Internet of Things-based intelligent control method and system for communication antennas

Abstract

This invention provides an intelligent control method and system for communication antennas based on the Internet of Things (IoT), relating to the field of communication antenna technology. The method includes collecting various types of data. User preference data is obtained by analyzing parameter data, and antenna control targets are determined by combining this with environmental characteristic data. An antenna control strategy is then formulated based on these targets. A reinforced neural Turing machine model is established, and balanced control parameters are obtained by analyzing parameter data and electromagnetic characteristic data. The antenna control strategy is adjusted using the balanced control parameters according to the control target decision method to obtain the antenna control decision. This invention utilizes social network analysis to analyze parameter data to obtain user preference data and combines it with environmental characteristic data to formulate antenna control strategies. This allows for precise determination of antenna control targets and strategies based on users' personalized needs and environmental factors, improving the adaptability of communication antennas to different user groups and environments, and enhancing communication quality.

Description

Technical Field

[0001] This invention relates to the field of communication antenna technology, and in particular to a method and system for intelligent control of communication antennas based on the Internet of Things. Background Technology

[0002] In today's era of rapid development of the Internet of Things (IoT), intelligent adjustment of communication antennas is crucial for ensuring efficient and stable communication. However, existing communication antenna adjustment strategies have many problems and are unable to meet increasingly complex communication needs.

[0003] On the one hand, with the increasing diversification of user behavior and the continuous increase in environmental interference, adjustment strategies are struggling to cope with the coupled effects of complex user behavior and environmental interference. Traditional antenna control methods are often based on fixed rules or simple models. These methods may perform well in a single, stable environment, but in practical applications, user mobility, changes in usage habits, and the presence of various electromagnetic interference sources in the surrounding environment cause user behavior and environmental interference to intertwine, forming complex coupling effects. Existing adjustment strategies cannot accurately capture this coupling relationship, resulting in poor antenna control performance and degraded communication quality, such as frequent occurrences of problems like unstable signal strength and reduced data transmission rates.

[0004] On the other hand, traditional models suffer from a significant drawback in terms of slow convergence speed when processing antenna control data. In the Internet of Things (IoT) environment, numerous sensors and devices generate massive amounts of data in real time. Traditional models require a considerable amount of time to converge to or near the optimal solution when analyzing and processing this data. This results in untimely updates to antenna control strategies, hindering their ability to quickly adapt to changes in the environment and user needs. For example, when strong electromagnetic interference suddenly occurs in the environment, traditional models may require a long time to adjust antenna parameters to ensure communication quality, during which time communication may be severely affected.

[0005] To address the shortcomings of the existing technology, this technical solution proposes an intelligent control method for communication antennas based on the Internet of Things. Summary of the Invention

[0006] This invention provides a method and system for intelligent control of communication antennas based on the Internet of Things, which solves the shortcomings of existing adjustment strategies in dealing with the coupled effects of complex user behavior and environmental interference, and the slow convergence speed of traditional models.

[0007] On one hand, the present invention provides a method for intelligent control of communication antennas based on the Internet of Things, comprising:

[0008] Collect parameter data from IoT devices and electromagnetic characteristic data from communication antennas, and collect environmental characteristic data within the target area at preset time intervals.

[0009] User preference data is obtained by analyzing parameter data using social network analysis methods. Antenna control targets are determined based on user preference data and environmental characteristic data. Antenna control strategies are then formulated based on antenna control targets.

[0010] A neural Turing machine model was established, and the sand cat swarm optimization algorithm was used to optimize the neural Turing machine model to obtain a reinforced neural Turing machine model. Based on the reinforced neural Turing machine model, the parameter data and electromagnetic property data were analyzed to obtain the balance control parameters.

[0011] Antenna control decisions are obtained by adjusting the antenna control strategy using balanced control parameters based on the control target decision method.

[0012] According to the IoT-based intelligent control method for communication antennas provided by the present invention, the steps for analyzing and obtaining user preference data include:

[0013] The device parameter set is obtained by integrating and normalizing various parameter data from multiple IoT devices.

[0014] Each IoT device in the device parameter set is treated as a device node, and the corresponding user using the IoT device is treated as a user node. The connection length is determined based on the relationship between IoT devices and between IoT devices and their corresponding users.

[0015] The degree, betweenness, proximity centrality, and clustering coefficient of each device node and each user node are calculated to determine network metrics, and key nodes are selected from them based on preset values.

