Electric energy metering information transmission system and method

Abstract

The invention relates to the technical field of electric energy metering information transmission, and discloses an electric energy metering information transmission system and method. Through data acquisition and preprocessing, voltage, current and power signals are acquired, a normalized time sequence matrix is generated, the feature expression capability is enhanced through nonlinear transformation, and the problem of signal complexity is solved. And feature extraction and compression are combined with sparse processing, key feature information is extracted, the data dimension and redundancy are reduced, the storage and transmission pressure is reduced, and the transmission efficiency is improved. The dynamic transmission strategy adaptively adjusts the frequency and priority based on the network state, and enhances the transmission reliability in combination with a verification mechanism. And in decoding and reconstruction, signal features are recovered by using a reverse reconstruction algorithm, so that the precision and data availability under a high compression ratio are ensured. Data analysis and anomaly detection are combined with high-quality features and a dynamic algorithm, abnormal values and abnormal fluctuations are recognized in real time, and the adaptive capacity of the system in a complex environment is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electric energy metering information transmission, and in particular to an electric energy metering information transmission method. Background Art

[0002] With the rapid development of smart grids, the energy metering information transmission system has gradually become an important part of the power system. The accurate collection, compression, transmission and processing of energy metering information are of great significance to the efficiency and stability of power grid operation and the improvement of user service experience. However, the existing energy metering information transmission technology still has many problems in practical applications, especially in data compression, transmission efficiency, data integrity and exception handling. Technical bottlenecks restrict the overall performance of the system.

[0003] In the existing technology, whether it is wireless communication or wired communication, the surge in data volume can easily lead to reduced transmission efficiency. Especially in high-frequency sampling scenarios, the transmission of large amounts of raw data poses severe challenges to bandwidth and latency. Conventional compression algorithms have limited processing capabilities for high-dimensional, multi-source data and cannot fully utilize redundant information in the data. The decompression process may cause additional delays. General encryption methods have high computational complexity and can easily cause performance bottlenecks for resource-constrained power metering equipment, such as embedded systems. In addition, traditional methods have limited ability to combat data tampering and forgery. The current cloud-based analysis model makes it difficult to provide real-time feedback on analysis results, and relies on complex deep learning or statistical modeling methods for abnormal data detection, resulting in high processing delays.

[0004] In response to the above problems, this solution proposes a new electric energy metering information transmission system and method based on data self-encoding technology, aiming to solve the pain points in the existing technology and significantly improve the efficiency, security and real-time performance of data transmission and analysis. Summary of the invention

[0005] The present invention provides an electric energy metering information transmission system and method, which facilitates solving the problems mentioned in the above background technology.

[0006] The present invention provides the following technical solution: a method for transmitting electric energy metering information, comprising: S1, data collection and preprocessing; Use the voltage measurement module to measure the voltage signal, recorded as V(t); Use a current sensor to measure the current signal, recorded as I(t); Use the power calculation module to calculate the real-time power signal, denoted as P(t); Where t is the timestamp; The voltage signal, current signal and power signal are organized in time series to form a matrix: ; Wherein, X(t) is a matrix containing voltage signal, current signal and power signal; Normalize the signal: ; Among them, X ij is the jth value of the ith signal in the matrix X(t); m i is the mean of the ith signal; s i is the standard deviation of the ith signal; Use nonlinear transformation to enhance the expressiveness of signal features: ; Among them, α ij , β ij and g ij is the dynamic change parameter of the signal; tanh() and sin() are hyperbolic tangent and sine functions respectively, which are used for nonlinear transformation; S2, feature extraction and compression; S3, data compression and sparsification; S4, data transmission; S5, data decoding and reconstruction; S6. Data analysis and anomaly detection.

[0007] Optionally, the feature extraction and compression specifically includes: Extract time and frequency domain features of each signal: ; Among them, f i is the time domain feature of the i-th signal; T is the time length of the signal; Perform principal component analysis on the extracted features: ; Among them, U, S and V are matrices after SVD decomposition; F' is the compressed eigenvector matrix; Activate the compressed feature vector: ; Among them, F is the eigenvector matrix; tanh() is the hyperbolic tangent function.

[0008] Optionally, the data compression and sparseness specifically include: Sparse the compressed features: ; Among them, F' iis the i-th value in the feature matrix; l is the sparsification control parameter, which is used to adjust the strength of sparsification; β is the sparsification index, and β>1 is used to enhance sparsity; Will satisfy the condition As important features; otherwise, as unimportant features, and set the unimportant features to 0: ; Among them, F final i is the feature value after screening; θ is the threshold, which is used to determine whether the feature is retained; Output the final sparse feature matrix F final , this matrix will be used for transmission.

[0009] Optionally, the data transmission specifically includes: S41, generate feature encoding matrix F encoded ; From the original input signal matrix X(t), the sparse matrix F is obtained by sparse feature extraction algorithm sparse : ; Where X(t) is the signal matrix; A is the feature basis matrix; l is the sparsity regularization parameter; F sparse Perform encryption encoding to generate the encoding feature matrix F encoded : ; Wherein, e() is the encryption mapping function; () is the feature verification function, specifically: ; Where W1 is the weight matrix of the verification function; b1 is the bias vector; S42, network status monitoring; Monitor the network status in real time to obtain the current delay Dt(t), bandwidth B(t) and packet loss P(t); S43, transmission rate calculation; According to the network status, the data transmission rate R(t) is adaptively adjusted: ; Among them, R min is the minimum transmission rate; Dt(t) is the delay difference of the current network; t max is the maximum delay allowed by the system; t th is the delay threshold; α, β and g are parameters for adjusting the transmission rate; S44, generating a data packet; Get the length of the maximum data packet transmitted over the network, recorded as L max ; F encoded Divided into multiple packets: ; Among them, P i is the i-th data packet; i represents the index of the data packet; L max Indicates the maximum length of each data packet; Each column of the data packet corresponds to a characteristic component, and each row of the data packet corresponds to a signal at a specific time step; If the last data packet is less than L max If the length is , the check bit is filled with 0; S45, data packaging and encoding; F encoded Divide into multiple small data packets P according to the transmission rate R(t) i , and add redundant check bits to each data packet ; in It is the redundant check bit function of the data packet, specifically: ; Among them, P i,k For data packet P i The kth data unit in w k is the weight coefficient, which is related to the length of the data packet; mod(•,2) is the modulo 2 operation, which is used to generate the binary check bit; S46, data transmission and verification; Send P at rate R(t) i , verify data integrity in real time at the receiving end: ; If the check fails, the data is retransmitted.

