System and method based on integration of wireless coverage enhancement and sensing communication

Abstract

The invention discloses a system based on integration of wireless coverage enhancement and sensing communication. The system comprises an environment sensing module which provides dynamic environment information of a target area; the edge computing node is used for carrying out data processing, model prediction and real-time optimization tasks; and model self-learning and optimization: predicting a future scene according to the environmental perception data and the channel state information. The invention discloses a wireless coverage enhancement and perception communication integration-based method. The method comprises the following steps of S1, data acquisition and processing; s2, environment perception and self-learning model training are carried out, and an environment dynamic weight formula is constructed; s3, RIS dynamic adaptive control is carried out; and S4, system feedback and adaptive optimization. According to the method, the reflection characteristics of the RIS can be adjusted in real time in a complex and fast-changing environment, the propagation effect and quality of wireless signals are remarkably improved, continuous optimization is carried out in actual operation of the system, and frequent manual intervention and adjustment are reduced.

Description

Technical Field

[0001] The present invention relates to the field of wireless communication technologies, and in particular to a system and method based on the integration of wireless coverage enhancement and perception communication. Background Art

[0002] With the rapid development of wireless communication technology, especially the continuous advancement of 5G and its evolution technology, traditional wireless networks are facing more and more challenges, especially in terms of wireless coverage and signal transmission performance. Modern communication networks have increasing demands for higher bandwidth, lower latency and wider coverage, which has led to traditional base station deployment and network optimization methods being unable to meet these demands. In order to solve this problem, in recent years, reflective intelligent surface (RIS, Reconfigurable Intelligent Surface) technology has gradually become a research hotspot in the field of wireless communications. RIS can improve signal propagation quality, network coverage and transmission efficiency by intelligently controlling the reflection, refraction and transmission characteristics of electromagnetic waves.

[0003] Existing wireless communication optimization methods mainly rely on preset static parameters and network configuration based on fixed rules. This method often cannot adapt to the complex and changing communication environment in a timely manner. Existing RIS control strategies mostly rely on single sensor data or static environmental information, lacking the ability to effectively predict future scene changes, resulting in a lack of flexibility and real-time performance in the optimization process. Therefore, how to combine environmental perception, dynamic data collection and self-learning models to achieve intelligent adjustment of RIS and optimize it based on real-time feedback has become a key technical difficulty in improving network performance, reducing operation and maintenance costs and enhancing user experience. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the problems existing in the above-mentioned existing system and method based on the integration of wireless coverage enhancement and perception communication, the present invention is proposed.

[0006] Therefore, the purpose of the present invention is to provide a system and method based on the integration of wireless coverage enhancement and perception communication, which is suitable for solving the problems that existing wireless communications cannot adapt to the complex and changeable communication environment in a timely manner and the optimization process lacks flexibility and real-time performance.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions: a system based on the integration of wireless coverage enhancement and perception communication, comprising:

[0008] Environmental perception module: provides dynamic environmental information of the target area and provides data support for subsequent prediction and optimization;

[0009] Edge computing nodes: undertake data processing, model prediction and real-time optimization tasks, and serve as the core computing platform for RIS dynamic control;

[0010] Self-learning and optimization model: predicts future scenarios based on environmental perception data and channel status information, and provides RIS configuration recommendations;

[0011] RIS dynamic control module: dynamically adjusts the reflection characteristics of RIS according to the optimization results provided by the self-learning model;

[0012] System feedback and monitoring module: Provides closed-loop feedback to ensure that the system is continuously optimized based on actual operating conditions.

[0013] A method based on the integration of wireless coverage enhancement and perception communication, the method is applicable to the above system, and the method comprises the following steps:

[0014] S1: Data acquisition and processing;

[0015] S2: Environmental perception and self-learning model training, building environmental dynamic weight formula;

[0016] S3: RIS dynamic adaptive control;

[0017] S4: System feedback and adaptive optimization.