[0016] User preference data is obtained by analyzing key nodes such as preferred device type, usage time pattern, and device interaction preference.

[0017] According to the IoT-based intelligent control method for communication antennas provided by the present invention, the step of determining the antenna control target includes:

[0018] Users are divided into different user groups based on their personalized needs, and corresponding needs are summarized for each user group.

[0019] Based on the analysis of environmental characteristic data, the influence of different climatic conditions on the performance of communication antennas is obtained as climatic influence, and the influence of different building materials on signal propagation is obtained as building influence.

[0020] For different user groups, ridge regression analysis is used to correlate climate impacts with building impacts to obtain multiple influencing factors. From these, the factors that have the greatest impact on demand under the current environment are identified as key influencing factors.

[0021] Antenna control objectives for each user group are determined based on different key influencing factors.

[0022] According to the IoT-based intelligent control method for communication antennas provided by the present invention, the steps for obtaining key influencing factors include:

[0023] Climate impacts and building impacts are standardized and used as independent variables. A matrix is ​​formed by combining various climate and building factors, and demand is used as the dependent variable.

[0024] By introducing regularization parameters, we construct the objective function for ridge regression.

[0025] Initialize the regression coefficients, and take the partial derivative of the objective function with respect to each regression coefficient to obtain the gradient vector.

[0026] The objective function is updated based on the gradient vector until the preset number of iterations is reached to obtain the coefficient values.

[0027] The independent variables are sorted according to the absolute value of their coefficients, and the independent variable with the largest absolute value is selected as the key influencing factor.

[0028] According to the IoT-based intelligent control method for communication antennas provided by the present invention, the steps for formulating an antenna control strategy include:

[0029] Multiple candidate control strategies are specified based on the antenna control objectives and the adjustable parameters of the communication antenna.

[0030] Based on the antenna control objective, evaluation indicators for candidate control strategies are determined. Multiple candidate control strategies are evaluated based on the evaluation indicators to obtain corresponding simulation scores, and the strategy with the highest score is selected as the antenna control strategy.

[0031] According to the IoT-based intelligent control method for communication antennas provided by the present invention, the steps for optimizing and obtaining the enhanced neural Turing machine model include:

[0032] Initialize the population size of the sand cat group, where each sand cat represents a set of parameters of the neural Turing machine model.

[0033] The parameters corresponding to each sand cat are applied to the neural Turing machine model, and the negative of the mean squared error loss is used as the fitness function.

[0034] Each sand cat will move randomly from its current position according to a preset probability to obtain a new position.

[0035] The fitness value of each new location is calculated based on the fitness function, and the one with the highest fitness value is selected as the global optimal sand cat.

[0036] Each sand cat moves to the globally optimal sand cat and updates its position.

[0037] Calculate the fitness value of the latest position of each sand cat, and select the one with the highest fitness value as the optimization parameter. Use the optimization parameter to construct a neural Turing machine model to obtain a reinforced neural Turing machine model.

[0038] According to the IoT-based intelligent control method for communication antennas provided by the present invention, the steps for analyzing and obtaining the balance control parameters include:

[0039] The parameter data and electromagnetic property data are integrated, and outliers and errors are removed to obtain a fused dataset.

[0040] The fused dataset is encoded and input into the reinforced neural Turing machine model according to the input requirements to generate control signals.

[0041] The system performs read and write operations based on control signals, outputs decision results, and adjusts the communication antenna according to the decision results to obtain balanced control parameters.

[0042] According to the IoT-based intelligent control method for communication antennas provided by the present invention, the steps for obtaining antenna control decisions include:

[0043] The impact of balanced control parameters on communication antenna performance and preset system objectives is analyzed, and the objectives and performance indicators of the currently used antenna control strategy are evaluated to obtain the evaluation results.

[0044] Based on the evaluation results, analyze the gap between the current antenna control strategy and the preset system objectives, and set adjustment targets.

[0045] Based on the adjustment target, a balance control adjustment strategy is formulated, multiple adjustment schemes are generated, and the scheme with the closest performance is selected as the antenna control decision based on the performance indicators.

[0046] According to the IoT-based intelligent control method for communication antennas provided by the present invention, the step of setting the adjustment target includes:

[0047] The data obtained from the evaluation of the current antenna control strategy's objectives and performance indicators are summarized to obtain the overall performance data. This data is then compared with the preset system objectives one by one. The difference between the actual value and the target value of each indicator is calculated and summarized to obtain the gap.

