication antennas. Background Art

[0002] In a 5G wireless communication system, beamforming technology realizes the directional transmission of signal energy by adjusting the phase and amplitude weights of an antenna array, and has become the core means to improve spectral efficiency and coverage quality. In the prior art, beam optimization methods based on channel state information feedback are widely used, which adjust the antenna weights according to the channel characteristics fed back by the receiving end to match the current channel conditions. In terms of coverage control, some solutions adopt a fixed partition weight allocation strategy, divide the antenna array into preset regions, and statically adjust the beam parameters according to the region characteristics. To address the signal blind spot problem, conventional methods trigger fixed power compensation or preset beam direction adjustment by detecting the received signal strength threshold. In addition, time-frequency interleaved coding technology is used to reduce multi-user interference and achieve signal orthogonality processing through predefined coding templates. In mobile terminal management, the prior art establishes a linear prediction model based on historical trajectory data for rough tracking of the beam direction. The current technology system mostly relies on offline parameter configuration and static optimization strategies, and its real-time performance and self-adaptability in complex dynamic environments still rely on the implementation of basic algorithms.

[0003] However, the prior art has problems of single channel, rigid adjustment, and slow response. Summary of the Invention

[0004] Aiming at the deficiencies of the prior art, the present invention provides a beamforming control method and system for 5G wireless communication antennas, and solves the problems of the existing beamforming control method and system for 5G wireless communication antennas.

[0005] To achieve the above objectives, the present invention is realized through the following technical solutions: a beamforming control method for a 5G wireless communication antenna, comprising the following steps: S1, a three-dimensional perception pre-calibration method, collecting meteorological data, terminal distribution data, and obstacle data, constructing a three-dimensional electromagnetic interference model, predicting the interference trend, dynamically adjusting the beam pointing angle range, and pre-calibrating the beam direction; S2, a zoning weight optimization method, dividing the antenna coverage area into a core area and an edge area, differentially adjusting the phase and amplitude weights of the antenna elements according to the frequency band propagation characteristics, and introducing an error compensation factor to suppress interference; S3, a blind area energy reconstruction method, monitoring the signal strength and attenuation, identifying the communication blind area, using the energy gradient diffusion algorithm to reconstruct the radiation pattern, and enhancing the coverage through the cooperation of the main beam and the auxiliary lobes; S4, an energy efficiency dynamic ratio method, establishing a mapping model between the beam energy and the terminal power consumption, and dynamically allocating the power of the main beam and the side lobes according to the service type requirements; S5, a space-time coding anti-interference method, assigning a unique time-frequency interleaved code to the user, embedding orthogonal phases in the beamforming, and using spatial domain filtering to eliminate co-frequency interference signals; S6, a trajectory-driven parameter migration method, predicting the motion vector based on the historical trajectory of the terminal, constructing a dynamic response model, and realizing the adaptation of the beam parameters.

[0006] Further, the three-dimensional perception pre-calibration method specifically includes the following steps: In the three-dimensional perception pre-calibration method, a multi-source heterogeneous data fusion technology is adopted. Based on meteorological sensors, meteorological data is obtained. The data collected by the sensor devices provided by the terminal positioning system includes: longitude, latitude, altitude, moving speed, moving direction, and the three-dimensional coordinates, shape, size, material, and surface roughness data of the obstacles collected by lidar are fused to form a data set that comprehensively reflects the influence of the obstacles and the surrounding environment on the electromagnetic wave propagation. Based on the improved D-S evidence theory algorithm, the uncertainty and conflict between the data of each sensor are processed to eliminate noise interference. Based on the principal component analysis algorithm, the fused data is dimensionally reduced, and the key environmental characteristic parameters that affect the electromagnetic wave propagation are extracted, including the signal attenuation coefficient under different meteorological conditions, the reflection loss coefficient, scattering coefficient, and diffraction coefficient of the obstacles to the electromagnetic waves. The high-precision data of the signal attenuation coefficient, reflection loss coefficient, scattering coefficient, and diffraction coefficient of the obstacles to the electromagnetic waves under different meteorological conditions are input into the three-dimensional electromagnetic interference model. Based on adjusting the coefficients, boundary conditions, and excitation source settings in the model, the model is refined and calibrated to obtain the dynamic adjustment of the beam pointing angle range and complete the pre-calibration work of the beam direction.

[0007] Furthermore, the partition weight optimization method specifically includes the following steps: For the partition weight optimization method, based on the data of three-dimensional perception pre-calibration, a real-time monitoring system for frequency band characteristics is built. This system includes multiple frequency band signal acquisition units, which can monitor the field strength distribution, phase change, fading characteristics, and multipath effect data of frequency band signals in the core area and the edge area in real time. Based on the real-time monitored data, combining historical monitored data and current environmental data, a prediction model for frequency band propagation characteristics based on deep learning is constructed; spatial features are extracted based on a convolutional neural network, and time series features are analyzed in combination with a long short-term memory network to predict the change trend of frequency band characteristics. When a frequency band switch or environmental change is detected, the system retrieves corresponding data from the frequency band characteristic database, recomputes in combination with the prediction results and intelligent optimization algorithms, and adjusts the phase and amplitude weights of the antenna units in the core area and the edge area; at the same time, according to the error feedback mechanism, using the signal transmission error data monitored in real time, the error compensation data is dynamically updated, and an adaptive filtering algorithm is used to correct the signal transmission error in real time, so as to achieve differential adjustment of the weights of different frequency band signals in different regions and interference suppression.

[0008] Furthermore, the blind area energy reconstruction method specifically includes the following steps: In the blind area energy reconstruction method, based on the data of three-dimensional perception pre-calibration, a multi-dimensional blind area identification system is constructed. The monitored signals include: intensity, signal attenuation, signal delay spread, Doppler frequency shift, signal-to-noise ratio fluctuation, and bit error rate index. Based on a convolutional neural network-long short-term memory network fusion model, signal feature extraction and analysis are performed on multi-dimensional monitored data. Among them, the convolutional neural network is used to extract spatial features, and the long short-term memory network fusion model is used to process time series features to obtain the accurate positioning of the communication blind area and the accurate judgment of the shape and size of the blind area; in the energy gradient diffusion algorithm, an adaptive step size adjustment mechanism is introduced, and according to the complexity of the blind area and the requirements of the number of users and service types that the signal needs to cover for signal strength, the step size and direction of energy diffusion are dynamically adjusted; at the same time, combined with the reinforcement learning algorithm, with the coverage effect and energy efficiency as the optimization goals, the cooperative working strategy of the main beam and the auxiliary lobes is continuously optimized; in a narrow and long blind area, by adjusting the radiation angle and power of the auxiliary lobe, it can cover along the extension direction of the blind area; in a large-area blind area, the energy of the main beam and multiple auxiliary lobes is reasonably allocated to ensure the uniformity and integrity of the blind area signal coverage, and the reconstruction of the radiation pattern is obtained.

