Intelligent Anti-interference system for power line carrier energy meter

Abstract

The present invention relates to the technical field of energy meter electrical parameter measurement. Disclosed is an intelligent anti-interference system for a power line carrier energy meter. The system comprises: collecting voltage and current signals of a power line, and constructing a sample database; performing time-frequency feature classification by means of a preset model, and establishing feature and scenario mapping by synchronizing scenario recognition results; building a scenario interference recognition network on the basis of the mapping result; collecting real-time data of N communication channels of a power line carrier energy meter, and performing channel coordination decision and anti-interference enhancement; performing communication data evaluation on the basis of a comprehensive scoring function; and performing anti-interference management on the basis of channel access decision, anti-interference enhancement, and a parallel access result. The present invention solves the technical problem of poor accuracy and reliability of metering data of existing power line carrier energy meters caused by interference signals and noise when the power line carrier energy meters are in complex electromagnetic environments, and achieves the technical effect of improving the anti-interference capability and the reliability of the power line carrier energy meters.

Description

Intelligent anti-interference system of carrier power meter

[0001] The present application claims priority to the Chinese patent application No. 202411111787.9, filed on August 14, 2024, and entitled "Intelligent anti-interference system of carrier power meter". TECHNICAL FIELD

[0002] The present application relates to the technical field of electric meter electric variable detection, in particular to an intelligent anti-interference system of a carrier power meter. BACKGROUND

[0003] With the rapid development of smart grid and Internet of Things technology and the increasing demand of modern power system for electric energy metering equipment, the electric energy meter as an important interface device between the power grid and the user not only needs to accurately measure the electric energy consumption, but also needs to transmit data in real time and reliably to support the intelligent management and operation of the power grid, and to enhance the anti-interference ability of the electric energy meter, which becomes the most important part in the field of power communication. However, in the complex power environment, the electric energy meter faces challenges from power grid noise, electromagnetic interference, equipment failure and other factors, which makes the electric energy meter inaccurate in measurement, unstable in data transmission and even data loss, seriously affecting the operation efficiency of the power grid.

[0004] Therefore, in the current carrier power meter related technology, there is a technical problem that when facing a complex electromagnetic environment, the carrier power meter is easily affected by interference signals and noise, resulting in poor accuracy and reliability of the carrier power meter's measurement data. SUMMARY

[0005] The present application provides an intelligent anti-interference system of a carrier power meter, which uses feature extraction and classification, scene interference recognition network building and other technical means to solve the technical problem of poor accuracy and reliability of the carrier power meter's measurement data caused by the influence of interference signals and noise when facing a complex electromagnetic environment, and achieves the technical effect of improving the anti-interference ability and reliability of the carrier power meter.

[0006] The application provides an intelligent anti-interference system of a carrier power meter, comprising: an intelligent sampling module, configured to call a high-precision ADC to continuously collect voltage and current signals of a power line, and to construct a sample database; a scene mapping module, configured to perform data preprocessing of the sample database, extract time-frequency features of the signals based on a time-frequency analysis tool, perform time-frequency feature classification through a preset model, and establish a feature and scene mapping through a synchronous scene recognition result; a prediction module, configured to build a scene interference recognition network based on a mapping result, wherein the scene interference recognition network is built-in in the prediction module; a reinforcement module, configured to collect real-time data of N communication channels of the carrier power meter, input the real-time data into the prediction module, and perform channel coordination decision and anti-interference reinforcement according to a decision result; a parallel calling module, configured to establish evaluation parameters of a signal-to-noise ratio, a bit error rate and data transmission requirements, construct a comprehensive score function through the evaluation parameters, perform communication data evaluation based on the comprehensive score function, and perform parallel calling of the N communication channels if the evaluation result cannot meet a preset threshold; and a management module, configured to perform anti-interference management according to channel calling decisions and anti-interference reinforcement and parallel calling results.

[0007] In a possible implementation, the reinforcement module further performs the following processing: the real-time data is analyzed to establish environment real-time data and signal real-time data; the environment real-time data is input into the scene interference recognition network, noise influence analysis is performed through a scene mapping subnetwork of the scene interference recognition network, an analysis result is established; noise interference development prediction is performed based on the environment real-time data through a prediction subnetwork of the scene interference recognition network, a prediction result is established; the analysis result and the prediction result are integrated, and anti-interference strategy matching is performed based on the integrated result to generate a decision result.

