A method and system for data partition processing of an electric energy meter

Abstract

The present invention is applicable to the field of data processing technology, and provides a method and system for data partitioning processing of an electric energy meter, including the following steps: collecting electric energy meter information, where the electric energy meter information includes power consumption data and archive information; extracting time series features from the electric energy meter information, where the time series features include peak-valley ratio, daily load rate, periodic features, and autocorrelation coefficient; extracting spatial features from the electric energy meter information, where the spatial features include transformer load rate, meter topology depth, spatial lag feature, and spatial autocorrelation index; screening and optimizing the extracted time series features and spatial features based on correlation pruning to obtain feature information; constructing a clustering partition model based on the feature information, and obtaining several data partitions according to the clustering results. The present invention makes full use of the spatio-temporal characteristics of electric energy meter data, effectively removes redundant features, and improves the data processing efficiency and the accuracy of clustering results.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and specifically relates to a method and system for data partitioning processing of an electric energy meter. Background Art

[0002] With the continuous development of smart grid technology, as an indispensable part of the power system, the collection and analysis of electric energy meter data play a crucial role in aspects such as power dispatching, load forecasting, and fault detection. Traditional methods for processing electric energy meter data are often limited to simple data recording and display, lacking in-depth mining and utilization of data, especially failing to fully utilize the temporal characteristics and spatial characteristics in electric energy meter data. Additionally, in the face of a large amount of electric energy meter data, how to efficiently and accurately perform data partitioning for subsequent better load management and optimized resource allocation is a major challenge currently. Traditional data partitioning methods often rely on simple geographical locations or administrative divisions, ignoring the internal connections and spatio-temporal characteristics between electric energy meter data, resulting in insufficiently refined and accurate partitioning results. Therefore, it is necessary to provide a method and system for data partitioning processing of an electric energy meter to address the above problems. Summary of the Invention

[0003] Aiming at the deficiencies existing in the prior art, the purpose of the present invention is to provide a method and system for data partitioning processing of an electric energy meter to solve the problems described in the above background art.

[0004] The present invention is implemented as follows. A method for data partitioning processing of an electric energy meter, the method comprising the following steps:

[0005] Collect electric energy meter information, where the electric energy meter information includes power consumption data and archive information, and the archive information includes installation location, substation, feeder, transformer, and meter code;

[0006] Extract temporal features from the electric energy meter information, where the temporal features include peak-valley ratio, daily load rate, periodic characteristics, and autocorrelation coefficient;

[0007] Extract spatial features from the electric energy meter information, where the spatial features include transformer load rate, meter topological depth, spatial lag feature, and spatial autocorrelation index;

[0008] Perform screening and optimization on the extracted temporal features and spatial features based on correlation pruning to obtain feature information;

[0009] Construct a clustering partition model based on the feature information, and obtain several data partitions according to the clustering results.

[0010] As a further aspect of the present invention: The step of extracting temporal features from the electric energy meter information specifically includes:

[0011] Calculate the peak-valley ratio and daily load rate of electricity consumption data. The peak-valley ratio = (maximum electricity consumption - minimum electricity consumption) ÷ average electricity consumption, and the daily load rate = average electricity consumption ÷ maximum electricity consumption;

[0012] Determine the electricity consumption time series x(t) based on the electricity consumption data, perform discrete Fourier transform on x(t) to obtain X(k), and take the amplitudes of the first K coefficients as periodic features;

[0013] Calculate the lag autocorrelation coefficient AT of, AT = , represents the mean of the time series, is the lag order, representing the number of time units by which the time series is shifted backward, and N is the length of the time series.

[0014] As a further solution of the present invention: The step of extracting spatial features from the electricity meter information specifically includes:

[0015] Calculate the load rates of all transformers and the topological depth of the electricity meters. The topological depth of the electricity meters is obtained according to the topological path;

[0016] Calculate the spatial lag features of the electricity meters, , is the spatial lag feature of electricity meter i, B represents the neighbor set of electricity meter i, is the spatial weight between electricity meters i and j;

[0017] Calculate the spatial autocorrelation index I, I = , n represents the total number of electricity meters, and U represents the average electricity consumption of all electricity meters.