[0010] Optionally, the data decoding and reconstruction specifically includes: S51, data reception and verification; For each received packet P i , first do a sanity check: ; Among them, P i is the i-th data packet received; The check digit generated by the check function; like If it is 0, it means that the data packet has not been tampered with and the data is complete; otherwise, the receiving end requests to retransmit the data packet; S52, data decryption; Use the data decryption formula to decrypt the received data packet P i To decrypt: ; Among them, F decoded i is the decrypted data matrix; Decrypt() is the decryption function, specifically: ; Among them, b1 is the bias term; W -1 1 is the inverse matrix of the check function.

[0011] S53, data reconstruction and splicing; All decrypted data fragments F decoded i Splice and reconstruct the complete feature matrix F decoded : ; Among them, ∪ represents the concatenation operation, which concatenates the decryption results of all data packets into a complete feature matrix in order; S54, data analysis and reconstruction; Restore the original data feature F through inverse transformation sparse : ; Among them, R() represents the inverse reconstruction function, which restores the decrypted feature matrix to the original sparse feature matrix.

[0012] Optionally, the inverse reconstruction function specifically includes: The design of the reverse reconstruction function R() is as follows: S541, input variables; Input variables include F encoded , (), and P i ; The F encoded is the data matrix after encoding; () is the verification function used in the encoding process; P i For data packets; S542, output variable; Output variable F reconstructed ; The F reconstructed is the feature matrix after inverse reconstruction; S543, data decompression; Use the inverse transformation matrix T -1 Decompress the data, and the decompressed data is recorded as F compressed : ; S544, data decryption; The decompressed data is decrypted by the decryption algorithm, and the decrypted data matrix is ​​recorded as F decrypted : ; S545, data reverse verification; ; in, () is the inverse check function, F reconstructed is the reconstructed data matrix.

[0013] Optionally, the data analysis and anomaly detection specifically include: Use adaptive transformation methods to construct the feature space of the data: ; Among them, F transformed is the transformed feature matrix; T is the adaptive transformation matrix; Use the weighted locality distance metric to assess the degree of abnormality of a data point: ; Among them, D(x i ) is the abnormality measure of the i-th data point; x i is the transformation feature matrix of the i-th data point; x j is the transformed feature vector of the jth data point; w ij is the weighting coefficient; Set a dynamic threshold T d Used to determine abnormal data points: ; Where m(D) is the mean of the weighted local distances of all data points; s(D) is the standard deviation of the weighted local distances of all data points; α is a hyperparameter that controls the sensitivity of the threshold; According to the threshold T d Mark anomalous data points; Suppose there is a label vector A whose elements are 1 or 0, indicating whether the data point is an anomaly: ; Among them, A i is the i-th element in the tag vector; 1 indicates abnormality; 0 indicates normality; Use the local pattern-based repair method to repair abnormal data, the abnormal data point x i Repair is performed using the following repair algorithm: ; Among them, x repaired i is the repaired data point; N i For data point x i The field contains x i Similar normal data points; w ij is the weight calculated based on the similarity between data points.

[0014] A system for implementing the electric energy metering information transmission method, comprising: Voltage measurement module: used to measure voltage signals; Current sensor: used to measure current signal; Power calculation module: used to calculate real-time power signals; Network status monitoring module: monitors the network status in real time and obtains the current delay, bandwidth and packet loss.

[0015] The present invention has the following beneficial effects: 1. Through data acquisition and preprocessing, the problem of complex electric energy signals and insufficient feature expression ability is solved, and the signal expression and analysis ability is effectively improved. The voltage measurement module, current sensor and power calculation module are used to collect voltage signals, current signals and real-time power signals respectively, and they are organized into time series to form a matrix. Subsequently, the matrix is ​​normalized to solve the problem that signals with different dimensions and amplitude ranges are difficult to process uniformly. At the same time, the nonlinear feature expression ability of the signal is enhanced through nonlinear transformation (using hyperbolic tangent and sine functions combined with dynamically changing parameters), laying a high-quality foundation for subsequent feature extraction and analysis. Through feature extraction and compression, and data sparsification steps, the problems of high data dimension and low transmission efficiency are solved, and the pressure of data storage and transmission is effectively reduced. In the process of feature extraction and compression, important feature information in the power signal is extracted, and redundant information is discarded. Subsequently, the dimension and redundancy of the data are further reduced through sparsification processing, the volume of data to be transmitted is reduced, the data transmission efficiency is optimized, and the system's adaptability to large-scale users is improved. Through the data transmission step, the problems of data loss and unstable transmission that may occur during the transmission of power information are solved, and the reliability of data transmission is improved. Using data packets that have been feature extracted and sparsified, combined with dynamic transmission strategies, such as adjusting the frequency and priority of data transmission based on network status, effectively reduce The risk of network congestion is reduced. At the same time, the verification mechanism in the transmission process ensures the integrity and accuracy of the data. Through the data decoding and reconstruction steps, the problem of insufficient reconstruction accuracy of data features under high compression rate is solved, ensuring the availability and accuracy of the data after decoding. In data decoding and reconstruction, the feature information extracted during the compression process is used to restore the original signal features through the inverse reconstruction algorithm. This process, combined with the verification mechanism, effectively improves the reconstruction accuracy of the decoded data and provides reliable basic data for subsequent analysis. Through the data analysis and anomaly detection steps, the problem of difficult detection of abnormal values ​​in electric energy metering data and insufficient efficiency of real-time analysis is solved, and the intelligence level of the system is improved. By using the extracted high-quality signal features and combining the dynamic analysis algorithm to process and detect anomalies in real time, abnormal conditions in the electric energy metering process, such as signal noise, abnormal power fluctuations, etc., can be quickly identified, effectively reducing the false alarm and missed alarm rates, and enhancing the system's adaptability to complex electric energy environments.

