Dynamic polarization-beam regulation and control anti-interference method and system based on intelligent metasurface

Abstract

The invention provides a dynamic polarization-beam regulation and control anti-interference method and system based on an intelligent metasurface, and relates to the technical field of wireless communication, and the system comprises an intelligent metasurface array, a controller, a channel sensing module and a joint optimization module. By sensing the channel state and interference characteristics in the wireless environment in real time and dynamically adjusting the polarization state and phase configuration of the intelligent metasurface unit, collaborative optimization of a polarization domain and a space domain is achieved, an enhanced propagation path for expected users is formed, meanwhile, an interference source is restrained, and the anti-interference capacity and communication quality of the system are improved. According to the method, a hybrid optimization strategy combining deep reinforcement learning with model driving is adopted, the calculation complexity is reduced, rapid response to a dynamic interference environment is realized, and meanwhile, the spectrum efficiency and the energy efficiency are improved through polarization-beam joint optimization. Through collaborative optimization of a polarization domain and a spatial domain, adaptive response to a complex interference environment is realized, and meanwhile, energy consumption and implementation cost are reduced.

Description

Technical Field

[0001] The present invention relates to the field of wireless communication technologies, and particularly to a dynamic polarization-beam control anti-interference method and system based on an intelligent reflecting surface. Background Art

[0002] As a key enabling technology for 6G wireless communication, the intelligent reflecting surface (IRS) has gradually attracted extensive attention from researchers. The intelligent reflecting surface is composed of a large number of programmable electromagnetic units, which can actively control the reflection, refraction or scattering characteristics of electromagnetic waves by adjusting the electromagnetic characteristics of each unit, thereby reconstructing the wireless signal propagation environment. Currently, the research on intelligent reflecting surfaces mainly focuses on the following directions:

[0003] 1. Beamforming technology: By adjusting the phase of the intelligent reflecting surface units, the optimization of beam directivity is achieved, thereby enhancing the signal strength in a specific direction. This method mainly optimizes the signal propagation in the spatial domain, and can avoid the direction of the interference source to a certain extent, improving the signal quality of the system.

[0004] 2. Polarization control technology: Utilize polarization characteristics to enhance the anti-interference ability of the communication system. Through polarization diversity coding or polarization control, the transmission of signals can achieve independence, thereby effectively avoiding the influence of interference sources on signals. Some studies have combined polarization control technology with intelligent reflecting surfaces to further improve the channel capacity and system reliability.

[0005] 3. Intelligent reflecting surface-assisted communication: By adjusting the reflection phase of electromagnetic waves through the intelligent reflecting surface, a favorable propagation environment is reconstructed, thereby improving the coverage range and signal quality of wireless communication. This technology can effectively increase the signal strength in a complex electromagnetic environment, reducing signal attenuation and interference.

[0006] 4. The combination of cognitive radio technology and intelligent reflecting surfaces: Intelligent reflecting surfaces are also combined with cognitive radio technology and applied to dynamic spectrum access and interference avoidance. In the research in this direction, intelligent reflecting surfaces are used to enhance the management of spectrum resources, optimize the channel environment, and improve the utilization efficiency of the spectrum.

[0007] Although these technical solutions have made positive progress in aspects such as beam control, polarization control, and spectrum management, the existing technologies usually regard beam control and polarization control as independent technical means and fail to fully exert the synergistic effect between the two. Especially in the face of an intelligent and ever-changing interference environment, a single control method often cannot provide comprehensive anti-interference capabilities. Summary of the Invention

[0008] Aiming at the deficiencies of the existing technologies, the purpose of the present invention is to provide a dynamic polarization-beam control anti-interference method and system based on intelligent metasurfaces, so as to solve the problems proposed in the above background technology. Through the collaborative optimization of the polarization domain and the spatial domain, the present invention realizes an adaptive response to complex interference environments, improves the anti-interference ability and spectrum utilization efficiency of the system, while reducing energy consumption and implementation costs.

[0009] To achieve the above object, the present invention is implemented through the following technical solutions: A dynamic polarization-beam control anti-interference system based on intelligent metasurfaces, the system includes a programmable intelligent metasurface array, a controller, a channel sensing module, a joint optimization module, and a communication interface. The programmable intelligent metasurface array is composed of M×N independently controllable units, and each unit can simultaneously control the polarization state and reflection phase of electromagnetic waves; the controller is responsible for generating control signals according to the output results of the optimization algorithm to drive the intelligent metasurface units to change their electromagnetic characteristics; the channel sensing module includes a multi-polarization sensor array and a signal processing unit, which are used to obtain the channel state information (CSI) and interference characteristics in the wireless environment in real time; the joint optimization module: based on a hybrid optimization framework of deep reinforcement learning and model-driven, receives the environmental information provided by the channel sensing module, and generates the optimal configuration strategy of the intelligent metasurface; the communication interface supports a variety of standard communication protocols for seamless integration with existing wireless communication systems.