[0009] Furthermore, the energy efficiency dynamic ratio method specifically includes the following steps: For the energy efficiency dynamic ratio method, based on the optimized data of the zoning weight optimization method, the business type division is refined. The real-time services are subdivided into services with extremely high requirements for real-time performance and image quality, such as high-definition video calls, cloud games, and video conferences, and ordinary voice call services; the non-real-time services are divided into different priority services such as large file transfers and database backups; a service demand - power allocation decision model is established, comprehensively considering the real-time requirements of the services, data transmission rate, and maximum allowable delay factors, and different power allocation strategies are formulated. For high-definition video call services, the power allocation scheme with the highest priority is adopted to preferentially ensure the high-power output of the main beam. At the same time, according to the movement of the terminal, the position and speed data obtained by the terminal positioning system are used to dynamically adjust the sidelobe power to ensure the smoothness and stability of the video image; for large file transfer services, on the premise of ensuring the basic transmission rate, the power of the main beam is appropriately reduced, and the sidelobe power is increased to expand the coverage area, and the transmission is carried out during the low-peak period at night; by real-time monitoring the change of service traffic, the sliding window prediction algorithm is used to predict the service traffic trend in the future for a period of time, and the power allocation ratio of the main beam and the sidelobe is dynamically adjusted to achieve the dynamic balance of beam energy and terminal power consumption, and optimize the coverage and energy efficiency.

[0010] Furthermore, the space-time coding anti-interference method specifically includes the following steps: In the space-time coding anti-interference method, based on the data of the interference environment determined by three-dimensional perception pre-calibration and the optimized data of the zoning weight optimization method, the time-frequency interleaved coding generation algorithm is improved. The chaotic sequence and the pseudo-random sequence are combined to optimize the spatial domain filtering algorithm, and the adaptive least mean square algorithm is introduced. According to the real-time monitored interference signal strength data, frequency data, and phase change data, the filter coefficients are adjusted to adjust the filtered data, and the dynamic tracking and suppression ability of the co-frequency interference signal is obtained.

[0011] Furthermore, the dynamic tracking and suppression ability of the co-frequency interference signal specifically includes the following steps: Design the collaborative workflow of coding and filtering. At the signal transmitter, the generated unique time-frequency interleaved coding and the orthogonal phase component are embedded in the beamforming process, and the phase and amplitude of each unit of the antenna array are adjusted to achieve coding modulation; at the receiver, the spatial characteristics of the signal are analyzed to remove the spatially uncorrelated interference signals. Based on the coding matching algorithm, the received signal is compared with the pre-stored user coding to identify and eliminate the interference signals with non-corresponding coding.

[0012] Furthermore, the trajectory-driven parameter migration method specifically includes the following steps: In the trajectory-driven data migration method, a multi-modal trajectory prediction technology is adopted to fuse multi-source information such as data collected by sensor devices provided by the terminal positioning system, inertial sensor data, and Wi-Fi positioning data, and a trajectory prediction model based on Transformer is constructed; an attention mechanism is introduced to enable the model to process feature data that has an important impact on the terminal's movement trend, such as the turning data and acceleration / deceleration data of the terminal at intersections, combined with the data collected by sensor devices provided by the terminal positioning system, considering road layout, traffic rules, and terrain factors to constrain and correct the prediction model; when predicting the terminal's motion vector, including its position, speed, and direction within a certain period in the future, based on the fast data migration algorithm, the phase, amplitude, and beam width data in the beam data dynamic response model are updated; a data migration error feedback mechanism is designed to compare the actual communication effect with the expected effect. If the error exceeds the set threshold, the model optimization process is automatically triggered, and the data of the trajectory prediction model and the beam data dynamic response model are adjusted based on the reinforcement learning algorithm to obtain a closed-loop optimization of trajectory prediction data, data migration, and effect feedback.

[0013] Furthermore, a multi-method collaborative scheduling mechanism is designed, which specifically includes the following steps: Design a multi-method collaborative scheduling mechanism, construct an environment-method matching database, and associate and match different communication environment characteristics, including high interference, multiple blind spots, dense terminals, and fast movement, with corresponding innovative methods or method combinations; when the system detects the current communication environment information through the environment perception module, based on the database, use the decision tree algorithm to quickly select the optimal method collaborative combination scheme, formulate collaborative execution rules, and clarify the execution order, data interaction method, and resource allocation strategy of each method during the collaboration. In an environment with high interference and communication blind spots, based on the three-dimensional perception pre-calibration method, collect meteorological data, terminal distribution data, and obstacle data, construct a three-dimensional electromagnetic interference model, predict the interference trend, dynamically adjust the beam pointing angle range, and perform preliminary calibration of the beam direction; based on the space-time coding anti-interference method, assign a unique time-frequency interleaved coding to users, embed orthogonal phases in beamforming, and use spatial domain filtering to eliminate co-frequency interference signals; based on the blind area energy reconstruction method, monitor the signal strength and attenuation, identify communication blind spots, and use the energy gradient diffusion algorithm to reconstruct the radiation pattern to obtain the collaborative enhancement of the main beam and auxiliary lobes for coverage; regularly collect system operation data and use the genetic algorithm to optimize the collaborative scheduling mechanism, and adjust the environment-method matching rules and collaborative execution strategies.

[0014] The beamforming control system of a 5G wireless communication antenna specifically includes: an environment perception and beam pre-calibration module, a three-dimensional perception pre-calibration method, which collects meteorological data, terminal distribution data, and obstacle data, constructs a three-dimensional electromagnetic interference model, predicts the interference trend, dynamically adjusts the beam pointing angle range, and pre-calibrates the beam direction; a regional weight optimization module, a partition weight optimization method, which divides the antenna coverage area into a core area and an edge area, and differentially adjusts the phase and amplitude weights of antenna elements according to the frequency band propagation characteristics, and introduces an error compensation factor to suppress interference; a blind area signal reconstruction module, a blind area energy reconstruction method, which monitors the signal strength and attenuation, identifies communication blind areas, and uses an energy gradient diffusion algorithm to reconstruct the radiation pattern, and enhances the coverage through the cooperation of the main beam and auxiliary lobes; a power energy efficiency allocation module, an energy efficiency dynamic ratio method, which establishes a mapping model between beam energy and terminal power consumption, and dynamically allocates the power of the main beam and side lobes according to the service type requirements; an anti-interference coding and filtering module, a space-time coding anti-interference method, which assigns a unique time-frequency interleaved code to users, embeds orthogonal phases in beamforming, and uses spatial domain filtering to eliminate co-frequency interference signals; a terminal trajectory adaptation module, a trajectory-driven parameter migration method, which predicts the motion vector based on the terminal historical trajectory, constructs a dynamic response model, and realizes beam parameter migration adaptation.