[0016] 2. By extracting the time domain and frequency domain features of each signal, the limitation that a single-dimensional feature is difficult to fully reflect the signal characteristics is solved, and the comprehensiveness and accuracy of the signal description are effectively improved. In the feature extraction process, the time domain features of the signal are calculated to fully reflect the changing trend of the signal in the time dimension. At the same time, the frequency distribution characteristics of the signal are revealed through frequency domain feature analysis. The combination of time domain and frequency domain features not only retains the time dynamic information of the signal, but also enhances the ability to characterize the characteristics of the signal periodicity, energy distribution, etc., laying the foundation for subsequent data compression and analysis. By performing principal component analysis on the extracted features, the problems of high redundancy and high computational complexity of high-dimensional feature data are solved, the dimension of the data is effectively reduced, and the computational efficiency is optimized. Principal component analysis extracts the main feature components through singular value decomposition, and the compressed feature matrix only retains the most representative part of the signal. This step not only reduces the redundant information of the data, but also improves the storage and transmission efficiency, while avoiding the interference of too many irrelevant features on the analysis results. By activating the compressed feature vector, the problem of insufficient signal feature expression ability is solved, and the nonlinear expression ability of the feature is effectively enhanced. The use of the hyperbolic tangent function to activate the eigenvector matrix further enhances the nonlinear expression of the signal. This process can highlight the dynamic characteristics and weak features hidden in complex signals, making the signal features more distinguishable and providing a more reliable data basis for subsequent analysis and anomaly detection.

[0017] 3. By sparse processing the compressed features, the problem of high data redundancy is solved and the data transmission efficiency is effectively improved. The sparse processing uses a formula to sparse the feature matrix, where the sparse control parameter and the sparse index β are used to adjust the sparse strength and sparse effect. A larger l value makes smaller features more compressed, and β>1 enhances sparsity. This process significantly reduces irrelevant or redundant feature information in the data and reduces the complexity of subsequent processing and transmission. By filtering eigenvalues ​​based on thresholds, the problem of insufficient feature screening accuracy is solved and the quality of the final feature matrix is ​​optimized. The sparse features are filtered using a conditional filtering formula, where q is the threshold, ensuring that only eigenvalues ​​that contribute significantly to signal expression are retained. Setting unimportant features to zero effectively reduces the data volume while retaining important feature information, improving the transmission efficiency and analysis accuracy of the feature matrix. By outputting the final sparse feature matrix, the problem of reduced quality of compressed data in traditional methods is solved, and the reliability and effectiveness of feature transmission are significantly improved. The final sparse feature matrix contains the important eigenvalues ​​after filtering, reducing the dimension and redundant information of the original feature matrix, while retaining the key features of the signal to the maximum extent. This design not only optimizes the transmission efficiency, but also ensures the high restoration of compressed features during the decoding and reconstruction process, meeting the real-time and accuracy requirements of data transmission.

[0018] 4. Through the feature coding matrix generation step, the security and integrity issues after data feature extraction are solved, and the reliability of data transmission is improved. The sparse matrix is ​​extracted from the original signal matrix using the sparse feature extraction formula. Subsequently, the feature matrix is ​​encrypted and integrity checked through the encryption coding function. The check function ensures that the data has not been tampered with during transmission, thereby enhancing the security and integrity of the data. Through the network status monitoring step, the adaptability problem of dynamic changes in network transmission is solved, ensuring the efficiency and stability of data transmission. Real-time monitoring of network delay, bandwidth and packet loss rate can obtain the status information of the transmission channel in time, providing a basis for subsequent adaptive adjustment of the transmission rate, thereby reducing the data loss and low transmission efficiency caused by network status fluctuations. Through the transmission rate calculation step, the data congestion problem caused by network status fluctuations is solved, and the transmission efficiency is improved. The rate adjustment formula is used to dynamically adjust the transmission rate according to network delay, bandwidth and packet loss rate. This method ensures that the rate is reduced when the network is congested and data loss is reduced; the rate is increased when the network is good, improving the transmission efficiency. Through the data packet generation step, the problem of data organization and efficient packaging is solved, and the flexibility of the transmission process is improved. The coding feature matrix is ​​divided into multiple small data packets according to the maximum data packet length, and the integrity of the last data packet is ensured by filling the check bit. This division mechanism optimizes the adaptability of data in different transmission links and reduces packet loss or data missing. Through the data packaging and encoding steps, the error checking problem of data packets during transmission is solved, and the accuracy of data transmission is improved. The redundant check bit function is used to add redundant check bits to each data packet. This method enables the receiving end to quickly detect and locate the integrity problem of the data packet by adding data redundancy information, reducing the number of retransmissions caused by data packet errors. Through the data sending and verification steps, the error detection and recovery problems in the data transmission process are solved, and the reliability of the system is enhanced. The sending end sends data packets at a dynamically adjusted rate, and the receiving end uses the integrity check formula to check the data integrity in real time. If the check fails, the data packet is automatically retransmitted. This mechanism effectively reduces the communication interruption problem caused by data packet damage or loss.

[0019] 5. Through the data receiving and verification steps, the problem that data may be tampered or lost during transmission is solved, and the integrity and reliability of the received data are improved. At the receiving end, each data packet is checked for integrity, and the integrity of the data packet is verified using a verification formula. If the check bit is 0, it means that the data has not been tampered with and is completely received; otherwise, the data packet is immediately requested to be retransmitted. This mechanism effectively reduces the storage and subsequent processing of erroneous data, ensuring the accuracy of the data and the reliability of the transmission link. Through the data decryption step, the problem that the encrypted data cannot be used directly is solved, and the operability of the data is restored. The decryption formula is used, combined with the inverse matrix and bias term of the verification function, to decrypt the encoded features in the data packet. This process not only restores the original features of the data, but also retains the integrity and expression ability of the features, thus laying the foundation for subsequent data reconstruction. Through the data reconstruction and splicing steps, the problem of incomplete feature matrix caused by data packet fragmentation is solved, and the original structure of the overall feature matrix is ​​restored. All decrypted data packets are spliced ​​into a complete feature matrix in sequence using the splicing operation. This process eliminates the discontinuity problem caused by data fragmentation, ensures the consistency and integrity of the decrypted data, and provides accurate input for subsequent data analysis. Through the data analysis and reconstruction steps, the problem that the encoded data features are difficult to use directly for analysis is solved, and the feature information before sparseness is restored. Through the inverse reconstruction function, the decrypted feature matrix is ​​converted back to a sparse feature matrix. This inverse process restores the original expression of the features, ensures the sparsity and accuracy of the data, and thus provides high-quality basic data for subsequent data analysis and anomaly detection.