[0018] As a further solution of the present invention: The step of screening and optimizing the extracted time series features and spatial features based on correlation pruning to obtain feature information specifically includes:

[0019] Calculate the variance values of each feature in the time series features and spatial features, and remove the features with variance values less than the first threshold;

[0020] Perform correlation pruning, pair the remaining features two by two, and calculate the correlation cardinality between each pair of features , , represents feature and feature covariance of, and respectively represent feature and feature standard deviation of;

[0021] Select one of the two features whose correlation base is greater than the second threshold, and obtain feature information based on the remaining feature.

[0022] As a further solution of the present invention: the step of constructing a clustering partition model based on the feature information specifically includes:

[0023] Determine the feature set F according to the feature information: F = , where m is the number of features, and perform standardization processing on each feature so that its mean is 0 and the standard deviation is 1;

[0024] Fuse the time series features and spatial features in the feature information into a feature matrix X, and use K-Means++ or GMM to perform clustering partition on the electricity meters.

[0025] Another object of the present invention is to provide a data partition processing system for electricity meters, and the system includes:

[0026] An electricity meter information collection module, which is used to collect electricity meter information, and the electricity meter information includes electricity consumption data and file information, and the file information includes installation location, substation, feeder, transformer and electricity meter code;

[0027] A time series feature extraction module, which is used to extract time series features from the electricity meter information, and the time series features include peak-valley ratio, daily load rate, periodic feature and autocorrelation coefficient;

[0028] A spatial feature extraction module, which is used to extract spatial features from the electricity meter information, and the spatial features include transformer load rate, electricity meter topological depth, spatial lag feature and spatial autocorrelation index;

[0029] A feature screening and optimization module, which is used to screen and optimize the extracted time series features and spatial features based on correlation pruning to obtain feature information;

[0030] A data clustering and partitioning module, which is used to construct a clustering partition model based on the feature information and obtain several data partitions according to the clustering results.

[0031] As a further solution of the present invention: the time series feature extraction module includes:

[0032] A daily load rate calculation unit, which is used to calculate the peak-valley ratio and daily load rate of the electricity consumption data, the peak-valley ratio = (maximum electricity consumption - minimum electricity consumption) ÷ average electricity consumption, and the daily load rate = average electricity consumption ÷ maximum electricity consumption;

[0033] A periodic feature unit, which is used to determine the electricity consumption time series x(t) according to the electricity consumption data, perform discrete Fourier transform on x(t) to obtain X(k), and take the amplitude of the first K coefficients as the periodic feature;

[0034] An autocorrelation coefficient unit for calculating the autocorrelation coefficient AT with a lag based on x(t), where AT = and is the mean value of the time series, is the order of lag, representing the number of time units by which the time series is shifted backward, and N is the length of the time series. As a further aspect of the present invention: the spatial feature extraction module includes:

[0035] A topological depth determination unit for calculating all transformer load rates and the topological depth of the electricity meters, where the topological depth of the electricity meters is obtained according to the topological path;

[0036] A spatial lag feature unit for calculating the spatial lag feature of the electricity meter,

[0037] where is the spatial lag feature of electricity meter i, B represents the neighbor set of electricity meter i, and is the spatial weight between electricity meters i and j;

[0038] A spatial autocorrelation index unit for calculating the spatial autocorrelation index I, where I = n represents the total number of electricity meters, and U represents the mean value of the electricity consumption of all electricity meters.

[0039] As a further aspect of the present invention: the feature screening and optimization module includes:

[0040] A variance value screening unit for calculating the variance value of each feature in the time series features and spatial features, and removing features with a variance value less than the first threshold;

[0041] A correlation pruning unit for performing correlation pruning, pairing the remaining features two by two, and calculating the correlation cardinality between each pair of features where is the covariance between feature and feature and respectively represent the standard deviations of feature and and feature and feature ;

[0042] A feature information determination unit for selecting one of the two features corresponding to a correlation cardinality greater than the second threshold, and obtaining feature information based on the remaining features.

[0043] As a further aspect of the present invention: the data clustering and partitioning module includes:

[0044] A feature set determination unit for determining the feature set F according to the feature information: F = , where m is the number of features, and each feature is standardized so that its mean is 0 and its standard deviation is 1;

[0045] An electricity meter clustering and partitioning unit, which is used to fuse the time series features and spatial features in the feature information into a feature matrix X, and uses K-Means++ or GMM to cluster and partition the electricity meters.

