A method and device for evaluating the metering state of an electric energy meter

Abstract

The application discloses a kind of electric energy metering state evaluation method and equipment.The method comprises: determining the technical line loss value of the object to be counted in the online loss statistical period;According to the technical line loss value, the initial line loss sample is classified, and the classified line loss sample is obtained;The abnormal sample data in the classified line loss sample is eliminated, and the target line loss sample is obtained;Based on the power level of each user in the target line loss sample and the correlation of power curve, the user is merged, and the merged target user is obtained;The multiple linear regression model of statistical line loss and the power correlation parameter in the target line loss sample and the actual power consumption of each target user are used to determine the model regression coefficient;The metering state of each user corresponding electric energy meter is analyzed using anomaly detection criteria and model regression coefficient, and the abnormal electric energy meter is obtained.The application realizes the effective detection of the metering state abnormal electric energy meter.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power supply, in particular to a kind of electric energy metering state evaluation method and equipment. BACKGROUND

[0002] With the growth of running time, the aging of metering equipment, the bad running environment, the over-capacity operation and the user electricity stealing and other factors, metering equipment failure, overage occurs from time to time. The traditional electronic electric energy meter does not have the function of self-monitoring of measurement error. Because the electric energy metering state cannot be monitored online, the fault, overage metering equipment and user electricity stealing cannot be found and processed in time for a long time, resulting in a large amount of power error, power loss, difficulty in power refund work, and potential marketing risk. SUMMARY

[0003] The present application provides a kind of electric energy metering state evaluation method and equipment, realize the effective detection of the electric energy metering state abnormality.

[0004] According to one aspect of the present application, a kind of electric energy metering state evaluation method is provided, comprising:

[0005] determine the technical line loss value of the online loss statistical period of the object to be counted;

[0006] According to the initial line loss sample of the associated statistical line loss value of the technical line loss value, classification and rejection are carried out, and classification line loss sample is obtained;

[0007] The abnormal sample data in the classification line loss sample is rejected by using data outlier detection method, and target line loss sample is obtained;

[0008] If the number of samples of the target line loss sample does not satisfy the preset sample margin set by the number of users contained in the object to be counted, the user is merged based on the power level and power curve correlation of each user in the target line loss sample, and the merged target user is obtained;

[0009] The multiple linear regression model of statistical line loss created in advance and the power related parameters and the actual power consumption of each target user in the target line loss sample are used to determine the corresponding model regression coefficient;

[0010] The electric energy metering state corresponding to each user is analyzed by using the model regression coefficient and the abnormal detection criterion, and the abnormal electric energy meter is obtained.

[0011] According to another aspect of the present application, a kind of electric energy metering state evaluation device is provided, comprising:

[0012] Line loss value determination module, for determining the technical line loss value of the online loss statistical period of the object to be counted;

[0013] The classification and elimination module is configured to classify and eliminate the initial line loss samples of the associated statistical line loss value according to the technical line loss value, to obtain classified line loss samples.

[0014] The detection and elimination module is configured to eliminate abnormal sample data in the classified line loss samples by using a data abnormal value detection method, to obtain target line loss samples.

[0015] The user merging module is configured to, if the number of the target line loss samples does not satisfy a preset sample margin set according to the number of users included in the object to be counted, merge users based on the power level and power curve correlation of each user in the target line loss samples, to obtain merged target users.

[0016] The coefficient determination module is configured to determine corresponding model regression coefficients by using a pre-created multivariate linear regression model of statistical line loss and the power-related parameters and actual power consumption of each target user in the target line loss samples.

[0017] The state analysis module is configured to analyze the metering state of each user by using an abnormality detection criterion and the model regression coefficients, to obtain abnormal electric energy meters.

[0018] According to another aspect of the present application, an electronic device is provided, which comprises:

[0019] at least one processor; and

[0020] a memory in communication with the at least one processor; wherein

[0021] the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the electric energy metering state evaluation method according to any one of the embodiments of the present application.