[0048] Based on the magnitude of the difference and its impact on performance, key gaps are selected from the gaps. Based on the key gaps, and considering the feasibility of the target while maintaining consistency with the preset system target, the adjustment target is obtained.

[0049] On the other hand, the present invention also provides an intelligent control system for communication antennas based on the Internet of Things, comprising:

[0050] The characteristic data acquisition module is used to collect parameter data of IoT devices and electromagnetic characteristic data of communication antennas, and to collect environmental characteristic data of the target area at preset time intervals.

[0051] The target strategy formulation module is used to analyze parameter data using social network analysis methods to obtain user preference data, determine antenna control targets based on user preference data and combined with environmental characteristic data, and formulate antenna control strategies based on antenna control targets.

[0052] The Sand Cat Optimization Modeling Module is used to establish a neural Turing machine model and optimize the neural Turing machine model using the Sand Cat swarm optimization algorithm to obtain a reinforced neural Turing machine model. Based on the reinforced neural Turing machine model, the parameter data and electromagnetic property data are analyzed to obtain the balance control parameters.

[0053] The parameter strategy adjustment module is used to adjust the antenna control strategy according to the balance control parameters to obtain the antenna control decision.

[0054] The present invention provides an intelligent control method and system for communication antennas based on the Internet of Things. By using social network analysis to analyze parameter data to obtain user preference data, and combining it with environmental characteristic data to determine antenna control targets, antenna control strategies are formulated accordingly. This allows for precise determination of antenna control targets and strategies based on users' personalized needs and environmental factors, thereby improving the adaptability of communication antennas to different user groups and environments, optimizing user experience, and enhancing communication quality.

[0055] This invention provides an intelligent control method and system for communication antennas based on the Internet of Things (IoT). By establishing a neural Turing machine model and optimizing it using the sand cat swarm optimization algorithm to obtain a reinforced neural Turing machine model, the system analyzes parameter data and electromagnetic characteristic data using this model to obtain balance control parameters. The sand cat swarm optimization algorithm has strong global search capabilities and fast convergence speed. Optimizing the neural Turing machine model using this algorithm yields better model parameters, enabling the reinforced neural Turing machine model to analyze data more accurately and obtain more reasonable balance control parameters, providing a more scientific basis for antenna control. Furthermore, the antenna control strategy is adjusted based on the balance control parameters to obtain antenna control decisions, realizing dynamic adjustment of the antenna control strategy. This allows the antenna control decisions to be continuously optimized and improved according to actual conditions, enhancing the performance and stability of the communication antenna and better meeting the system's preset goals and user needs. Attached Figure Description

[0056] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0057] Figure 1 This is one of the flowcharts illustrating the intelligent control method for communication antennas based on the Internet of Things provided in this embodiment of the invention;

[0058] Figure 2 This is the second flowchart illustrating the intelligent control method for communication antennas based on the Internet of Things provided in this embodiment of the invention.

[0059] Figure 3 This is a schematic diagram of the structure of an intelligent control system for communication antennas based on the Internet of Things provided in an embodiment of the present invention. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0061] The following is combined with Figures 1-3 This invention describes an intelligent control method and system for communication antennas based on the Internet of Things.

[0062] like Figure 1 and Figure 2 As shown, the IoT-based intelligent control method and system for communication antennas provided in this embodiment of the invention can be executed by an IoT-based intelligent control method for communication antennas, including:

[0063] Collect parameter data from IoT devices and electromagnetic characteristic data from communication antennas, and collect environmental characteristic data within the target area at preset time intervals.

[0064] Parameter data for IoT devices can include device type (e.g., temperature sensors, smart home appliances), device operating status (running, sleeping, faulty, etc.), operating frequency band, transmission power, data transmission rate, signal strength, etc. Environmental characteristic data can include terrain, landforms, building and climate condition data. Electromagnetic characteristic data can include impedance, radiation pattern, polarization, etc. For high-density deployment scenarios, distributed edge computing nodes are used to preprocess parameter data locally, filtering redundant data and compressing transmission bandwidth. A dynamic sampling mechanism is introduced to automatically adjust the sampling frequency based on device activity (e.g., active devices sample every 5 seconds, sleeping devices every 30 minutes).

