Bidirectional metering correction method and system for electric energy meter

Abstract

The invention belongs to the technical field of electric energy meter metering correction, and provides a two-way metering correction method and system for an electric energy meter, and the method comprises the following steps: obtaining the power generation amount of distributed energy in historical data and the power consumption of a user, recognizing a continuous time period in which the power generation amount and the power consumption have a significant difference as a mismatch high-incidence time period, and determining the mismatch high-incidence time period; performing selection analysis on the mismatch high-incidence time period, and determining a time period division rule for prediction analysis; and performing time interval division based on the determined time interval division rule to obtain an analysis time interval. By analyzing the metering abnormal proportions of different types of key mismatch time period groups, screening out high-proportion class groups, predicting the occurrence trend and time of the high-proportion class groups by using a neural network model, and performing electric energy metering correction compensation, the occurrence of the key mismatch time periods can be predicted in advance, and correction compensation is performed based on a historical metering deviation rate mean value. Settlement errors caused by inaccurate metering of the electric energy meter can be effectively reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of electric energy meter measurement correction, and in particular relates to a bidirectional measurement correction method and system for electric energy meters. Background Art

[0002] The bidirectional metering function allows the meter to simultaneously track and record the electricity consumed by the user from the grid (positive electricity) and the electricity supplied by the user to the grid (negative electricity). This metering method clearly distinguishes the direction of power and energy flow. Electricity consumption is regarded as positive power or positive energy, while electricity generation is regarded as negative power or negative energy. When distributed power sources such as photovoltaics and wind power are connected to the grid, there may be a time mismatch between power generation and power load. For example, during the day, photovoltaic power generation is high, but user power load is low, resulting in excess power being fed back to the grid. At night, photovoltaic power generation is low, and users may need to draw power from the grid. When distributed power sources are connected to the grid, using bidirectional meters can accurately measure the power fed back to the grid by users, eliminating the problems of "power leakage" or "settlement disputes" caused by traditional one-way meters. However, if the electricity meter is inaccurate, it may affect the settlement between the user and the grid. In this case, the meter needs to be corrected. However, the lack of accurate identification of the mismatch period between distributed energy resources and loads leads to delayed correction actions. To this end, the present invention provides a bidirectional measurement correction method and system for an electric energy meter. Summary of the Invention

[0003] In order to make up for the deficiencies of the prior art, at least one technical problem raised in the background technology is solved.

[0004] The technical solution adopted by the present invention to solve the technical problem is: a bidirectional measurement correction method for an electric energy meter, comprising the following steps: Obtain the power generation of distributed energy and the power consumption of users from historical data, identify the continuous periods with significant differences between power generation and power consumption as the high-incidence mismatch periods, conduct selection analysis on the high-incidence mismatch periods, and determine the period division rules for predictive analysis.

[0005] Based on the determined period division rules, the time periods are divided into analysis periods, the difference between the total power generation and the total power consumption in each analysis period is calculated, the time periods with high degree of difference are extracted as key mismatch periods, and cluster analysis of the key mismatch periods with respect to the difference value range is performed to obtain different types of key mismatch period groups.

[0006] Analyze the proportion of different types of critical mismatch time periods in the occurrence of electricity metering anomalies, extract the critical mismatch time period groups with a high proportion of metering anomalies as the high-proportion group, analyze the trend of the key mismatch time periods in the common proportion group, predict the time of the next occurrence, and perform electricity metering correction and compensation.

[0007] As a further solution of the present invention: the process of obtaining the time period division rule is as follows: All the time periods with high incidence of mismatches are extracted, and these time periods are arranged according to their corresponding time period lengths to obtain an ascending sequence of the time periods with high incidence of mismatches.

[0008] Calculate the average value and standard deviation of the time period lengths in the ascending sequence of the mismatch high-incidence time period to obtain the time length mean and time length standard deviation; set the retention range based on the time length mean and time length standard deviation.

[0009] Traverse the ascending sequence of the high-incidence mismatch periods, retain the high-incidence mismatch periods within the retention range, and extract the minimum value of the retained high-incidence mismatch periods as the period division rule for prediction analysis.

[0010] As a further solution of the present invention: the process of obtaining the high-incidence period of mismatch is as follows: The absolute value of the difference between power generation and power consumption at each time point is calculated as the power difference value. The time points exceeding the preset limit are marked as significant difference time points. Adjacent significant difference points are merged through the time deviation limit to form an integrated group. The time period corresponding to the integrated group is calculated as the period with high mismatch incidence.