[0008] In a possible implementation, the parallel calling module further performs the following processing: a construction unit is configured to construct a comprehensive score function as follows:

[0009] wherein S is a comprehensive score result, n is a total number of evaluation indexes, i is an arbitrary evaluation index, ω i is a weight of the i th index, x i is an actual value of the i th index, x opt,i is a standard value of the i th index.

[0010] In a possible implementation, the parallel calling module further performs the following processing: an adaptive threshold updating unit is configured to obtain a busy state of a channel and an importance of communication data, and construct a preset threshold through the busy state and the importance; a comparison unit is configured to call the comprehensive score function and the preset threshold, perform comparison of an evaluation result and the preset threshold, and complete evaluation determination.

[0011] In a possible implementation, the reinforcement module further performs the following processing: a channel optimization unit configured to acquire real-time data transmission requirements, importance of communication data, and busy state of a channel, perform adaptive evaluation of the channel based on the data transmission requirements, the importance of the communication data, and the busy state of the channel, establish an adaptive evaluation result, perform channel matching update under the highest total fitness based on the adaptive evaluation result, and complete channel coordination decision-making according to a matching update result.

[0012] In a possible implementation, the management module further performs the following processing: a supervision unit configured to perform decision-making supervision of the channel calling decision and construct a feedback data set; and a feedback unit configured to receive the feedback data set and the channel calling decision, perform adaptive evaluation optimization of the channel, and perform subsequent channel coordination decision-making according to the optimized adaptive evaluation of the channel.

[0013] In a possible implementation, the management module further performs the following processing: a verification subunit configured to verify the parallel calling result and generate a verification result; and a feature fusion subunit configured to receive the verification result, perform adaptive timing density alignment of P communication channels for parallel tasks if the verification result is a verification pass result, wherein P≤N, perform transmission data verification of the aligned P communication channels, establish a verification identifier, perform feature fusion under the aligned timing based on the verification identifier, and complete anti-interference management based on a feature fusion result.

[0014] In a possible implementation, the reinforcement module further performs the following processing: configuring an adaptive defect filter, and reconstructing adjustment sensitivity of the adaptive defect filter according to stability of the real-time data; inputting the decision result into the adaptive defect filter with the adjusted sensitivity, performing adaptive filtering processing, and completing anti-interference reinforcement.

[0015] The intelligent anti-interference system of the carrier electric energy meter provided in the application, an intelligent sampling module, a scene mapping module, a prediction module, a reinforcement module, a parallel calling module, and a management module are provided. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments of the present disclosure will be briefly introduced below. In the present application, a flowchart is used to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the foregoing or the following operations are not necessarily performed in sequence. On the contrary, various steps can be processed in reverse order or simultaneously according to needs. At the same time, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0017] FIG. 1 is a schematic diagram of the structure of the intelligent anti-interference system of the carrier electric energy meter provided by the embodiments of the present application;

[0018] FIG. 2 is a schematic diagram of the execution process of the reinforcement module in the intelligent anti-interference system of the carrier electric energy meter provided by the embodiments of the present application.

[0019] Legend: intelligent sampling module 10, scene mapping module 20, prediction module 30, reinforcement module 40, parallel calling module 50, and management module 60. DETAILED DESCRIPTION

[0020] The above description is only a summary of the technical solutions of the present application. In order to make the technical means of the present application more clearly understood and can be implemented according to the content of the specification, and in order to make the above and other purposes, characteristics and advantages of the present application more obvious and easy to understand, the following specific embodiments of the present application are described.

[0021] In order to make the purposes, technical solutions and advantages of the present application more clear, the present application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0022] In the following description, "some embodiments" are related to a subset of all possible embodiments, but it can be understood that "some embodiments" can be the same subset or different subset of all possible embodiments, and can be combined with each other without conflict. The term "first\second" is only to distinguish similar objects, and does not represent the specific order of the object. The terms "include" and "have" and any variations, are intended to cover non-exclusive inclusion, for example, a process, system, product or server including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or modules not clearly listed or inherent to these processes, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as understood by those skilled in the art to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application.

