A 5G-based intelligent Internet of Things communication system and its control method

Abstract

The present invention discloses a 5G intelligent Internet of Things communication system and its control method, which specifically relates to the technical field of Internet of Things communication. It includes controlling the parameters of the antenna unit in the Internet of Things device to complete communication with receiving Internet of Things devices at different levels, determining the signal characteristics of communication signals at different levels through wavelet analysis, and using cross-entropy analysis by estimating the probability density function of the signal to determine the complexity of the communication signal at each level, obtaining the spectrum information of the communication signal, real-time monitoring and recording the response time of the communication signal, training an ARMA model based on the response time data at different levels to obtain the time deviation information of the communication signal, and comprehensively analyzing the spectrum information and time deviation information of the communication signal at different levels to quantify the performance of the communication signal under different signals. The present invention helps to analyze the communication performance at different levels and optimize the signal transmission quality in various complex environments.

Description

Technical Field

[0001] The present invention relates to the field of Internet of Things communication technologies, and more specifically, to a 5G intelligent Internet of Things communication system and a control method thereof. Background Art

[0002] In a 5G intelligent Internet of Things communication system, the transmission situation of signals is dynamically changing and is affected by various factors, such as user distribution, environmental changes, wireless interference, frequency selection, etc. Due to supporting more device connections, high-speed data transmission, and lower latency, the fluctuations in communication quality are more significant. The communication between Internet of Things devices is no longer limited to a single frequency band or a static environment. The changes in the directionality, spectrum requirements, and signal transmission status between devices all require a more flexible and intelligent communication control mechanism. Traditional signal evaluation usually targets a single signal parameter (such as signal strength, bandwidth, delay, etc.) and cannot fully cope with complex channel changes at different levels.

[0003] To solve the above defects, a technical solution is provided now. Summary of the Invention

[0004] In order to overcome the above defects of the prior art, embodiments of the present invention provide a 5G intelligent Internet of Things communication system and a control method thereof to solve the problems raised in the above background art.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A 5G intelligent Internet of Things communication system specifically includes a tunable radio frequency front-end module, a spectrum analysis module, a response analysis module, and a multi-level channel evaluation module, and the modules are signal-connected to each other;

[0007] The tunable radio frequency front-end module is used to complete communication with receiving Internet of Things devices at different levels by controlling the parameters of the antenna unit in the transmitting Internet of Things device. Here, different levels refer to the direction where the receiving Internet of Things device is located and the required frequency band; the spectrum analysis module is used to determine the signal characteristics of communication signals at different levels through wavelet analysis based on the communication signals received by the receiving Internet of Things device, and use cross-entropy analysis by estimating the probability density function of the signal to determine the complexity of the communication signal at each level and obtain the spectrum information of the communication signal.

[0008] The response analysis module is used to monitor and record the response time of the communication signal in real time, and train an ARMA model based on the response time data at different levels to obtain the time deviation information of the communication signal.

[0009] A multi - level channel evaluation module is used to comprehensively analyze the spectrum information and time deviation information of communication signals at different levels, construct a level channel evaluation model, and quantify the performance of communication signals under different signals.

[0010] In a preferred embodiment, obtaining the spectrum information of a communication signal includes:

[0011] Representing the spectrum information of the signal by a signal energy anomaly coefficient and a signal complexity variation coefficient;

[0012] The acquisition logic of the signal energy anomaly coefficient is: Collect the signal within the monitoring time period at the set level, perform wavelet transform on the received signal, and determine the waveform data of the signal in the level frequency band. The expression is: Where, FZ i is the frequency - domain waveform data of the signal in the i - th level frequency band, F(t) is the time - domain waveform data of the signal within the monitoring time period at the i - th level, ψ a，b (t) is the wavelet function with scale and translation parameter b, i = 1, 2, 3, ……, I, I is a positive integer, and i is the number of different levels;

[0013] Obtain the frequency difference coefficient of the signal in the level frequency band, and mark the frequency difference coefficient of the signal in the level frequency band as: CY i ; Where, argmax(FZ i ) is the maximum frequency of the signal within the monitoring time period, argmin(FZ i ) is the minimum frequency of the signal within the monitoring time period; Obtain the energy proportion coefficient of the signal in the level frequency band, and mark the energy difference coefficient of the signal in the level frequency band as: Where, (t1, t2) is the time point from the minimum frequency to the maximum frequency of the signal within the monitoring time period;

[0014] Calculate the signal energy anomaly coefficient. The calculation formula is: Where, YC i is the signal energy anomaly coefficient.