[0011] As a further solution of the present invention: the process of obtaining the integrated group is: The difference between the significant difference time points corresponding to the adjacent power difference values ​​in the significant difference value sequence is calculated to obtain the time deviation value; if it is less than or equal to the time deviation limit, it is marked as a mergeable value group.

[0012] Extract all mergible value groups, traverse all mergible value groups, and integrate the same power difference values ​​in different mergible value groups to obtain an integrated group.

[0013] As a further solution of the present invention: the process of obtaining the critical mismatch period is: The absolute value of the difference between the total power generation and the total power consumption in each analysis period is calculated as the total power deviation value of the period; if it is greater than the deviation degree judgment threshold, it is marked as a high-degree difference period and the high-degree difference period is regarded as a key mismatch period.

[0014] As a further solution of the present invention: the process of obtaining the high-proportion cluster is as follows: Obtain the proportion of measurement anomalies corresponding to each type of key mismatch period group; use the K-means clustering method to perform cluster analysis on the measurement anomaly proportion, and set the number of clusters to 2, namely, the high measurement anomaly proportion and the low measurement anomaly proportion; the group with the higher mean anomaly proportion in the two obtained clusters is the high proportion group.

[0015] As a further solution of the present invention: the process of obtaining the measurement abnormality ratio is as follows: For the key mismatch period in each type of key mismatch period group, the sum of the forward power and reverse power in the key mismatch period is calculated as the total interactive power of the period; the absolute value of the difference between the metered value and the actual value of the electric energy meter is used as the absolute deviation value of the period, and the ratio of the absolute deviation of the period to the total interactive power of the period is used as the electric energy metering deviation rate; if it is greater than the standard value of the electric energy metering deviation rate, it is marked as a metering abnormality.

[0016] The key mismatch periods of measurement anomalies are extracted, and their total number is counted as the number of measurement anomalies. The ratio of the number of measurement anomalies to the total number of key mismatch periods of this type is taken as the measurement anomaly proportion.

[0017] As a further solution of the present invention: the process of predicting the time of next occurrence is: Obtain the key mismatch periods in the high-proportion clusters and build a prediction model by training the prediction model through a neural network model.

[0018] Based on the prediction model output, the probability of the future analysis period being a critical mismatch period is output. If the output probability of the critical mismatch period is greater than the probability limit, the analysis period is predicted to be a critical mismatch period, and the time of its next occurrence is set.

[0019] As a further solution of the present invention: the process of performing electric energy measurement correction and compensation is: For the analysis period predicted to be a critical mismatch period, the average value of the electric energy metering deviation rate corresponding to the critical mismatch period in the high-proportion group is calculated as the benchmark deviation compensation rate.

[0020] A bidirectional measurement correction system for an electric energy meter, the system comprising: Time period division rule determination module: obtains the power generation of distributed energy and the power consumption of users in historical data, identifies the continuous time periods with significant differences between power generation and power consumption as the high-incidence mismatch periods, selects and analyzes the high-incidence mismatch periods, and determines the time period division rules for predictive analysis.

[0021] Critical mismatch period analysis module: Based on the determined period division rules, the period is divided into analysis periods, the difference between the total power generation and the total power consumption in each analysis period is calculated, the periods with high degree of difference are extracted as critical mismatch periods, and cluster analysis of the difference value range is performed on the critical mismatch periods to obtain different types of critical mismatch period groups.

[0022] Time period prediction and correction module: Analyzes the proportion of different types of key mismatch time period groups in the occurrence of power metering anomalies, extracts key mismatch time period groups with a high proportion of metering anomalies as high-proportion groups, analyzes the trend of key mismatch time periods in the total proportion groups, predicts the time of next occurrence, and performs power metering correction and compensation.

[0023] The beneficial effects of the present invention are as follows: 1. By analyzing the distributed energy generation and user electricity consumption in historical data, the high-incidence periods of mismatch with significant electricity differences are identified, and the period division rules are determined based on this. The period division can be based on actual data characteristics rather than subjective experience, which can capture the compact mismatch occurrence cycle, reduce subjective bias, and fit the actual mismatch time distribution characteristics. At the same time, it can automatically adapt to the operating characteristics and mismatch patterns of different power systems to form a personalized adaptation plan, providing a more scientific and accurate period division basis for subsequent metering corrections, thereby improving the adaptability of the entire correction method to the actual power system and the accuracy of data analysis.