[0046] Compared with the prior art, the beneficial effects of the present invention are:

[0047] By extracting the time series features and spatial features of the electricity meter information, the present invention makes full use of the spatio-temporal characteristics of the electricity meter data, providing a more comprehensive and accurate data basis for subsequent clustering and partitioning. Based on correlation pruning, the extracted time series features and spatial features are screened and optimized, effectively removing redundant features, improving the data processing efficiency and the accuracy of the clustering results, and ensuring the differentiation after data partitioning. Finally, a clustering and partitioning model is constructed based on the optimized feature information, which can more precisely and accurately reflect the internal relationship and spatio-temporal characteristics between the electricity meter data, so as to obtain several more practically meaningful data partitions, facilitating subsequent better load management and optimized resource allocation. Description of the Drawings

[0048] Figure 1 It is a flowchart of a data partitioning processing method for an electricity meter.

[0049] Figure 2 It is a flowchart of extracting time series features from electricity meter information in a data partitioning processing method for an electricity meter.

[0050] Figure 3 It is a flowchart of extracting spatial features from electricity meter information in a data partitioning processing method for an electricity meter.

[0051] Figure 4 It is a flowchart of screening and optimizing features in a data partitioning processing method for an electricity meter.

[0052] Figure 5 It is a flowchart of constructing a clustering and partitioning model in a data partitioning processing method for an electricity meter.

[0053] Figure 6 It is a schematic structural diagram of a data partitioning processing system for an electricity meter. Detailed Embodiments

[0054] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0055] The following describes the specific implementation of the present invention in detail in conjunction with specific embodiments.

[0056] As Figure 1 shown, an embodiment of the present invention provides a method for data partitioning processing of an electric energy meter, and the method includes the following steps:

[0057] S100, collect electric energy meter information, where the electric energy meter information includes power consumption data and archive information, and the archive information includes installation location, substation, feeder, transformer, and meter code;

[0058] S200, extract time series features from the electric energy meter information, where the time series features include peak-valley ratio, daily load rate, periodic features, and autocorrelation coefficient;

[0059] S300, extract spatial features from the electric energy meter information, where the spatial features include transformer load rate, meter topological depth, spatial lag feature, and spatial autocorrelation index;

[0060] S400, perform screening and optimization on the extracted time series features and spatial features based on correlation pruning to obtain feature information;

[0061] S500, construct a clustering partition model based on the feature information, and obtain several data partitions according to the clustering result.

[0062] It should be noted that currently, in the face of a large amount of electric energy meter data, how to efficiently and accurately perform data partitioning for subsequent better load management and optimization of resource allocation is a major challenge currently faced. Traditional data partitioning methods often rely on simple geographical locations or administrative divisions, ignoring the internal connections and spatio-temporal characteristics between electric energy meter data, resulting in insufficiently fine and accurate partitioning results. The embodiments of the present invention aim to solve the above problems.

[0063] In the embodiments of the present invention, first, it is necessary to collect electricity meter information, which includes data of all electricity meters in a certain area. Specifically, the electricity meter information includes electricity consumption data and archive information. Then, time series features are extracted from the electricity consumption data in the electricity meter information. The time series features include peak-valley ratio, daily load rate, periodic features, and autocorrelation coefficient. The peak-valley ratio can reflect the electricity consumption volatility, and the daily load rate can reflect the electricity consumption balance; the periodic features and the autocorrelation coefficient respectively reveal the internal laws of the electricity consumption data from the perspectives of frequency domain and time domain. The periodic features are used to capture the periodic change laws in the electricity consumption data, such as daily cycle, weekly cycle, etc., which are usually closely related to the user's work and rest habits, production activities, etc. The autocorrelation coefficient is used to measure the correlation between the time series and its lagged version, reflecting the self-similarity and trend of the electricity consumption data. Then, spatial features are extracted from the electricity meter information. The spatial features include transformer load rate, electricity meter topological depth, spatial lag feature, and spatial autocorrelation index. The transformer load rate is used to measure the load condition of the transformer, and the electricity meter topological depth is the number of levels of the electricity meter in the power grid topological structure, which is used to reflect its position in the power grid; the spatial lag feature is used to reflect the influence of neighboring electricity meters on the current electricity meter, and the spatial autocorrelation index measures the clustering of spatial data, which is used to reflect the spatial distribution pattern of the electricity meter data. Since there are many features extracted here, only the features with large differences are retained for more efficient data partitioning. Here, the extracted time series features and spatial features are screened and optimized according to the correlation pruning to obtain feature information, and the features in the feature information can better partition the electricity meters. Finally, a clustering partition model is constructed based on the feature information, and several data partitions are obtained according to the clustering results. The partition results are accurate, with obvious differences, and the partitioning process is efficient.