[0065] User preference data is obtained by analyzing parameter data using social network analysis methods. Antenna control targets are determined based on user preference data and environmental characteristic data. Antenna control strategies are then formulated based on antenna control targets.

[0066] The steps involved in analyzing user preference data include:

[0067] The process involves integrating and normalizing various parameter data from multiple IoT devices to obtain a device parameter set. During integration, parameter data from different sources and formats needs to be cleaned and preprocessed to remove noise and invalid data, ensuring accuracy and consistency. Normalization enables parameter data of different magnitudes and ranges to be compared and analyzed on the same scale, improving the effectiveness of data analysis. For example, data transmission rate and signal strength may have significantly different numerical ranges and magnitudes; normalization transforms them into comparable values.

[0068] Each IoT device in the device parameter set is treated as a device node, and the corresponding user using the IoT device is treated as a user node. The connection length is determined based on the relationship between IoT devices and between IoT devices and their corresponding users.

[0069] Different device nodes are distinguished by a unique identifier (such as a device ID), and user nodes are distinguished by account and device binding information.

[0070] Device-device relationship: When there is data interaction (such as data transmission) between two devices, an edge is established between the corresponding nodes. The weight of the edge can be determined based on factors such as the frequency of interaction and the amount of data.

[0071] User-Device Relationship: When a user uses a device, an edge is established between the user node and the device node. The weight of the edge can be determined based on the usage duration and frequency.

[0072] Network metrics are determined by calculating the degree, betweenness number, proximity centrality, and clustering coefficient of each device node and user node, and key nodes are selected based on preset values. Degree reflects the number of connections a node has in the network; betweenness number reflects the importance of a node in information transmission; proximity centrality measures the average distance from a node to other nodes; and the clustering coefficient indicates the closeness between a node's neighbors. Through comprehensive analysis of these metrics, key nodes with significant influence throughout the network can be accurately identified. For example, a high degree for a device node indicates frequent data interaction with other devices, suggesting it may be a core device in the entire IoT system; a high betweenness number for a user node indicates that the user plays a crucial bridging role in information transmission. In-depth analysis of key nodes, considering their preferred device types, usage patterns, and device interaction preferences, can uncover users' potential needs and behavioral patterns when using IoT devices, thus obtaining accurate user preference data.

[0073] User preference data is obtained by analyzing key nodes such as preferred device type, usage time pattern, and device interaction preference.

[0074] The steps to determine the antenna control target include:

[0075] Users are divided into different user groups based on their personalized needs, and corresponding needs are summarized for each user group.

[0076] Personalized needs can include users' device usage habits (such as usage frequency, duration, and device type preference), communication needs (such as data transmission rate and signal stability requirements), and usage scenarios (such as indoor, outdoor, and mobile status).

[0077] Users with similar needs and behavioral patterns can be grouped together based on their individualized requirements. For example, users who frequently use IoT devices for video calls while on the go can be categorized as mobile video call users; users who primarily use smart office devices for file transfer and processing in indoor office environments can be categorized as indoor office users. Understanding the specific needs of different user groups helps in developing more precise antenna control targets. For instance, mobile video call users have higher requirements for signal stability and data transmission rates, while indoor office users may be more concerned with signal coverage and interference resistance.

[0078] Based on the analysis of environmental characteristic data, the influence of different climatic conditions on the performance of communication antennas is obtained as climatic influence, and the influence of different building materials on signal propagation is obtained as building influence.

[0079] For different user groups, ridge regression analysis is used to correlate climate impacts with building impacts to obtain multiple influencing factors. From these, the factors that have the greatest impact on demand under the current environment are identified as key influencing factors.

[0080] The steps to obtain key influencing factors include:

[0081] Climate impacts and building impacts are standardized and used as independent variables. A matrix is ​​formed by combining various climate and building factors, and demand is used as the dependent variable.

[0082] By introducing regularization parameters, we construct the objective function for ridge regression, which is expressed as follows:

[0083]

[0084] In the formula, It is the sample size. It is the number of independent variables. It is the first The dependent variable values ​​for each sample It is the first The first sample Each independent variable value It is the first The regression coefficients of the independent variables, It is a regularization parameter. yes The square of is used to calculate the penalty strength of the regularization term.

[0085] Initialize the regression coefficients, and take the partial derivative of the objective function with respect to each regression coefficient to obtain the gradient vector.

[0086] According to the chain rule Find the partial derivatives with respect to the regression coefficients:

[0087] make ,but .

[0088] .