[0024] 2. Analyze the time period division based on the time period division rules. By calculating the total electricity deviation value of each time period, extract the key mismatch time period and perform cluster analysis on it. Use the K-means clustering method to group the key mismatch time periods according to the deviation value range, which can effectively identify different degrees of electricity mismatch types. This cluster analysis can quantify the distribution characteristics of different mismatch situations and provide a classification basis for the subsequent targeted analysis of metering anomalies in various mismatch time periods. This makes the subsequent metering anomaly analysis and correction compensation more targeted and efficient, helps to more accurately locate the mismatch time periods that need to be focused on, and improves the efficiency and accuracy of metering corrections.

[0025] 3. By analyzing the proportion of metering anomalies in different types of key mismatch time groups, we screen out the groups with high proportions, use the neural network model to predict their occurrence trends and time, and perform electricity metering corrections and compensation. This can predict the occurrence of key mismatch periods in advance, and perform corrections and compensation based on the average historical metering deviation rate, which can effectively reduce settlement errors caused by inaccurate electricity meter measurement. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The present invention will be further described below with reference to the accompanying drawings.

[0027] Figure 1The present invention is a flowchart of the steps of a bidirectional measurement correction method for an electric energy meter.

[0028] Figure 2 This is a partial logic judgment flow chart of step S1 in a bidirectional measurement correction method for an electric energy meter according to the present invention.

[0029] Figure 3 This is an architectural diagram of a bidirectional measurement correction system for an electric energy meter according to the present invention. DETAILED DESCRIPTION

[0030] In order to make the technical means, creative features, objectives and effects achieved by the present invention easier to understand, the present invention is further described below in conjunction with specific implementation methods.

[0031] Example 1 See also Figure 1 and Figure 2 As shown, a bidirectional measurement correction method for an electric energy meter according to an embodiment of the present invention includes the following steps: Step S1: Obtain the power generation of distributed energy and the power consumption of users in historical data, identify the continuous time periods with significant differences between power generation and power consumption as the high-incidence mismatch periods, select and analyze the high-incidence mismatch periods, and determine the time period division rules for predictive analysis.

[0032] In some embodiments, the power generation data of distributed energy and the power consumption data of users are obtained from historical data; the power generation of distributed energy and the power consumption of users are used for analysis as the basic data of the entire correction method, and by analyzing the different spatiotemporal distributions of the two, the full process logical closed loop of mismatch period identification, period rule division, period type clustering, and deviation prediction correction can be completed.

[0033] Among them, distributed energy includes but is not limited to: solar photovoltaic systems and wind turbines.

[0034] Specifically, the distributed energy generation data and user power consumption data for the historical period are extracted from the historical data storage system of the electric energy meter and the distributed energy monitoring system.

[0035] The extraction period may be one month, one quarter or one year, and the historical period for extraction is set by those skilled in the art based on their experience and the characteristics of data changes.

[0036] It should be noted that the integrity and accuracy of the data must be ensured when acquiring data, including but not limited to: the timestamp of the data, the power generation value, the power consumption value, and for different types of distributed energy, the corresponding power generation data must be obtained separately.

[0037] Based on the extracted historical time period range, the obtained distributed energy generation data and user electricity consumption data are aligned according to timestamps to ensure that the two sets of data correspond one to one at the same time.

[0038] The absolute value of the difference between the power generation and power consumption corresponding to each time point is calculated as the power difference value.

[0039] The power difference value is compared with the preset power difference limit. If the power difference value is less than or equal to the power difference limit, it is marked as a non-significant difference time point. If the power difference value is greater than the power difference limit, it is marked as a significant difference time point.

[0040] It should be explained that the power difference limit is used to determine whether the power difference value exceeds the standard at the corresponding time point. This value is set by technical personnel in this field according to industry standards.

[0041] All significant difference time points are extracted and serialized in time dimension according to the corresponding timestamps to obtain the power difference value sequence corresponding to the significant difference time points as the significant difference value sequence.

[0042] The difference between the significant difference time points corresponding to the adjacent power difference values ​​in the significant difference value sequence is calculated to obtain the time deviation value.

[0043] Compare the time deviation value with the time deviation limit. If the time deviation value is less than or equal to the time deviation limit, the corresponding two power difference values ​​are marked as a mergeable value group. If the time deviation value is greater than the time deviation limit, the corresponding two power difference values ​​are marked as a non-mergeable value group.

[0044] It should be explained that for the time deviation limit, it is used to determine whether two adjacent values ​​in a significant difference value sequence are approximately continuous at a time point. This value is set by technical personnel in this field based on reference to the requirements for load fluctuation tolerance in industry specifications and experience.