[0015] The present invention has the following beneficial effects: The beamforming control method and system of the 5G wireless communication antenna realize precise beam pointing control in complex scenarios through multi-dimensional environment perception and dynamic prediction calibration technology, significantly eliminating the problem of traditional coverage blind areas. Adopting a sub-region differential weight optimization strategy and combining an intelligent energy reconstruction mechanism, it enhances the edge coverage ability while ensuring the performance of the main beam. Through the dynamic power allocation technology based on service perception, it effectively balances the network coverage quality and terminal energy consumption efficiency, and improves the overall energy efficiency of the system. The innovative space-time coding and spatial domain filtering cooperation scheme greatly suppresses co-frequency interference and strengthens the communication stability in dense user scenarios. The fast parameter migration technology based on terminal behavior prediction breaks through the beam tracking bottleneck in high-speed mobile scenarios and realizes continuous seamless coverage. The whole system comprehensively improves the adaptability of the 5G network in complex dynamic environments through the closed-loop cooperation of environment perception, intelligent decision-making, and dynamic execution, providing reliable low-latency and high-capacity wireless connection support for high-demand scenarios such as smart cities and industrial interconnection.

[0016] Of course, it is not necessary for any product implementing the present invention to achieve all the above-mentioned advantages simultaneously. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a module diagram of the beamforming control method and system of the 5G wireless communication antenna of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0019] Please refer to Figure 1 , the embodiments of the present invention provide a technical solution: a beamforming control method for a 5G wireless communication antenna, including the following steps: S1. Three-dimensional perception pre-calibration method, collect meteorological data, terminal distribution data, and obstacle data, construct a three-dimensional electromagnetic interference model, predict the interference trend, dynamically adjust the beam pointing angle range, and pre-calibrate the beam direction; The three-dimensional perception pre-calibration method specifically includes the following steps: In the three-dimensional perception pre-calibration method, a multi-source heterogeneous data fusion technology is adopted. Based on meteorological sensors, meteorological data is obtained. The data collected by the sensor devices provided by the terminal positioning system includes: longitude, latitude, altitude, moving speed, moving direction, and the three-dimensional coordinates, shape, size, material, and surface roughness data of obstacles collected by lidar are fused to form a data set that comprehensively reflects the influence of obstacles and the surrounding environment on the propagation of electromagnetic waves; Based on the improved D-S evidence theory algorithm, the uncertainty and conflict between the data of each sensor are processed to eliminate noise interference. Based on the principal component analysis algorithm, the fused data is dimensionally reduced to extract the key environmental characteristic parameters that affect the propagation of electromagnetic waves, including the signal attenuation coefficient under different meteorological conditions, the reflection loss coefficient, scattering coefficient, and diffraction coefficient of obstacles to electromagnetic waves. The high-precision data of the signal attenuation coefficient, reflection loss coefficient, scattering coefficient, and diffraction coefficient of obstacles to electromagnetic waves under different meteorological conditions are input into the three-dimensional electromagnetic interference model. Based on adjusting the coefficients, boundary conditions, and excitation source settings in the model, the model is refined and calibrated to obtain a dynamic adjustment of the beam pointing angle range and complete the pre-calibration work of the beam direction.

[0020] In this implementation, the multi-source heterogeneous data fusion technology is first adopted to fuse the meteorological data obtained by meteorological sensors, the longitude, latitude, altitude, moving speed, moving direction and other data provided by the terminal positioning system, and the three-dimensional coordinates, shapes, sizes, materials, surface roughness data of obstacles collected by lidar to form a comprehensive data set. Then, the improved D-S evidence theory algorithm is used to process the uncertainty and conflict between the data of each sensor, eliminate the noise interference, and then reduce the dimension of the fused data based on the principal component analysis algorithm to extract the key environmental characteristic parameters such as the signal attenuation coefficient, the reflection loss coefficient, the scattering coefficient and the diffraction coefficient of obstacles to electromagnetic waves under different meteorological conditions. Finally, these high-precision data are input into the three-dimensional electromagnetic interference model, and the model is finely calibrated by adjusting the coefficients, boundary conditions and excitation source settings in the model, so as to realize the dynamic adjustment of the beam pointing angle range and complete the pre-calibration work of the beam direction.

[0021] It is beneficial to comprehensively and accurately reflect the influence of obstacles and the surrounding environment on the propagation of electromagnetic waves; using the improved D-S evidence theory algorithm to process data is beneficial to eliminating the uncertainty, conflict and noise interference between sensor data and improving data reliability; using the principal component analysis algorithm to reduce the dimension and extract key environmental characteristic parameters is beneficial to streamlining data while retaining core information and improving data processing efficiency; inputting high-precision characteristic parameters into the three-dimensional electromagnetic interference model and finely calibrating it is beneficial to accurately predicting the interference trend, realizing the dynamic adjustment of the beam pointing angle range, completing the pre-calibration work of the beam direction, and thus laying a solid foundation for the stable transmission of subsequent 5G wireless communication signals and improving communication quality.

[0022] S2. Zoning weight optimization method: divide the antenna coverage area into a core area and an edge area, and differentially adjust the phase and amplitude weights of antenna elements according to the propagation characteristics of frequency bands, and introduce an error compensation factor to suppress interference; Blind area energy reconstruction method, which specifically includes the following steps: For the zoning weight optimization method, based on the data of three-dimensional perception pre-calibration, a real-time monitoring system for frequency band characteristics is built. This system includes multiple frequency band signal acquisition units, which can monitor the field strength distribution, phase change, fading characteristics, and multipath effect data of frequency band signals in the core area and the edge area in real time. Based on the real-time monitoring data, historical monitoring data and current environmental data are fused at the same time to construct a prediction model for frequency band propagation characteristics based on deep learning. Extract spatial features based on a convolutional neural network, analyze time series features in combination with a long short-term memory network, and predict the changing trend of frequency band characteristics. When detecting a frequency band switch or environmental change, the system retrieves corresponding data from the frequency band characteristics database, recomputes in combination with the prediction result and an intelligent optimization algorithm, and adjusts the phase and amplitude weights of the antenna elements in the core area and the edge area; at the same time, according to the error feedback mechanism, using the signal transmission error data monitored in real time, dynamically update the error compensation data, and use an adaptive filtering algorithm to correct the signal transmission error in real time, so as to achieve differential adjustment of the weights of different frequency band signals in different areas and interference suppression.