[0018] As a preferred solution of the method based on wireless coverage enhancement and perception communication integration described in the present invention, wherein: in S2, the self-learning model is constructed by the following steps:

[0019] S21: Building an environmental perception and prediction model based on deep reinforcement learning,

[0020] S22: input real-time user distribution, obstacle dynamic changes and channel status information;

[0021] S23: Output the user location distribution prediction and channel change trend prediction in the future time period;

[0022] The environmental dynamic weight formula is as follows:

[0023]

[0024] Among them, Φ1(t) is the dynamic weight of the current environment, which indicates the degree of influence of the environment on future scenes. D(t) is the user distribution data, which comes from the environment perception module. H(t,f) is the channel state information, which comes from the feedback information of the user device. φ(t) is the time weight factor, which is used to control the influence of historical data on the current judgment. Ψ(H(t,f)) is the Gaussian modeling of channel disturbance, which captures the random changes in the dynamic environment.

[0025] As a preferred solution of the method based on wireless coverage enhancement and perception communication integration described in the present invention, the first threshold is set to Φ1 according to the output result of the environment dynamic weight formula. th ;

[0026] If Φ1(t)>Φ1 th , indicating that the environment changes dynamically and the system enters a high-frequency adaptive adjustment mode;

[0027] If Φ1(t)≤Φ1 th , indicating that the current environment is stable and the system adopts a low-frequency adjustment mode.

[0028] As a preferred solution of the method based on wireless coverage enhancement and perception communication integration described in the present invention, a communication loss optimization evaluation formula is constructed according to the output result of the environmental dynamic weight formula, and the communication loss optimization evaluation formula is as follows:

[0029]

[0030] Among them, Φ2(t) is the scenario weight after comprehensive evaluation, which measures the impact of the environment and channel status on the future RIS configuration. ζ(t,f) is the communication loss function, which captures the deviation between the target channel and the actual channel and comes from the system feedback and monitoring module. λ(f) is the frequency weight factor, which represents the nonlinear relationship between frequency and loss.

[0031] As a preferred solution of the method based on wireless coverage enhancement and perception communication integration described in the present invention, the second threshold Φ2 is set according to the output result of the communication loss optimization evaluation formula. th ;

[0032] If Φ2(t)>Φ2 th , indicating that the current environment and channel conditions are suitable for significantly adjusting the reflection characteristics of RIS;

[0033] If Φ2(t)≤Φ2 th , indicating that the current conditions change little and the system maintains the existing configuration.

[0034] As a preferred solution of the method based on wireless coverage enhancement and perception communication integration described in the present invention, the RIS dynamic adaptive control algorithm formula is constructed according to the output result of the communication loss optimization evaluation formula, as follows:

[0035]

[0036] Among them, θ(t,n) is the current reflection phase matrix of the RIS unit, which is the optimization target of the final dynamic control, and ω(n) is the unit priority weight, which determines the influence of each unit in the adjustment process. It is an energy conservation constraint to ensure that the adjustment of RIS does not affect the communication quality. γ is an adjustment factor used to smooth the adjustment process of RIS and avoid large jumps.

[0037] As a preferred solution of the method based on wireless coverage enhancement and perception communication integration described in the present invention, the third threshold value θ is set according to the output result of the RIS dynamic adaptive control algorithm formula. low and the fourth threshold θ high ;

[0038] If θ(t,n)≤θ low , indicating that the current channel status is stable, the dynamic adjustment demand of RIS is low, and the system enters the low-frequency adjustment mode to reduce computing resource consumption;

[0039] If θ low <θ(t,n)<θ high , indicating that the current channel status fluctuates, RIS needs to be dynamically adjusted to optimize the reflection performance, and the system enters the normal adjustment mode;

[0040] If θ(t,n)>θ high , indicating that the channel state changes dramatically, RIS must quickly adjust the reflection characteristics to ensure communication quality, the system enters high-frequency adjustment mode, and responds to high-priority units ω(n) first.

[0041] As a preferred solution of the method based on the integration of wireless coverage enhancement and perception communication described in the present invention, the data acquisition and processing include multi-source data fusion and channel status information acquisition, and the CSI data reported by the user terminal is combined with multi-source environmental information to form a real-time status map of the user channel.