[0045] Extract all mergible value groups, traverse all mergible value groups, and integrate the same power difference values ​​in different mergible value groups to obtain an integrated group.

[0046] For the integration process, for example, from the mergeable value group A (electricity difference value a, electricity difference value b), the mergeable value group B (electricity difference value b, electricity difference value c), the mergeable value group C (electricity difference value c, electricity difference value d), and the mergeable value group D (electricity difference value e, electricity difference value f), the corresponding mergeable value group A, the mergeable value group B and the mergeable value group C can be integrated to obtain the integrated group.

[0047] Extract all integration groups and calculate the time period corresponding to the integration group based on the timestamp corresponding to the power difference value in the integration group as the mismatch high-incidence period.

[0048] The notable feature of the mismatch period is the large difference between power generation and power consumption. At this time, the impact of the metering deviation of the electricity meter is more prominent, and it is a high-risk scenario for metering errors.

[0049] All the time periods with high incidence of mismatches are extracted, and these time periods are arranged according to their corresponding time period lengths to obtain an ascending sequence of the time periods with high incidence of mismatches.

[0050] The statistical distribution method is used to screen the extreme values ​​in the ascending sequence during the period of high mismatch incidence, thereby improving the accuracy and practicality of data analysis and eliminating the interference of extreme values.

[0051] The average value and standard deviation of the time period lengths in the ascending sequence of the high-incidence mismatching time periods are calculated to obtain the mean time length and the standard deviation time length.

[0052] Set the extreme value screening range value based on the mean time length and the standard deviation time length, and then set the retention range to ,in, is the proportional coefficient, which is set according to the data characteristics of the ascending sequence during the high-incidence period of mismatches and can be set to 1.5 or 2, where is the mean time length, is the standard deviation of time length.

[0053] Traverse the ascending sequence of the high-incidence mismatch periods, retain the high-incidence mismatch periods within the retention range, and extract the minimum value of the retained high-incidence mismatch periods as the period division rule for prediction analysis.

[0054] That is, the time length corresponding to the minimum value in the high-incidence mismatch period is used as the standard for dividing the period size.

[0055] Among them, the reason for using the time length corresponding to the minimum value in the period of high mismatch incidence as the standard for period size division is that the period division standard corresponding to the minimum value can capture the mismatch more accurately. The period length reflects the most compact mismatch occurrence cycle in the system. Using the minimum value as the division standard can ensure that the period division granularity is fine enough. Using this as the period division for predictive analysis can reduce the subjective bias of empirical settings and make the period division more in line with the time distribution characteristics of actual mismatches.

[0056] Different power systems have different operating characteristics and mismatch patterns. The minimum value division standard obtained through analysis based on actual historical data can automatically adapt to the characteristics of various power systems. Different division standards can be calculated for different power systems, and then a personalized adaptation plan can be formed for each system and division.

[0057] Step S1 has at least the following effects: by analyzing the distributed energy generation and user electricity consumption in historical data, the high-incidence mismatch periods with significant electricity differences are identified, and the period division rules are determined based on this. The period division can be based on actual data characteristics rather than subjective experience, which can capture compact mismatch occurrence cycles, reduce subjective bias, and fit the actual mismatch time distribution characteristics. At the same time, it can automatically adapt to the operating characteristics and mismatch modes of different power systems to form a personalized adaptation plan, providing a more scientific and accurate period division basis for subsequent metering corrections, thereby improving the adaptability of the entire correction method to the actual power system and the accuracy of data analysis.

[0058] Step S2: Based on the determined time period division rules, the time period is divided into analysis periods, the difference between the total power generation and the total power consumption in each analysis period is calculated, the time periods with high degree of difference are extracted as key mismatch time periods, and the key mismatch time periods are clustered with respect to the difference value range to obtain different types of key mismatch time period groups.

[0059] In some embodiments, the extracted historical period is divided into several analysis periods according to the period division rule obtained in the aforementioned step S1.

[0060] For each analysis period, the absolute value of the difference between the total power generation and the total power consumption in the analysis period is calculated as the total power deviation value of the period.

[0061] Compare the total power deviation value of the time period with the deviation degree judgment threshold. If the total power deviation value of the time period is less than or equal to the deviation degree judgment threshold, it is marked as a low degree difference time period. If the total power deviation value of the time period is greater than the deviation degree judgment threshold, it is marked as a high degree difference time period.