[0089] In the formula, It is an intermediate variable, representing the first... The difference between the predicted and actual values ​​of the dependent variable for each sample. Yes Find the partial derivatives.

[0090] In the Find the partial derivatives with respect to the regression coefficients:

[0091]

[0092] That is, the formula for the gradient vector is expressed as:

[0093]

[0094] In the formula, It is the gradient vector.

[0095] The objective function is updated based on the gradient vector until the preset number of iterations is reached to obtain the coefficient values.

[0096] The independent variables are ranked according to their absolute values, and the variable with the largest absolute value is selected as the key influencing factor. For example, for mobile office users, signal attenuation is a critical factor affecting communication during rainy weather. In densely built-up commercial areas, signal obstruction and handover issues are key influencing factors.

[0097] Antenna control objectives for each user group are determined based on different key influencing factors.

[0098] The steps involved in developing an antenna control strategy include:

[0099] Multiple candidate control strategies can be specified based on the antenna control objectives and the adjustable parameters of the communication antenna. These adjustable parameters may include transmit power, operating frequency band, polarization, azimuth angle, and gain. When specifying candidate control strategies, the relationship between the antenna control objectives and these adjustable parameters must be comprehensively considered. For example, if the antenna control objective is to improve signal coverage, strategies such as increasing transmit power, adjusting the antenna azimuth angle, or optimizing the antenna gain can be considered; if the objective is to reduce interference, switching the operating frequency band or adjusting the polarization may be necessary. By combining these adjustable parameters in different ways, multiple candidate control strategies can be generated, providing more possibilities for subsequent optimization selection.

[0100] Based on the antenna control objective, evaluation indicators for candidate control strategies are determined. Multiple candidate control strategies are evaluated based on the evaluation indicators to obtain corresponding simulation scores, and the strategy with the highest score is selected as the antenna control strategy.

[0101] A neural Turing machine model was established, and the sand cat swarm optimization algorithm was used to optimize the neural Turing machine model to obtain a reinforced neural Turing machine model. Based on the reinforced neural Turing machine model, the parameter data and electromagnetic property data were analyzed to obtain the balance control parameters.

[0102] The steps to optimize and obtain the enhanced neural Turing machine model include:

[0103] Initialize the population size of the sand cat group, where each sand cat represents a set of parameters of the neural Turing machine model.

[0104] The parameters corresponding to each sand cat are applied to the neural Turing machine model, and the negative of the mean squared error loss is used as the fitness function, expressed by the formula:

[0105]

[0106] In the formula, is the sample size. It is the fitness function. It is the first The actual output value of each sample In the parameters The following model is for the first The predicted value for each sample.

[0107] Each sand cat moves randomly from its current position according to a preset probability to obtain a new position, expressed by the formula:

[0108]

[0109] In the formula, This is the Sand Cat's current location. It is the exploration step size. It is a random number that follows a standard normal distribution. It means moving to a new location.

[0110] The fitness value of each new location is calculated based on the fitness function, and the one with the highest fitness value is selected as the global optimal sand cat.

[0111] Each sand cat moves towards the globally optimal sand cat, updating its latest position. The formula is as follows:

[0112]

[0113] In the formula, represents the latest position of each sand cat. It is a learning factor. It is the globally optimal sand cat.

[0114] Calculate the fitness value of the latest position of each sand cat, and select the one with the highest fitness value as the optimization parameter. Use the optimization parameter to construct a neural Turing machine model to obtain a reinforced neural Turing machine model.

[0115] The steps for obtaining the balance control parameters include:

[0116] The parameter data and electromagnetic property data are integrated, and outliers and errors are removed to obtain a fused dataset. Statistical methods, such as the 3σ principle, can be used to identify and remove outliers; errors can be corrected or deleted through data validation and error correction algorithms.

[0117] The fused dataset is encoded and fed into the reinforced neural Turing machine model according to the input requirements to generate control signals. These control signals can include the attention distribution of the read / write head, erase vectors, and add vectors.

[0118] The system performs read and write operations based on control signals, outputs decision results, and adjusts the communication antenna according to these results to obtain balanced control parameters. The read operation retrieves relevant information from memory based on the attention distribution and feeds it back to the controller. The write operation updates the memory content based on erase and add vectors to store intermediate results and knowledge generated during the model's computation.

[0119] Antenna control decisions are obtained by adjusting the antenna control strategy using balanced control parameters based on the control target decision method.