[0023] The embodiments of the present application provide an intelligent anti-interference system of carrier power meter, as shown in FIG. 1, the system comprises:

[0024] The intelligent sampling module 10 is used to call high-precision ADC to continuously collect the voltage and current signals of the power line and construct a sample database. The high-precision ADC refers to an electronic element for converting an analog signal into a digital signal, including traditional parallel, step-by-step approach, integration, and voltage-to-frequency conversion, as well as the newly developed pipeline ADC in recent years, such as SAR ADC, Delta-Sigma ADC, etc. The high-precision ADC converts continuous analog signals into a series of analog signals with equal time intervals. The selection of the sampling frequency is usually 3-5 times the highest frequency of the original signal to ensure that the sampled signal is close to the original signal. Specifically, when the high-precision ADC continuously collects the voltage signal of the power line, the 24V power voltage is high enough to be directly sent to the AD pin of the micro control unit (MCU) for sampling, and a capacitor (such as 100nF) is connected in parallel for charge storage and filtering to ensure the performance of the high-precision ADC during rapid charging and discharging. When continuously collecting the current signal of the power line, a differential amplification circuit is used, i.e. using the virtual short and virtual open characteristics of the operational amplifier, to select appropriate resistance values for current amplification, for example, setting the amplification factor to 10 times. The sampled data (including voltage and current signals) is processed by a digital signal processor and stored in a memory to construct a sample database. The sample database contains many data samples covering the voltage and current changes of the power line under different conditions (such as normal, overload, fault, etc.). Each sample data contains corresponding voltage value, current value, and collection time, etc.

[0025] The scene mapping module 20 is configured to perform data preprocessing of the sample database, extract time-frequency features of the signals based on a time-frequency analysis tool, perform time-frequency feature classification through a preset model, and establish a feature and scene mapping through a synchronous scene recognition result. The voltage and current signal data of the sample database are preprocessed to improve the data quality and facilitate subsequent analysis and modeling. For example, data cleaning is performed, including missing value processing (deletion, replacement or interpolation), outlier detection and processing, data format conversion, data transformation, standardization, normalization and other operations. Specifically, the time-frequency features of the signals are extracted based on a time-frequency analysis tool, which means that the time and frequency domain features of the voltage and current signals are extracted, such as through Fourier transform and inverse transform or continuous wavelet transform, etc. The voltage and current signals are converted from the time domain to the frequency domain, and key features such as peak frequency, bandwidth, energy distribution, etc. are extracted. The time-frequency features are classified through a preset model, which means that the extracted time-frequency features are classified using a preset model, such as a neural network or a decision tree. The time-frequency features and corresponding categories are used as sample data to train a model based on space and frequency. The new time-frequency features are input into the trained model to obtain the category to which they belong. The time-frequency features and specific scenes are mapped to each other, so that the corresponding scene can be identified when the time-frequency features are given. For example, a scene recognition algorithm based on image retrieval is used to identify the scene and obtain a scene label. The time-frequency features are matched with the scene label to form a mapping relationship between the features and the scene. When new time-frequency features are given, the corresponding scene is determined by searching the mapping relationship.

[0026] The prediction module 30 is configured to build a scene interference recognition network based on the mapping result, and the scene interference recognition network includes a prediction sub-network, wherein the scene interference recognition network is built-in in the prediction module. Specifically, based on the mapping result of the features and the scene, the structure, parameters and configuration of the network are determined, and the scene interference recognition network is built to ensure that it can effectively identify and predict the interference signals in the scene. The scene interference recognition network is a network model based on a convolutional neural network (CNN) for identifying interference signals in a specific scene, which is used to process and analyze the collected voltage and current signal data. The prediction sub-network is an important part of the scene interference recognition network, which is trained using historical data to predict the possible interference situation in the future based on the current data. The scene interference recognition network (including the prediction sub-network) is integrated or embedded into a larger prediction module. The prediction module is a larger prediction module for processing and analyzing various types of data and providing various prediction and analysis results. By building the scene interference recognition network into the prediction module, it can be more convenient to integrate and exchange data with other modules.

[0027] The reinforcement module 40 is used to collect real-time data of N communication channels of the carrier power meter, and input the real-time data to the prediction module to perform channel coordination decision and anti-interference reinforcement according to the decision result. The communication channel refers to the path for data transmission between the carrier power meter and other devices or systems (such as concentrators, master stations, etc.), and N communication channels indicate that the carrier power meter simultaneously interacts with multiple devices for data transmission, thereby improving the efficiency and flexibility of data transmission. Specifically, data is collected from N communication channels of the carrier power meter in real time by using sensors, data acquisition cards, signal analyzers, etc., and the collected data usually includes key parameters such as signal strength, noise level, interference condition, and transmission quality. Before the collected data is input to the prediction module, data preprocessing is performed. The prediction module is usually trained based on historical data to learn the relationship between the communication channel state and the carrier power meter parameters, and is used to analyze and predict the future state of the communication channel. The prediction module predicts the state of each communication channel, such as signal quality and interference level, based on real-time data and other related information. According to the decision result of the prediction module, corresponding channel coordination decisions are performed, such as reallocating channels, adjusting transmission parameters, switching communication frequency bands, etc., to ensure that the interference between each communication channel is minimized while ensuring the efficiency and stability of data transmission. According to the decision result of the prediction module, the anti-interference capability of the communication channel is strengthened, for example, by using advanced modulation techniques, coding techniques, signal processing techniques, or adding redundant information, etc. After the implementation of the anti-interference measures, the state of the communication channel is continuously monitored to ensure the effectiveness of these measures and to adjust and optimize them when necessary.