[0023] In this implementation plan, based on the three-dimensional perception pre-calibration data, build a real-time monitoring system for frequency band characteristics that includes multiple frequency band signal acquisition units, and monitor in real time the field strength distribution, phase change, fading characteristics, and multipath effect data of the frequency band signals in the core area and the edge area. Integrate historical monitoring data and current environmental data to build a prediction model for frequency band propagation characteristics based on deep learning; use a convolutional neural network to extract spatial features, and analyze time series features in combination with a long short-term memory network to predict the changing trend of frequency band characteristics; once a frequency band switch or environmental change is detected, the system retrieves data from the frequency band characteristics database, recomputes in combination with the prediction result and an intelligent optimization algorithm, and adjusts the phase and amplitude weights of the antenna elements in the core area and the edge area; in addition, through the error feedback mechanism, dynamically update the error compensation data according to the signal transmission error data monitored in real time, and use an adaptive filtering algorithm to correct the signal transmission error in real time, and finally achieve differential adjustment of the weights of different frequency band signals in different areas and interference suppression.

[0024] Building a real-time monitoring system for frequency band characteristics based on three-dimensional perception pre-calibration data is conducive to obtaining comprehensive and dynamic frequency band signal data, covering various aspects of information such as the field strength distribution and phase change in the core area and the edge area; constructing a prediction model based on deep learning and analyzing it in combination with a convolutional neural network and a long short-term memory network is conducive to accurately predicting the changing trend of frequency band characteristics; when there is a frequency band switch or environmental change, the system can quickly retrieve data and adjust the weights in combination with an intelligent algorithm, which is conducive to timely adapting to the complex and changeable communication environment; using the error feedback mechanism and an adaptive filtering algorithm to dynamically update the error compensation data according to the signal transmission error data monitored in real time and correct the error in real time is conducive to improving the accuracy of signal transmission, achieving accurate differential adjustment of the weights of different frequency band signals in different areas, thereby effectively suppressing interference and ensuring the stable transmission of 5G wireless communication signals and the improvement of communication quality.

[0025] S3. Blind area energy reconstruction method, monitor the signal strength and attenuation, identify the communication blind area, use the energy gradient diffusion algorithm to reconstruct the radiation pattern, and enhance the coverage through the cooperation of the main beam and the auxiliary lobes; Blind area energy reconstruction method, specifically including the following steps: In the blind area energy reconstruction method, based on the data of three-dimensional perception pre-calibration, a multi-dimensional blind area recognition system is constructed. The monitored signals include: intensity, signal attenuation, signal delay spread, Doppler frequency shift, signal-to-noise ratio fluctuation, bit error rate index. Based on the convolutional neural network-long short-term memory network fusion model, signal feature extraction and analysis are performed on multi-dimensional monitoring data. Among them, the convolutional neural network is used to extract spatial features, and the long short-term memory network fusion model is used to process time series features, so as to obtain the accurate positioning of the communication blind area and the accurate judgment of the shape and size of the blind area; In the energy gradient diffusion algorithm, an adaptive step size adjustment mechanism is introduced. According to the complexity of the blind area and the requirements of the number of users and service types that the signal needs to cover for the signal intensity, the step size and direction of energy diffusion are dynamically adjusted; at the same time, combined with the reinforcement learning algorithm, with the coverage effect and energy efficiency as the optimization objectives, the cooperative working strategy of the main beam and the auxiliary lobes is continuously optimized; in the long and narrow blind area, by adjusting the radiation angle and power of the auxiliary lobe, it can cover along the extension direction of the blind area; in the large-area blind area, the energy of the main beam and multiple auxiliary lobes is reasonably allocated to ensure the uniformity and integrity of the blind area signal coverage, and the reconstruction of the radiation pattern is obtained.

[0026] In this implementation plan, based on the three-dimensional perception pre-calibration data, a multi-dimensional blind area recognition system is constructed, and indicators such as signal intensity, attenuation, delay spread, Doppler frequency shift, signal-to-noise ratio fluctuation, and bit error rate are monitored. The convolutional neural network-long short-term memory network fusion model is used to extract spatial features by the convolutional neural network and process time series features by the long short-term memory network, so as to accurately locate the communication blind area and accurately judge its shape and size; in the energy gradient diffusion algorithm, an adaptive step size adjustment mechanism is introduced, and according to the complexity of the blind area, the number of covered users and the requirements of the service type for the signal intensity, the step size and direction of energy diffusion are dynamically adjusted. At the same time, combined with the reinforcement learning algorithm, with the coverage effect and energy efficiency as the optimization objectives, the cooperative working strategy of the main beam and the auxiliary lobes is optimized. For the long and narrow blind area, the radiation angle and power of the auxiliary lobe are adjusted to cover along its extension direction, and for the large-area blind area, the energy of the main beam and multiple auxiliary lobes is reasonably allocated, and finally the reconstruction of the radiation pattern is realized.

[0027] It is beneficial to comprehensively and accurately locate communication blind spots, precisely judge their shapes and sizes, and provide a basis for subsequent targeted processing. Analyzing data using a convolutional neural network-long short-term memory network fusion model helps to fully extract data features and improve the accuracy and reliability of blind spot identification. Introducing an adaptive step size adjustment mechanism into the energy gradient diffusion algorithm to dynamically adjust the step size and direction according to different factors is conducive to flexibly coping with complex blind spot environments and improving the efficiency of energy diffusion. Combining a reinforcement learning algorithm to optimize the collaborative working strategy of the main beam and auxiliary lobes and adopting different coverage methods for different types of blind spots helps to achieve the uniformity and integrity of blind spot signal coverage, improve energy utilization efficiency, and ultimately reconstruct the radiation pattern, greatly enhancing the coverage effect of 5G wireless communication and improving communication quality.

[0028] S4. Energy efficiency dynamic ratio method: Establish a mapping model between beam energy and terminal power consumption, and dynamically allocate the power of the main beam and side lobes according to the requirements of service types. The energy efficiency dynamic ratio method specifically includes the following steps: For the energy efficiency dynamic ratio method, based on the optimized data of the partition weight optimization method, the service type division is refined. Real-time services are subdivided into services with extremely high requirements for real-time performance and image quality, such as high-definition video calls, cloud games, and video conferences, and ordinary voice call services. Non-real-time services are divided into different priority services such as large file transfers and database backups. A service demand-power allocation decision model is established. Considering factors such as the real-time requirements of services, data transmission rates, and allowable maximum delays, different power allocation strategies are formulated. For high-definition video call services, the power allocation scheme with the highest priority is adopted to ensure the high-power output of the main beam. At the same time, according to the movement of the terminal, the position and speed data obtained by the terminal positioning system are used to dynamically adjust the side lobe power to ensure the smoothness and stability of the video image. For large file transfer services, on the premise of ensuring the basic transmission rate, the power of the main beam is appropriately reduced, and the side lobe power is increased to expand the coverage area, and the transmission is carried out during the low-peak period at night. By real-time monitoring the change of service traffic and using the sliding window prediction algorithm to predict the service traffic trend in the future for a period of time, the power allocation ratio of the main beam and side lobes is dynamically adjusted to achieve the dynamic balance between beam energy and terminal power consumption, and optimize coverage and energy efficiency.