[0022] According to another aspect of the present application, a computer readable storage medium is provided, which stores computer instructions for enabling a processor to execute the electric energy metering state evaluation method according to any one of the embodiments of the present application.

[0023] According to another aspect of the present application, a computer program product is provided, which comprises a computer program for enabling a processor to execute the electric energy metering state evaluation method according to any one of the embodiments of the present application.

[0024] The technical scheme of the embodiment of the present application classifies the initial line loss sample of the associated statistical line loss value according to the determined technical line loss value, guarantees the consistency of the line loss sample attribute, adopts the data anomaly detection method to eliminate the abnormal sample data in the classified line loss sample, reduces the influence of the unstable independent variable on the evaluation result, and solves the independent variable combination according to the principle of the similar power level and the highest power curve correlation, so as to achieve the independent variable dimension reduction effect of the multiple linear regression model. In addition, the anomaly detection criterion is used to detect the significant regression coefficient to determine the electric energy meter with the abnormal metering state, and the effective detection of the electric energy meter with the abnormal metering state is realized.

[0025] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0027] Figure 1 is a flow chart of an electric energy meter metering state evaluation method provided by an embodiment of the present application;

[0028] Figure 2 is a flow chart of another electric energy meter metering state evaluation method provided by an embodiment of the present application;

[0029] Figure 3 is a structural schematic diagram of an electric energy meter metering state evaluation device provided by an embodiment of the present application;

[0030] Figure 4 is a structural block diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings of the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0032] It is to be understood that the terminology "first", "second" and the like used in the specification and the claims of the application as well as the foregoing drawings is merely intended to distinguish between similar objects and not necessarily to describe a particular sequential or chronological order. It is to be understood that the use of data "herein" is meant to encompass the use of data in the present application, unless otherwise indicated. Moreover, the use of the terms "including", "comprising", and variations thereof, is intended to encompass the inclusion of the recited elements, but not the exclusion of others. The use of the term "about" in relation to a given value is intended to encompass the recited value and variations of the value due to tolerances, measurement errors, and the like.

[0033] In an embodiment, Figure 1 is a flowchart of an electric energy metering state evaluation method provided by an embodiment of the application. The embodiment can be applied to the online automatic evaluation of the metering state of an electric energy meter. The method can be executed by an electric energy metering state evaluation device, which can be implemented in the form of hardware and / or software, and can be configured in an electronic device. Exemplarily, the electronic device can be a terminal device such as a tablet computer or a personal computer. As shown in Figure 1 , the method comprises the following steps.

[0034] S110, determining a technical line loss value of a to-be-counted object in an online line loss counting period.

[0035] In an example, the to-be-counted object refers to a power supply and use unit that needs to be counted for line loss, for example, the to-be-counted object can be a transformer area and a line. Generally, several hundred electric energy meters, i.e., several hundred users, can be included in a to-be-counted object. The line loss counting period refers to a time period for counting the line loss value of the to-be-counted object. The line loss counting period can be counted in units of hours, days, or weeks, for example, the line loss counting period can be one day. The technical line loss value refers to the electric energy loss caused by the physical characteristics of the power supply equipment during electric energy transmission and distribution. In an example, the technical line loss value can include fixed line loss and variable line loss. The fixed line loss, which can also be referred to as no-load loss, refers to the loss generated by the power supply equipment when there is no load current passing through, i.e., the fixed line loss is a constant value and does not change significantly with the change of the load current. The variable line loss, which can also be referred to as load loss, refers to the loss generated by the power supply equipment when there is a load current passing through, i.e., the variable loss changes with the size of the load current and the power factor.

[0036] In an example, the technical line loss value of the to-be-counted object in a line loss counting period can be counted based on a voltage lossless transmission theory line loss calculation method.