[0015] In a preferred embodiment, the signal complexity variation coefficient includes:

[0016] The acquisition logic of the signal complexity variation coefficient is: According to the signal within the monitoring time period at the set level, obtain the frequency change of the received signal of the receiving Internet of Things device, and use kernel density estimation to determine the probability density of the received signal frequency. The expression is: Where, P(PL) jsis the probability density of the signal frequency of the received signal, pl is the frequency value at different time points within the monitoring time period, n = 1, 2, 3, ……, N, N is a positive integer, n is the number of different time points within the monitoring time period, h is the bandwidth, and K is the Gaussian kernel function;

[0017] Obtain the frequency change of the transmission signal of the transmission Internet of Things device, and use kernel density estimation to determine the probability density of the transmission signal frequency. The expression is: Among them, P(cs) is the probability density of the transmission signal frequency;

[0018] Calculate the complex coefficient of variation, and the calculation formula is: Among them, FZ i is the complex coefficient of variation of the signal.

[0019] In a preferred embodiment, obtain the time deviation information of the communication signal, including:

[0020] Express the time deviation information of the communication signal through the response time deviation coefficient;

[0021] The acquisition logic of the response time deviation coefficient: According to the response time data of the received Internet of Things devices at different levels, use the ARMA model for training, optimize the parameters of the ARMA model through the least squares method, and obtain the error function of the ARMA model. The expression is: ε i is the error function of the ARMA model at different levels, TYC m is the communication response time predicted by the ARMA model for the received Internet of Things device, TSJ m is the actual communication response time of the received Internet of Things device, m = 1, 2, 3, ……, M, M is a positive integer, and m is the number of the response time data;

[0022] Obtain the actual value of the response time of the received Internet of Things device within the monitoring time period, and mark the actual value of the response time of the received Internet of Things device within the monitoring time period as: SJ k , where k = 1, 2, 3, ……, K, K is a positive integer, k is the number of each response of the received Internet of Things device, use the trained ARMA model to predict the response time within the monitoring time period, obtain the predicted value of the response time of the received Internet of Things device within the monitoring time period, and mark the predicted value of the response time of the received Internet of Things device within the monitoring time period as: YC k ;

[0023] Calculate the sum of squared residuals of the response time of the received Internet of Things device within the monitoring time period. The calculation formula is: Among them, CC i is the sum of squared residuals of the response time of the received Internet of Things device within the monitoring time period;

[0024] Calculate the scale coefficient of the error function at different levels. The calculation formula is as follows: Where CD is the scale coefficient of the error function at the same level, and ε max is the maximum value of the error function at different levels, and ε min is the minimum value of the error function at different levels;

[0025] Calculate the response time deviation coefficient. The calculation formula is as follows: Where PC i is the response time deviation coefficient.

[0026] In a preferred embodiment, a hierarchical channel evaluation model is constructed, including:

[0027] Through comprehensive analysis of the spectrum information and time deviation information of communication signals at different levels, calculate the weighted values of the signal energy anomaly coefficient, complex variation coefficient, and response time deviation coefficient, construct a hierarchical channel evaluation model, and generate a hierarchical channel evaluation coefficient. The calculation formula of the hierarchical channel evaluation coefficient is as follows: Where PG i is the hierarchical channel evaluation coefficient, and α1, α2, and α3 are the proportionality coefficients of the signal energy anomaly coefficient, complex variation coefficient, and response time deviation coefficient respectively, and α1, α2, and α3 are all greater than 0.

[0028] In a preferred embodiment, quantify the performance of communication signals under different signals, including:

[0029] Set the threshold of the hierarchical channel evaluation coefficient, compare the hierarchical channel evaluation coefficients of different levels with the threshold of the hierarchical channel evaluation coefficient. If the hierarchical channel evaluation coefficient is greater than the threshold of the hierarchical channel evaluation coefficient, generate a warning signal; if the hierarchical channel evaluation coefficient is less than the threshold of the hierarchical channel evaluation coefficient, do not generate a warning signal.