[0062] It should be explained that the deviation degree judgment threshold is used to judge the degree of difference between the total power generation and the total power consumption in the corresponding analysis period. This value is set by technical personnel in this field based on industry standards and actual power system characteristics.

[0063] The high-degree difference period is regarded as the key mismatch period, and the total power deviation value of the period corresponding to the key mismatch period is obtained. Cluster analysis is performed based on the total power deviation value of the period to obtain different types of key mismatch period groups.

[0064] Specifically, the process of selecting the K-means clustering method for cluster analysis is: S201: Randomly select K different deviation values ​​from the deviation value sequence as initial cluster centers; For example, when K=3, the initial centers may be 50kWh, 80kWh, and 120kWh.

[0065] S202: Calculate the distance between each deviation value and the center of all clusters, and assign it to the cluster with the closest distance. The distance value can be represented by absolute distance or Euclidean distance. For example, the total power deviation value in a time period is 75 kWh, the distance value to 50 kWh is 25, the distance to 80 kWh is 5, and the distance to 120 kWh is 45, so it is allocated to the cluster where 80 kWh is located.

[0066] S203: Calculate the mean of the total power deviation values ​​of all time periods in each cluster as the new cluster center; For example, a cluster includes deviation values ​​50 kWh and 65 kWh, and the new center is 57.5 kWh.

[0067] S204: Repeat steps S202 and S203 until the cluster center no longer changes significantly or the maximum number of iterations is reached; wherein, the standard for no longer changing significantly can be that the center difference between two iterations is less than 0.1 kWh, and the maximum number of iterations is set to 50 times.

[0068] S205: Verify the results of each obtained cluster, that is, for each cluster, calculate the variance of the total power deviation value of the time period and evaluate the dispersion of the data within the group. The smaller the variance, the closer the deviation values ​​within the same cluster are, and the better the clustering effect.

[0069] Get each cluster, each cluster corresponds to a type, and get different types of key mismatch period groups.

[0070] In this embodiment, the type refers to the range of the total power deviation value in the time period.

[0071] Step S2 has at least the following effects: analyzing the time period division based on the time period division rule, extracting the key mismatch time period by calculating the total power deviation value of each time period, and performing cluster analysis on it, and using the K-means clustering method to group the key mismatch time periods according to the deviation value range, which can effectively identify different degrees of power mismatch types. This cluster analysis can quantify the distribution characteristics of different mismatch situations, and provide a classification basis for subsequent targeted analysis of metering anomalies in various mismatch time periods, making subsequent metering anomaly analysis and correction compensation more targeted and efficient, helping to more accurately locate the mismatch time periods that need to be focused on, and improving the efficiency and accuracy of metering corrections.

[0072] Step S3: Analyze the proportion of different types of critical mismatch time periods in the occurrence of abnormal energy metering, extract the critical mismatch time period group with a high proportion of metering abnormalities as the high-proportion group, analyze the trend of the occurrence of critical mismatch time periods in the total proportion group, predict the time of the next occurrence, and perform energy metering correction and compensation.

[0073] In some embodiments, for each type of critical mismatch period in the critical mismatch period group, the corresponding electric energy metering deviation rate is calculated.

[0074] The calculation process of the electricity calculation deviation value is as follows: calculate the sum of the forward electricity and the reverse electricity in the key mismatch period as the total interactive electricity in the period; take the absolute value of the difference between the meter value and the actual value as the absolute deviation value of the period; and take the ratio of the absolute deviation of the period to the total interactive electricity in the period as the electricity metering deviation rate.

[0075] It should be explained that the metered value is the statistical data of the electric energy exchanged between the user and the grid during the period, recorded by the electric energy meter itself; the actual value is the real data of the electric energy exchanged between the user and the grid during the period, obtained through verification methods, and the verification methods include but are not limited to: standard power source, third-party verification device, and energy conservation verification method; the forward electric quantity is the amount of electricity drawn from the grid by the user during the period, recorded by the electric energy meter (current flows from the grid to the user side); the reverse electric quantity is the amount of electricity supplied to the grid by the user during the period, recorded by the electric energy meter (current flows from the user side to the grid).

[0076] For example, the electric energy meter measures: the forward power (household electricity) is 20kWh, the reverse power (photovoltaic grid connection) is 15kWh, and the electric energy meter measurement value is 20+15=35kWh; after verification through the verification method, the actual forward power is 19.5kWh, the actual reverse power is 15.2kWh, and the actual value is 34.7kWh.