[0010] Furthermore, the independently controllable units adopt technologies such as liquid crystal, graphene, or varactor diodes to achieve dynamic regulation of polarization and phase. The controller is implemented by FPGA and supports high-speed parallel control; the channel state information includes multi-dimensional information such as signal strength, angle of arrival, and polarization state.

[0011] Furthermore, each unit of the intelligent metasurface unit structure is composed of a tunable dielectric layer, a polarization rotation layer, and a metal backplane. The tunable dielectric layer is used to control the reflection phase; the polarization rotation layer can change the polarization state of the incident electromagnetic wave; the metal backplane ensures high reflection efficiency. The size of the unit is λ / 4×λ / 4, where λ is the wavelength of the operating frequency.

[0012] Furthermore, the intelligent metasurface with an array layout structure adopts a planar rectangular array layout, including M×N units, and the adjacent unit spacing is λ / 2.

[0013] Furthermore, the control network structure adopts a hierarchical control architecture. The main controller communicates with multiple sub-controllers through a serial peripheral interface or an I2C interface. Each sub-controller is responsible for controlling a group of intelligent metasurface units; the algorithm processing unit adopts a high-performance embedded processor and an AI acceleration chip, and is used to process the connection between the unit and the controller through a high-speed data bus to ensure low-latency control.

[0014] Furthermore, the channel sensing structure consists of an array of multiple orthogonal polarization antenna pairs, which can simultaneously acquire the intensity and phase information of horizontally polarized and vertically polarized signals. After the signals pass through the low-noise amplifier and analog-to-digital converter, they are sent to the signal processing unit for analysis.

[0015] A dynamic polarization-beam steering anti-jamming method based on intelligent metasurface, which includes establishing a polarization-beam joint steering mathematical model. The steps are as follows:

[0016] The system channel is expressed as:

[0017]

[0018] where represents the direct channel from the base station to the user, including horizontal and vertical polarization components; represents the channel from the base station to the IRS; represents the channel from the IRS to the user; is the reflection coefficient matrix of the IRS, where is the total number of IRS units;

[0019] The reflection coefficient matrix Φ is composed of polarization control and phase control of each IRS unit, and is expressed as:

[0020]

[0021] where respectively represent the co-polarization reflection coefficients, represents the cross-polarization reflection coefficient. For the (m,n)th IRS unit, its reflection characteristics are represented by the following parameters:

[0022]

[0023] where represents the reflection amplitude, represents the reflection phase, is the polarization reflection characteristic of each IRS unit.

[0024] Furthermore, it includes establishing an interference source model: Considering the existence of J interference sources, the signal received by the user is expressed as:

[0025]

[0026] where is the transmitted signal, is the interference signal transmitted by the jth interference source, is the channel from the jth interference source to the user, is the additive white Gaussian noise.

[0027] Furthermore, it includes the modeling of joint optimization problems: by optimizing the reflection coefficient matrix of the IRS , the signal-to-interference-plus-noise ratio (SINR) of the user is maximized, which is formally expressed as

[0028] where is the Hermitian transpose of the total channel, is the Hermitian transpose of the interference channel, is the noise power.

[0029] The optimization constraints are as follows:

[0030]

[0031]

[0032]

[0033] Furthermore, it also includes a hybrid optimization algorithm combining deep reinforcement learning and model-driven, and the work process is as follows:

[0034] Environmental perception stage: Obtain the channel state information (CSI) and interference characteristics through channel sounding, and establish a system model;

[0035] Feature extraction stage: Use a deep neural network to extract key features from the CSI, including the direction of the interference source, polarization characteristics, etc.;

[0036] State space definition: Define the state space SS, including the channel state, interference information, and current system performance metrics;

[0037] Action space definition: Define the action space AA, which contains the adjustment scheme for the polarization and phase of each unit of the IRS.

[0038] Reward function design: The reward function RR is a weighted combination of the gain of the user's SINR and the energy consumption:

[0039]

[0040] Policy network training: Use the deep deterministic policy gradient (DDPG) algorithm to train the policy network to generate the IRS configuration policy;

[0041] Model-driven optimization: Combine physical model constraints to adjust the output of the policy network to ensure energy conservation and physical realizability;

[0042] Polarization-beam joint optimization: Based on the output of the policy network, optimize the polarization control matrix and the phase control matrix respectively, and then perform joint optimization;

[0043] Fast Adaptive Update: For a dynamically changing environment, an incremental learning method is adopted to quickly adjust the IRS configuration.