[0030] In a preferred embodiment, a 5G intelligent IoT communication control method specifically includes the following steps: S1: The IoT device receives the communication signal from the transmission device, performs time-frequency conversion on the signal using wavelet analysis, extracts the signal characteristics in different frequency bands and directions, estimates the probability density of the signal through cross-entropy analysis, evaluates the complexity of the signal, and obtains the spectrum information of the communication signal;

[0031] S2: Real-time monitor and record the response time of each communication, train an ARMA model based on historical response time data, the model predicts the response time of different levels and compares it with the actual response time to obtain time deviation information;

[0032] S3: Integrate the spectrum information and time deviation information, and evaluate the signal quality at different levels by analyzing the signal performance at different levels;

[0033] S4: Adjust the communication parameters of the IoT device according to the level evaluation result.

[0034] Technical effects and advantages of the present invention:

[0035] By comprehensively analyzing the signal spectrum information, response time and their changes at different levels, the present invention monitors and optimizes the communication quality in real time, evaluates the signal using wavelet analysis, cross entropy and ARMA model, and then adjusts the configuration of the antenna unit and the beam direction to achieve dynamic optimization for different directions and frequency bands, quantifying the performance of the communication signal at each level. The present invention can improve the stability of the communication system, reduce latency, and optimize the signal transmission quality in various complex environments, ensuring efficient and reliable communication between IoT devices. Description of the drawings

[0036] For the convenience of those skilled in the art to understand, the present invention will be further described below in conjunction with the accompanying drawings;

[0037] Figure 1 It is a schematic structural diagram of a 5G intelligent IoT communication system according to the present invention;

[0038] Figure 2 It is a schematic flow diagram of a 5G intelligent IoT communication control method according to the present invention. Detailed implementation manners

[0039] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0040] Embodiment

[0041] Figure 1The structural schematic diagram of an intelligent IoT communication system based on 5G according to the present invention is given, which specifically includes a tunable RF front-end module, a spectrum analysis module, a response analysis module, and a multi-level channel evaluation module, and the signals between the modules are connected; the tunable RF front-end module is used to complete communication with receiving IoT devices at different levels by controlling the parameters of the antenna unit in the transmitting IoT device, where different levels refer to the direction and required frequency band of the receiving IoT device; the spectrum analysis module is used to determine the signal characteristics of communication signals at different levels through wavelet analysis according to the communication signals received by the receiving IoT device, and use cross-entropy analysis by estimating the probability density function of the signal to determine the complexity of the communication signal at each level, and obtain the spectrum information of the communication signal.

[0042] The response analysis module is used to monitor and record the response time of the communication signal in real time, and train an ARMA model based on the response time data at different levels to obtain the time deviation information of the communication signal.

[0043] The multi-level channel evaluation module is used to comprehensively analyze the spectrum information and time deviation information of the communication signal at different levels, construct a level channel evaluation model, and quantify the performance of the communication signal under different signals.

[0044] In a 5G intelligent IoT communication system, data exchange, control, and communication between IoT (Internet of Things) devices are realized through the joint cooperation of transmitting IoT devices and receiving IoT devices. Among them, the transmitting IoT device is equipped with multiple antenna units, MIMO (Multiple-Input Multiple-Output) technology, and beamforming technology. The multiple antenna units work together through MIMO technology, and can realize parallel transmission of multiple data streams on the same spectrum, thereby greatly improving the signal transmission rate and system throughput, and by precisely controlling the phase and amplitude of the multiple antenna units, the signal is concentrated in a specific direction to enhance the signal transmission ability. By dynamically adjusting the configuration of the antenna unit, the direction of the beam can be precisely controlled to optimize the signal propagation path.

[0045] For receiving IoT devices (such as 5G receiving devices), the reception quality of signals may exhibit different characteristics at different levels. By analyzing the reception quality of signals at these different levels and adjusting the parameters of the antenna unit of the transmitting IoT device, the communication quality and system performance can be optimized, including:

[0046] Phase adjustment: By controlling the phase of the signal transmitted by each antenna unit, a specific beam direction can be formed, and the signal can be concentrated in the direction of the receiving device, thereby reducing interference from other directions;

[0047] Amplitude adjustment: Adjusting the signal amplitude (gain) of each antenna element can enhance or reduce the signal strength in a specific direction. By dynamically adjusting the signal amplitude, beam deepening or expansion can be achieved;