[0037] S120, classify and eliminate the initial line loss samples according to the technical line loss value and the associated statistical line loss value, to obtain classified line loss samples.

[0038] The statistical line loss value refers to the amount of electricity lost in the process of inputting electrical energy of a statistical object to user consumption. The statistical line loss value can be the difference between the total power supply and the total power consumption. The initial line loss sample refers to the amount of electricity related parameters associated with the statistical line loss value based on a pre-created statistical line loss multiple linear regression model. For example, the initial line loss sample can include the following variables: line loss statistical actual value y, fixed loss x b , number of users n, power consumption u n of n users, user regression coefficients x n corresponding to n users, total power supply S, total power supply regression coefficient x s , variable line loss w t , variable line loss regression coefficient x t . Wherein, x n is used to represent the attribute and weight of user power consumption in line loss; x t is used to represent the adjustment degree of the technical line loss value.

[0039] The classified line loss sample refers to a line loss anomaly type corresponding to an abnormal line loss sample in the initial line loss sample. For example, the line loss anomaly type of the classified line loss sample can include: high loss abnormal sample and low loss abnormal sample.

[0040] In an embodiment, the upper threshold and lower threshold of the classification of the initial line loss sample can be determined in a preconfigured manner, the initial line loss sample with a statistical line loss value between the lower threshold and the upper threshold is regarded as a normal line loss sample, and the normal line loss sample is eliminated from the initial line loss sample to obtain an abnormal line loss sample in the initial line loss sample; then the initial line loss sample with a statistical line loss value less than the lower threshold is regarded as a low loss abnormal sample, and the initial line loss sample with a statistical line loss value greater than the upper threshold is regarded as a high loss abnormal sample; then the number of low loss abnormal samples and the number of high loss abnormal samples are counted, if the number of high loss abnormal samples is greater than the number of low loss abnormal samples, the low loss abnormal sample is eliminated from the initial line loss sample, and the high loss abnormal sample is taken as the classified line loss sample; if the number of high loss abnormal samples is less than the number of low loss abnormal samples, the high loss abnormal sample is eliminated from the initial line loss sample, and the low loss abnormal sample is taken as the classified line loss sample.

[0041] S130, eliminate abnormal sample data in the classified line loss sample by using a data outlier detection method, to obtain target line loss samples.

[0042] In an example, the data anomaly detection method is used to identify an algorithm for identifying data points that do not conform to expectations or exhibit significant differences in the classified line loss samples. For example, the data anomaly detection method can be a quartile method or a standard deviation method. An example is provided to illustrate the process of removing abnormal sample data using the data anomaly detection method. Specifically, the quartile method is used to determine the upper and lower abnormal boundary values, and then the abnormal sample data with a statistical line loss rate greater than the upper abnormal boundary value and the abnormal sample data with a statistical line loss rate less than the lower abnormal boundary value are removed from the classified line loss samples to obtain the target line loss samples.

[0043] In an example, the number of samples in the initial line loss samples is determined according to the number of users included in the object to be counted and the preset sample margin. In order to better extract sample features, the number of samples in the initial line loss samples needs to be greater than the number of users included in the object to be counted. If sufficient number of samples cannot be obtained, the maximum value of the actual number of samples that can be obtained is taken.

[0044] S140, if the number of samples in the target line loss samples does not satisfy the preset sample margin set according to the number of users included in the object to be counted, the users are merged based on the power level and the power curve correlation of each user in the target line loss samples to obtain the merged target users.

[0045] In an example, the users with zero power consumption in the full cycle in the target line loss samples can be removed, and then the power curve correlation coefficient between the power curve of each user and the power curve of other single users is calculated. The power curve correlation between the power curve of each user and the power curve of other single users is determined based on the power curve correlation coefficient, and the user with the highest power curve correlation with one user is found, and the two users with a correlation coefficient reaching a correlation coefficient threshold are merged into a user group. If the number of users composed of the user group and the single users not merged does not satisfy the preset sample margin, the two single users with similar power levels are merged to obtain the merged target users.