[0064] As Figure 2 shown, as a preferred embodiment of the present invention, the step of extracting time series features from the electricity meter information specifically includes:

[0065] S201, calculate the peak-valley ratio and daily load rate of the electricity consumption data;

[0066] S202, determine the electricity consumption time series x(t) according to the electricity consumption data, perform discrete Fourier transform on x(t) to obtain X(k), and take the amplitude of the first K coefficients as the periodic feature;

[0067] S203, calculate the lag autocorrelation coefficient AT of.

[0068] In the embodiments of the present invention, the power consumption data is unified to the hourly granularity, and then the peak-valley ratio and daily load rate of the power consumption data are calculated. The peak-valley ratio = (maximum power consumption - minimum power consumption) ÷ average power consumption, and the daily load rate = average power consumption ÷ maximum power consumption. The maximum power consumption is the maximum value of the power consumption in a certain hour. And it is necessary to determine the power consumption time series x(t) according to the power consumption data, perform a discrete Fourier transform on x(t) to obtain X(k), and take the amplitudes of the first K coefficients as periodic features to capture the periodic patterns of the power consumption data. K is a fixed value. Finally, the autocorrelation coefficient AT of the lag is calculated, and AT = , represents the mean of the time series, is the lag order, representing the time unit by which the time series is shifted backward, and N is the length of the time series. The value of needs to be set within a fixed range. For hourly data, usually

[0069] is taken to analyze the autocorrelation within one day. Figure 3 As shown in

[0070] In a preferred embodiment of the present invention, the steps of extracting the spatial features of the electricity meter information specifically include:

[0071] S301, calculating all transformer load rates and the electricity meter topological depth, where the electricity meter topological depth is obtained according to the topological path;

[0071] S302, calculating the spatial lag feature of the electricity meter;

[0072] S303, calculating the spatial autocorrelation index I.

[0073] In the embodiments of the present invention, all transformer load rates and the electricity meter topological depth will be calculated. The transformer load rate is the ratio of the sum of the power consumptions of all electricity meters under the transformer to the transformer capacity. The electricity meter topological depth reflects the number of levels of the electricity meter in the power grid and is obtained according to the topological path. Then, the spatial lag feature of the electricity meter is calculated. , is the spatial lag feature of electricity meter i, which is the weighted average of the data of the neighbor electricity meters of electricity meter i and is used to reflect the influence of the neighbor electricity meters on the current electricity meter; B represents the set of neighbors of electricity meter i, and the neighbors can be other electricity meters under the same transformer or electricity meters within a certain spatial distance range. is the spatial weight between electricity meters i and j, . represents the spatial distance between electricity meters i and j. Finally, the spatial autocorrelation index I is calculated, and I = , n represents the total number of electricity meters, U represents the average of the power consumptions of all electricity meters, represents the power consumption data of electricity meter i.

[0074] As shown in Figure 4 the following figure, as a preferred embodiment of the present invention, the step of screening and optimizing the extracted temporal features and spatial features based on correlation pruning to obtain feature information specifically includes:

[0075] S401, calculating the variance value of each feature in the temporal features and spatial features, and removing the features with variance values less than the first threshold;

[0076] S402, performing correlation pruning, pairing the remaining features in pairs, and calculating the correlation cardinality between each pair of features ;

[0077] S403, selecting one of the two features corresponding to the correlation cardinality greater than the second threshold, and obtaining the feature information according to the remaining features.