[0044] Advantages of the present invention:

[0045] 1. By combining the joint optimization mechanism of the polarization domain and the spatial domain, the present invention significantly improves the anti-interference ability of the system. The simulation experiment results in a strong interference environment (for example, the interference power is 20 dB higher than the signal power) show that, compared with the traditional beamforming method, the present invention can increase the signal-to-interference-plus-noise ratio (SINR) by about 12 dB; compared with the scheme that solely relies on polarization regulation, the present invention improves the anti-interference performance by about 8 dB. This indicates that the present invention can effectively improve the communication quality in a complex interference environment.

[0046] 2. By precisely controlling the signal propagation path and polarization state, the present invention realizes the efficient utilization of spectrum resources. In a multi-user scenario (for example, 20 users), the present invention improves the spectrum efficiency by about 45% compared with the traditional method and by about 25% compared with the simple beamforming method. This achievement demonstrates the advantages of the present invention in enhancing network capacity and multi-user cooperative communication ability.

[0047] 3. The present invention adopts a hybrid optimization method combining deep reinforcement learning and model-driven, successfully reducing the computational complexity of the system. Compared with the traditional joint optimization method, the calculation time is reduced by about 60%, greatly improving the response speed and real-time performance of the system. This feature enables the present invention to quickly adjust and maintain high performance in a dynamic environment.

[0048] 4. The modular design of the present invention enables the system to have good scalability and can adapt to different scales of intelligent metasurface arrays and communication requirements. Experiments verify the expansion ability from 8×8 to 64×64 units, and the system performance steadily improves with the increase in the number of units, indicating that this method is applicable to large-scale wireless communication systems.

[0049] 5. The present invention can adaptively adjust the configuration of the intelligent metasurface according to environmental changes, especially performing excellently in a dynamic interference environment. The experimental results show that in the case where the interference environment changes every 5 seconds, the method of the present invention can maintain a communication reliability of more than 92%, while the reliability of the traditional method is only 45%. This result indicates that the present invention has strong adaptability in a rapidly changing environment.

[0050] 6. By optimizing the configuration strategy of the IRS, the present invention reduces unnecessary energy consumption. On the premise of ensuring communication quality, compared with the traditional method, the present invention can save about 35% of the total system energy consumption, meeting the requirements of green communication and low-power communication systems.

[0051] 7. The present invention can be seamlessly integrated into existing communication systems without large-scale modification of terminal devices, reducing the deployment cost and difficulty. Experiments have verified the compatibility of the present invention with 4G / 5G communication systems, ensuring its universality and feasibility in practical applications. Description of the Drawings

[0052] Figure 1 is the overall architecture diagram of the dynamic polarization-beam steering anti-jamming system based on intelligent metasurfaces of the present invention;

[0053] Figure 2 is the schematic diagram of the intelligent metasurface unit structure of the present invention;

[0054] Figure 3 is the schematic diagram of the polarization-beam joint steering principle of the present invention;

[0055] Figure 4 is the flowchart of the joint optimization algorithm;

[0056] Figure 5 is the schematic diagram of dynamic polarization control;

[0057] Figure 6 is the schematic diagram of the beamforming effect;

[0058] Figure 7 is the architecture diagram of the joint optimization module;

[0059] Figure 8 is the experimental result of the system performance comparison in the embodiment of the present invention. Detailed Embodiments

[0060] To make the technical means, creative features, achieved purposes and effects of the present invention easy to understand, the present invention will be further described below in conjunction with specific embodiments.

[0061] Please refer to Figures 1 to 8 , the present invention provides the following technical solutions:

[0062] Embodiment 1

[0063] The dynamic polarization-beam steering anti-jamming system based on intelligent metasurfaces mainly consists of the following key components:

[0064] 1. Programmable intelligent metasurface array: It consists of M×N independently controllable units, and each unit can simultaneously control the polarization state and reflection phase of electromagnetic waves. The units use technologies such as liquid crystals, graphene, or varactor diodes to achieve dynamic control of polarization and phase.

[0065] 2. Controller: It is responsible for generating control signals according to the output results of the optimization algorithm to drive the intelligent metasurface units to change their electromagnetic characteristics. The controller is implemented by FPGA and supports high-speed parallel control.

[0066] 3. Channel Sensing Module: It includes a multi-polarization sensor array and a signal processing unit, which are used to obtain the channel state information (CSI) and interference characteristics in the wireless environment in real time, including multi-dimensional information such as signal strength, angle of arrival, and polarization state.