[0046] In an example, the preset sample margin is used to represent the number of samples that need to be greater than the number of variables. For example, the number of variables is 10, and the preset sample margin is 4, then the number of samples needs to be 14.

[0047] S150, the multiple linear regression model of the statistical line loss created in advance and the power related parameters in the target line loss samples and the actual power consumption of each target user are used to determine the corresponding model regression coefficients.

[0048] In an example, the model regression coefficient refers to a regression coefficient involved in the pre-created multivariate linear regression model of the statistical line loss, and the model regression coefficient can include a user regression coefficient. n , a total power supply regression coefficient x s , and a variable line loss regression coefficient x t .

[0049] In an example, the total power supply and the actual power consumption of each target user in the target line loss sample can be obtained, and the sum of the actual power consumption of all target users in the target line loss sample is determined as the total actual power consumption; then the difference between the total power supply and the total actual power consumption is taken as the statistical line loss actual value, and then the statistical line loss actual value, the actual power consumption, and the technical line loss value are input into the pre-created multivariate linear regression model solving formula of the statistical line loss to obtain the corresponding model regression coefficient.

[0050] S160, analyze the metering state of each user's electric energy meter according to the anomaly detection criterion and the model regression coefficient to obtain an abnormal electric energy meter.

[0051] In an example, the model regression coefficient refers to a regression coefficient involved in the pre-created multivariate linear regression model of the statistical line loss, and the model regression coefficient can include a user regression coefficient. The anomaly detection criterion refers to a criterion for detecting anomalies in the user regression coefficient, and the anomaly detection criterion can be a 3σ criterion. In an embodiment, the positive and negative values of the user regression coefficient are classified according to the positive and negative values, i.e., the user regression coefficient is classified into two categories of positive and negative values; then the anomaly detection criterion is used to detect the regression coefficient that is significantly different in a group of data composed of positive values, and the anomaly detection criterion is used to detect the regression coefficient that is significantly different in a group of data composed of negative values, and the regression coefficient that is significantly different is an abnormal user regression coefficient, the electric energy meter corresponding to the abnormal user regression coefficient is an abnormal electric energy meter, and the corresponding user is an abnormal user.

[0052] The technical solution of the embodiment classifies the initial line loss sample associated with the determined statistical line loss value according to the technical line loss value, ensures the consistency of the line loss sample properties; uses the data anomaly detection method to eliminate the abnormal sample data in the classified line loss sample, reduces the influence of unstable independent variables on the evaluation result; and uses the independent variable merging and combination principle of similar power level and highest power curve correlation to solve, to achieve the independent variable dimension reduction effect of the multivariate linear regression model; and uses the anomaly detection criterion to detect the significant regression coefficient to determine the electric energy meter with abnormal metering state, to effectively detect the electric energy meter with abnormal metering state.

[0053] In an embodiment, Figure 2is a flowchart of another electric energy metering state evaluation method provided by the embodiment of the present application, and the embodiment is a further description of the determination process of the technical line loss value, the screening process of the classified line loss sample, the screening process of the target line loss sample, the user merging process, the determination process of the model regression coefficient, and the screening process of the abnormal electric energy meter based on the above embodiment. As shown in Figure 2 the method comprises:

[0054] S210, acquiring actual active power of each user in each line loss statistical sub-period in the to-be-counted object, user voltage, and gateway power supply voltage.

[0055] The line loss statistical sub-period is a subset of the line loss statistical period, that is, the line loss statistical period is divided into multiple sub-periods, and each sub-period is taken as a line loss statistical sub-period; the actual active power refers to the power corresponding to the active power actually consumed by the user in the power consumption process; the user voltage refers to the actual voltage value delivered to the user; and the gateway power supply voltage refers to the voltage value of the metering gateway of the power input of the to-be-counted object, for example, the gateway power supply voltage can be the voltage value at the outgoing line side of the transformer substation or the incoming line side of the user distribution room.