[0077] Based on the energy metering deviation rate corresponding to each key mismatch period, determine whether energy metering deviation occurs in the corresponding period. If the energy metering deviation rate is less than or equal to the standard value of the energy metering deviation rate, it is marked as normal measurement. If the energy metering deviation rate is greater than the standard value of the energy metering deviation rate, it is marked as abnormal measurement.

[0078] The key mismatch periods of measurement anomalies are extracted, and their total number is counted as the number of measurement anomalies. The ratio of the number of measurement anomalies to the total number of key mismatch periods of this type is taken as the measurement anomaly proportion.

[0079] The process of clustering analysis of the measurement anomaly ratio using the K-means clustering method is as follows: the clustering process is the same as the method in the aforementioned step S2, the difference being that the number of clusters needs to be set to 2, namely, the measurement anomaly ratio is high and the measurement anomaly ratio is low.

[0080] The two clusters with a higher mean abnormal proportion are classified as the high-proportion group, and the two clusters with a lower mean abnormal proportion are classified as the low-proportion group.

[0081] Obtain the key mismatch periods in the high-proportion group, analyze the occurrence trends of these key mismatch periods by building a prediction model, and predict the time of their next occurrence.

[0082] Specifically, a neural network model is used to train the prediction model. The input layer is the timestamp corresponding to the critical mismatch period and the corresponding electricity metering deviation rate; the hidden layer is composed of 1-2 layers of LSTM units to capture the long-term dependencies of the time series; the output layer is composed of a fully connected layer to output the critical mismatch probability (between 0 and 1).

[0083] Training parameters: batch size: 32-64, number of iterations: 50-100, learning rate: 0.001; loss function: binary cross entropy.

[0084] Based on the prediction model output, the probability of the future analysis period being a critical mismatch period is determined. If the output probability of a critical mismatch period is greater than the probability limit, the analysis period is predicted to be a critical mismatch period. If the output probability of a critical mismatch period is less than or equal to the probability limit, the analysis period is predicted to be a non-critical mismatch period.

[0085] For the analysis period predicted to be a critical mismatch period, energy metering correction compensation is performed.

[0086] Specifically, the average value of the electric energy metering deviation rate corresponding to the key mismatch period in the high-proportion group is calculated as the benchmark deviation compensation rate.

[0087] Combined with the positive and negative nature of the difference between the metered value and the actual value, the meter measurement correction compensation is performed on the analysis period predicted to be the critical mismatch period using the benchmark deviation compensation rate.

[0088] If the difference between the metered value and the actual value is positive, the metered value is large and needs to be reduced during correction. If the difference between the metered value and the actual value is negative, the metered value is small and needs to be increased during correction.

[0089] For example, if the average deviation rate of the high-proportion group is 3.5%, the benchmark deviation compensation rate is 3.5%. For the predicted key mismatch period, the electricity meter measurement value is adjusted according to this ratio (for example, the original measurement is 100kWh, and after correction it is 100×(1-3.5%)=96.5kWh).

[0090] Optionally, to leave enough time for data processing and system response, you can make corrections in advance. The time for early correction can be set to half or one third of the analysis period. For example, if the analysis period is one hour, you can complete the correction 30 minutes or 20 minutes in advance.

[0091] Step S3 has at least the following effects: by analyzing the proportion of metering anomalies in different types of key mismatch time groups, screening out high-proportion groups, using a neural network model to predict their occurrence trends and times, and performing electricity metering correction and compensation, the occurrence of key mismatch periods can be predicted in advance, and correction and compensation can be performed based on the average of historical metering deviation rates, which can effectively reduce settlement errors caused by inaccurate metering of electricity meters. At the same time, targeted adjustments can be made based on the positive or negative difference between the metered value and the actual value, making the correction more scientific and reasonable.

[0092] In this embodiment, step S1 identifies the time periods with high incidence of mismatches through historical data and determines the time period division rules based on the actual data characteristics, which provides a time period division framework for step S2. Step S2 divides the historical time periods into analysis time periods based on the rules, so that the subsequent deviation calculation and cluster analysis are based on time units that fit the actual mismatch cycle, thereby optimizing the analysis errors caused by subjective division; the analysis results of steps S1 and S2 are the core inputs of the prediction model of step S3.