[0028] The parallel calling module 50 is used to establish evaluation parameters of signal-to-noise ratio, bit error rate and data transmission requirement, and construct a comprehensive score function based on the evaluation parameters, and evaluate the communication data based on the comprehensive score function. If the evaluation result cannot meet the preset threshold, the parallel calling of N communication channels is executed. Among them, the signal-to-noise ratio (SNR) represents the proportion of signal to noise, which is an important indicator for evaluating signal transmission quality. The larger the SNR is, the better the signal transmission quality is. The bit error rate is a key parameter for evaluating the transmission quality of a digital communication system, which represents the probability of error code appearing in the transmission process. The lower the BER is, the better the signal transmission quality is. The data transmission requirement usually refers to the amount of data to be transmitted, the data rate or the real-time requirement of data transmission in the communication system. Specifically, according to the signal-to-noise ratio (SNR), the bit error rate (BER) and the data transmission requirement, the corresponding evaluation parameters are established, and the three evaluation parameters are used as inputs to construct a comprehensive score function, and an overall score value is output. Specifically, the comprehensive score function may be based on different weight distribution, reflecting the importance of signal-to-noise ratio, bit error rate and data transmission requirement in communication data evaluation. For example, SNR and BER may have a high weight, while the weight of data transmission requirement may be adjusted according to specific circumstances. The constructed comprehensive score function is used to evaluate the communication data, that is, the established signal-to-noise ratio parameter, bit error rate and data transmission requirement are input into the comprehensive score function to calculate the comprehensive score value, and the calculated comprehensive score value is compared with the preset threshold. The preset threshold is a critical value set to judge whether the performance of the current communication system meets the requirements. If the evaluation result cannot meet the preset threshold, that is, the performance of the current communication system does not meet the requirements, the system will execute the parallel calling of N communication channels, which means that multiple communication channels are used for data transmission at the same time or almost at the same time to increase the bandwidth of data transmission, improve the rate of data transmission or reduce the delay of data transmission. Through parallel calling, communication resources can be more effectively utilized, and the overall performance of the communication system can be improved to meet the data transmission requirement.

[0029] The management module 60 is used for anti-interference management according to the channel calling decision and the anti-interference reinforcement, and the parallel calling result. The channel calling decision, the anti-interference reinforcement and the parallel calling result are comprehensively applied to the anti-interference management. According to the real-time channel state and the service demand, the communication strategy is dynamically adjusted, the stability and the reliability of the communication system are ensured, and specifically, when the performance of a certain channel is lower than a preset threshold, the system can decide to call other backup channels or switch to a more suitable frequency band, the spectrum allocation and management such as frequency band planning and power control are performed, and the interference between channels is minimized; according to the channel calling decision, the anti-interference reinforcement measures are implemented on the selected channel, the channel state is monitored in real time, and the reinforcement measures are adjusted according to the feedback; if the parallel calling effect is not good, the channel calling decision and the anti-interference reinforcement measures need to be reevaluated, according to the parallel calling result, the channel allocation, the power control and other parameters are adjusted, and the communication performance is optimized. Through continuous optimization and adjustment of the communication strategy, the communication system can maintain efficient and stable operation in a complex environment.

[0030] The intelligent anti-interference system of the carrier power meter according to the embodiment of the application is used for solving the technical problem that the existing carrier power meter is easily affected by interference signals and noise when facing a complex electromagnetic environment, and leading to poor accuracy and reliability of the metering data of the carrier power meter, and achieves the technical effect of improving the anti-interference ability and reliability of the carrier power meter. The intelligent anti-interference system of the carrier power meter comprises an intelligent sampling module 10, a scene mapping module 20, a prediction module 30, a reinforcement module 40, a parallel calling module 50 and a management module 60.