[0042] As a preferred solution of the method based on wireless coverage enhancement and perception communication integration described in the present invention, the RIS dynamic adaptive control is implemented by the following steps:

[0043] S31: Optimization target definition;

[0044] S32: dynamic reflection parameter calculation;

[0045] S33: The edge computing node sends the optimization results to each RIS device, dynamically adjusts the reflection parameters, and realizes real-time optimization.

[0046] Beneficial effects of the present invention: The RIS dynamic control module of the present invention can adjust the reflection characteristics of RIS in real time according to the optimization suggestions of the self-learning model, significantly improving the propagation effect and quality of wireless signals. Especially in complex and rapidly changing environments, the self-learning and optimization model dynamically adjusts network parameters based on the prediction of future scenarios, so that the network can respond in real time in different environments;

[0047] The present invention combines environmental perception with self-learning models, and can perform continuous optimization during the actual operation of the system, reduce frequent manual intervention and adjustment, and reduce network maintenance costs. Through accurate real-time data analysis and prediction, the system can respond to potential problems in advance and can be dynamically adjusted according to environmental changes and fluctuations in user needs, making the network more flexible and scalable, and can be widely used in the construction and optimization of wireless communication networks in urban, industrial, indoor and high-density user environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0049] Figure 1 This is a schematic diagram of the overall framework of a system based on the integration of wireless coverage enhancement and perception communication proposed by the present invention;

[0050] Figure 2 A schematic diagram of the steps of a method based on the integration of wireless coverage enhancement and perception communication proposed by the present invention. DETAILED DESCRIPTION

[0051] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0052] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0053] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0054] Secondly, the present invention is described in detail with reference to the schematic diagram. When describing the embodiments of the present invention in detail, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0055] Embodiment 1

[0056] Reference Figure 1-Figure 2 , which is an embodiment of the present invention, provides a system based on the integration of wireless coverage enhancement and perception communication, including:

[0057] Environmental perception module: It generally includes radar (for collecting obstacle distance and motion information), camera (for collecting scene images and user distribution characteristics) and auxiliary sensors (infrared sensors, ultrasonic sensors, etc.: to further enhance environmental perception capabilities), providing dynamic environmental information of the target area and providing data support for subsequent prediction and optimization;

[0058] Edge computing nodes: undertake data processing, model prediction and real-time optimization tasks, and serve as the core computing platform for RIS dynamic control;

[0059] It includes a channel state information processing module: obtaining the channel state information reported by the user terminal and combining it with the environmental sensor data to generate a channel state map;

[0060] Real-time data processing unit: responsible for data preprocessing and feature extraction, optimizing the transmission and computing efficiency of multi-source data;

[0061] Machine learning model operating environment: provides computing resources for deep reinforcement learning, self-learning models, and optimization algorithms;

[0062] Self-learning and optimization model: predicts future scenarios based on environmental perception data and channel status information, and provides RIS configuration recommendations;

[0063] It includes deep learning models: predicting user distribution and channel change trends based on time series prediction models;

[0064] Model update module: using real-time feedback to improve the adaptability of the model;

[0065] RIS dynamic control module: dynamically adjusts the reflection characteristics of RIS according to the optimization results provided by the self-learning model;

[0066] It includes a reflection unit array: equipped with a phased array or adjustable reflection unit for dynamically adjusting reflection parameters (such as phase and direction);

[0067] Communication module: receives optimization instructions from edge computing nodes and updates reflection parameter configuration in real time;

[0068] Power consumption management module: optimizes the energy efficiency of RIS and ensures the stability of system operation;

[0069] System feedback and monitoring module: provides closed-loop feedback to ensure that the system is continuously optimized according to actual operating conditions;

[0070] It includes a performance monitoring unit: real-time monitoring of communication performance (such as signal-to-noise ratio, coverage) and perception performance (such as target recognition rate);

[0071] Feedback loop: transmits monitoring data to edge computing nodes for model training and optimization strategy adjustment;

[0072] Alarm and fault tolerance mechanism: If the system performance is below the threshold, an alarm is triggered and the fault tolerance adjustment mechanism is started.