[0093] Example 2 Based on the same inventive concept as the bidirectional measurement correction method for an electric energy meter in the aforementioned embodiment, Figure 3 As shown, the present application provides a bidirectional measurement correction system for an electric energy meter, wherein the system specifically includes: Time period division rule determination module: obtains the power generation of distributed energy and the power consumption of users in historical data, identifies the continuous time periods with significant differences between power generation and power consumption as the high-incidence mismatch periods, selects and analyzes the high-incidence mismatch periods, and determines the time period division rules for predictive analysis.

[0094] The execution process is as follows: obtain the power generation of distributed energy and user electricity consumption in historical data, calculate the electricity difference value at each time point after aligning the timestamps, mark the points that exceed the preset limit as significant difference points, merge adjacent significant difference points through the time deviation limit to form an integrated group, and then determine the time periods with high mismatch incidence. These time periods are arranged in ascending order of length, and the mean and standard deviation are calculated to filter out extreme values. Finally, the minimum value within the retained range is taken as the time period division rule for predictive analysis to make the time period division fit the actual mismatch cycle.

[0095] Critical mismatch period analysis module: Based on the determined period division rules, the period is divided into analysis periods, the difference between the total power generation and the total power consumption in each analysis period is calculated, the periods with high degree of difference are extracted as critical mismatch periods, and cluster analysis of the difference value range is performed on the critical mismatch periods to obtain different types of critical mismatch period groups.

[0096] The execution process is as follows: Based on the determined period division rules, the historical period is divided into several analysis periods, and the total deviation value between power generation and power consumption in each period is calculated. The period exceeding the deviation degree judgment threshold is marked as a high-degree difference period, that is, a critical mismatch period.

[0097] K-means clustering was used to analyze the deviation values ​​of critical mismatch periods. The initial cluster centers were randomly selected, and the deviation values ​​were assigned to the nearest cluster according to distance. The cluster centers were iteratively updated until convergence or the maximum number of iterations was reached. The clustering effect was verified by variance, and critical mismatch period groups with different deviation value ranges were obtained.

[0098] Time period prediction and correction module: Analyzes the proportion of different types of key mismatch time period groups in the occurrence of power metering anomalies, extracts key mismatch time period groups with a high proportion of metering anomalies as high-proportion groups, analyzes the trend of key mismatch time periods in the total proportion groups, predicts the time of next occurrence, and performs power metering correction and compensation.

[0099] The execution process is as follows: the energy metering deviation rate of each key mismatch period group is calculated, and those exceeding the standard value are marked as metering anomalies. The abnormal proportion is counted and K-means clustering is used to distinguish high and low proportion groups.

[0100] For the high-proportion group, the LSTM neural network model is used (input timestamp and deviation rate, the hidden layer captures time series dependency) to predict the time of the next critical mismatch period. If the predicted probability exceeds the limit, the benchmark compensation rate is calculated based on the mean deviation rate of the high-proportion group. Combined with the positive or negative difference between the measured value and the actual value, the metered value of the electricity meter in the predicted period is corrected and compensated.

[0101] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the foregoing embodiments. The foregoing embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A bidirectional measurement correction method for an electric energy meter, characterized in that: The following steps are involved: Obtain historical data on the generation of distributed energy resources and the power consumption of users, identify sustained periods with significant differences between generation and consumption as periods with high mismatch incidence, conduct selection analysis on these periods, and determine the period division rules for predictive analysis; Based on the determined period division rules, the period is divided into analysis periods, the difference between the total power generation and the total power consumption in each analysis period is calculated, the periods with high degree of difference are extracted as key mismatch periods, and cluster analysis is performed on the key mismatch periods based on the difference value range to obtain different types of key mismatch period groups; Analyze the proportion of different types of critical mismatch time periods in the occurrence of electricity metering anomalies, extract the critical mismatch time period groups with a high proportion of metering anomalies as the high-proportion group, analyze the trend of the key mismatch time periods in the common proportion group, predict the time of the next occurrence, and perform electricity metering correction and compensation.

2. A bidirectional measurement correction method for an electric energy meter according to claim 1, characterized in that: The process of obtaining the time period division rule is as follows: Extract all the time periods with high mismatch incidence, arrange these time periods according to their corresponding time period lengths, and obtain an ascending sequence of the time periods with high mismatch incidence; Calculating the average value and standard deviation of the time period lengths in the ascending sequence of the time period with high incidence of mismatches to obtain the time length mean and time length standard deviation; setting a retention range based on the time length mean and time length standard deviation; Traverse the ascending sequence of the high-incidence mismatch periods, retain the high-incidence mismatch periods within the retention range, and extract the minimum value of the retained high-incidence mismatch periods as the period division rule for prediction analysis.