[0067] 4. Joint Optimization Module: Based on a hybrid optimization framework of deep reinforcement learning and model-driven, it receives the environmental information provided by the channel sensing module, generates the optimal configuration strategy of the intelligent metasurface, and realizes the joint optimization of polarization-beam.

[0068] 5. Communication Interface: It supports multiple standard communication protocols to achieve seamless integration with existing wireless communication systems.

[0069] This embodiment also provides the structural description of the above system:

[0070] The physical structure and functional flow of the system of the present invention are as follows:

[0071] 1. Structure of Intelligent Metasurface Unit: Each unit consists of a tunable dielectric layer, a polarization rotation layer, and a metal backplane. The tunable dielectric layer is used to control the reflection phase; the polarization rotation layer can change the polarization state of the incident electromagnetic wave; the metal backplane ensures high reflection efficiency. The size of the unit is λ / 4 × λ / 4, where λ is the wavelength of the operating frequency.

[0072] 2. Array Arrangement Structure: The intelligent metasurface adopts a planar rectangular array arrangement, including M×N units. The spacing between adjacent units is λ / 2 to avoid grating lobe effects. The size of the entire array can be flexibly configured according to the application scenario requirements, and typical configurations are 32×32 or 64×64 units.

[0073] 3. Control Network Structure: It adopts a hierarchical control architecture. The main controller communicates with multiple sub-controllers through a serial peripheral interface (SPI) or I2C interface. Each sub-controller is responsible for controlling a group of intelligent metasurface units to achieve efficient parallel control.

[0074] 4. Channel Sensing Structure: An array composed of multiple orthogonal polarization antenna pairs can simultaneously obtain the intensity and phase information of horizontally polarized and vertically polarized signals. The signal is sent to the signal processing unit for analysis after passing through a low-noise amplifier (LNA) and an analog-to-digital converter (ADC).

[0075] 5. Algorithm Processing Unit: It adopts a high-performance embedded processor and an AI acceleration chip to realize real-time calculation of complex optimization algorithms. The processing unit is connected to the controller through a high-speed data bus to ensure low-latency control.

[0076] Embodiment 2

[0077] This embodiment also provides a dynamic polarization-beam control method based on intelligent metasurfaces, which is used to optimize the signal transmission quality of wireless communication systems in complex interference environments. In the system, there are a base station, an intelligent metasurface (IRS), and multiple user terminals. To cope with multiple interference sources and complex environments, the present invention improves the anti-interference ability of the system by jointly controlling polarization and beam.

[0078] Consider a wireless communication system consisting of a base station (BS), an intelligent metasurface (IRS), and multiple user terminals. The system channel is expressed as:

[0079]

[0080] where, represents the direct channel from the base station to the user, including horizontal and vertical polarization components; represents the channel from the base station to the IRS; represents the channel from the IRS to the user; is the reflection coefficient matrix of the IRS, where is the total number of IRS units.

[0081] IRS reflection coefficient matrix

[0082] The reflection coefficient matrix Φ is composed of the polarization control and phase control of each IRS unit, and is expressed as:

[0083]

[0084] where, respectively represent the co-polarization reflection coefficients, represents the cross-polarization reflection coefficient. For the (m,n)-th IRS unit, its reflection characteristics are represented by the following parameters:

[0085]

[0086] where, represents the reflection amplitude, represents the reflection phase, is the polarization reflection characteristic of each IRS unit.

[0087] Interference source model

[0088] Considering the existence of J interference sources, the signal received by the user is expressed as:

[0089]

[0090] where, is the transmitted signal, is the interference signal transmitted by the j-th interference source, is the channel from the j-th interference source to the user, is additive white Gaussian noise.

[0091] Modeling of the joint optimization problem

[0092] The objective of the present invention is to maximize the signal-to-interference-plus-noise ratio (SINR) of the user by optimizing the reflection coefficient matrix of the IRS, which is formally expressed as where

[0093] is the Hermitian transpose of the total channel, is the Hermitian transpose of the interference channel, is the noise power.

[0094] The optimization constraints are as follows:

[0095]

[0096]

[0097]

[0098] These constraints ensure that the reflection amplitude and phase of each IRS unit satisfy the physical constraints, thus ensuring the feasibility of practical implementation.

[0099] Deep reinforcement learning combined with model-driven hybrid optimization algorithm

[0100] To address the non-convexity of the above optimization problem and reduce the computational complexity, the present invention proposes a hybrid optimization method combining deep reinforcement learning with model-driven. The workflow of the algorithm is as follows:

[0101] Environment perception stage: Obtain the channel state information (CSI) and interference characteristics through channel sounding, and establish a system model.