[0048] Beam directivity: By controlling the directivity of the antenna array, the signal can be ensured to be focused on the area that needs to be covered. For example, when multiple receiving devices are distributed at different positions, the beam direction can be flexibly adjusted to maximize the received signal;

[0049] Number of antenna arrays: Increasing the number of antenna arrays can improve the system coverage and data throughput. For example, using a massive antenna array (Massive MIMO) can greatly improve the signal quality in a multi-user environment;

[0050] Layout of antenna arrays: By optimizing the layout of antenna arrays (such as the distance and orientation of adjacent elements), the signal transmission characteristics can be improved, thereby enhancing the reliability of transmission.

[0051] It should be noted that in the 5G intelligent IoT communication system, the hierarchical division is for more accurate analysis and optimization of signal transmission, reception quality, and system performance. The hierarchy can be divided from different perspectives, including:

[0052] Hierarchical division by frequency: Low-frequency band (Sub-6 GHz), millimeter wave, and ultra-high frequency band;

[0053] Hierarchical division by direction: By controlling the phase and amplitude of different antenna elements to achieve beamforming and focus on signal transmission in a specific direction, the signal can be divided into multiple levels according to different directions and beam controls.

[0054] In the 5G intelligent IoT communication system, the transmission and reception of signals are affected by various factors, such as channel conditions, device characteristics, user distribution, environmental noise, etc. Hierarchical division and evaluation of different levels are a key step in optimizing these factors, aiming to improve signal quality, reduce interference, and enhance the adaptability and response ability of the system, including:

[0055] The performance of signals in different frequency bands may vary significantly. For example, low-frequency signals (such as Sub-6 GHz) may be stronger in penetration and coverage than high-frequency signals (such as millimeter waves), but may be inferior in high-speed data transmission and capacity;

[0056] In different directions, the signal strength and transmission quality will also be different. By implementing beamforming through the antenna array, the phase and amplitude of the antenna elements can be dynamically adjusted to concentrate the signal in the required direction and optimize the transmission;

[0057] In a wireless communication system, the state of the channel is constantly changing and may be affected by factors such as the environment, weather, obstacles, interference from other devices, etc. By dividing the signal into multiple levels, the channel state can be evaluated in detail, so as to identify which frequency bands, directions, and time domains have the worst signal performance.

[0058] A spectrum analysis module, which is used to determine the signal characteristics of communication signals at different levels through wavelet analysis according to the communication signals received by the receiving Internet of Things device, and use cross-entropy analysis by estimating the probability density function of the signal to determine the complexity of the communication signal at each level, and obtain the spectrum information of the communication signal.

[0059] The spectrum information of the signal is represented by a signal energy anomaly coefficient and a signal complexity variation coefficient.

[0060] After the receiving Internet of Things device receives the communication signal, the signal characteristics of communication signals at different levels are determined through wavelet analysis, and the signal energy anomaly coefficient is obtained. The signal energy anomaly coefficient is used to evaluate the performance of the signal at different levels. The advantages of the signal energy anomaly coefficient are as follows:

[0061] The Internet of Things device (such as a 5G receiving device) receives communication signals from the transmitting device. These signals contain information from multiple levels (such as different frequency bands, different directions). Since the signals are affected by noise, interference, and attenuation during propagation, the quality of the signals may be uneven.

[0062] The received signal is decomposed into multiple frequency bands and time scales using wavelet analysis. Wavelet transform can not only analyze the frequency domain characteristics of the signal, but also provide time domain information, which makes it particularly suitable for processing time-varying signals.

[0063] By calculating the signal energy anomaly coefficient of each level, the signal quality of different frequency bands and directions can be effectively evaluated, which helps to identify problems in signal transmission, such as interference, attenuation, etc., and guides the transmitting Internet of Things device (such as an antenna unit, a radio frequency module, etc.) to perform optimization and adjustment.

[0064] Different from the traditional Fourier transform, wavelet transform can provide both time domain and frequency domain information at the same time, and is particularly suitable for analyzing signals with fast time and frequency changes. For dynamically changing signals (such as 5G communication signals), wavelet analysis can efficiently capture the local characteristics of the signal, which helps to accurately evaluate the signal quality of different levels (such as frequency bands, directions, etc.).