[0031] In the following, the specific configuration of the reinforcement module 40 will be described in detail. As shown in FIG. 2, the reinforcement module 40 can further include: parsing the real-time data, establishing environmental real-time data and signal real-time data. Real-time data refers to data generated by the carrier electric energy meter during real-time operation, including electric energy use data, device state data, etc. Real-time data parsing refers to processing and analyzing data generated in real time to extract useful information, including environmental real-time data and signal real-time data. Specifically, environmental real-time data generally refers to real-time data related to the operating environment of the power system, such as temperature, humidity, air pressure, etc. These data are of great significance to the evaluation of the operating environment of the power system and the prediction of equipment failure. In the carrier electric energy meter, environmental real-time data can be collected by sensors and other devices and transmitted to the master station or other devices for analysis through the communication channel. Signal real-time data refers to real-time signal data generated by the carrier electric energy meter during communication, such as carrier signal strength, frequency, phase, etc. It reflects the real-time state of the communication channel and helps to evaluate communication quality and optimize communication parameters. Through the analysis of signal real-time data, communication failures or interferences can be detected in time and appropriate measures can be taken to handle them. It also includes inputting the environmental real-time data into the scene interference identification network, performing noise impact analysis through the scene mapping subnetwork of the scene interference identification network, and establishing analysis results. Through the scene mapping subnetwork of the scene interference identification network, the network can analyze the impact of noise and interference on power system communication in a specific environment, including signal attenuation, increased error rate, and decreased communication quality. For example, using signal propagation models, noise statistical models, etc., the impact of noise and interference is quantitatively evaluated, and corresponding analysis results are established, which usually include detailed information such as the type, intensity, duration, and impact range of noise and interference. It also includes noise interference development prediction based on environmental real-time data through the prediction subnetwork of the scene interference identification network, and establishing prediction results. When new environmental real-time data is received, the prediction subnetwork analyzes these environmental real-time data, and based on the results of real-time analysis, the prediction subnetwork predicts the development trend of noise interference in the future period of time, including possible intensity, frequency, duration, etc. The prediction result is usually presented in a quantitative form, such as predicting the intensity of noise interference will increase by how many percentage points, the duration will be extended by how many minutes, etc. The analysis results and the prediction results are integrated, and based on the integrated results, the anti-interference strategy matching is performed, and the decision results are generated. The established analysis results and prediction results are integrated, and based on the integrated results, the most suitable anti-interference strategy is selected from the strategy library for matching, including quantitative evaluation of the integrated analysis results and prediction results, and comparison and matching with the anti-interference strategies in the strategy library, to generate specific anti-interference decisions, such as adjusting communication parameters, optimizing device configuration, adding anti-interference devices, etc.

[0032] The specific configuration of the parallel calling module 50 will be described in detail below. The parallel calling module 50 can further include a construction unit for constructing a comprehensive scoring function as follows:

[0033] wherein S is the comprehensive scoring result, n is the total number of evaluation indexes, i is any one evaluation index, ω i is the weight of the i-th index, x i is the actual value of the i-th index, x opt,i is the standard value of the i-th index.

[0034] The specific configuration of the parallel calling module 50 will be described in detail below. The parallel calling module 50 can further include an adaptive threshold updating unit for obtaining the busy state of the channel and the importance of the communication data, and constructing a preset threshold value based on the busy state and the importance. The adaptive threshold updating unit is mainly used to dynamically adjust the threshold value according to the real-time state of the channel and the importance of the data, to ensure the effectiveness of the communication and the proper handling of the importance of the data. Specifically, the node collects the received signal strength indication value of the environment in real time, compares it with the currently set threshold value, and if it is less than the set threshold value, it is judged that the communication channel is in an idle state, and if it is greater than or equal to the threshold value, it is judged that the communication channel is in a busy state. The node updates the judgment of the communication channel state according to the number of consecutive judgments of the communication channel as idle or busy. The importance of the communication data comes from the priority label carried by the data itself, or from the data importance evaluation obtained by other means (such as upper-layer application, user configuration, etc.). The importance of the communication data will affect the setting of the threshold value, to ensure that important data can still obtain sufficient transmission resources when the channel is busy. According to the real-time busy state of the channel and the importance of the data, the adaptive threshold updating unit will construct a preset threshold value, which is a dynamically changing value that adjusts with the changes in the channel state and the data importance. For example, when the channel is busy and important data needs to be transmitted, the threshold value may be lowered to increase the probability of successful data transmission. When the channel is idle or the data importance is low, the threshold value may be increased accordingly to reduce unnecessary resource occupation. It also includes a comparison unit for calling the comprehensive scoring function and the preset threshold value, performing comparison between the evaluation result and the preset threshold value, and completing the evaluation determination. The main responsibility of the comparison unit is to call the comprehensive scoring function and obtain the evaluation result of the function on a certain object or data. At the same time, the comparison unit will obtain the preset threshold value in the system, and by comparing the evaluation result with the preset threshold value, the comparison unit can make an evaluation determination, for example, if the evaluation result meets the requirements of the preset threshold value (such as greater than the threshold value, equal to the threshold value, etc.), it is determined as qualified or meets the conditions; otherwise, it is determined as unqualified or does not meet the conditions.