[0029] In this implementation plan, based on the optimized data of the partition weight optimization method, the business type division is first refined. The real-time services are divided into high-definition video calls, cloud games, video conferences, and ordinary voice call services with extremely high requirements for real-time performance and image quality, and the non-real-time services are divided into different priority services such as large file transfer and database backup. Then, a business demand - power allocation decision model is established, and different power allocation strategies are formulated by comprehensively considering factors such as the real-time requirements of the services, data transmission rate, and maximum allowable delay. For example, for high-definition video calls, the high power output of the main beam is preferentially guaranteed and the side lobe power is dynamically adjusted according to the movement of the terminal. For large file transfer services, the main and side lobe powers are adjusted while ensuring the basic rate, and the low peak period is used for transmission. Finally, by real-time monitoring the change of service traffic, the sliding window prediction algorithm is used to predict the service traffic trend, and the power allocation ratio of the main beam and side lobe is dynamically adjusted to achieve the dynamic balance between beam energy and terminal power consumption, and optimize the coverage and energy efficiency.

[0030] Refining the business type division based on the optimized data of the partition weight optimization is beneficial to accurately positioning the characteristics and requirements of different services; establishing a business demand - power allocation decision model and formulating strategies by comprehensively considering multiple factors is beneficial to customizing appropriate power allocation schemes for various services; preferentially guaranteeing the high power output of the main beam for services such as high-definition video calls and dynamically adjusting the side lobe power in combination with the movement of the terminal is beneficial to ensuring the high-quality experience of real-time services; reasonably adjusting the main and side lobe powers for large file transfer services and using the low peak period for transmission is beneficial to improving the energy utilization efficiency while meeting the transmission requirements; adjusting the power allocation ratio by real-time monitoring the service traffic and using the sliding window prediction algorithm is beneficial to achieving the dynamic balance between beam energy and terminal power consumption, optimizing the coverage effect and energy efficiency of 5G wireless communication as a whole, and improving the comprehensive performance of the communication system.

[0031] S5. Space-time coding anti-interference method: Assign a unique time-frequency interleaved code to the user, embed orthogonal phases in beamforming, and use spatial domain filtering to eliminate co-frequency interference signals; The space-time coding anti-interference method specifically includes the following steps: In the space-time coding anti-interference method, based on the data of the interference environment determined by three-dimensional perception pre-calibration and the optimized data of the partition weight optimization method, the time-frequency interleaved coding generation algorithm is improved. The chaotic sequence and pseudo-random sequence are combined to optimize the spatial domain filtering algorithm, and the adaptive least mean square algorithm is introduced. According to the real-time monitored interference signal strength data, frequency data, and phase change data, the filter coefficients are adjusted, and the filtering data is adjusted to obtain the dynamic tracking and suppression ability for co-frequency interference signals.

[0032] The dynamic tracking and suppression ability for co-frequency interference signals specifically includes the following steps: Design the collaborative workflow of coding and filtering. At the signal transmitting end, embed the generated unique time-frequency interleaved coding and orthogonal phase components into the beamforming process, and based on adjusting the phases and amplitudes of each unit of the antenna array, realize coding modulation; at the receiving end, analyze the spatial characteristics of the signal, remove the spatially uncorrelated interference signals, and based on the coding matching algorithm, compare the received signal with the pre-stored user coding to identify and eliminate the interference signals with non-corresponding coding.

[0033] In this implementation scheme, based on the data of three-dimensional perception pre-calibration and partition weight optimization, first improve the time-frequency interleaved coding generation algorithm, adopt the combination of chaotic sequence and pseudo-random sequence, and optimize the spatial domain filtering algorithm. Introduce the adaptive least mean square algorithm, and adjust the filter coefficients and filtering data according to the real-time monitored interference signal intensity, frequency and phase change data to obtain the dynamic tracking and suppression ability of the co-channel interference signals; then design the collaborative workflow of coding and filtering. At the transmitting end, embed the unique time-frequency interleaved coding and orthogonal phase components into the beamforming, adjust the phases and amplitudes of the antenna array units to realize coding modulation. At the receiving end, analyze the spatial characteristics of the signal to remove the uncorrelated interference signals, and then compare the received signal with the pre-stored user coding through the coding matching algorithm to identify and eliminate the interference signals with non-corresponding coding.

[0034] It is beneficial to accurately grasp the interference environment and optimize the basic conditions. Improving the time-frequency interleaved coding generation algorithm and adopting the combination of chaotic and pseudo-random sequences is beneficial to increasing the complexity and uniqueness of the coding and reducing the probability of coding coincidence between the interference signal and the useful signal. Optimizing the spatial domain filtering algorithm and introducing the adaptive least mean square algorithm, and adjusting the filter coefficients and filtering data according to the real-time interference signal data, is beneficial to realizing the dynamic tracking and efficient suppression of the co-channel interference signals. Designing the collaborative workflow of coding and filtering, embedding coding and orthogonal phase for modulation at the transmitting end, and removing interference signals at the receiving end through analyzing spatial characteristics and coding matching algorithm, is beneficial to jointly ensure the accuracy and stability of communication from both the signal transmitting and receiving ends, greatly improving the anti-interference ability of the 5G wireless communication system in a complex interference environment and ensuring the reliable transmission of communication signals.

[0035] S6. Trajectory-driven parameter migration method, predict the motion vector based on the terminal historical trajectory, construct a dynamic response model, and realize the beam parameter migration adaptation.

[0036] The trajectory-driven parameter migration method specifically includes the following steps: In the trajectory-driven data migration method, adopt the multi-modal trajectory prediction technology, fuse the multi-source information of the data collected by the sensor devices provided by the terminal positioning system, inertial sensor data, and Wi-Fi positioning data, and construct a trajectory prediction model based on Transformer; Introduce an attention mechanism to enable the model to focus on feature data that has an important impact on the terminal's movement trend, such as the terminal's turning data and acceleration / deceleration data at intersections. Combine the data collected by the sensor devices provided by the terminal positioning system, and consider factors such as road layout, traffic rules, and terrain and landform to constrain and correct the prediction model. After predicting the terminal's movement vectors, including its position, speed, and direction over a period of time in the future, update the phase, amplitude, and beam width data in the beam data dynamic response model based on the fast data migration algorithm. Design a data migration error feedback mechanism to compare the actual communication effect with the expected effect. If the error exceeds the set threshold, automatically trigger the model optimization process, and adjust the data of the trajectory prediction model and the beam data dynamic response model based on the reinforcement learning algorithm to obtain a closed-loop optimization of trajectory prediction data, data migration, and effect feedback.