[0073] A method based on the integration of wireless coverage enhancement and perception communication, the method is applicable to the above system, and the method comprises the following steps:

[0074] S1: Data acquisition and processing;

[0075] Data collection and processing include multi-source data fusion and channel status information acquisition. The data collected by environmental sensors in real time are transmitted to the edge computing node. The spatial target information of the radar and the image data of the camera are integrated to generate a unified environmental feature description. The CSI data reported by the user terminal is combined with multi-source environmental information to form a real-time status map of the user channel.

[0076] S2: Environmental perception and self-learning model training, building environmental dynamic weight formula;

[0077] In S2, the self-learning model is constructed through the following steps:

[0078] S21: Building an environmental perception and prediction model based on deep reinforcement learning,

[0079] S22: input real-time user distribution, obstacle dynamic changes and channel status information;

[0080] S23: Output the user location distribution prediction and channel change trend prediction in the future time period;

[0081] Initial training is completed using offline simulated data to ensure basic accuracy;

[0082] In the online stage, real-time data is used for incremental updates to improve the model's adaptability to dynamic environments.

[0083] The formula for environmental dynamic weight is as follows:

[0084]

[0085] Among them, Φ1(t) is the dynamic weight of the current environment, which indicates the degree of influence of the environment on future scenes. D(t) is the user distribution data, which comes from the environment perception module. H(t,f) is the channel state information, which comes from the feedback information of the user device. φ(t) is the time weight factor, which is used to control the influence of historical data on the current judgment. Ψ(H(t,f)) is the Gaussian modeling of channel disturbance, which captures the random changes in the dynamic environment.

[0086] According to the output result of the environment dynamic weight formula, the first threshold is set to Φ1 th ;

[0087] Φ1(t)>Φ1, indicating that the environment changes dramatically and the system enters a high-frequency adaptive adjustment mode;

[0088] If Φ1(t)≤Φ1 th , indicating that the current environment is stable and the system adopts a low-frequency adjustment mode.

[0089] The communication loss optimization evaluation formula is constructed according to the output result of the environmental dynamic weight formula, and the communication loss optimization evaluation formula is as follows:

[0090]

[0091] Among them, Φ2(t) is the scenario weight after comprehensive evaluation, which measures the impact of the environment and channel status on the future RIS configuration. ζ(t,f) is the communication loss function, which captures the deviation between the target channel and the actual channel and comes from the system feedback and monitoring module. λ(f) is the frequency weight factor, which represents the nonlinear relationship between frequency and loss.

[0092] The second threshold Φ2 is set according to the output result of the communication loss optimization evaluation formula th ;

[0093] If Φ2(t)>Φ2 th , indicating that the current environment and channel conditions are suitable for significantly adjusting the reflection characteristics of RIS;

[0094] If Φ2(t)≤Φ2 th , indicating that the current conditions change little and the system maintains the existing configuration.

[0095] S3: RIS dynamic adaptive control;

[0096] RIS dynamic adaptive control is achieved through the following steps:

[0097] S31: Optimization target definition;

[0098] The optimization objectives include improving communication channel gain, reducing channel interference, enhancing perception accuracy, etc. The priorities are determined based on the multi-objective weight allocation strategy, and the optimization objectives are adjusted dynamically.

[0099] S32: dynamic reflection parameter calculation;

[0100] Using the environmental prediction results provided by the self-learning model and combining them with the optimization objectives, the optimal reflection parameter configuration of RIS, including phase and direction, is calculated through a reinforcement learning algorithm.

[0101] According to the output results of the communication loss optimization evaluation formula, the RIS dynamic adaptive control algorithm formula is constructed as follows:

[0102]

[0103] Among them, θ(t,n) is the current reflection phase matrix of the RIS unit, which is the optimization target of the final dynamic control, and ω(n) is the unit priority weight, which determines the influence of each unit in the adjustment process. It is an energy conservation constraint to ensure that the adjustment of RIS does not affect the communication quality. γ is an adjustment factor used to smooth the adjustment process of RIS and avoid large jumps.