[0035] In the following, the specific configuration of the reinforcement module 40 will be described in detail. The reinforcement module 40 can further include a channel optimization unit for obtaining real-time data transmission requirements, importance of communication data, busy state of the channel, performing channel adaptation evaluation based on the data transmission requirements, importance of communication data, and busy state of the channel, establishing an adaptation evaluation result, performing channel matching update under the highest total fitness based on the adaptation evaluation result, and completing channel coordination decision according to the matching update result. The channel optimization unit is responsible for performing channel adaptation evaluation according to real-time data transmission requirements, importance of communication data, and busy state of the channel, and updating channel matching according to the evaluation result, and finally completing channel coordination decision. Specifically, the channel optimization unit first obtains real-time data transmission requirements, including data transmission rate, bandwidth, latency, and other requirements. At the same time, based on factors such as data priority, service type, or user configuration, the importance information of communication data is obtained. The channel optimization unit also monitors the busy state of the channel by real-time detecting channel occupancy, signal strength, interference level, and other indicators. Based on the obtained data transmission requirements, importance of communication data, and busy state of the channel, the channel optimization unit will perform channel adaptation evaluation, including the consideration of multiple parameters and indicators such as signal-to-noise ratio (SNR), bit error rate (BER), and spectral efficiency, to determine whether the current channel state can meet the data transmission requirements and whether it can provide sufficient transmission resources for important data. After adaptation evaluation, the channel optimization unit establishes an adaptation evaluation result, which can be a quantitative indicator, such as an adaptation score, for measuring the matching degree between the current channel state and the data transmission requirements. Based on the adaptation evaluation result, the channel optimization unit performs channel matching update under the highest total fitness, i.e., compares multiple communication channels to find the best channel that meets the data transmission requirements and ensures that important communication data is prioritized. According to the matching update result, the channel optimization unit will complete channel coordination decision, such as adjusting channel allocation, switching communication frequency bands, optimizing transmission parameters, etc., to ensure the efficiency, stability, and reliability of data transmission, and optimize the utilization of network resources.

[0036] The specific configuration of the management module 60 will be described in detail below. The management module 60 can further include a supervision unit for performing decision supervision of channel invocation decisions and building a feedback dataset. The main function of the supervision unit is to supervise the execution of channel invocation decisions, including checking whether the decisions are executed as expected, the execution effect of the decisions, and possible abnormalities. Specifically, the supervision unit tracks the execution of channel invocation decisions in real time, analyzes the execution effect of the decisions, such as changes in indicators such as communication quality, data transmission efficiency, etc., such as channel allocation, switching, etc. If it is found that the decisions are not executed properly or there are abnormal situations, the supervision unit will timely issue an alarm or take appropriate corrective measures; the feedback dataset is the basis for the supervision unit to evaluate and analyze the execution of channel invocation decisions. By building the feedback dataset, the supervision unit can more accurately understand the effect and problems of channel invocation, and provide a basis for subsequent decision optimization. Specifically, the feedback dataset can contain information in multiple dimensions, such as channel status, data transmission quality, decision execution time, etc. The supervision unit can use the feedback dataset to post-evaluate channel invocation decisions, find problems and deficiencies, and based on the analysis results of the feedback dataset, the supervision unit can provide optimization suggestions or adjustment schemes to the decision maker. Also includes a feedback unit for receiving the feedback dataset and channel invocation decisions, performing channel adaptation evaluation optimization, and making subsequent channel coordination decisions based on the optimized channel adaptation evaluation. The feedback unit uses the received feedback dataset and channel invocation decisions to perform communication channel adaptation evaluation optimization, including comprehensive analysis of multiple dimensions such as channel status, data transmission quality, decision execution effect, etc. to evaluate the adaptability of the current channel invocation. If it is found that the adaptability is poor or there is room for improvement, the feedback unit will optimize the adaptation evaluation based on advanced algorithms and models, such as adjusting channel allocation strategies, optimizing transmission parameters, etc. After completing the adaptation evaluation optimization of the channel, the feedback unit will make subsequent channel coordination decisions based on the optimized results, which may include adjusting channel allocation, switching communication frequency bands, optimizing transmission parameters, etc., to further improve the performance, stability and reliability of the communication system, and ensure the efficiency and accuracy of data transmission.