[0102] Feature extraction stage: Use a deep neural network to extract key features from the CSI, including the direction of the interference source, polarization characteristics, etc.

[0103] State space definition: Define the state space SS, including the channel state, interference information, and current system performance metrics.

[0104] Action space definition: Define the action space AA, which contains the adjustment schemes for the polarization and phase of each IRS unit.

[0105] Reward function design: The reward function RR is a weighted combination of the gain of the user's SINR and the energy consumption:

[0106]

[0107] ​Policy Network Training: The policy network is trained using the Deep Deterministic Policy Gradient (DDPG) algorithm to generate IRS configuration policies.

[0108] Model-Driven Optimization: Combining physical model constraints, the output of the policy network is adjusted to ensure energy conservation and physical realizability.

[0109] Polarization-Beam Joint Optimization: Based on the output of the policy network, the polarization control matrix and the phase control matrix are optimized separately and then jointly optimized.

[0110] Fast Adaptive Update: For a dynamically changing environment, an incremental learning method is adopted to quickly adjust the IRS configuration.

[0111] Example 3

[0112] In this example, by combining the dynamic polarization and beam joint control of the intelligent metasurface, a significantly innovative wireless communication optimization method is proposed. Compared with the prior art, the present invention adopts the following scheme:

[0113] Polarization and Beam Joint Control: The present invention combines polarization and beam control for optimization for the first time, while the prior art usually processes these two separately.

[0114] Combination of Deep Reinforcement Learning and Model-Driven Optimization: By combining deep reinforcement learning with physical models, the present invention can reduce the computational complexity while ensuring system performance, and can quickly adaptively adjust in a dynamic environment.

[0115] Anti-Jamming Optimization in a Multi-Jammer Environment: The algorithm of the present invention can significantly improve the anti-jamming ability of the system by jointly optimizing polarization and beam control in a multi-jammer and complex electromagnetic environment.

[0116] By comparing with the prior art, the present invention has great advantages in anti-jamming performance, adaptability and computational efficiency, ensuring innovation and application value.

[0117] The core algorithms and optimization methods in this example include:

[0118] 1. Polarization-Beam Joint Control Mathematical Model

[0119] The system consists of a base station (BS), an intelligent metasurface (IRS) and user terminals. The IRS contains M×N programmable units, and each unit independently controls the reflection phase and the polarization conversion matrix . Considering a dual-polarized antenna system, the total channel model is:

[0120]

[0121] Where:

[0122] : Direct channel (including horizontal / vertical polarization)

[0123] : BS→IRS channel

[0124] : IRS→user channel

[0125] : Phase control matrix

[0126] : Unit polarization conversion matrix

[0127] In this embodiment, the polarization control matrix is decoupled and modeled with the phase control , breaking through the limitation of traditional IRS that only controls the phase, and forming a four-dimensional control parameter space .

[0128] 2. Modeling of anti-interference optimization problem

[0129] For interference sources, the received signal of the user is:[[]]

[0130]

[0131] The optimization goal is to maximize the signal-to-interference-plus-noise ratio

[0132]

[0133] Constraints:

[0134]

[0135]

[0136]

[0137] In this embodiment, a non-convex optimization problem with polarization-phase joint constraints is constructed. Compared with the existing model that only considers phase optimization, the control dimension is increased by 300%.

[0138] 3. Design of hybrid optimization algorithm

[0139] A two-stage optimization framework of "deep reinforcement learning + physical model correction" is proposed:

[0140] Stage 1: Preliminary optimization of DRL

[0141] State space:

[0142] Action space:

[0143] Reward function:

[0144]

[0145] Stage 2: Physical constraint correction

[0146] Perform feasibility correction on the DRL output:

[0147]

[0148] In this embodiment, a constraint correction operator is proposed , which maps the DRL output to the feasible solution space and solves the problem that traditional DRLs are difficult to handle complex physical constraints. Compared with the pure model-driven method, the computational efficiency is increased by 5.8 times.

[0149] 4. Key theoretical derivations

[0150] Theorem 1 (Polarization control interference suppression bound):

[0151] When the interference polarization state is orthogonal to the desired signal, the maximum interference suppression ratio is:

[0152]

[0153] where is the polarization covariance matrix of the interference and the desired signal.

[0154] Proof:

[0155] According to the Rayleigh quotient extreme value theory, when makes achieve the extreme value, the optimal suppression ratio can be obtained. Substituting the constraint conditions into the KKT conditions can prove it.

[0156] Theorem 2 (Convergence guarantee):

[0157] Under the Lipschitz continuity condition, the hybrid optimization algorithm converges to the local optimal solution with probability 1.