[0020] 6. Through the input variable definition step, the problem of unknown variable sources in the reverse reconstruction process is solved, and the scope and meaning of the required input data are clarified. In the input stage, the reverse reconstruction function clearly requires the input of the coded data matrix, the check function used in the encoding process, and the data packet. This design ensures that the source of each variable is clear, provides a clear basis for subsequent reverse calculations, and effectively reduces errors and uncertainties in the calculation process. Through the output variable definition step, the problem of fuzzy goals in the reconstruction process is solved, and the output results of the reverse reconstruction are clarified. The output variable is the feature matrix after reverse reconstruction, which is specifically used to restore the integrity of the original signal characteristics. This step sets a clear goal for the entire reverse reconstruction process, effectively ensuring the consistency of the data processing flow and the practicality of the output. Through the data decompression step, the problem of complicated data structure caused by coding compression is solved, and partial restoration of feature data is achieved. Use the inverse transformation matrix to decompress the coded data and restore the compressed data to F compressedThis step restores part of the original structure of the feature data through reverse mapping, reduces the complexity introduced by the compression process, and provides complete basic data for subsequent decryption operations. Through the data decryption step, the problem that the encrypted data cannot be used directly is solved, and the usability of the feature matrix is ​​restored. compressed Decrypt and generate F decrypted . This process uses a decryption formula to restore the true information of the feature matrix, effectively solving the problem of opacity of encrypted data and ensuring data security and operability. Through the data anti-verification step, the consistency problem of data verification and recovery during transmission is solved, and the integrity and reliability of the reconstructed data are improved. The data is verified through the anti-verification function to ensure that the reconstructed data matrix meets the integrity and consistency requirements of the original feature matrix. This step performs a final verification of the integrity of the reconstructed data, effectively reducing errors caused by data loss or tampering, and providing a reliable basis for subsequent data analysis.

[0021] 7. By using the adaptive transformation method to construct the feature space of the data, the problem of difficulty in expressing abnormal features caused by the complexity of data distribution is solved, and flexible representation of data features is achieved. The adaptive transformation matrix is ​​adjusted according to the dynamic characteristics of the data, so that the transformed feature matrix can better characterize the intrinsic characteristics of the data. This step improves the ability to separate data in the feature space and provides a more accurate basis for subsequent anomaly detection. By using the weighted local distance metric, the problem of traditional distance metric methods ignoring local structures in anomaly detection is solved, and the detection accuracy is improved. This step uses adaptive weighting coefficients to emphasize local importance and effectively captures the abnormal characteristics of data points in the local neighborhood. Compared with the global distance metric, the weighted local distance is more sensitive to local changes in data and can accurately evaluate the degree of abnormality of data points. By setting the dynamic threshold, the problem that the static threshold is difficult to adapt to the dynamic data distribution is solved, and the flexibility of anomaly detection is improved. The dynamic threshold is calculated based on the mean and standard deviation of the weighted local distance, combined with hyperparameters to adjust the sensitivity. This design enables the detection system to automatically adjust the judgment criteria according to the data distribution, enhancing adaptability. By marking vectors, the problem of difficulty in automatic marking of abnormal data is solved, and rapid classification of data points is achieved. The data points are divided into normal points and abnormal points using the marker vector, which directly gives the result of data anomaly detection. This step is fast and efficient, which facilitates subsequent data repair and further analysis. The repair method based on local patterns solves the problem of data integrity degradation caused by direct deletion of abnormal data and restores the validity of the data. The repair method uses the normal data points in the neighborhood of the abnormal point and its weighted coefficients to reconstruct the abnormal data through local information. This step not only retains the overall structure of the data, but also reduces the impact of abnormal data on the analysis results, and improves the accuracy of data repair. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] Example, see Figure 1 , an electric energy metering information transmission method, comprising: S1, data collection and preprocessing; Use the voltage measurement module to measure the voltage signal, recorded as V(t); Use a current sensor to measure the current signal, recorded as I(t); Use the power calculation module to calculate the real-time power signal, denoted as P(t); Where t is the timestamp; The voltage signal, current signal and power signal are organized in time series to form a matrix: ; Wherein, X(t) is a matrix containing voltage signal, current signal and power signal; Normalize the signal: ; Among them, X ij is the jth value of the ith signal in the matrix X(t); m i is the mean of the ith signal; s i is the standard deviation of the ith signal; Use nonlinear transformation to enhance the expressiveness of signal features: ; Among them, α ij , β ij and g ij is the dynamic change parameter of the signal; tanh() and sin() are hyperbolic tangent and sine functions respectively, which are used for nonlinear transformation; S2, feature extraction and compression; S3, data compression and sparsification; S4, data transmission; S5, data decoding and reconstruction; S6. Data analysis and anomaly detection.

[0025] Through data acquisition and preprocessing, the problems of complex electric energy signals and insufficient feature expression capabilities were solved, and the signal expression and analysis capabilities were effectively improved. The voltage measurement module, current sensor and power calculation module were used to collect voltage signals, current signals and real-time power signals respectively, and they were organized into time series to form a matrix. Subsequently, the matrix was normalized to solve the problem that signals with different dimensions and amplitude ranges were difficult to process uniformly. At the same time, the nonlinear feature expression capabilities of the signal were enhanced through nonlinear transformation (using hyperbolic tangent and sine functions combined with dynamically changing parameters), laying a high-quality foundation for subsequent feature extraction and analysis.

[0026] Through feature extraction and compression, and data sparsification steps, the problem of high data dimension and low transmission efficiency is solved, effectively reducing the pressure of data storage and transmission. In the process of feature extraction and compression, important feature information in the power signal is extracted and redundant information is discarded. Subsequently, the dimension and redundancy of the data are further reduced through sparsification processing, which reduces the volume of data to be transmitted, optimizes data transmission efficiency, and improves the system's adaptability to large-scale users.

[0027] Through the data transmission step, the data loss and unstable transmission problems that may occur during the transmission of power information are solved, and the reliability of data transmission is improved. The data packets that have been feature extracted and sparsely processed are used, combined with dynamic transmission strategies, such as adjusting the frequency and priority of data transmission based on the network status, effectively reducing the risk of network congestion. At the same time, the verification mechanism during the transmission process ensures the integrity and accuracy of the data.