[0078] In the embodiment of the present invention, during feature screening, first calculate the variance value of each feature in the temporal features and spatial features, remove the features with variance values less than the first threshold, and retain the features with significant changes, which is more reference-worthy. Then perform correlation pruning, pair the remaining features in pairs, and pair any two features, and calculate the correlation cardinality between each pair of features , , represents the covariance of feature and feature , and respectively represent the standard deviations of feature and feature . Finally, select one of the two features corresponding to the correlation cardinality greater than the second threshold. If the correlation cardinality is greater than the second threshold (such as 0.85), it means that the two features are highly correlated, and only one needs to be selected. The final feature information can be obtained according to the remaining features.

[0079] As shown in Figure 5 the following figure, as a preferred embodiment of the present invention, the step of constructing a clustering partition model based on the feature information specifically includes:

[0080] S501, determining the feature set F according to the feature information: F = , where m is the number of features, and standardize each feature;

[0081] S502, fusing the temporal features and spatial features in the feature information into a feature matrix X, and using K-Means++ or GMM to perform clustering and partitioning on the electric energy meters.

[0082] In the embodiment of the present invention, the final feature set F is determined: F = , where m is the number of features. Each feature is standardized so that its mean is 0 and its standard deviation is 1. After standardization, the temporal features and spatial features in the feature information are fused into a feature matrix X, and K-Means++ or GMM is used to cluster and partition the electricity meters. The steps of K-Means++ clustering are briefly described below: Randomly select the first cluster center C1; for each sample xi, calculate its minimum distance D(xi) to the selected centers; select the next center with probability D(xi) 2 / (∑ j D(xj) 2 ); repeat until K centers are selected; perform iterative optimization: assign each sample to the nearest cluster center; recalculate the center of each cluster; stop when the cluster centers no longer change or reach the maximum number of iterations to obtain the clustering result.

[0083] As Figure 6 shown, an embodiment of the present invention also provides a data partitioning processing system for an electricity meter, and the system includes:

[0084] An electricity meter information collection module 100, configured to collect electricity meter information, where the electricity meter information includes electricity consumption data and archive information, and the archive information includes installation location, substation, feeder, transformer, and electricity meter code;

[0085] A temporal feature extraction module 200, configured to extract temporal features from the electricity meter information, where the temporal features include peak-valley ratio, daily load rate, periodic features, and autocorrelation coefficient;

[0086] A spatial feature extraction module 300, configured to extract spatial features from the electricity meter information, where the spatial features include transformer load rate, electricity meter topological depth, spatial lag feature, and spatial autocorrelation index;

[0087] A feature screening and optimization module 400, configured to screen and optimize the extracted temporal features and spatial features based on correlation pruning to obtain feature information;

[0088] A data clustering and partitioning module 500, configured to construct a clustering and partitioning model based on the feature information and obtain several data partitions according to the clustering result.

[0089] As a preferred embodiment of the present invention, the temporal feature extraction module 200 includes:

[0090] A daily load rate calculation unit, configured to calculate the peak-valley ratio and daily load rate of the electricity consumption data, where the peak-valley ratio = (maximum electricity consumption - minimum electricity consumption) ÷ average electricity consumption, and the daily load rate = average electricity consumption ÷ maximum electricity consumption;

[0091] A periodic feature unit, which is used to determine the power consumption time series x(t) according to power consumption data, perform a discrete Fourier transform on x(t) to obtain X(k), and take the amplitudes of the first K coefficients as periodic features;

[0092] An autocorrelation coefficient unit, which is used to calculate the lag autocorrelation coefficient AT of, AT = , represents the mean of the time series, is the lag order, representing the number of time units by which the time series is shifted backward, and N is the length of the time series.

[0093] As a preferred embodiment of the present invention, the spatial feature extraction module 300 includes:

[0094] A topological depth determination unit, which is used to calculate all transformer load rates and the topological depth of the electricity meters, and the topological depth of the electricity meters is obtained according to the topological path;

[0095] A spatial lag feature unit, which is used to calculate the spatial lag feature of the electricity meter, , is the spatial lag feature of electricity meter i, B represents the neighbor set of electricity meter i, is the spatial weight between electricity meters i and j;

[0096] A spatial autocorrelation index unit, which is used to calculate the spatial autocorrelation index I, I = , n represents the total number of electricity meters, and U represents the mean of the power consumption of all electricity meters.