[0104] The third threshold θ is set according to the output result of the RIS dynamic adaptive control algorithm formula low and the fourth threshold θ high ;

[0105] If θ(t,n)≤θ low , indicating that the current channel status is stable, the dynamic adjustment demand of RIS is low, and the system enters the low-frequency adjustment mode to reduce computing resource consumption;

[0106] If θ low <θ(t,n)<θ high , indicating that the current channel status fluctuates, RIS needs to be dynamically adjusted to optimize the reflection performance, and the system enters the normal adjustment mode;

[0107] If θ(t,n)>θ high , indicating that the channel state changes dramatically, RIS must quickly adjust the reflection characteristics to ensure communication quality, the system enters high-frequency adjustment mode, and responds to high-priority units ω(n) first.

[0108] S33: The edge computing node sends the optimization results to each RIS device, dynamically adjusts the reflection parameters, and realizes real-time optimization.

[0109] S4: System feedback and adaptive optimization;

[0110] Communication performance and perception accuracy are monitored through sensors and user terminals, and the monitoring data is fed back to the model for adjusting the optimization strategy; based on the feedback data, the self-learning model and optimization algorithm are updated in real time.

[0111] The RIS dynamic control module of the present invention can adjust the reflection characteristics of RIS in real time according to the optimization suggestions of the self-learning model, significantly improving the propagation effect and quality of wireless signals. Especially in complex and rapidly changing environments, the self-learning and optimization model dynamically adjusts network parameters based on the prediction of future scenarios, so that the network can respond in real time in different environments;

[0112] The present invention combines environmental perception with self-learning models, and can continuously optimize the actual operation of the system, reduce frequent manual intervention and adjustment, and reduce network maintenance costs. Through accurate real-time data analysis and prediction, the system can respond to potential problems in advance, and can dynamically adjust according to environmental changes and fluctuations in user needs, making the network more flexible and scalable, and can be widely used in the construction and optimization of wireless communication networks in urban, industrial, indoor and high-density user environments.

[0113] Embodiment 2

[0114] Referring to Tables 1 to 3, which are the second embodiment of the present invention, this embodiment is different from the first embodiment in that, in order to verify its beneficial effects, experimental comparison data between the present invention and the prior art are provided.

[0115] In order to verify the innovation and advantages of the present invention, this embodiment designs an experiment to compare the performance differences between the system of the present invention and the existing wireless communication technology in terms of signal coverage, network throughput, delay and optimization accuracy. During the experiment, a number of experiments were carried out based on the wireless coverage enhancement and perception communication integrated system of the present invention, focusing on verifying the actual effects of dynamic environmental perception, RIS dynamic control and self-learning optimization model.

[0116] A typical urban environment (with an area of ​​2 square kilometers) was selected, which includes multiple complex environments such as commercial areas, residential areas, and public transportation networks to ensure wide wireless signal coverage, many obstacles, and frequent channel changes; 10 RIS devices were deployed, distributed in key locations in the experimental area (such as commercial areas, office buildings, etc.), and equipped with an environmental perception module, edge computing node, and RIS dynamic control module on each RIS device. Each device is also equipped with a self-learning and optimization model that can adjust the reflection parameters in real time according to the channel status information; 15 mobile terminals were used, each of which can report real-time channel status information (CSI) and record the terminal's location and environmental change data.

[0117] Implementation steps:

[0118] Before starting data collection, we first conduct a benchmark test on the base station signal quality in the experimental area and collect the quality indicators of the communication signals. These benchmark data provide a comparative basis for the evaluation of subsequent optimization effects.

[0119] Implement the environment perception module, collect data from multiple sensors (including obstacles, weather conditions, user distribution, mobile obstacles, etc.), and use edge computing nodes to fuse and process the data. The data collection content includes: real-time changes in the environment of each RIS node, user distribution, CSI data reported by the terminal, etc.;

[0120] Based on the data provided by the environmental perception module, the edge computing node begins to calculate the dynamic reflection parameters, and the system adaptively optimizes the environmental model and RIS reflection characteristics based on real-time feedback.