[0158] In this embodiment, the convergence of the IRS joint optimization algorithm is strictly proven for the first time, filling the theoretical gap in existing research (such as IEEE TIV 2023).

[0159] 5. This embodiment also provides an innovative comparative analysis

[0160]

[0161] Numerical simulation verification To further verify the actual anti-interference performance of the method of the present invention and quantify its advantages, detailed numerical simulation experiments were carried out. The simulation platform used MATLAB, simulated a variety of typical interference scenarios, and compared the performance differences between the method of the present invention and traditional methods.

[0162] Scenario 1: Single interference source scenario The sensitivity of the signal-to-interference-plus-noise ratio (SINR) to the change of interference power was investigated under the typical scenario of a single interference source. The simulation results clearly showed that when the interference power increased significantly by 30 dB, the SINR value of the system using the traditional method decreased sharply by about 24 dB, and the communication quality was severely impaired. However, when the polarization-beam joint regulation method proposed by the present invention was used, the SINR value only decreased by about 9 dB, and the performance attenuation amplitude was significantly reduced, fully demonstrating the strong anti-interference ability of the method of the present invention in the single interference source scenario.

[0163] Scenario 2: Multiple interference sources scenario In the actual wireless communication environment, there are often multiple interference sources working simultaneously. To simulate a more realistic scenario, the relationship between the anti-interference success rate of the system and the increase in the number of interference sources was investigated under the multiple interference sources scenario. The simulation results showed that when the number of interference sources increased from a small amount to 10, the anti-interference success rate of the traditional method rapidly decreased to less than 10%, and the system could hardly communicate normally. However, under the same conditions, the anti-interference success rate of the method of the present invention could still remain above 65%, demonstrating excellent robustness in a complex multi-interference environment.

[0164] Scenario 3: Dynamic interference scenario The wireless environment is dynamically changing, and the position, power, and polarization characteristics of interference sources may change over time. To evaluate the adaptability of the system in a dynamic interference environment, a scenario where the position and characteristics of interference sources change dynamically was simulated, and the anti-interference adaptability of the system was investigated. The simulation results proved that the method of the present invention could quickly respond to the changes in the interference environment. After the interference environment changed, the system could quickly adjust the IRS configuration within an extremely short time (average response time < 10 ms), continuously maintain a high system performance, and ensure the stable and reliable communication link.

[0165] Scenario 4: Extreme interference scenario To test the anti-interference limit of the method of the present invention, an extreme interference scenario was designed, that is, the case where the interference power is much greater than the desired signal power. The simulation results showed that even under the extremely harsh condition that the interference power was 40 dB higher than the desired signal power, the communication link of the traditional method had completely failed, and the system could not communicate effectively.

[0166] Under the same extreme conditions, the method of the present invention can still maintain a basic communication link, ensure a certain communication quality, and demonstrate strong anti-interference resilience in extreme interference scenarios. In summary, through theoretical analysis and multi-scenario numerical simulation verification, the anti-interference algorithm based on intelligent metasurface dynamic polarization-beam control proposed by the present invention is significantly superior to the prior art in terms of anti-interference performance, environmental adaptability, and robustness under extreme conditions, providing strong technical support for improving the system performance in complex wireless communication environments.

[0167] Conclusion: This method breaks through the bottlenecks of the prior art in terms of regulation dimension, computational efficiency, and anti-interference performance.

[0168] Embodiment 4

[0169] This embodiment provides an end-to-end optimization method based on deep learning, which directly maps from the original channel state information to the optimal configuration of the intelligent metasurface.

[0170] The specific implementation is as follows:

[0171] Network architecture: A hybrid structure of a convolutional neural network (CNN) and a long short-term memory network (LSTM) is adopted. The CNN is used to extract the spatial features of the channel state, and the LSTM is used to capture the time series change features. By combining these two neural network structures, effective features can be better extracted from complex channel information.

[0172] Loss function: Directly use the signal-to-interference-plus-noise ratio (SINR) of the system as the objective function for supervised learning, or use the communication capacity as the objective function, with the goal of maximizing the communication performance of the system.

[0173] Training method: Use a large amount of simulated data and actual measurement data for offline training. After training is completed, use the fine-tuning method to apply the model to the actual system to further optimize its performance in the real environment.

[0174] Techniques for reducing complexity: Adopt techniques such as network pruning and knowledge distillation to reduce the complexity of the model, enabling it to run in resource-constrained environments, thereby reducing hardware requirements.

[0175] Advantages and disadvantages of alternative solutions:

[0176] Advantages: This solution is simple to implement and has a relatively fast inference speed, making it suitable for application scenarios with high real-time requirements.