[0065] The acquisition logic of the signal energy anomaly coefficient is as follows: collect the signals within the monitoring time period at the set level, perform wavelet transform on the received signal, and determine the waveform data of the signal at the level frequency band. The expression is: Among them, FZ iThe frequency-domain waveform data of the signal at the i-th hierarchical frequency band, F(t) is the time-domain waveform data of the signal during the monitoring time period at the i-th level, ψ a，b (t) is a wavelet function with scale and translation parameter b. i = 1, 2, 3, ……, I, where I is a positive integer and i is the number of different levels;

[0066] It should be noted that the monitoring time period is a specific time period set by the staff in the professional field.

[0067] Obtain the frequency difference coefficient of the signal at the hierarchical frequency band, and mark the frequency difference coefficient of the signal at the hierarchical frequency band as: CY i ; where, argmax(FZ i ) is the maximum frequency of the signal during the monitoring time period, and argmax(FZ i ) is the minimum frequency of the signal during the monitoring time period;

[0068] Obtain the energy proportion coefficient of the signal at the hierarchical frequency band, and mark the energy difference coefficient of the signal at the hierarchical frequency band as: where, (t1, t2) is the time point from the minimum frequency to the maximum frequency of the signal during the monitoring time period;

[0069] It should be noted that the larger the frequency difference coefficient, the worse the signal performance. Especially when the spectrum of the signal changes too complexly, the signal quality may be affected by factors such as noise and multipath effects, resulting in a decline in communication quality. The larger the energy proportion coefficient, it means that more energy of the signal is concentrated in the frequency band of interest, indicating that the signal in this frequency band is stronger and the communication quality is better. The lower the energy proportion coefficient, it means that the energy distribution of the signal is more dispersed, or there is strong interference from other frequency bands, resulting in a lower signal energy in the target frequency band.

[0070] Calculate the signal energy anomaly coefficient, and the calculation formula is: where, YC i is the signal energy anomaly coefficient.

[0071] After receiving the communication signal received by the receiving IoT device, use cross-entropy analysis by estimating the probability density function of the signal to determine the signal complexity variation coefficient. The signal complexity variation coefficient is used to evaluate the stability and noise level of the transmitted signal to the received signal. The advantages of the signal complexity variation coefficient are:

[0072] The signal complexity variation coefficient analyzes the probability density difference between the transmitted signal and the received signal through cross - entropy, and can effectively quantify the stability and variation of the signal. If the signal changes significantly during transmission (such as being interfered with or attenuated), the cross - entropy is large, and thus the signal complexity variation coefficient increases. This quantization feature enables the objective evaluation of signal quality;

[0073] By analyzing the difference between the received signal and the transmitted signal, the signal complexity variation coefficient can reflect factors such as noise, interference, and attenuation existing in the system. When the noise level is high, the complexity variation coefficient of the signal will be relatively high. Therefore, the signal quality and noise situation can be judged through this coefficient, and corresponding remedial measures can be taken;

[0074] The signal complexity variation coefficient can be dynamically calculated over time, which helps to monitor the health status of the communication system in real - time. Especially in dynamic environments (such as complex scenarios of 5G networks and Internet of Things devices), it can reflect the real - time changes and stability of the signal;

[0075] The complexity variation coefficient calculated through cross - entropy can help to locate potential problems in signal transmission, such as attenuation, distortion, multipath interference, etc. This provides quantitative analysis support for network optimization, enabling the effective diagnosis of the root cause of the problem and corresponding adjustments;

[0076] In 5G and Internet of Things communication systems, there may be a large number of different types of receiving devices. By comparing the signal quality of different receiving devices, the complexity variation coefficient can provide targeted signal optimization suggestions for different devices, which helps the system to perform load balancing, beamforming, or other optimization operations.

[0077] The acquisition logic of the signal complexity variation coefficient is as follows: Based on the signal within the monitoring time period under the set hierarchy, obtain the frequency variation of the signal received by the receiving Internet of Things device, and use kernel density estimation to determine the probability density of the received signal frequency. The expression is: where, P(PL) js is the probability density of the received signal frequency, pl is the frequency value at different time points within the monitoring time period, n = 1, 2, 3, ……, N, N is a positive integer, n is the number of different time points within the monitoring time period, h is the bandwidth, and K is the Gaussian kernel function;

[0078] Obtain the frequency variation of the signal transmitted by the transmitting Internet of Things device, and use kernel density estimation to determine the probability density of the transmitted signal frequency. The expression is: where, P(cs) is the probability density of the transmitted signal frequency;

[0079] Calculate the signal complexity variation coefficient. The calculation formula is: where, FZ iis the signal complexity variation coefficient.