[0028] Through the data decoding and reconstruction steps, the problem of insufficient reconstruction accuracy of data features under high compression rates is solved, ensuring the availability and accuracy of the data after decoding. In data decoding and reconstruction, the feature information extracted during the compression process is used to restore the original signal features through the inverse reconstruction algorithm. This process, combined with the verification mechanism, effectively improves the reconstruction accuracy of the decoded data and provides reliable basic data for subsequent analysis.

[0029] Through data analysis and anomaly detection steps, the problem of difficult detection of abnormal values ​​in power metering data and insufficient efficiency of real-time analysis is solved, and the intelligence level of the system is improved. By using the extracted high-quality signal features and combining dynamic analysis algorithms to process data in real time and detect anomalies, abnormal conditions in the power metering process, such as signal noise and abnormal power fluctuations, can be quickly identified, effectively reducing the false alarm and missed alarm rates and enhancing the system's adaptability to complex power environments.

[0030] The feature extraction and compression specifically include: Extract time and frequency domain features of each signal: ; Among them, f i is the time domain feature of the i-th signal; T is the time length of the signal; Perform principal component analysis on the extracted features: ; Among them, U, S and V are matrices after SVD decomposition; F' is the compressed eigenvector matrix; Activate the compressed feature vector: ; Among them, F is the feature vector matrix; tanh() is the hyperbolic tangent function, which is used to enhance the nonlinear expression ability of the feature.

[0031] By extracting the time domain and frequency domain features of each signal, the limitation that a single-dimensional feature is difficult to fully reflect the signal characteristics is solved, and the comprehensiveness and accuracy of the signal description are effectively improved. In the feature extraction process, the time domain features of the signal are calculated to fully reflect the changing trend of the signal in the time dimension. At the same time, the frequency distribution characteristics of the signal are revealed through frequency domain feature analysis. The combination of time domain and frequency domain features not only retains the time dynamic information of the signal, but also enhances the ability to characterize the characteristics of the signal periodicity, energy distribution, etc., laying the foundation for subsequent data compression and analysis. By performing principal component analysis on the extracted features, the problems of high redundancy and high computational complexity of high-dimensional feature data are solved, the dimension of the data is effectively reduced, and the computational efficiency is optimized. Principal component analysis extracts the main feature components through singular value decomposition, and the compressed feature matrix only retains the most representative part of the signal. This step not only reduces the redundant information of the data, but also improves the storage and transmission efficiency, while avoiding the interference of too many irrelevant features on the analysis results. By activating the compressed feature vector, the problem of insufficient signal feature expression ability is solved, and the nonlinear expression ability of the feature is effectively enhanced. The use of the hyperbolic tangent function to activate the eigenvector matrix further enhances the nonlinear expression of the signal. This process can highlight the dynamic characteristics and weak features hidden in complex signals, making the signal features more distinguishable and providing a more reliable data basis for subsequent analysis and anomaly detection.

[0032] The data compression and sparseness specifically include: Sparse the compressed features to reduce data redundancy and improve transmission efficiency: ; Among them, F' i is the i-th value in the feature matrix; l is the sparsification control parameter, which is used to adjust the strength of sparsification. A larger l value will compress more small features; β is the sparsification index, and β>1 is used to enhance sparsity; Will satisfy the condition As important features; otherwise, as unimportant features, and set the unimportant features to 0: ; Among them, F final i is the feature value after screening; θ is the threshold, which is used to determine whether the feature is retained; Output the final sparse feature matrix F final , this matrix will be used for transmission.

[0033] By sparse processing the compressed features, the problem of high data redundancy is solved and the data transmission efficiency is effectively improved. The sparse processing sparses the feature matrix through a formula, where the sparsification control parameter and the sparsity index β are used to adjust the sparsification strength and sparsification effect. A larger l value makes smaller features more compressed, and β>1 enhances sparsity. This process significantly reduces irrelevant or redundant feature information in the data and reduces the complexity of subsequent processing and transmission. By filtering eigenvalues ​​based on thresholds, the problem of insufficient feature screening accuracy is solved and the quality of the final feature matrix is ​​optimized. The sparse features are filtered using a conditional filtering formula, where q is the threshold, ensuring that only eigenvalues ​​that contribute significantly to signal expression are retained. Setting unimportant features to zero effectively reduces the data volume while retaining important feature information, improving the transmission efficiency and analysis accuracy of the feature matrix. By outputting the final sparse feature matrix, the problem of reduced quality of compressed data in traditional methods is solved, and the reliability and effectiveness of feature transmission are significantly improved. The final sparse feature matrix contains the important eigenvalues ​​after filtering, reducing the dimension and redundant information of the original feature matrix, while maximally retaining the key features of the signal. This design not only optimizes the transmission efficiency, but also ensures the high restoration of compressed features during the decoding and reconstruction process, meeting the real-time and accuracy requirements of data transmission.

[0034] The data transmission specifically includes: S41, generate feature encoding matrix F encoded ; From the original input signal matrix X(t), the sparse matrix F is obtained by sparse feature extraction algorithm sparse : ; Where X(t) is the signal matrix; A is the feature basis matrix; l is the sparsity regularization parameter; F sparse Perform encryption encoding to generate the encoding feature matrix F encoded : ; Wherein, e() is the encryption mapping function; () is a feature verification function to ensure data integrity, specifically: ; Where W1 is the weight matrix of the verification function; b1 is the bias vector; S42, network status monitoring; Monitor the network status in real time to obtain the current delay Dt(t), bandwidth B(t) and packet loss P(t); S43, transmission rate calculation; According to the network status, the data transmission rate R(t) is adaptively adjusted: ; Among them, R min is the minimum transmission rate; Dt(t) is the delay difference of the current network; t max is the maximum delay allowed by the system; t th is the delay threshold; α, β and g are parameters for adjusting the transmission rate; S44, generating a data packet; Get the length of the maximum data packet transmitted over the network, recorded as L max ; F encoded Divided into multiple packets: ; Among them, P i is the i-th data packet; i represents the index of the data packet; L max Indicates the maximum length of each data packet; Each column of the data packet corresponds to a characteristic component, and each row of the data packet corresponds to a signal at a specific time step; If the last data packet is less than L max If the length is , the check bit is filled with 0; S45, data packaging and encoding; F encoded Divide into multiple small data packets P according to the transmission rate R(t) i , and add redundant check bits to each data packet ; in It is the redundant check bit function of the data packet, which is used to check the integrity of the data packet. Specifically: ; Among them, P i,k For data packet P i The kth data unit in w kis the weight coefficient, which is related to the length of the data packet; mod(•,2) is the modulo 2 operation, which is used to generate the binary check bit; S46, data transmission and verification; Send P at rate R(t) i , verify data integrity in real time at the receiving end: ; If the check fails, the data is retransmitted.