[0120] The steps to obtain antenna control decisions include:

[0121] The impact of balanced control parameters on communication antenna performance and preset system objectives is analyzed, and the objectives and performance indicators of the currently used antenna control strategy are evaluated to obtain the evaluation results.

[0122] Based on the evaluation results, analyze the gap between the current antenna control strategy and the preset system objectives, and set adjustment targets.

[0123] The steps for setting adjustment goals include:

[0124] The data obtained from the evaluation of the current antenna control strategy's objectives and performance indicators are summarized to obtain the overall performance data. This data is then compared with the preset system objectives one by one. The difference between the actual value and the target value of each indicator is calculated and summarized to obtain the gap.

[0125] Based on the magnitude of the difference and its impact on performance, key gaps are selected from the gaps. Based on the key gaps, and considering the feasibility of the target while maintaining consistency with the preset system target, the adjustment target is obtained.

[0126] Adjustment targets may include:

[0127] Signal coverage category: Improve signal coverage in a specific area, such as increasing the signal coverage in the city center from the current 80% to 90% within a certain period of time (e.g., one month), or achieving a signal coverage of over 95% in a large building.

[0128] Expand the geographical range of signal coverage, such as extending the signal coverage of remote suburbs outward by a certain distance (e.g., 5 kilometers) to cover more users or areas.

[0129] Signal strength category: Improve the average signal strength in a specific area, such as increasing the average signal strength in a commercial area from the current -80dBm to -70dBm, thereby improving the user's communication experience. Ensure signal strength stability and reduce the fluctuation range of signal strength, ensuring that the fluctuation of signal strength within a certain period of time (such as 24 hours) does not exceed a certain threshold (such as ±5dBm).

[0130] Data transmission rate: Increase the average data transmission rate, for example, increasing the average data transmission rate for users in a certain community from the current 10Mbps to 20Mbps to meet users' needs for services such as high-definition video and large file transfer. Reduce data transmission latency, lowering the average data transmission latency from the current 50ms to less than 30ms to improve the quality of real-time services (such as video calls and online games).

[0131] Bit error rate (BER) related measures: Reduce the system's BER, for example, from the current 1% to below 0.1%, to improve the accuracy of data transmission. Ensure that the BER remains within an acceptable range under different environmental conditions (such as severe weather or high electromagnetic interference environments), for example, the BER should not exceed 0.5% during heavy rain.

[0132] Energy consumption: Reduce the energy consumption of the antenna system without compromising communication performance. For example, reduce the antenna's transmit power by 20% while still meeting signal coverage and transmission requirements to save energy costs. Optimize antenna energy management so that the antenna can intelligently adjust energy consumption under different workloads to achieve a balance between energy consumption and performance, such as automatically reducing transmit power during periods with fewer users.

[0133] Anti-interference: Enhance the antenna system's resistance to interference. For example, in areas with co-channel interference, adjust the operating frequency band or polarization to reduce the interference signal strength by more than 30dB. Improve the antenna's resistance to multipath interference by employing appropriate signal processing algorithms or antenna technologies to reduce the impact of multipath interference on signal quality to a negligible level.

[0134] A balance control adjustment strategy is formulated based on the adjustment objectives. This strategy may include changing the transmit power, switching the operating frequency band, adjusting the antenna polarization and azimuth angle, and optimizing the antenna gain. Multiple adjustment schemes are generated, and the one with the closest performance is selected as the antenna control decision based on performance indicators. When formulating the balance control adjustment strategy, it is necessary to comprehensively consider different adjustment objectives and the adjustable parameters of the communication antenna. Different adjustment objectives may require different adjustment strategies or combinations of strategies. For example, to improve signal strength, strategies such as increasing transmit power, optimizing antenna gain, or adjusting antenna polarization may be considered; to reduce energy consumption, methods such as reducing transmit power or optimizing the antenna's operating frequency band may be used. By generating multiple adjustment schemes and evaluating and comparing them based on performance indicators, the most suitable antenna control decision for the current situation can be selected, thereby achieving precise control of the communication antenna.