[0037] In this implementation plan, the trajectory-driven parameter migration method adopts multi-modal trajectory prediction technology, integrates multi-source information such as sensor data of the terminal positioning system, inertial sensor data, and Wi-Fi positioning data, and constructs a trajectory prediction model based on Transformer. Introduce an attention mechanism, combine the terminal positioning data, and consider factors such as road layout, traffic rules, terrain and landform, etc., to constrain and correct the model. After predicting the movement vectors of the terminal, such as its position, speed, and direction over a period of time in the future, use the fast data migration algorithm to update the phase, amplitude, and beam width data in the beam data dynamic response model. Design a data migration error feedback mechanism to compare the actual and expected communication effects. When the error exceeds the set threshold, automatically adjust the data of the trajectory prediction model and the beam data dynamic response model based on the reinforcement learning algorithm to achieve a closed-loop optimization of trajectory prediction data, data migration, and effect feedback.

[0038] It is beneficial to make full use of various data resources to more accurately predict the terminal's movement trajectory. Introducing an attention mechanism and combining multiple factors to constrain and correct the model is conducive to highlighting key feature data and improving the accuracy of the prediction model's grasp of the terminal's movement trend. After predicting the terminal's movement vectors, updating the beam parameters through the fast data migration algorithm is conducive to quickly adapting the beam to the movement of the terminal and ensuring the stable tracking of communication signals. Designing a data migration error feedback mechanism, based on the difference between the actual and expected communication effects, automatically triggers the model optimization process based on the reinforcement learning algorithm to achieve closed-loop optimization, which is conducive to continuously improving the accuracy of trajectory prediction and beam parameter adaptation, and then maintaining good communication quality during the terminal's movement and enhancing the adaptability of the 5G wireless communication system to dynamic scenarios.

[0039] The above content is only an example and explanation of the structure of the present invention. Those skilled in the art of this technology can make various modifications or supplements to the described specific embodiments or use similar methods for substitution. As long as they do not deviate from the structure of the invention or exceed the scope defined by this claim book, they should fall within the protection scope of the present invention.

[0040] Design a multi-method collaborative scheduling mechanism, which specifically includes the following steps: Design a multi-method collaborative scheduling mechanism, construct an environment-method matching database, and associate and match different communication environment characteristics, including: high interference, multiple blind spots, dense terminals, and fast movement, with corresponding innovative methods or method combinations; when the system detects the current communication environment information through the environment perception module, based on the database, use the decision tree algorithm to quickly select the optimal method collaborative combination plan, formulate collaborative execution rules, and clarify the execution order, data interaction method, and resource allocation strategy of each method during the collaboration. In an environment with high interference and communication blind spots, based on the three-dimensional perception pre-calibration method, collect meteorological data, terminal distribution data, and obstacle data, construct a three-dimensional electromagnetic interference model, predict the interference trend, dynamically adjust the beam pointing angle range, and perform preliminary calibration on the beam direction; based on the space-time coding anti-interference method, assign a unique time-frequency interleaved code to the user, embed orthogonal phases in beamforming, and use spatial domain filtering to eliminate co-frequency interference signals; based on the blind area energy reconstruction method, monitor the signal strength and attenuation, identify communication blind spots, and use the energy gradient diffusion algorithm to reconstruct the radiation pattern to obtain the collaborative enhancement of the main beam and auxiliary lobes for coverage; regularly collect system operation data and use the genetic algorithm to optimize the collaborative scheduling mechanism, and adjust the environment-method matching rules and collaborative execution strategies.

[0041] It is beneficial to quickly establish the corresponding relationship between the environment and applicable methods; using the decision tree algorithm to select the optimal collaborative combination plan based on the database and formulate collaborative execution rules is beneficial to clarify the execution logic of each method and ensure the orderly progress of data interaction and resource allocation; in a complex environment with high interference and communication blind spots, successively using the three-dimensional perception pre-calibration method to preliminarily calibrate the beam direction, the space-time coding anti-interference method to eliminate co-frequency interference, and the blind area energy reconstruction method to enhance the blind area coverage is beneficial to give full play to the advantages of each method and specifically solve the communication problems in complex environments; regularly collecting system operation data and using the genetic algorithm to optimize the collaborative scheduling mechanism is beneficial to continuously adjust the matching rules and execution strategies, enabling the multi-method collaborative scheduling mechanism to better adapt to the dynamic changes of the communication environment, thereby improving the overall performance and stability of the 5G wireless communication system and ensuring efficient communication in various complex scenarios.

[0042] The beamforming control system of a 5G wireless communication antenna specifically includes: Environmental perception and beam pre-calibration module, three-dimensional perception pre-calibration method, collect meteorological data, terminal distribution data and obstacle data, construct a three-dimensional electromagnetic interference model, predict the interference trend, dynamically adjust the beam pointing angle range, and pre-calibrate the beam direction; Regional weight optimization module, partition weight optimization method, divide the antenna coverage area into a core area and an edge area, and differentially adjust the phase and amplitude weights of antenna elements according to the propagation characteristics of the frequency band, and introduce an error compensation factor to suppress interference; Blind area signal reconstruction module, blind area energy reconstruction method, monitor signal strength and attenuation, identify communication blind areas, use the energy gradient diffusion algorithm to reconstruct the radiation pattern, and enhance coverage through the cooperation of the main beam and auxiliary lobes; Power energy efficiency allocation module, energy efficiency dynamic ratio method, establish a mapping model between beam energy and terminal power consumption, and dynamically allocate the power of the main beam and side lobes according to the service type requirements; Anti-interference coding and filtering module, spatio-temporal coding anti-interference method, allocate a unique time-frequency interleaved code for users, embed orthogonal phases in beamforming, and use spatial domain filtering to eliminate co-frequency interference signals; Terminal trajectory adaptation module, trajectory-driven parameter migration method, predict the motion vector based on the terminal's historical trajectory, construct a dynamic response model, and realize the migration and adaptation of beam parameters.

[0043] The environmental perception and beam pre-calibration module collects multi-source data to construct a model and pre-calibrate the beam direction, which is conducive to accurately grasping the interference trend and laying a good foundation for signal transmission; the regional weight optimization module adjusts the weights and suppresses interference according to the frequency band characteristics in different regions, which is conducive to improving the signal quality in different regions; the blind area signal reconstruction module monitors signals to identify blind areas and reconstructs the radiation pattern, which is conducive to enhancing the coverage of blind areas and eliminating communication dead spots; the power energy efficiency allocation module dynamically allocates power based on service requirements, which is conducive to balancing coverage and energy efficiency and improving energy utilization; the anti-interference coding and filtering module allocates codes for users and combines filtering to eliminate interference, which is conducive to ensuring the purity and reliability of communication signals; the terminal trajectory adaptation module realizes the migration and adaptation of beam parameters based on the terminal trajectory, which is conducive to maintaining stable communication when the terminal moves. Each module cooperates with each other and works together, which is conducive to comprehensively improving the performance, stability and communication quality of the 5G wireless communication system and meeting the requirements of diverse communication scenarios.