[0035] Through the feature coding matrix generation step, the security and integrity issues after data feature extraction are solved, and the reliability of data transmission is improved. The sparse feature extraction formula is used to extract the sparse matrix from the original signal matrix. Subsequently, the feature matrix is ​​encrypted and integrity checked through the encryption coding function. The check function ensures that the data has not been tampered with during transmission, thereby enhancing the security and integrity of the data. Through the network status monitoring step, the adaptability problem of dynamic changes in network transmission is solved, and the efficiency and stability of data transmission are ensured. Real-time monitoring of network delay, bandwidth and packet loss rate can obtain the status information of the transmission channel in time, providing a basis for subsequent adaptive adjustment of the transmission rate, thereby reducing the data loss and low transmission efficiency caused by network status fluctuations. Through the transmission rate calculation step, the data congestion problem caused by network status fluctuations is solved, and the transmission efficiency is improved. The rate adjustment formula is used to dynamically adjust the transmission rate according to the network delay, bandwidth and packet loss rate. This method ensures that the rate is reduced when the network is congested and data loss is reduced; the rate is increased when the network is good and the transmission efficiency is improved. Through the data packet generation step, the problem of data organization and efficient packaging is solved, and the flexibility of the transmission process is improved. The coding feature matrix is ​​divided into multiple small data packets according to the maximum data packet length, and the integrity of the last data packet is ensured by filling the check bit. This division mechanism optimizes the adaptability of data in different transmission links and reduces packet loss or data missing. Through the data packaging and encoding steps, the error checking problem of data packets during transmission is solved, and the accuracy of data transmission is improved. The redundant check bit function is used to add redundant check bits to each data packet. This method enables the receiving end to quickly detect and locate the integrity problem of the data packet by adding data redundancy information, reducing the number of retransmissions caused by data packet errors. Through the data sending and verification steps, the error detection and recovery problems in the data transmission process are solved, and the reliability of the system is enhanced. The sending end sends data packets at a dynamically adjusted rate, and the receiving end uses the integrity check formula to check the data integrity in real time. If the check fails, the data packet is automatically retransmitted. This mechanism effectively reduces the communication interruption problem caused by data packet damage or loss.

[0036] The data decoding and reconstruction specifically include: S51, data reception and verification; For each received packet P i , first do a sanity check: ; Among them, P i is the i-th data packet received; The check digit generated by the check function; like If it is 0, it means that the data packet has not been tampered with and the data is complete; otherwise, the receiving end requests to retransmit the data packet; S52, data decryption; Use the data decryption formula to decrypt the received data packet P i To decrypt: ; Among them, F decoded i is the decrypted data matrix; Decrypt() is the decryption function, specifically: ; Among them, b1 is the bias term; W -1 1 is the inverse matrix of the verification function, which ensures the recovery of features during the decryption process.

[0037] S53, data reconstruction and splicing; All decrypted data fragments F decoded i Splice and reconstruct the complete feature matrix F decoded : ; Among them, ∪ represents the concatenation operation, which concatenates the decryption results of all data packets into a complete feature matrix in order; S54, data analysis and reconstruction; Restore the original data feature F through inverse transformation sparse : ; Among them, R() represents the inverse reconstruction function, which restores the decrypted feature matrix to the original sparse feature matrix.

[0038] Through the data receiving and verification steps, the problem that data may be tampered or lost during transmission is solved, and the integrity and reliability of the received data are improved. At the receiving end, each data packet is checked for integrity, and the integrity of the data packet is verified using a check formula. If the check bit is 0, it means that the data has not been tampered with and is completely received; otherwise, the data packet is immediately requested to be retransmitted. This mechanism effectively reduces the storage and subsequent processing of erroneous data, ensuring the accuracy of the data and the reliability of the transmission link. Through the data decryption step, the problem that the encrypted data cannot be used directly is solved, and the operability of the data is restored. The decryption formula is used, combined with the inverse matrix and bias term of the check function, to decrypt the encoded features in the data packet. This process not only restores the original features of the data, but also retains the integrity and expression ability of the features, thus laying the foundation for subsequent data reconstruction. Through the data reconstruction and splicing steps, the problem of incomplete feature matrix caused by data packet fragmentation is solved, and the original structure of the overall feature matrix is ​​restored. All decrypted data packets are spliced ​​into a complete feature matrix in sequence using the splicing operation. This process eliminates the discontinuity problem caused by data fragmentation, ensures the consistency and integrity of the decrypted data, and provides accurate input for subsequent data analysis. Through the data analysis and reconstruction steps, the problem that the encoded data features are difficult to use directly for analysis is solved, and the feature information before sparseness is restored. Through the inverse reconstruction function, the decrypted feature matrix is ​​converted back to a sparse feature matrix. This inverse process restores the original expression of the features, ensures the sparsity and accuracy of the data, and thus provides high-quality basic data for subsequent data analysis and anomaly detection.

[0039] The inverse reconstruction function specifically includes: The design of the reverse reconstruction function R() is as follows: S541, input variables; Input variables include F encoded , (), and P i ; The F encoded is the data matrix after encoding; () is the verification function used in the encoding process; P i For data packets; S542, output variable; Output variable F reconstructed ; The F reconstructed is the feature matrix after inverse reconstruction; S543, data decompression; Use the inverse transformation matrix T -1 Decompress the data, and the decompressed data is recorded as F compressed : ; S544, data decryption; The decompressed data is decrypted by the decryption algorithm, and the decrypted data matrix is ​​recorded as F decrypted : ; S545, data reverse verification; ; in, () is the inverse check function, F reconstructed is the reconstructed data matrix.