[0097] As a preferred embodiment of the present invention, the feature screening and optimization module 400 includes:

[0098] A variance value screening unit, which is used to calculate the variance values of each type of feature in the time series features and spatial features, and remove the features with variance values less than the first threshold;

[0099] A correlation pruning unit, which is used to perform correlation pruning, pair the retained features two by two, and calculate the correlation cardinality between each pair of features , , represents the feature and the feature covariance of, and respectively represent the features and the feature standard deviation of;

[0100] A feature information determination unit, which is used to select one of the two features corresponding to the correlation cardinality greater than the second threshold, and obtain the feature information according to the retained features.

[0101] As a preferred embodiment of the present invention, the data clustering and partitioning module 500 includes:

[0102] A feature set determination unit, configured to determine a feature set F according to feature information: F = , where m is the number of features, and each feature is normalized so that its mean is 0 and its standard deviation is 1;

[0103] An electricity meter clustering and partitioning unit, configured to fuse the temporal feature and the spatial feature in the feature information into a feature matrix X, and use K-Means++ or GMM to perform clustering and partitioning on the electricity meters.

[0104] The above only describes the preferred embodiments of the present invention in detail, and is not intended to limit the present invention. Any modifications, equivalent replacements, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

[0105] It should be understood that although the steps in the flowcharts of the embodiments of the present invention are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in each embodiment may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same moment, but can be executed at different moments. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or sub-steps or stages of other steps.

[0106] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0107] After considering the specification and the disclosure of the embodiments, those skilled in the art will readily conceive of other embodiments of the present disclosure. The present application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include known common knowledge or conventional technical means in the technical field not disclosed in the present disclosure. The specification and the embodiments are only regarded as exemplary, and the true scope and spirit of the present disclosure are pointed out by the claims.

Claims

1. A data partition processing method for an electric energy meter, characterized in that: The method comprises the following steps: Collecting electric energy meter information, the electric energy meter information including power consumption data and archive information, the archive information including installation location, substation, feeder, transformer and meter code; Extracting time series features from the electric energy meter information, wherein the time series features include peak-to-valley ratio, daily load rate, periodicity features and autocorrelation coefficient; Extracting spatial features from the electric energy meter information, wherein the spatial features include transformer load rate, electric energy meter topology depth, spatial hysteresis feature and spatial autocorrelation index; Based on correlation pruning, the extracted temporal features and spatial features are screened and optimized to obtain feature information; Building a clustering partition model based on the feature information, and obtaining a number of data partitions according to the clustering results; The step of screening and optimizing the extracted temporal features and spatial features based on correlation pruning to obtain feature information specifically includes: calculating the variance value of each feature in the temporal features and spatial features, removing features whose variance value is less than a first threshold; performing correlation pruning, pairing the retained features in pairs, and calculating the correlation cardinality R between each pair of features. ij , Cov(f i , f j ) represents the feature f i and feature f j The covariance of i and σ j Respectively represent the features f i and feature f j The standard deviation of ; select one of the two features corresponding to the correlation cardinality greater than the second threshold, and obtain the feature information based on the retained features.

2. The data partition processing method of the electric energy meter according to claim 1 is characterized in that: The step of extracting time series features from the electric energy meter information specifically includes: Calculate the peak-to-valley ratio and daily load rate of electricity consumption data: Peak-to-valley ratio = (maximum electricity consumption - minimum electricity consumption) / average electricity consumption; Daily load rate = average electricity consumption / maximum electricity consumption; Determine the power consumption time series x(t) based on the power consumption data, perform discrete Fourier transform on x(t) to obtain X(k), and take the amplitudes of the first K coefficients as the periodic characteristics; Based on x(t), the autocorrelation coefficient AT of lag τ is calculated, μ represents the mean of the time series, τ is the lag order, which represents the number of time units of the time series shifted backward, and N is the length of the time series.

3. The data partition processing method of the electric energy meter according to claim 2 is characterized in that: The step of extracting spatial features from the electric energy meter information specifically includes: Calculate all transformer load factors and meter topology depths, where the meter topology depths are obtained based on topology paths; Calculate the spatial hysteresis characteristics of the energy meter, SL i =∑ j∈B w ij x j (t), SL i is the spatial lag feature of meter i, B represents the neighbor set of meter i, and w ij is the spatial weight between meters i and j; Calculate the spatial autocorrelation index I, n represents the total number of electricity meters, and U represents the mean electricity consumption of all electricity meters.