[0080] A response analysis module for real-time monitoring and recording of the response time of communication signals, training an ARMA model based on response time data at different levels to obtain the time deviation information of communication signals.

[0081] Express the time deviation information of communication signals through the response time deviation coefficient.

[0082] Train the ARMA model through response time data at different levels. Among them, the response time data at different levels are obtained through the Internet of Things system, network topology, and device configuration simulated by a simulation tool, and the response time data of receiving devices at different levels are obtained. By using the ARMA model for training, ARMA models at different levels are obtained. The response time deviation coefficient is used to evaluate the delay performance of the communication signal response at different levels. The advantages of the response time deviation coefficient are as follows:

[0083] The response time deviation coefficient reflects the fitting effect of the training model on the data, measuring the relative difference between the fitting ability of the model on historical data and the prediction ability on new data (monitoring time period);

[0084] By comparing the ratio of the training residual and the residual in the monitoring time period, the generalization ability of the model can be evaluated. A good model should be able to fit the training data well and make reasonable predictions for the future (or monitoring data). If the ratio is large, it may indicate that the model is only applicable to the training data and has poor prediction effects on new data;

[0085] The response time deviation coefficient can reveal the instability of the network. For example, during high-traffic periods, when the network load is heavy, or due to environmental interference (such as weather, obstacles, etc.) resulting in signal attenuation and other problems, these may all cause the response time of the signal to become longer, thereby increasing the sum of squared residuals.

[0086] The acquisition logic of the response time deviation coefficient: According to the response time data of receiving Internet of Things devices at different levels, use the ARMA model for training, optimize the parameters of the ARMA model through the least squares method, and obtain the error function of the ARMA model. The expression is: ε i is the error function of the ARMA model at different levels, TYC m is the predicted communication response time of the receiving Internet of Things device by the ARMA model, TSJ m is the actual communication response time of the receiving Internet of Things device, m = 1, 2, 3,..., M, M is a positive integer, and m is the number of response time data;

[0087] Obtain the actual value of the response time of the IoT device received during the monitoring period, and mark the actual value of the response time of the IoT device received during the monitoring period as: SJ k where k = 1, 2, 3, ……, K, K is a positive integer, and k is the number of each response of the IoT device received. Use the trained ARMA model to predict the response time during the monitoring period, obtain the predicted value of the response time of the IoT device received during the monitoring period, and mark the predicted value of the response time of the IoT device received during the monitoring period as: YC k ;

[0088] Calculate the sum of squared residuals of the response time of the IoT device received during the monitoring period. The calculation formula is: where CC i is the sum of squared residuals of the response time of the IoT device received during the monitoring period;

[0089] Calculate the scale coefficient of the error function at different levels. The calculation formula is: where CD is the scale coefficient of the error function at the same level, ε max is the maximum value of the error function at different levels, and ε min is the minimum value of the error function at different levels;

[0090] Calculate the response time deviation coefficient. The calculation formula is: where PC i is the response time deviation coefficient.

[0091] The multi-level channel evaluation module is used to comprehensively analyze the spectrum information and time deviation information of the communication signal at different levels, construct a level channel evaluation model, and quantify the performance of the communication signal under different signals.

[0092] Through the comprehensive analysis of the spectrum information and time deviation information of the communication signal at different levels, perform weighted calculations on the signal energy anomaly coefficient, complex variation coefficient, and response time deviation coefficient, construct a level channel evaluation model, and generate a level channel evaluation coefficient. The calculation formula of the level channel evaluation coefficient is: where PG i is the level channel evaluation coefficient, and α1, α2, α3 are the proportionality coefficients of the signal energy anomaly coefficient, complex variation coefficient, and response time deviation coefficient respectively, and α1, α2, α3 are all greater than 0.