[0037] The specific configuration of the management module 60 will be described in detail below. The management module 60 can further include a verification subunit for verifying the parallel call results and generating verification results. The verification subunit first receives the results of the parallel calls, predefines a plurality of verification rules according to system requirements, such as the integrity and accuracy of the verification results, and verifies the parallel call results to generate corresponding verification results, which are classified into several categories, such as passing verification, partially passing verification (which may need further processing), and failing verification. It also includes a feature fusion subunit for receiving the verification results. If the verification result is a verification pass result, the feature fusion subunit performs adaptive timing density alignment of P communication channels for parallel tasks, where P ≤ N, performs transmission data verification of the P communication channels after alignment, establishes a verification identifier, performs feature fusion under the aligned timing based on the verification identifier, and completes anti-interference management based on the feature fusion result. The feature fusion subunit first receives the verification results from the verification subunit. If the verification result is a verification pass, the feature fusion subunit will perform adaptive timing density alignment of P communication channels for parallel tasks. P represents the number of communication channels that are aligned, and P is less than or equal to N, where N is the total number of available communication channels in the system. Adaptive timing density alignment aims to ensure that data transmission between different communication channels is optimally matched in time and density, thereby improving overall communication efficiency. After completing adaptive timing density alignment, the feature fusion subunit will verify the transmission data of the P communication channels to ensure that the aligned data still maintains accuracy and integrity. According to the data verification result of the aligned communication channels, the feature fusion subunit will establish a corresponding verification identifier, which may include data valid, data invalid, and other state information. The feature fusion subunit will use the verification identifier as a guide to perform feature fusion on the communication channel data after timing alignment, that is, to combine information or features from different sources, different representations, or different abstraction levels into a single representation, such as using concat (series feature fusion), add (parallel strategy), and other feature fusion techniques to combine information from multiple communication channels. After feature fusion, the feature fusion subunit will obtain a feature representation that integrates information from multiple communication channels, which is used for anti-interference management, such as signal enhancement, noise suppression, error correction, etc., to ensure that data is not or as little as possible affected by external interference during transmission, and to improve the stability and reliability of the system in complex communication environments.

[0038] Below, the specific configuration of the reinforcement module 40 will be described in detail. The management module 40 can further include: configuring an adaptive defect filter, reconstructing the adjustment sensitivity of the adaptive defect filter according to the stability of the real-time data. Among them, the adaptive defect filter is a filter that can automatically adjust its parameters to adapt to the changes of the input signal. When there are defects (such as noise, interference, etc.) in the signal, the role of the filter is to remove or reduce the impact of these defects. Specifically, before configuring the adaptive defect filter, the stability of the real-time data needs to be evaluated. If the real-time data shows high stability, the adjustment sensitivity of the filter can be relatively low to avoid unnecessary fluctuations caused by excessive adjustment. If the real-time data shows low stability, the adjustment sensitivity of the filter should be increased accordingly to adapt to the changes of the signal faster. Configuring an adaptive defect filter includes selecting the type of filter (such as FIR, IIR, etc.), setting the initial parameters of the filter (such as cutoff frequency, order, etc.), and selecting an appropriate adaptive algorithm (such as LMS, RLS, etc.). The reconstruction of the adjustment sensitivity is based on the stability of the real-time data. Specifically, when the stability index changes, the adjustment sensitivity of the filter is adjusted according to the direction and degree of change. For example, if the stability index decreases (indicating that the data becomes more unstable), the adjustment sensitivity of the filter is increased. Conversely, if the stability index rises (indicating that the data becomes more stable), the adjustment sensitivity of the filter is reduced. It also includes inputting the decision result into the adaptive defect filter with adjusted sensitivity, performing adaptive filtering processing to complete the anti-interference reinforcement. The decision result is input into the adaptive defect filter with adjusted sensitivity, and the filter starts to perform adaptive filtering processing. Specifically, based on the current parameters of the filter and the characteristics of the input signal, a series of mathematical operations are performed to remove or reduce defects in the signal. The adaptive defect filter can automatically adjust its parameters according to the changes of the input signal, thereby maintaining the best filtering effect. The result of the adaptive filtering processing has reduced defects in the signal, higher quality and stronger anti-interference ability compared to the original signal, and improves the stability and reliability of the entire communication system.

[0039] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for easy differentiation, and do not limit the protection scope of the present application.