[0040] Through the input variable definition step, the problem of unknown variable sources in the reverse reconstruction process is solved, and the scope and meaning of the required input data are clarified. In the input stage, the reverse reconstruction function clearly requires the input of the coded data matrix, the check function used in the encoding process, and the data packet. This design ensures that the source of each variable is clear, provides a clear basis for subsequent reverse calculations, and effectively reduces errors and uncertainties in the calculation process. Through the output variable definition step, the problem of fuzzy reconstruction process goals is solved, and the output results of reverse reconstruction are clarified. The output variable is the feature matrix after reverse reconstruction, which is specifically used to restore the integrity of the original signal characteristics. This step sets a clear goal for the entire reverse reconstruction process, effectively ensuring the consistency of the data processing flow and the practicality of the output. Through the data decompression step, the problem of complicated data structure caused by coding compression is solved, and partial restoration of feature data is achieved. The coded data is decompressed using the inverse transformation matrix to restore the compressed data to F compressed This step restores part of the original structure of the feature data through reverse mapping, reduces the complexity introduced by the compression process, and provides complete basic data for subsequent decryption operations. Through the data decryption step, the problem that the encrypted data cannot be used directly is solved, and the usability of the feature matrix is ​​restored. compressed Decrypt and generate F decrypted . This process uses a decryption formula to restore the true information of the feature matrix, effectively solving the problem of opacity of encrypted data and ensuring data security and operability. Through the data anti-verification step, the consistency problem of data verification and recovery during transmission is solved, and the integrity and reliability of the reconstructed data are improved. The data is verified through the anti-verification function to ensure that the reconstructed data matrix meets the integrity and consistency requirements of the original feature matrix. This step performs a final verification of the integrity of the reconstructed data, effectively reducing errors caused by data loss or tampering, and providing a reliable basis for subsequent data analysis.

[0041] The data analysis and anomaly detection specifically include: Use adaptive transformation methods to construct the feature space of the data: ; Among them, F transformed is the transformed feature matrix; T is the adaptive transformation matrix; Use the weighted locality distance metric to assess the degree of abnormality of a data point: ; Among them, D(x i ) is the abnormality measure of the i-th data point; x i is the transformation feature matrix of the i-th data point; x j is the transformed feature vector of the jth data point; w ij is the weighting coefficient used to measure the point x i With x j The local importance between Set a dynamic threshold T d Used to determine abnormal data points: ; Where m(D) is the mean of the weighted local distances of all data points; s(D) is the standard deviation of the weighted local distances of all data points; α is a hyperparameter that controls the threshold sensitivity and can adjust the strictness of anomaly detection; According to the threshold T d Mark anomalous data points; Suppose there is a label vector A whose elements are 1 or 0, indicating whether the data point is an anomaly: ; Among them, A i is the i-th element in the tag vector; 1 indicates abnormality; 0 indicates normality; Use the local pattern-based repair method to repair abnormal data, the abnormal data point x i Repair is performed using the following repair algorithm: ; Among them, x repaired i is the repaired data point; N i For data point x i The field contains x i Similar normal data points; w ij is the weight calculated based on the similarity between data points.

[0042] By using the adaptive transformation method to construct the feature space of the data, the problem of difficulty in expressing abnormal features caused by the complexity of data distribution is solved, and flexible representation of data features is achieved. The adaptive transformation matrix is ​​adjusted according to the dynamic characteristics of the data, so that the transformed feature matrix can better characterize the intrinsic characteristics of the data. This step improves the ability to separate data in the feature space and provides a more accurate basis for subsequent anomaly detection. By using the weighted local distance metric, the problem of traditional distance metric methods ignoring local structures in anomaly detection is solved, and the detection accuracy is improved. This step uses adaptive weighting coefficients to emphasize local importance and effectively captures the abnormal characteristics of data points in the local neighborhood. Compared with the global distance metric, the weighted local distance is more sensitive to local changes in data and can accurately evaluate the degree of abnormality of data points. By setting the dynamic threshold, the problem that the static threshold is difficult to adapt to the dynamic data distribution is solved, and the flexibility of anomaly detection is improved. The dynamic threshold is calculated based on the mean and standard deviation of the weighted local distance, combined with hyperparameters to adjust the sensitivity. This design enables the detection system to automatically adjust the judgment criteria according to the data distribution, enhancing adaptability. By using the label vector, the problem of difficulty in automatic labeling of abnormal data is solved, and rapid classification of data points is achieved. The data points are divided into normal points and abnormal points using the marker vector, which directly gives the result of data anomaly detection. This step is fast and efficient, which facilitates subsequent data repair and further analysis. The repair method based on local patterns solves the problem of data integrity degradation caused by direct deletion of abnormal data and restores the validity of the data. The repair method uses the normal data points in the neighborhood of the abnormal point and its weighted coefficients to reconstruct the abnormal data through local information. This step not only retains the overall structure of the data, but also reduces the impact of abnormal data on the analysis results, and improves the accuracy of data repair.

[0043] This embodiment also provides a system for the electric energy metering information transmission method, including: Voltage measurement module: used to measure voltage signals; Current sensor: used to measure current signal; Power calculation module: used to calculate real-time power signals; Network status monitoring module: monitors the network status in real time and obtains the current delay, bandwidth and packet loss.

[0044] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0045] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for transmitting electric energy metering information, characterized in that: include: S1, data collection and preprocessing; Use the voltage measurement module to measure the voltage signal, recorded as V(t); Use a current sensor to measure the current signal, recorded as I(t); Use the power calculation module to calculate the real-time power signal, denoted as P(t); Where t is the timestamp; The voltage signal, current signal and power signal are organized in time series to form a matrix: ； Wherein, X(t) is a matrix containing voltage signal, current signal and power signal; Normalize the signal: ； Among them, X ij is the jth value of the ith signal in the matrix X(t); m i is the mean of the ith signal; s i is the standard deviation of the ith signal; Use nonlinear transformation to enhance the expressiveness of signal features: ； Among them, α ij , β ij and g ij is the dynamic change parameter of the signal; tanh() and sin() are hyperbolic tangent and sine functions respectively, which are used for nonlinear transformation; S2, feature extraction and compression; S3, data compression and sparsification; S4, data transmission; S5, data decoding and reconstruction; S6. Data analysis and anomaly detection.