[0056] In an example, the user voltage can be acquired by using an electric energy meter or a multifunctional power detector, or the user voltage can be acquired by using an oscilloscope or a voltage meter. In an example, the gateway power supply voltage can be acquired from a transformer substation monitoring system or by using a gateway metering device. In an example, the actual active power can be acquired by using an electric energy meter or from a power supply management system.

[0057] S220, determining the theoretical active power of the associated user in the line loss statistical sub-period according to the actual active power, the user voltage, and the gateway power supply voltage.

[0058] In an example, it is assumed that the theoretical active power of the i-th user in the t-th Δt period is denoted as ΔW ti , and the calculation formula of the theoretical active power can be: ΔW ti = ΔW' ti * U t0 / U ti ; wherein U ti is the user voltage of the i-th user in the t-th Δt period, U t0 is the gateway power supply voltage in the t-th Δt period, and ΔW' ti is the actual active power of the i-th user in the t-th Δt period.

[0059] S230, determining the user theoretical power of the associated user in the line loss statistical period according to the theoretical active power of each user in each line loss statistical sub-period.

[0060] In an example, the user theoretical power in the line loss statistics period can be the sum of the theoretical active power in each line loss statistics sub-period. Illustratively, assuming that the line loss statistics period is divided into N line loss statistics sub-periods, the formula of the user theoretical power can be: wherein, W i is the user theoretical power of the i-th user, N is the number of line loss statistics sub-periods contained in the line loss statistics period, ΔW ti is the theoretical active power of the i-th user in the t-th Δt period.

[0061] S240, determining the theoretical loss power of each user in the line loss statistics period according to the user theoretical power and the measured power of each user in the line loss statistics period.

[0062] wherein, the measured power refers to the power actually monitored in the line loss statistics period of each user; the theoretical loss power refers to the power value theoretically lost in the line loss statistics period of each user. In an example, the difference between the user theoretical power and the measured power of each user in the line loss statistics period can be used as the theoretical loss power of each user in the line loss statistics period. Illustratively, the calculation formula of the theoretical loss power of the i-th user in the line loss statistics period can be: W iloss = W i -W’ i ; wherein, W iloss represents the theoretical loss power of the i-th user in the line loss statistics period; W i represents the user theoretical power of the i-th user in the line loss statistics period; W’ i represents the measured power of the i-th user in the line loss statistics period.

[0063] S250, determining the technical line loss value of the to-be-counted object in the line loss statistics period according to the theoretical loss power of each user and the number of users contained in the to-be-counted object.

[0064] In an example, the theoretical loss power of each user contained in the to-be-counted object can be added to obtain the technical line loss of the to-be-counted object in the line loss statistics period. Illustratively, the calculation formula of the technical line loss value of the to-be-counted object in the line loss statistics period can be: wherein, W loss represents the variable line loss in the technical line loss value of the to-be-counted object in the line loss statistics period; n represents the number of users contained in the to-be-counted object; W iloss represents the theoretical loss power of the i-th user in the line loss statistics period. Wherein, W loss is equivalent to w t .

[0065] In an example, S210-S250 is a technical line loss statistical method for calculating the technical line loss value by using the voltage lossless conduction theory line loss calculation method. The technical line loss statistical method is based on the supply voltage lossless conduction to the user side, and the user theoretical power is calculated from the measurement angle under the voltage lossless condition. The difference between the user theoretical power and the measured power is the user theoretical loss power. The cumulative total user theoretical loss power is the theoretical loss power of the object to be counted, which is used as the technical line loss value.

[0066] S260, based on the technical line loss value and the total power meter power consumption and the power consumption of the associated equipment not included in the measurement and the power meter accuracy level, determine the upper threshold and the lower threshold of the initial line loss sample classification.