[0040] The above detailed description does not limit the scope of the application. Various modifications, combinations and equivalents thereof can be made in light of the above detailed description. Any modification, equivalent replacement and improvement made within the spirit and principle of the application shall fall within the scope of the application.

Claims

1. An intelligent anti-interference system of a carrier power meter, characterized in that, The system comprises: An intelligent sampling module for calling a high-precision ADC to continuously collect voltage and current signals of a power line and constructing a sample database; A scene mapping module for performing data preprocessing of the sample database, extracting time-frequency features of the signals based on a time-frequency analysis tool, performing time-frequency feature classification through a preset model, and establishing a feature and scene mapping through a synchronous scene recognition result; A prediction module for building a scene interference recognition network based on a mapping result, the scene interference recognition network comprising a prediction subnetwork, wherein the scene interference recognition network is built-in in the prediction module; A reinforcement module for collecting real-time data of N communication channels of a carrier power meter, inputting the real-time data into the prediction module, and performing channel coordination decision and anti-interference reinforcement according to a decision result; A parallel calling module for establishing evaluation parameters of a signal-to-noise ratio, a bit error rate, and data transmission requirements, constructing a comprehensive scoring function through the evaluation parameters, performing communication data evaluation based on the comprehensive scoring function, and performing parallel calling of the N communication channels if the evaluation result cannot meet a preset threshold; A management module for performing anti-interference management according to channel calling decisions and anti-interference reinforcement and parallel calling results.

2. The intelligent anti-interference system of carrier power meter as claimed in claim 1, wherein, The reinforcement module comprises the following steps: Analyzing the real-time data to establish environmental real-time data and signal real-time data; Inputting the environmental real-time data into the scene interference recognition network, performing noise influence analysis through a scene mapping subnetwork of the scene interference recognition network, and establishing an analysis result; Performing noise interference development prediction based on the environmental real-time data through a prediction subnetwork of the scene interference recognition network, and establishing a prediction result; Integrating the analysis result and the prediction result, and performing anti-interference strategy matching based on the integrated result to generate a decision result.

3. The intelligent anti-jamming system of carrier power meter as claimed in claim 1, wherein, The parallel calling module comprises the following steps: A building unit for building a composite scoring function as follows: Wherein S is the comprehensive score result, n is the total number of evaluation indexes, i is any one evaluation index, ω i is the weight of the i th index, x i is the actual value of the i th index, x opt，i is the standard value of the i th index.

4. The intelligent anti-interference system of carrier power meter as claimed in claim 3, wherein, The parallel calling module comprises the following steps: An adaptive threshold updating unit for obtaining a busy state of a channel and an importance of communication data, and constructing a preset threshold through the busy state and the importance; A comparison unit for calling a comprehensive scoring function and a preset threshold, performing comparison of an evaluation result and the preset threshold, and completing evaluation determination.

5. The intelligent anti-jamming system of carrier power meter as claimed in claim 1, wherein, The reinforcement module comprises the following steps: A channel optimization unit for obtaining a real-time data transmission requirement, an importance of communication data, and a busy state of a channel, performing channel adaptation evaluation based on the data transmission requirement, the importance of communication data, and the busy state of the channel, establishing an adaptation evaluation result, performing channel matching update under a highest total adaptability based on the adaptation evaluation result, and completing channel coordination decision according to a matching update result.

6. The intelligent anti-interference system of carrier power meter as claimed in claim 5, wherein, The management module comprises the following steps: A supervision unit for performing decision supervision of a channel calling decision, and constructing a feedback data set; A feedback unit for receiving the feedback data set and the channel calling decision, performing channel adaptation evaluation optimization, and performing subsequent channel coordination decision according to the optimized channel adaptation evaluation.

7. The intelligent anti-jamming system of carrier power meter as claimed in claim 1, wherein, The management module comprises the following steps: A verification subunit for verifying the parallel calling result to generate a verification result; The feature fusion subunit is configured to receive the verification result, perform adaptive timing density alignment of P communication channels for parallel tasks if the verification result is a verification pass result, where P≤N, perform transmission data verification on the P communication channels after alignment, establish a verification identifier, perform feature fusion based on the verification identifier, and complete anti-interference management based on a feature fusion result.

8. The system of claim 1, wherein, The reinforcement module performs the following steps: An adaptive defect filter is configured, and an adjustment sensitivity of the adaptive defect filter is reconstructed according to stability of the real-time data; The decision result is input into the adaptive defect filter with the adjusted sensitivity, adaptive filtering processing is performed, and anti-interference reinforcement is completed.

Images