[0135] This embodiment provides an intelligent control method for communication antennas based on the Internet of Things (IoT). By analyzing user preference data and segmenting user groups, it enables personalized antenna control tailored to the individual needs of different users, avoiding a "one-size-fits-all" approach and better meeting diverse user requirements. Furthermore, it considers the impact of environmental factors such as different climate conditions and building materials on the performance of the communication antenna, allowing the antenna control to adapt to complex and changing environments and reducing interference and obstruction of signal propagation by environmental factors. The sand cat swarm optimization algorithm is also used to optimize the neural Turing machine model, improving the model's accuracy and adaptability. This ensures that the analyzed balance control parameters more accurately reflect the actual situation, providing a more reliable basis for antenna control. This method can adapt to different user needs, environmental changes, and system objectives, giving the communication antenna system greater adaptability and flexibility, and enabling it to better cope with various complex situations.

[0136] Based on the same general inventive concept, this invention also protects an intelligent control system for communication antennas based on the Internet of Things (IoT). The following describes an intelligent control system for communication antennas based on the IoT provided by this invention. The intelligent control system for communication antennas based on the IoT described below can be referred to in correspondence with the intelligent control method for communication antennas based on the IoT described above.

[0137] like Figure 3 As shown, the IoT-based intelligent control system for communication antennas includes:

[0138] The characteristic data acquisition module is used to collect parameter data of IoT devices and electromagnetic characteristic data of communication antennas, and to collect environmental characteristic data of the target area at preset time intervals.

[0139] The target strategy formulation module is used to analyze parameter data using social network analysis methods to obtain user preference data, determine antenna control targets based on user preference data and combined with environmental characteristic data, and formulate antenna control strategies based on antenna control targets.

[0140] The Sand Cat Optimization Modeling Module is used to establish a neural Turing machine model and optimize the neural Turing machine model using the Sand Cat swarm optimization algorithm to obtain a reinforced neural Turing machine model. Based on the reinforced neural Turing machine model, the parameter data and electromagnetic property data are analyzed to obtain the balance control parameters.

[0141] The parameter strategy adjustment module is used to adjust the antenna control strategy using balanced control parameters according to the control target decision method to obtain the antenna control decision.

[0142] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0143] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for intelligent control of communication antennas based on the Internet of Things, characterized in that, include: Collect parameter data from IoT devices and electromagnetic characteristic data from communication antennas, and collect environmental characteristic data within the target area at preset time intervals; User preference data is obtained by analyzing the parameter data using social network analysis methods. Antenna control targets are determined based on the user preference data and combined with the environmental feature data. Antenna control strategies are then formulated based on the antenna control targets. A neural Turing machine model is established, and the model is optimized using the sand cat swarm optimization algorithm to obtain a reinforced neural Turing machine model. Based on the reinforced neural Turing machine model, the parameter data and the electromagnetic property data are analyzed to obtain the balance control parameters. Antenna control decisions are obtained by adjusting the antenna control strategy using the balance control parameters according to the control target decision method.

2. The intelligent control method for communication antennas based on the Internet of Things according to claim 1, characterized in that, The steps for analyzing and obtaining the user preference data include: The device parameter set is obtained by integrating and normalizing various parameter data from multiple IoT devices. Each IoT device in the device parameter set is treated as a device node, and the corresponding user using the IoT device is treated as a user node. The connection length is determined based on the relationship between IoT devices and between IoT devices and their corresponding users. The degree, betweenness, proximity centrality, and clustering coefficient of each device node and each user node are calculated to determine network metrics, and key nodes are selected from them based on preset values. The user preference data is obtained by analyzing the key nodes based on preferred device type, usage time patterns, and device interaction preferences.

3. The intelligent control method for communication antennas based on the Internet of Things according to claim 1, characterized in that, The steps for determining the antenna control target include: Users are divided into different user groups based on their personalized needs, and corresponding needs are summarized for each user group. Based on the environmental characteristic data, the influence of different climatic conditions on the performance of communication antennas is analyzed to obtain the climatic influence, and the influence of different building materials on signal propagation is analyzed to obtain the building influence; For different user groups, ridge regression analysis is used to correlate the climate impact with the building impact to obtain multiple influencing factors. From these, the factors that have the greatest impact on demand under the current environment are identified as key influencing factors. The antenna control objectives for each user group are determined based on different key influencing factors.

4. The intelligent control method for communication antennas based on the Internet of Things according to claim 3, characterized in that, The steps to obtain the key influencing factors include: The climate impact and the building impact are standardized and used as independent variables. A matrix is ​​formed by combining various climate and building factors, and demand is used as the dependent variable. By introducing regularization parameters, the objective function of ridge regression is constructed; Initialize the regression coefficients, and calculate the partial derivative of the objective function with respect to each regression coefficient to obtain the gradient vector; The objective function is updated based on the gradient vector until a preset number of iterations are reached to obtain the coefficient value. The independent variables are sorted according to the absolute values ​​of the coefficients, and the independent variable with the largest absolute value is selected as the key influencing factor.