3. The bidirectional measurement correction method for an electric energy meter according to claim 1, characterized in that: The process of obtaining the high-incidence mismatch period is as follows: The absolute value of the difference between power generation and power consumption at each time point is calculated as the power difference value. The time points exceeding the preset limit are marked as significant difference time points. Adjacent significant difference points are merged through the time deviation limit to form an integrated group. The time period corresponding to the integrated group is calculated as the period with high mismatch incidence.

4. A bidirectional measurement correction method for an electric energy meter according to claim 3, characterized in that: The acquisition process of the integration group is as follows: Calculate the difference between the significant difference time points corresponding to the adjacent power difference values ​​in the significant difference value sequence to obtain the time deviation value; if it is less than or equal to the time deviation limit, mark it as a value group that can be merged; Extract all mergible value groups, traverse all mergible value groups, and integrate the same power difference values ​​in different mergible value groups to obtain an integrated group.

5. The bidirectional measurement correction method for an electric energy meter according to claim 1, characterized in that: The process of obtaining the critical mismatch period is as follows: Calculate the absolute value of the difference between the total power generation and the total power consumption in each analysis period as the total power deviation value of the period; If it is greater than the deviation degree judgment threshold, it is marked as a high degree difference period and the high degree difference period is regarded as a key mismatch period.

6. A bidirectional measurement correction method for an electric energy meter according to claim 1, characterized in that: The process of obtaining the high-proportion cluster is as follows: Obtain the proportion of measurement anomalies corresponding to each type of key mismatch period group; use the K-means clustering method to perform cluster analysis on the measurement anomaly proportion, and set the number of clusters to 2, namely, the high measurement anomaly proportion and the low measurement anomaly proportion; the group with the higher mean anomaly proportion in the two obtained clusters is the high proportion group.

7. A bidirectional measurement correction method for an electric energy meter according to claim 6, characterized in that: The process of obtaining the measurement anomaly ratio is as follows: For each type of critical mismatch period in the critical mismatch period group, the sum of the forward and reverse electricity in the critical mismatch period is calculated as the total interactive electricity in the period; the absolute value of the difference between the metered value and the actual value is used as the absolute deviation value of the period, and the ratio of the absolute deviation of the period to the total interactive electricity in the period is used as the electricity measurement deviation rate; if it is greater than the standard value of the electricity measurement deviation rate, it is marked as a measurement abnormality; The key mismatch periods of measurement anomalies are extracted, and their total number is counted as the number of measurement anomalies. The ratio of the number of measurement anomalies to the total number of key mismatch periods of this type is taken as the measurement anomaly proportion.

8. The bidirectional measurement correction method for an electric energy meter according to claim 1, characterized in that: The process of predicting the next occurrence time is: Obtain the key mismatch periods in the high-proportion clusters and build a prediction model by training the prediction model with a neural network model; Based on the prediction model output, the probability of the future analysis period being a critical mismatch period is output. If the output probability of the critical mismatch period is greater than the probability limit, the analysis period is predicted to be a critical mismatch period, and the time of its next occurrence is set.

9. A bidirectional measurement correction method for an electric energy meter according to claim 8, characterized in that: The process of performing electric energy measurement correction and compensation is as follows: For the analysis period predicted to be a critical mismatch period, the average value of the electric energy metering deviation rate corresponding to the critical mismatch period in the high-proportion group is calculated as the benchmark deviation compensation rate.

10. A bidirectional measurement correction system for electric energy meters, characterized in that: The system is used to execute the method according to any one of claims 1 to 9, and the system comprises: Time period division rule determination module: This module obtains the power generation of distributed energy resources and the power consumption of users from historical data, identifies the continuous periods with significant differences between power generation and power consumption as the high-incidence mismatch periods, selects and analyzes the high-incidence mismatch periods, and determines the time period division rules for predictive analysis; Key mismatch period analysis module: Based on the determined period division rules, the period is divided into analysis periods, the difference between the total power generation and the total power consumption in each analysis period is calculated, the periods with high degree of difference are extracted as key mismatch periods, and cluster analysis is performed on the key mismatch periods based on the difference value range to obtain different types of key mismatch period groups; Time period prediction and correction module: Analyzes the proportion of different types of key mismatch time period groups in the occurrence of power metering anomalies, extracts key mismatch time period groups with a high proportion of metering anomalies as high-proportion groups, analyzes the trend of key mismatch time periods in the total proportion groups, predicts the time of next occurrence, and performs power metering correction and compensation.

Images