[0093] Set the hierarchical channel evaluation coefficient threshold, compare the hierarchical channel evaluation coefficients of different levels with the hierarchical channel evaluation coefficient threshold. If the hierarchical channel evaluation coefficient is greater than the hierarchical channel evaluation coefficient threshold, generate a warning signal, indicating that the communication quality of this level is poor, and it may be necessary to adjust the configuration of the antenna unit, control the direction of the beam, and optimize the communication of the signal. If the hierarchical channel evaluation coefficient is less than the hierarchical channel evaluation coefficient threshold, no warning signal is generated, indicating that the communication quality of the current level is good, and there is no need to adjust the parameters of the antenna unit in the transmission IoT device through the tunable radio frequency front-end module.

[0094] The present invention comprehensively analyzes the signal spectrum information, response time and its changes at different levels, monitors and optimizes the communication quality in real time, evaluates the signal using wavelet analysis, cross entropy and ARMA model, and then adjusts the configuration of the antenna unit and the beam direction to achieve dynamic optimization of different directions and frequency bands, quantifying the performance of communication signals at each level. The present invention can improve the stability of the communication system, reduce latency, and optimize the signal transmission quality in various complex environments to ensure efficient and reliable communication between IoT devices.

[0095] Embodiment 2

[0096] As Figure 2 The present invention provides a 5G intelligent IoT communication control method, which specifically includes the following steps:

[0097] S1: The IoT device receives the communication signal from the transmission device, performs time-frequency conversion on the signal using wavelet analysis, extracts the signal characteristics under different frequency bands and directions, estimates the probability density of the signal through cross entropy analysis, evaluates the complexity of the signal, and obtains the spectrum information of the communication signal;

[0098] S2: Monitor and record the response time of each communication in real time, train the ARMA model based on the historical response time data, the model predicts the response time of different levels and compares it with the actual response time to obtain the time deviation information;

[0099] S3: Integrate the spectrum information and the time deviation information, and evaluate the signal quality at different levels by analyzing the signal performance at different levels;

[0100] S4: Adjust the communication parameters of the IoT device according to the hierarchical evaluation results.

[0101] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to obtain a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0102] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired or wireless (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that contains a collection of one or more available media. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0103] It should be understood that in various embodiments of the present application, the sequence numbers of the above processes do not imply the order of execution, and the order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0104] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0105] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be described herein again.

[0106] In several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces. The indirect coupling or communication connection of the devices or units can be in electrical, mechanical, or other forms.

[0107] If the above functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs and other various media that can store program codes.