2. The method for transmitting electric energy metering information according to claim 1, characterized in that: The feature extraction and compression specifically include: Extract time and frequency domain features of each signal: ； Among them, f i is the time domain feature of the i-th signal; T is the time length of the signal; Perform principal component analysis on the extracted features: ； Among them, U, S and V are matrices after SVD decomposition; F' is the compressed eigenvector matrix; Activate the compressed feature vector: ； Among them, F is the eigenvector matrix; tanh() is the hyperbolic tangent function.

3. The method for transmitting electric energy metering information according to claim 2, characterized in that: The data compression and sparseness specifically include: Sparse the compressed features: ； Among them, F' i is the i-th value in the feature matrix; l is the sparsification control parameter, which is used to adjust the strength of sparsification; β is the sparsification index, and β>1 is used to enhance sparsity; Will satisfy the condition As important features; otherwise, as unimportant features, and set the unimportant features to 0: ； Among them, F final i is the feature value after screening; θ is the threshold, which is used to determine whether the feature is retained; Output the final sparse feature matrix F final , this matrix will be used for transmission.

4. The method for transmitting electric energy metering information according to claim 3, characterized in that: The data transmission specifically includes: S41, generate feature encoding matrix F encoded ; From the original input signal matrix X(t), the sparse matrix F is obtained by sparse feature extraction algorithm sparse : ； Where X(t) is the signal matrix; A is the feature basis matrix; l is the sparsity regularization parameter; F sparse Perform encryption encoding to generate the encoding feature matrix F encoded : ； Wherein, e() is the encryption mapping function; () is the feature verification function, specifically: ； Where W1 is the weight matrix of the verification function; b1 is the bias vector; S42, network status monitoring; Monitor the network status in real time to obtain the current delay Dt(t), bandwidth B(t) and packet loss P(t); S43, transmission rate calculation; According to the network status, the data transmission rate R(t) is adaptively adjusted: ； Among them, R min is the minimum transmission rate; Dt(t) is the delay difference of the current network; t max is the maximum delay allowed by the system; t th is the delay threshold; α, β and g are parameters for adjusting the transmission rate; S44, generating a data packet; Get the length of the maximum data packet transmitted over the network, recorded as L max ; F encoded Divided into multiple packets: ； Among them, P i is the i-th data packet; i represents the index of the data packet; L max Indicates the maximum length of each data packet; Each column of the data packet corresponds to a characteristic component, and each row of the data packet corresponds to a signal at a specific time step; If the last data packet is less than L max If the length is , the check bit is filled with 0; S45, data packaging and encoding; F encoded Divide into multiple small data packets P according to the transmission rate R(t) i , and add redundant check bits to each data packet ; in It is the redundant check bit function of the data packet, specifically: ； Among them, P i,k For data packet P i The kth data unit in w k is the weight coefficient, which is related to the length of the data packet; mod(•,2) is the modulo 2 operation, which is used to generate the binary check bit; S46, data transmission and verification; Send P at rate R(t) i , verify data integrity in real time at the receiving end: ； If the check fails, the data is retransmitted.

5. The method for transmitting electric energy metering information according to claim 4, characterized in that: The data decoding and reconstruction specifically include: S51, data reception and verification; For each received packet P i , first do a sanity check: ； Among them, P i is the i-th data packet received; The check digit generated by the check function; like If it is 0, it means that the data packet has not been tampered with and the data is complete; otherwise, the receiving end requests to retransmit the data packet; S52, data decryption; Use the data decryption formula to decrypt the received data packet P i To decrypt: ； Among them, F decoded i is the decrypted data matrix; Decrypt() is the decryption function, specifically: ； Among them, b1 is the bias term; W -1 1 is the inverse matrix of the check function. 6.S53, data reconstruction and splicing; All decrypted data fragments F decoded i Splice and reconstruct the complete feature matrix F decoded : ； in, ∪ represents the concatenation operation, which concatenates the decryption results of all data packets into a complete feature matrix in order; S54, data analysis and reconstruction; Restore the original data feature F through inverse transformation sparse : ； Among them, R() represents the inverse reconstruction function, which restores the decrypted feature matrix to the original sparse feature matrix.

7. The method for transmitting electric energy metering information according to claim 5, characterized in that: The inverse reconstruction function specifically includes: The design of the reverse reconstruction function R() is as follows: S541, input variables; Input variables include F encoded , (), and P i ; The F encoded is the data matrix after encoding; () is the verification function used in the encoding process; P i For data packets; S542, output variable; Output variable F reconstructed ; The F reconstructed is the feature matrix after inverse reconstruction; S543, data decompression; Use the inverse transformation matrix T -1 Decompress the data, and the decompressed data is recorded as F compressed : ； S544, data decryption; The decompressed data is decrypted by the decryption algorithm, and the decrypted data matrix is ​​recorded as F decrypted : ； S545, data reverse verification; ； in, () is the inverse check function, F reconstructed is the reconstructed data matrix.

8. The method for transmitting electric energy metering information according to claim 6, characterized in that: The data analysis and anomaly detection specifically include: Use adaptive transformation methods to construct the feature space of the data: ； Among them, F transformed is the transformed feature matrix; T is the adaptive transformation matrix; Use the weighted locality distance metric to assess the degree of abnormality of a data point: ； Among them, D(x i ) is the abnormality measure of the i-th data point; x i is the transformation feature matrix of the i-th data point; x j is the transformed feature vector of the jth data point; w ij is the weighting coefficient; Set a dynamic threshold T d Used to determine abnormal data points: ； Where m(D) is the mean of the weighted local distances of all data points; s(D) is the standard deviation of the weighted local distances of all data points; α is a hyperparameter that controls the sensitivity of the threshold; According to the threshold T d Mark anomalous data points; Suppose there is a label vector A whose elements are 1 or 0, indicating whether the data point is an anomaly: ； Among them, A i is the i-th element in the tag vector; 1 indicates abnormality; 0 indicates normality; Use the local pattern-based repair method to repair abnormal data, the abnormal data point x i Repair is performed using the following repair algorithm: ； Among them, x repaired i is the repaired data point; N i For data point x i The field contains x i Similar normal data points; w ij is the weight calculated based on the similarity between data points.

9. A system using the electric energy metering information transmission method according to claim 7, characterized in that: include: Voltage measurement module: used to measure voltage signals; Current sensor: used to measure current signal; Power calculation module: used to calculate real-time power signals; Network status monitoring module: monitors the network status in real time and obtains the current delay, bandwidth and packet loss.

Images