[0177] Disadvantages: It requires a large amount of training data, and it is difficult to ensure the satisfaction of physical constraints, which may lead to some non-physically realizable configurations, and the performance stability may be poor.

[0178] Embodiment 5

[0179] This embodiment provides a hierarchical optimization method for polarization-beam control. This method adopts a hierarchical optimization strategy, first optimizing the polarization state and then optimizing the beam direction.

[0180] The specific implementation is as follows:

[0181] 1. Polarization layer optimization:

[0182] First, estimate the polarization states of the interfering source and the desired user.

[0183] Optimize the polarization control matrix of the IRS unit to match the polarization state of the desired user with the receiving end, and at the same time make the polarization state of the interfering source orthogonal to the receiving end.

[0184] Solve the constrained optimization problem:

[0185] where and are the polarization states of the desired signal and the interfering signal, respectively.

[0186] 2. Beam layer optimization:

[0187] Based on the determined polarization control, optimize the phase configuration of the IRS unit.

[0188] Use classical beamforming algorithms, such as maximum ratio combining (MRC) or zero forcing beamforming (ZF).

[0189] Solve the constrained optimization problem:

[0190]

[0191] where and are the directions of the desired user and the interfering source, respectively.

[0192] 3. Feedback adjustment:

[0193] Evaluate the system performance. If necessary, return to the first step for iterative optimization.

[0194] Advantages and disadvantages of the alternative:

[0195] Advantages: The algorithm complexity of this scheme is low, it is easy to implement, and it is suitable for scenarios that require rapid implementation and deployment.

[0196] Disadvantages: Decomposing the joint optimization problem into two independent sub-problems may not achieve the global optimal solution.

[0197] Embodiment 6

[0198] This embodiment provides a polarization-beam optimization method based on coding iteration. This method uses the discrete coding iteration method, which is especially suitable for the case where the IRS units can only take a limited number of states.

[0199] The specific implementation is as follows:

[0200] 1. Discrete codebook design:

[0201] Design a codebook containing K possible configurations for each IRS unit, and each configuration corresponds to a specific polarization state and phase value.

[0202] The codebook design is based on electromagnetic field theory and the principle of uniform coverage.

[0203] 2. Greedy iterative search:

[0204] Initialize all IRS units to random configurations.

[0205] Try all possible configurations in the codebook for each unit in turn, and retain the configuration that can make the system 3. performance optimal.

[0206] Repeat the iteration until the performance converges or the maximum number of iterations is reached.

[0207] 3. Swarm intelligence optimization:

[0208] Particle swarm optimization (PSO) or genetic algorithm (GA) can be combined to improve the search efficiency.

[0209] Define appropriate population coding and fitness function.

[0210] Advantages and disadvantages of alternative solutions:

[0211] Advantages: This solution is suitable for IRS units with hardware constraints and has a low implementation complexity.

[0212] Disadvantages: The search space is large, and in a large-scale IRS system, the convergence speed may be slow, and the performance may be lower than that of the continuous optimization method.

[0213] The above shows and describes the basic principles, main features and advantages of the present invention. For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or basic features of the present invention.

[0214] In addition, it should be understood that although this specification is described according to embodiments, not every embodiment only contains an independent technical solution. This narrative way of the specification is only for clarity. Those skilled in the art should regard the specification as a whole, and the technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art.

Claims

1. A dynamic polarization-beam control anti-jamming system based on intelligent metasurfaces, characterized in that: The system includes a programmable intelligent metasurface array, a controller, a channel sensing module, a joint optimization module, and a communication interface. The programmable intelligent metasurface array consists of M×N independently controllable units, and each unit can simultaneously regulate the polarization state and reflection phase of electromagnetic waves. The controller is responsible for generating control signals according to the output results of the optimization algorithm to drive the intelligent metasurface units to change their electromagnetic characteristics. The channel sensing module includes a multi-polarization sensor array and a signal processing unit, which are used to obtain the channel state information (CSI) and interference characteristics in the wireless environment in real time. The joint optimization module: Based on a hybrid optimization framework of deep reinforcement learning and model-driven, it receives the environmental information provided by the channel sensing module and generates the optimal configuration strategy of the intelligent metasurface. The communication interface supports multiple standard communication protocols and is used to achieve seamless integration with existing wireless communication systems.

2. The dynamic polarization-beam control anti-jamming system based on intelligent metasurface according to claim 1, wherein: The independently controllable units use technologies such as liquid crystal, graphene, or varactor diodes to achieve dynamic regulation of polarization and phase. The controller is implemented by FPGA and supports high-speed parallel control. The channel state information includes multi-dimensional information such as signal strength, angle of arrival, and polarization state.