[0121] Table 1: Comparison of data collection and processing effects

[0122]

[0123]

[0124] Table 2: RIS dynamic control and reflection characteristics optimization effect table

[0125] parameter Prior art The present invention Improvement Optimal reflection characteristic calculation time 200ms 50ms -75％ Network throughput 150Mbps 210Mbps +40％ Signal coverage 85％ 98％ +15％ Spectrum Utilization 60％ 85％ +42％

[0126] Table 3: Comparison of system feedback and adaptive optimization results

[0127] parameter Prior art The present invention Improvement System stability medium high high Network capacity 500Gbps 650Gbps +30％ Optimizing response time 500ms 100ms -80％ Dynamic adjustment times 3 10 +233％

[0128] By comparing the experimental data, it can be clearly seen that the present invention has obvious advantages over the prior art in multiple key performance indicators, which can be analyzed specifically from the following three aspects:

[0129] In terms of data collection and processing: the present invention performs well in the prediction accuracy of user location distribution and channel state change, which are improved by 17% and 15% respectively. This shows that the fusion solution based on environmental perception and self-learning optimization model can significantly improve the prediction accuracy, thereby reducing coverage blind spots (reduced by 75%) and improving the response speed of the system (delay reduced by 50%).

[0130] RIS dynamic control and reflection characteristic optimization: In terms of RIS dynamic control, the present invention calculates reflection characteristics through a self-learning model and can adjust reflection characteristics within 50ms, which reduces the calculation time by 75% compared with the existing technology. The optimized network throughput is increased by 40% and the signal coverage is increased by 15%. This significant improvement is due to the fact that the present invention can accurately adjust reflection parameters according to real-time data, thereby improving spectrum utilization and signal quality.

[0131] System feedback and adaptive optimization: Under the guidance of the feedback mechanism, the system of the present invention can respond quickly and optimize in a dynamic environment. The optimization response time is shortened by 80%, and the number of dynamic adjustments is increased by 233%. This means that the present invention can respond quickly to environmental changes efficiently through a real-time feedback mechanism, ensuring that the system is always in an optimized state in a complex and dynamic environment.

[0132] In summary: by combining the environmental perception module, edge computing nodes and self-learning optimization model, the present invention can realize efficient RIS dynamic adaptive control and optimize the performance of the wireless communication network, including improving signal coverage, enhancing network throughput, reducing latency and improving system stability and reliability.

[0133] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A system based on the integration of wireless coverage enhancement and perception communication, characterized in that: include: Environmental perception module: provides dynamic environmental information of the target area and provides data support for subsequent prediction and optimization; Edge computing nodes: undertake data processing, model prediction and real-time optimization tasks, and serve as the core computing platform for RIS dynamic control; Self-learning and optimization model: predicts future scenarios based on environmental perception data and channel status information, and provides RIS configuration recommendations; RIS dynamic control module: dynamically adjusts the reflection characteristics of RIS according to the optimization results provided by the self-learning model; System feedback and monitoring module: Provides closed-loop feedback to ensure that the system is continuously optimized based on actual operating conditions.

2. A method based on the integration of wireless coverage enhancement and perception communication, the method is applicable to the above system, characterized in that: And the method comprises the following steps: S1: Data acquisition and processing; S2: Environmental perception and self-learning model training, building environmental dynamic weight formula; S3: RIS dynamic adaptive control; S4: System feedback and adaptive optimization.