5. The intelligent control method for communication antennas based on the Internet of Things according to claim 4, characterized in that, The steps for formulating the antenna control strategy include: Based on the antenna control objective and the adjustable parameters of the communication antenna, multiple candidate control strategies are specified. Based on the antenna control objective, evaluation metrics for candidate control strategies are determined. Multiple candidate control strategies are evaluated based on the evaluation metrics to obtain corresponding simulation scores, and the strategy with the highest score is selected as the antenna control strategy.

6. The intelligent control method for communication antennas based on the Internet of Things according to claim 1, characterized in that, The steps to optimize and obtain the enhanced neural Turing machine model include: Initialize the population size of the sand cat group, where each sand cat represents a set of parameters of the neural Turing machine model; The parameters corresponding to each sand cat are applied to the neural Turing machine model, and the negative of the mean squared error loss is used as the fitness function. Each sand cat moves randomly from its current position according to a preset probability to obtain a new position. The fitness value for each new location is calculated based on the fitness function, and the one with the highest fitness value is selected as the globally optimal sand cat. Each sand cat moves towards the globally optimal sand cat, updating its latest position; Calculate the fitness value of the latest position of each sand cat, and select the one with the highest fitness value as the optimization parameter. Use the optimization parameter to construct the neural Turing machine model to obtain the reinforced neural Turing machine model.

7. The intelligent control method for communication antennas based on the Internet of Things according to claim 1, characterized in that, The steps for analyzing and obtaining the balance control parameters include: The parameter data and the electromagnetic property data are integrated, and outliers and errors are removed to obtain a fused dataset; The fused dataset is encoded and input into the enhanced neural Turing machine model according to the input requirements to generate control signals. The control signal is used to perform read and write operations, output the decision result, and adjust the communication antenna according to the decision result to obtain the balance control parameters.

8. The intelligent control method for communication antennas based on the Internet of Things according to claim 1, characterized in that, The steps for adjusting the antenna control decision include: The impact of the balance control parameters on the communication antenna performance and the preset system objectives is analyzed, and the objectives and performance indicators of the currently used antenna control strategy are evaluated to obtain the evaluation results. Based on the evaluation results, analyze the gap between the current antenna control strategy and the preset system target, and set adjustment targets; Based on the stated adjustment objectives, a balance control adjustment strategy is formulated, generating multiple adjustment schemes. Based on the stated performance indicators, the scheme with the closest performance is selected as the antenna control decision.

9. The intelligent control method for communication antennas based on the Internet of Things according to claim 8, characterized in that, The steps for setting the adjustment target include: The total performance data is obtained by summarizing the data obtained from the evaluation of the target and performance indicators of the current antenna control strategy. This data is then compared with the preset system target one by one. The difference between the actual value and the target value of each indicator is calculated and summed to obtain the gap. Based on the magnitude of the difference and its impact on performance, key gaps are selected from the gaps. Based on the key gaps, and considering the feasibility of the target, and in accordance with the preset system target, the adjustment target is obtained.

10. An intelligent control system for communication antennas based on the Internet of Things (IoT), which employs the intelligent control method for communication antennas based on the IoT as described in any one of claims 1 to 9, characterized in that, The control system includes: The characteristic data acquisition module is used to collect parameter data of IoT devices and electromagnetic characteristic data of communication antennas, and to collect environmental characteristic data of the target area at preset time intervals. The target strategy formulation module is used to analyze the parameter data using social network analysis methods to obtain user preference data, determine the antenna control target based on the user preference data and combined with the environmental feature data, and formulate the antenna control strategy based on the antenna control target. The Sand Cat Optimization Modeling Module is used to establish a neural Turing machine model and optimize the neural Turing machine model using the Sand Cat swarm optimization algorithm to obtain a reinforced neural Turing machine model. Based on the reinforced neural Turing machine model, the parameter data and the electromagnetic characteristic data are analyzed to obtain the balance control parameters. The parameter strategy adjustment module is used to adjust the antenna control strategy using the balance control parameters according to the control target decision method to obtain the antenna control decision.

Images