[0044] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media including, but not limited to, magnetic disk storage, CD-ROM, optical storage, etc., containing computer-usable program code.

[0045] The present invention is described with reference to the flowcharts and / or block diagrams of systems, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0046] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0047] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0048] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed as including the preferred embodiments and all changes and modifications falling within the scope of the present invention.

[0049] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these changes and modifications.

Claims

1. Beamforming control method for 1.5G wireless communication antennas, characterized in that, It includes the following steps: S1. Three-dimensional perception pre-calibration method: Collect meteorological data, terminal distribution data, and obstacle data, construct a three-dimensional electromagnetic interference model, predict the interference trend, dynamically adjust the beam pointing angle range, and pre-calibrate the beam direction; S2. Zoning weight optimization method: Divide the antenna coverage area into a core area and an edge area, and differentially adjust the phase and amplitude weights of the antenna elements according to the frequency band propagation characteristics, and introduce an error compensation factor to suppress interference; S3. Blind area energy reconstruction method: Monitor the signal strength and attenuation, identify the communication blind area, use the energy gradient diffusion algorithm to reconstruct the radiation pattern, and enhance the coverage through the cooperation of the main beam and the auxiliary lobe; S4. Energy efficiency dynamic ratio method: Establish a mapping model between the beam energy and the terminal power consumption, and dynamically allocate the power of the main beam and the side lobe according to the service type requirements; S5. Space-time coding anti-interference method: Assign a unique time-frequency interleaved code to the user, embed orthogonal phases in the beamforming, and use spatial domain filtering to eliminate co-frequency interference signals; S6. Trajectory-driven parameter migration method: Predict the motion vector based on the historical trajectory of the terminal, construct a dynamic response model, and realize the migration and adaptation of the beam parameters.

2. The beamforming control method for 5G wireless communication antennas according to claim 1, characterized in that, S1. Three-dimensional perception pre-calibration method, specifically including the following steps: In the three-dimensional perception pre-calibration method, a multi-source heterogeneous data fusion technology is adopted. Based on the meteorological sensor, meteorological data is obtained. The data collected by the sensor devices provided by the terminal positioning system includes: longitude, latitude, altitude, moving speed, moving direction, and the three-dimensional coordinates, shape, size, material, and surface roughness data of the obstacles collected by the lidar are fused to form a data set that comprehensively reflects the influence of the obstacles and the surrounding environment on the electromagnetic wave propagation; Based on the improved D-S evidence theory algorithm, the uncertainty and conflict between the data of each sensor are processed to eliminate noise interference. Based on the principal component analysis algorithm, the fused data is dimensionally reduced, and the key environmental characteristic parameters affecting the electromagnetic wave propagation are extracted, including the signal attenuation coefficient under different meteorological conditions, the reflection loss coefficient, scattering coefficient, and diffraction coefficient of the obstacle to the electromagnetic wave. The high-precision data of the signal attenuation coefficient, reflection loss coefficient, scattering coefficient, and diffraction coefficient of the obstacle to the electromagnetic wave under different meteorological conditions are input into the three-dimensional electromagnetic interference model. Based on adjusting the coefficients, boundary conditions, and excitation source settings in the model, the model is refined and calibrated to obtain the dynamic adjustment of the beam pointing angle range and complete the pre-calibration work of the beam direction.

3. The beamforming control method for 5G wireless communication antennas according to claim 1, characterized in that, S2. Zoning weight optimization method, specifically including the following steps: For the zoning weight optimization method, based on the data of the three-dimensional perception pre-calibration, a real-time monitoring system for frequency band characteristics is built. This system includes multiple frequency band signal acquisition units, which can monitor the field strength distribution, phase change, fading characteristics, and multipath effect data of the frequency band signals in the core area and the edge area in real time. Based on the real-time monitored data, combined with the historical monitored data and the current environmental data, a prediction model for the frequency band propagation characteristics based on deep learning is constructed; Extract spatial features based on a convolutional neural network, analyze time series features in combination with a long short-term memory network, and predict the change trend of frequency band characteristics. When detecting a frequency band switch or environmental change, the system retrieves corresponding data from the frequency band characteristic database, recomputes in combination with the prediction result and an intelligent optimization algorithm, and adjusts the phase and amplitude weights of the antenna elements in the core area and the edge area; at the same time, according to the error feedback mechanism, using the signal transmission error data monitored in real time, dynamically update the error compensation data, and adopt an adaptive filtering algorithm to correct the signal transmission error in real time, so as to achieve differential adjustment of the weights of different frequency band signals in different regions and suppress interference.

4. The beamforming control method for 5G wireless communication antennas according to claim 1, characterized in that, S3. Blind area energy reconstruction method, which specifically includes the following steps: In the blind area energy reconstruction method, based on the data basis of three-dimensional perception pre-calibration, construct a multi-dimensional blind area recognition system. The monitored signals include: intensity, signal attenuation, signal delay spread, Doppler frequency shift, signal-to-noise ratio fluctuation, bit error rate index. Based on a convolutional neural network-long short-term memory network fusion model, perform signal feature extraction and analysis on multi-dimensional monitoring data, where the convolutional neural network is used to extract spatial features, and the long short-term memory network fusion model is used to process time series features, to obtain the precise positioning of the communication blind area and the accurate judgment of the shape and size of the blind area; In the energy gradient diffusion algorithm, introduce an adaptive step size adjustment mechanism, and dynamically adjust the step size and direction of energy diffusion according to the complexity of the blind area and the requirements of the number of users and service types that the signal needs to cover for the signal intensity; at the same time, in combination with the reinforcement learning algorithm, with the coverage effect and energy efficiency as the optimization objectives, continuously optimize the cooperative working strategy of the main beam and the auxiliary lobes; in a narrow and long blind area, by adjusting the radiation angle and power of the auxiliary lobe, enable it to cover along the extension direction of the blind area; in a large-area blind area, reasonably allocate the energy of the main beam and multiple auxiliary lobes to ensure the uniformity and integrity of the blind area signal coverage, and obtain the reconstruction of the radiation pattern.