3. The method based on wireless coverage enhancement and perception communication integration according to claim 2, characterized in that: In S2, the self-learning model is constructed by the following steps: S21: Building an environmental perception and prediction model based on deep reinforcement learning, S22: input real-time user distribution, obstacle dynamic changes and channel status information; S23: Output the user location distribution prediction and channel change trend prediction in the future time period; The environmental dynamic weight formula is as follows: Among them, Φ1(t) is the dynamic weight of the current environment, which indicates the degree of influence of the environment on future scenes. D(t) is the user distribution data, which comes from the environment perception module. H(t,f) is the channel state information, which comes from the feedback information of the user device. φ(t) is the time weight factor, which is used to control the influence of historical data on the current judgment. Ψ(H(t,f)) is the Gaussian modeling of channel disturbance, which captures the random changes in the dynamic environment.

4. The method based on wireless coverage enhancement and perception communication integration according to claim 3 is characterized in that: According to the output result of the environment dynamic weight formula, the first threshold is set to Φ1 th ; If Φ1(t)>Φ1 th , indicating that the environment changes dynamically and the system enters a high-frequency adaptive adjustment mode; If Φ1(t)≤Φ1 th , indicating that the current environment is stable and the system adopts a low-frequency adjustment mode.

5. The method based on wireless coverage enhancement and perception communication integration according to claim 3 is characterized in that: The communication loss optimization evaluation formula is constructed according to the output result of the environmental dynamic weight formula, and the communication loss optimization evaluation formula is as follows: Among them, Φ2(t) is the scenario weight after comprehensive evaluation, which measures the impact of the environment and channel status on the future RIS configuration. ζ(t,f) is the communication loss function, which captures the deviation between the target channel and the actual channel and comes from the system feedback and monitoring module. λ(f) is the frequency weight factor, which represents the nonlinear relationship between frequency and loss.

6. The method based on wireless coverage enhancement and perception communication integration according to claim 5, characterized in that: The second threshold Φ2 is set according to the output result of the communication loss optimization evaluation formula th ; If Φ2(t)>Φ2 th , indicating that the current environment and channel conditions are suitable for significantly adjusting the reflection characteristics of RIS; If Φ2(t)≤Φ2 th , indicating that the current conditions change little and the system maintains the existing configuration.

7. The method based on wireless coverage enhancement and perception communication integration according to claim 5, characterized in that: According to the output results of the communication loss optimization evaluation formula, the RIS dynamic adaptive control algorithm formula is constructed as follows: θ(t,n)=θ(t-1,n)+γ·Φ2(t)·ω(n)·g(θ(t-1,n)) Among them, θ(t,n) is the current reflection phase matrix of the RIS unit, which is the optimization target of the final dynamic control. ω(n) is the unit priority weight, which determines the influence of each unit in the adjustment process. g(θ) is the energy conservation constraint, which ensures that the adjustment of RIS does not affect the communication quality. γ is the adjustment factor, which is used to smooth the adjustment process of RIS and avoid large jumps.

8. The method based on wireless coverage enhancement and perception communication integration according to claim 7, characterized in that: The third threshold θ is set according to the output result of the RIS dynamic adaptive control algorithm formula low and the fourth threshold θ high ; If θ(t,n)≤θ low , indicating that the current channel status is stable, the dynamic adjustment demand of RIS is low, and the system enters the low-frequency adjustment mode to reduce computing resource consumption; If θ low <θ(t,n)<θ high , indicating that the current channel status fluctuates, RIS needs to be dynamically adjusted to optimize the reflection performance, and the system enters the normal adjustment mode; If θ(t,n)>θ high , indicating that the channel state changes dramatically, RIS must quickly adjust the reflection characteristics to ensure communication quality, the system enters high-frequency adjustment mode, and responds to high-priority units ω(n) first.

9. The method based on wireless coverage enhancement and perception communication integration according to claim 2, characterized in that: The data collection and processing includes multi-source data fusion and channel status information acquisition, using the CSI data reported by the user terminal and combining multi-source environmental information to form a real-time status map of the user channel.

10. The method based on wireless coverage enhancement and perception communication integration according to claim 2, characterized in that: The RIS dynamic adaptive control is achieved by the following steps: S31: Optimization target definition; S32: dynamic reflection parameter calculation; S33: The edge computing node sends the optimization results to each RIS device, dynamically adjusts the reflection parameters, and realizes real-time optimization.

Images