3. The dynamic polarization-beam control anti-jamming system based on intelligent metasurface according to claim 2, wherein: Each unit of the intelligent metasurface unit structure consists of a tunable dielectric layer, a polarization rotation layer, and a metal backplane. The tunable dielectric layer is used to control the reflection phase. The polarization rotation layer can change the polarization state of the incident electromagnetic wave. The metal backplane ensures high reflection efficiency. The size of the unit is λ / 4×λ / 4, where λ is the wavelength of the operating frequency.

4. The dynamic polarization-beam control anti-jamming system based on intelligent metasurface according to claim 2, characterized in that: The intelligent metasurface with an array arrangement structure adopts a planar rectangular array arrangement, including M×N units, and the adjacent unit spacing is λ / 2.

5. The dynamic polarization-beam control anti-jamming system based on intelligent metasurface according to claim 1, characterized in that: The control network structure adopts a hierarchical control architecture. The main controller communicates with multiple sub-controllers through a serial peripheral interface or an I2C interface. Each sub-controller is responsible for controlling a group of intelligent metasurface units. The algorithm processing unit uses a high-performance embedded processor and an AI acceleration chip, and is connected to the units and the controller through a high-speed data bus to ensure low-latency control.

6. The dynamic polarization-beam control anti-jamming system based on intelligent metasurface according to claim 2, wherein: It also includes a channel sensing structure. The channel sensing structure is an array composed of multiple orthogonal polarization antenna pairs, which can simultaneously obtain the intensity and phase information of horizontally polarized and vertically polarized signals. The signals are sent to the signal processing unit for analysis after passing through a low-noise amplifier and an analog-to-digital converter.

7. A dynamic polarization-beam control anti-jamming method based on intelligent metasurface, characterized in that, This method includes establishing a polarization-beam joint regulation mathematical model, and the steps are as follows: The system channel is expressed as: Among them, represents the direct channel from the base station to the user, including horizontal and vertical polarization components; represents the channel from the base station to the IRS; represents the channel from the IRS to the user; is the reflection coefficient matrix of the IRS, where is the total number of IRS units; The reflection coefficient matrix Φ is composed of the polarization regulation and phase regulation of each IRS unit, and is expressed as: Among them, respectively represent the co-polarization reflection coefficient, represents the cross-polarization reflection coefficient. For the (m,n)-th IRS unit, its reflection characteristics are represented by the following parameters: Among them, represents the reflection amplitude, represents the reflection phase, is the polarization reflection characteristic of each IRS unit.

8. The dynamic polarization-beam steering anti-jamming method based on intelligent metasurface according to claim 7, characterized in that, It includes establishing an interference source model: Considering the existence of J interference sources, the signal received by the user is expressed as: Among them, is the transmitted signal, is the interference signal transmitted by the j-th interference source, is the channel from the j-th interference source to the user, is the additive white Gaussian noise.

9. The dynamic polarization-beam control anti-jamming method based on intelligent metasurface according to claim 8, wherein Including the modeling of the joint optimization problem: By optimizing the reflection coefficient matrix of the IRS , to maximize the signal-to-interference-plus-noise ratio (SINR) of the user, which is formally expressed as: where is the Hermitian transpose of the total channel, is the Hermitian transpose of the interference channel, is the noise power; The optimization constraint conditions are as follows: 。 10. The dynamic polarization-beam control anti-jamming method based on intelligent metasurface according to claim 7, characterized in that: It also includes a hybrid optimization algorithm combining deep reinforcement learning and model-driven, and the working process is as follows: Environmental perception stage: Obtain the channel state information (CSI) and interference characteristics through channel detection, and establish a system model. Feature extraction stage: Use a deep neural network to extract key features from the CSI, including the direction of interference sources, polarization characteristics, etc. State space definition: Define the state space S, including channel state, interference information, and current system performance indicators. Action space definition: Define the action space $\mathcal{A}$, which includes the adjustment schemes for the polarization and phase of each unit of the IRS; Reward function design: The reward function $R$ is a weighted combination of the user's SINR gain and energy consumption: Policy network training: The policy network is trained using the Deep Deterministic Policy Gradient (DDPG) algorithm to generate IRS configuration policies; Model-driven optimization: Combine physical model constraints to adjust the output of the policy network to ensure energy conservation and physical realizability; Polarization-beam joint optimization: Based on the output of the policy network, optimize the polarization control matrix and the phase control matrix respectively, and then perform joint optimization; Fast adaptive update: For a dynamically changing environment, adopt an incremental learning method to quickly adjust the IRS configuration.

Images