[0108] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A 5G intelligent IoT communication system, characterized in that: Specifically, it includes a tunable RF front-end module, a spectrum analysis module, a response analysis module, and a multi-level channel evaluation module, and signal connections between the modules; A tunable RF front-end module is used to communicate with receiving IoT devices at different levels by controlling the parameters of the antenna unit in the transmitting IoT device, where the different levels refer to the direction and the required frequency band of the receiving IoT device; The spectrum analysis module is used to determine the signal characteristics of communication signals at different levels through wavelet analysis based on the communication signals received by the IoT device, and to determine the complexity of the communication signals at each level by estimating the probability density function of the signals using cross entropy analysis to obtain the spectrum information of the communication signals; The response analysis module is used to monitor and record the response time of communication signals in real time, train the ARMA model based on the response time data at different levels, and obtain the time deviation information of communication signals; The multi-level channel assessment module is used to comprehensively analyze the spectrum information and time deviation information of communication signals at different levels, build a hierarchical channel assessment model, and quantify the performance of communication signals at different levels; Among them, the spectrum information of the signal is represented by the signal energy anomaly coefficient and the signal complex variation coefficient; The acquisition logic of the signal energy anomaly coefficient is: collect the signal within the monitoring time period under the set level, perform wavelet transform on the received signal, and determine the waveform data of the signal under the level frequency band. The expression is: ;in, is the frequency domain waveform data of the signal in the i-th level frequency band, is the time domain waveform data of the signal in the monitoring period at the i-th level, is a wavelet function with scale parameter a and translation parameter b, i=1, 2, 3, ..., I, I is a positive integer, and i is the number of different levels; The frequency difference coefficient of the signal in the hierarchical frequency band is obtained, and the frequency difference coefficient of the signal in the hierarchical frequency band is marked as: ;in, , is the maximum frequency of the signal during the monitoring period, is the minimum frequency of the signal during the monitoring period; The energy ratio coefficient of the signal in the hierarchical frequency band is obtained, and the energy difference coefficient of the signal in the hierarchical frequency band is marked as: ;in, It is the time point from the minimum frequency to the maximum frequency of the signal within the monitoring period; Calculate the signal energy anomaly coefficient, the calculation formula is: ;in, is the signal energy anomaly coefficient; The logic for obtaining the complex coefficient of variation of the signal is as follows: according to the signal in the monitoring time period at the set level, the frequency change of the signal received by the IoT device is obtained, and the probability density of the received signal frequency is determined using kernel density estimation; Obtain the frequency change of the transmission signal of the IoT device, and use kernel density estimation to determine the probability density of the transmission signal frequency; Calculate the signal complex variation coefficient, the calculation formula is: ;in, is the probability density of the received signal frequency, is the probability density of the transmission signal frequency, is the signal complexity coefficient of variation; Wherein, the time deviation information of the communication signal is represented by a response time deviation coefficient; The logic for obtaining the response time deviation coefficient is as follows: according to the response time data of IoT devices received at different levels, the ARMA model is used for training, the parameters of the ARMA model are optimized by the least squares method, and the error function of the ARMA model is obtained, which is expressed as follows: , is the error function of ARMA models at different levels, Predict the communication response time of receiving IoT devices for the ARMA model, is the actual response time of receiving the communication of the IoT device, m=1, 2, 3, ..., M, M is a positive integer, and m is the number of the response time data; The actual value of the response time of the IoT device received during the monitoring period is obtained, and the actual value of the response time of the IoT device received during the monitoring period is marked as: , where k=1, 2, 3, ..., K, K is a positive integer, k is the number of each response of the receiving IoT device, the trained ARMA model is used to predict the response time within the monitoring time period, and the predicted value of the response time of the receiving IoT device within the monitoring time period is obtained, and the predicted value of the response time of the receiving IoT device within the monitoring time period is marked as: ; Calculate the residual sum of squares of the response time of the receiving IoT device during the monitoring period. The calculation formula is: ;in, is the residual sum of squares of the response time of the IoT devices received during the monitoring period; Calculate the scale coefficient of the error function at different levels. The calculation formula is: ;in, is the scale coefficient of the error function at the same level, is the maximum value of the error function at different levels, is the minimum value of the error function at different levels; Calculate the response time deviation coefficient using the following formula: ;in, is the response time deviation coefficient.

2. According to claim 1, a 5G intelligent IoT communication system is characterized in that: Construct a hierarchical channel assessment model, including: Through comprehensive analysis of the spectrum information and time deviation information of communication signals at different levels, the signal energy anomaly coefficient, complex variation coefficient and response time deviation coefficient are weighted and calculated to construct a hierarchical channel assessment model and generate a hierarchical channel assessment coefficient. The calculation formula of the hierarchical channel assessment coefficient is: ;in, is the hierarchical channel estimation coefficient, are the proportional coefficients of signal energy anomaly coefficient, complex variation coefficient, and response time deviation coefficient, respectively. Both are greater than 0.

3. A 5G intelligent IoT communication system according to claim 2, characterized in that: Quantify the performance of communication signals under different signals, including: A hierarchical channel assessment coefficient threshold is set, and the hierarchical channel assessment coefficients of different levels are compared with the hierarchical channel assessment coefficient threshold. If the hierarchical channel assessment coefficient is greater than the hierarchical channel assessment coefficient threshold, a warning signal is generated; if the hierarchical channel assessment coefficient is less than the hierarchical channel assessment coefficient threshold, no warning signal is generated.

4. A 5G smart IoT communication control method, used to implement a 5G smart IoT communication system according to any one of claims 1 to 3, characterized in that: The specific steps include: S1: The receiving IoT device receives the communication signal from the transmission device, performs time-frequency conversion on the signal using wavelet analysis, extracts the signal characteristics in different frequency bands and directions, estimates the probability density of the signal through cross entropy analysis, evaluates the complexity of the signal, and obtains the spectrum information of the communication signal; S2: Monitor and record the response time of each communication in real time, train the ARMA model based on historical response time data, and use the model to predict the response time of different levels and compare it with the actual response time to obtain time deviation information; S3: integrates spectrum information and time deviation information, analyzes signal performance at different levels, and evaluates signal quality at different levels; S4: Adjust the communication parameters of IoT devices based on the hierarchical evaluation results.

Images