4. The data partition processing method of the electric energy meter according to claim 1, characterized in that: The step of constructing a cluster partition model based on the feature information specifically includes: Determine the feature set F based on the feature information: F = [f1, f2, ..., f m ], where m is the number of features, and each feature is standardized to have a mean of 0 and a standard deviation of 1; The temporal features and spatial features in the feature information are fused into a feature matrix X, and K-Means++ or GMM is used to cluster and partition the electric energy meter.

5. A data partition processing system for an electric energy meter, characterized in that: The system comprises: An electric meter information collection module is used to collect electric energy meter information, wherein the electric energy meter information includes power consumption data and archive information, wherein the archive information includes installation location, substation, feeder, transformer and electric meter code; A time series feature extraction module is used to extract time series features from the electric energy meter information, wherein the time series features include peak-to-valley ratio, daily load rate, periodicity characteristics and autocorrelation coefficient; A spatial feature extraction module is used to extract spatial features from electric energy meter information, wherein the spatial features include transformer load rate, electric energy meter topology depth, spatial hysteresis feature and spatial autocorrelation index; The feature screening and optimization module is used to screen and optimize the extracted temporal features and spatial features based on correlation pruning to obtain feature information; A data clustering and partitioning module is used to construct a clustering and partitioning model based on the feature information and obtain a number of data partitions according to the clustering results; The feature screening and optimization module includes: a variance value screening unit, which is used to calculate the variance value of each feature in the time series feature and the spatial feature, and remove the features whose variance value is less than the first threshold; a correlation pruning unit, which is used to perform correlation pruning, pair the retained features in pairs, and calculate the correlation cardinality R between each pair of features. ij , Cov(f i , f j ) represents the feature f i and feature f j The covariance of i and σ j Respectively represent the features f i and feature f j a characteristic information determination unit, used to select one of the two characteristics corresponding to the correlation cardinality greater than the second threshold, and obtain characteristic information according to the retained characteristics.

6. The data partition processing system of the electric energy meter according to claim 5, characterized in that: The temporal feature extraction module comprises: Daily load rate calculation unit, used to calculate the peak-to-valley ratio and daily load rate of power consumption data, peak-to-valley ratio = (maximum power consumption - minimum power consumption) / average power consumption, daily load rate = average power consumption / maximum power consumption; The periodic feature unit is used to determine the power consumption time series x(t) according to the power consumption data, perform discrete Fourier transform on x(t) to obtain X(k), and take the amplitude of the first K coefficients as the periodic feature; The autocorrelation coefficient unit is used to calculate the autocorrelation coefficient AT of the lag τ based on x(t). μ represents the mean of the time series, τ is the lag order, which represents the number of time units of the time series shifted backward, and N is the length of the time series.

7. The data partition processing system of the electric energy meter according to claim 6, characterized in that: The spatial feature extraction module comprises: A topology depth determination unit, used to calculate all transformer load rates and electric meter topology depths, wherein the electric meter topology depths are obtained according to the topology path; Spatial hysteresis characteristic unit, used to calculate the spatial hysteresis characteristics of the electric energy meter, SL i =∑ j∈B w ij x j (t), SL i is the spatial lag feature of meter i, B represents the neighbor set of meter i, and w ij is the spatial weight between meters i and j; Spatial autocorrelation index unit, used to calculate the spatial autocorrelation index I, n represents the total number of electricity meters, and U represents the mean electricity consumption of all electricity meters.

8. The data partition processing system of the electric energy meter according to claim 5, characterized in that: The data clustering partitioning module comprises: A feature set determination unit is used to determine a feature set F according to feature information: F = [f1, f2, ..., f m ], where m is the number of features, and each feature is standardized to have a mean of 0 and a standard deviation of 1; The electric meter clustering and partitioning unit is used to fuse the temporal features and spatial features in the feature information into a feature matrix X, and use K-Means++ or GMM to cluster and partition the electric energy meter.

Images