5. The beamforming control method for 5G wireless communication antennas according to claim 1, characterized in that: S4. Energy efficiency dynamic ratio method, which specifically includes the following steps: For the energy efficiency dynamic ratio method, based on the optimized data of the partition weight optimization method, the business type division is refined. The real-time services are subdivided into high-definition video calls, cloud games, and video conferencing services with extremely high requirements for real-time performance and image quality, as well as ordinary voice call services; the non-real-time services are divided into different priority services such as large file transfer and database backup; a service demand-power allocation decision model is established, comprehensively considering the real-time requirements, data transmission rate, and maximum allowable delay factors of the services, and different power allocation strategies are formulated. For high-definition video call services, the power allocation scheme with the highest priority is adopted to ensure the high-power output of the main beam first. At the same time, according to the movement of the terminal, the position and speed data obtained by the terminal positioning system are used to dynamically adjust the sidelobe power to ensure the smoothness and stability of the video picture; for large file transfer services, on the premise of ensuring the basic transmission rate, the power of the main beam is appropriately reduced, and the sidelobe power is increased to expand the coverage area, and the transmission is carried out during the low-peak period at night; by real-time monitoring the change of service traffic, the sliding window prediction algorithm is used to predict the service traffic trend in the future period of time, and the power allocation ratio of the main beam and the sidelobe is dynamically adjusted to achieve the dynamic balance of beam energy and terminal power consumption, and optimize the coverage and energy efficiency.

6. The beamforming control method for 5G wireless communication antennas according to claim 1, characterized in that, S5. Space-time coding anti-interference method, specifically including the following steps: In the space-time coding anti-interference method, based on the data of the interference environment determined by three-dimensional perception pre-calibration and the optimized data of the partition weight optimization method, the time-frequency interleaving coding generation algorithm is improved. The chaotic sequence and the pseudo-random sequence are combined to optimize the spatial domain filtering algorithm, and the adaptive least mean square algorithm is introduced. According to the interference signal intensity data, frequency data, and phase change data monitored in real time, the filter coefficients are adjusted, and the filtered data is adjusted to obtain the dynamic tracking and suppression ability for co-frequency interference signals.

7. The beamforming control method for 5G wireless communication antennas according to claim 6, characterized in that, The dynamic tracking and suppression ability for co-frequency interference signals specifically includes the following steps: Design the collaborative working process of coding and filtering. At the signal transmitting end, the generated unique time-frequency interleaving coding and orthogonal phase components are embedded in the beamforming process, and the phase and amplitude of each unit of the antenna array are adjusted to achieve coding modulation; at the receiving end, the spatial characteristics of the signal are analyzed to remove the spatially uncorrelated interference signals. Based on the coding matching algorithm, the received signal is compared with the pre-stored user coding to identify and eliminate the interference signals with non-corresponding coding.

8. The beamforming control method for 5G wireless communication antennas according to claim 1, characterized in that, S6. Trajectory-driven parameter migration method, specifically including the following steps: In the trajectory-driven data migration method, the multi-modal trajectory prediction technology is adopted to fuse the multi-source information of the data collected by the sensor device provided by the terminal positioning system, inertial sensor data, and Wi-Fi positioning data, and a trajectory prediction model based on Transformer is constructed; Introduce the attention mechanism to enable the model to focus on feature data that has an important impact on the terminal's movement trend, such as the terminal's turning data and acceleration / deceleration data at intersections. Combine the data collected by the sensor devices provided by the terminal positioning system, and consider factors such as road layout, traffic rules, and terrain and landform to constrain and correct the prediction model. When predicting the terminal's motion vector, including its position, speed, and direction over a period of time in the future, update the phase, amplitude, and beam width data in the beam data dynamic response model based on the fast data migration algorithm. Design a data migration error feedback mechanism to compare the actual communication effect with the expected effect. If the error exceeds the set threshold, automatically trigger the model optimization process, and adjust the data of the trajectory prediction model and the beam data dynamic response model based on the reinforcement learning algorithm to obtain a closed-loop optimization of trajectory prediction data, data migration, and effect feedback.

9. The beamforming control method for 5G wireless communication antennas according to claim 1, characterized in that,Design a multi-method collaborative scheduling mechanism, which specifically includes the following steps: Design a multi-method collaborative scheduling mechanism, construct an environment-method matching database, and associate and match different communication environment characteristics, including high interference, multiple blind spots, dense terminals, and fast movement, with corresponding innovative methods or method combinations. When the system detects the current communication environment information through the environment perception module, based on the database, use the decision tree algorithm to quickly select the optimal method collaborative combination scheme, formulate collaborative execution rules, and clarify the execution order, data interaction method, and resource allocation strategy of each method during the collaboration. In an environment with high interference and communication blind spots, based on the three-dimensional perception pre-calibration method, collect meteorological data, terminal distribution data, and obstacle data, construct a three-dimensional electromagnetic interference model, predict the interference trend, dynamically adjust the beam pointing angle range, and preliminarily calibrate the beam direction. Based on the space-time coding anti-interference method, assign a unique time-frequency interleaved coding to users, embed orthogonal phases in beamforming, and use spatial domain filtering to eliminate co-frequency interference signals. Based on the blind area energy reconstruction method, monitor the signal strength and attenuation, identify communication blind spots, and use the energy gradient diffusion algorithm to reconstruct the radiation pattern to obtain the collaborative enhancement of coverage by the main beam and auxiliary lobes. Regularly collect system operation data and use the genetic algorithm to optimize the collaborative scheduling mechanism and adjust the environment-method matching rules and collaborative execution strategies. The beamforming control system of a 10.5G wireless communication antenna, for the beamforming control method of the 5G wireless communication antenna according to any one of claims 1-9, is characterized in that, Specifically include: The environment perception and beam pre-calibration module, using the three-dimensional perception pre-calibration method, collects meteorological data, terminal distribution data, and obstacle data, constructs a three-dimensional electromagnetic interference model, predicts the interference trend, dynamically adjusts the beam pointing angle range, and pre-calibrates the beam direction; The regional weight optimization module, using the partition weight optimization method, divides the antenna coverage area into the core area and the edge area, and differentially adjusts the phase and amplitude weights of the antenna elements according to the frequency band propagation characteristics, and introduces an error compensation factor to suppress interference; The blind area signal reconstruction module, using the blind area energy reconstruction method, monitors the signal strength and attenuation, identifies communication blind spots, uses the energy gradient diffusion algorithm to reconstruct the radiation pattern, and enhances the coverage through the collaboration of the main beam and auxiliary lobes; Power energy efficiency allocation module, energy efficiency dynamic ratio method, establish a mapping model between beam energy and terminal power consumption, and dynamically allocate the main beam and sidelobe power according to the service type requirements; Anti-interference coding and filtering module, space-time coding anti-interference method, allocate a unique time-frequency interleaved coding for users, embed orthogonal phases in beamforming, and use spatial domain filtering to eliminate co-frequency interference signals; Terminal trajectory adaptation module, trajectory-driven parameter migration method, predict the motion vector based on the terminal's historical trajectory, construct a dynamic response model, and realize the migration and adaptation of beam parameters.

Images