[0067] Wherein, the total power meter power consumption refers to the power consumed by the power meter when it is running; the power consumption of the associated equipment not included in the measurement refers to the fixed loss; the threshold basic value can be the sum of the calculated theoretical loss power and the quantifiable fixed loss of the equipment. In an example, the upper threshold of the initial line loss sample classification can be the sum of the threshold basic value and the uncertainty caused by the difference between the power meter accuracy level; the lower threshold can be the uncertainty caused by the difference between the threshold basic value and the power meter accuracy level.

[0068] S270, according to the upper threshold, the high loss abnormal sample is screened from the initial line loss sample, and according to the lower threshold, the low loss abnormal sample is screened from the initial line loss sample.

[0069] In an example, the initial line loss sample with a statistical line loss value between the lower threshold and the upper threshold is a normal line loss sample; the initial line loss sample with a statistical line loss value exceeding the upper threshold is a high loss abnormal sample; the initial line loss sample with a statistical line loss value lower than the lower threshold is a low loss abnormal sample. In the embodiment, the normal line loss sample in the initial line loss sample is removed to obtain the abnormal line loss sample; then the line loss sample greater than the upper threshold in the abnormal line loss sample is taken as the high loss abnormal sample, and the line loss sample less than the lower threshold in the abnormal line loss sample is taken as the low loss abnormal sample.

[0070] S280, if the number of high loss abnormal samples contained in the initial line loss sample is greater than the number of low loss abnormal samples, the low loss abnormal samples are removed from the initial line loss sample, and the high loss abnormal samples are taken as the classified line loss samples.

[0071] The number of high loss abnormal samples and the number of low loss abnormal samples contained in the initial line loss sample are compared, and the abnormal sample with more samples is retained, for example, if the number of high loss abnormal samples is greater than the number of low loss abnormal samples, the low loss abnormal samples are removed from the initial line loss sample, and the high loss abnormal samples are taken as the classified line loss samples.

[0072] S290, if the number of high-loss abnormal samples contained in the initial line loss samples is less than the number of low-loss abnormal samples, the high-loss abnormal samples are removed from the initial line loss samples, and the low-loss abnormal samples are taken as the classification line loss samples.

[0073] In an example, the number of high-loss abnormal samples and the number of low-loss abnormal samples contained in the initial line loss samples are compared, and the abnormal samples with more number of samples are retained, for example, if the number of high-loss abnormal samples is less than the number of low-loss abnormal samples, the high-loss abnormal samples are removed from the initial line loss samples, and the low-loss abnormal samples are taken as the classification line loss samples.

[0074] S2100, determining the corresponding statistical line loss rate according to the statistical line loss power and the total power supply in the classification line loss samples.

[0075] In an example, the statistical line loss rate is used to represent the operation efficiency and management level of the power system. Generally, the statistical line loss rate refers to the percentage of the statistical line loss power to the total power supply in a certain time. The statistical line loss power is the difference between the total power supply and the total actual power consumption; the statistical line loss rate is the percentage of the ratio between the statistical line loss power and the total power supply. The total actual power consumption is the sum of the actual power consumptions of all users contained in the classification line loss samples. It should be noted that the statistical line loss power can also be referred to as the statistical line loss actual value, or the statistical line loss value.

[0076] S2110, determining the corresponding abnormal upper boundary value and abnormal lower boundary value by using the quartile method and the statistical line loss rate.

[0077] In an example, the statistical line loss rates corresponding to each classification line loss sample are arranged in ascending order; then the positions of the quartiles, i.e. the lower quartile, the median and the upper quartile, are determined from the arranged statistical line loss rates; then since the positions of the quartiles are usually not integers, the values of the specific quartiles can be determined by interpolation; then the interquartile range is determined based on the difference between the upper quartile and the lower quartile; then the abnormal lower boundary value is determined based on the lower quartile and the interquartile range, and the abnormal upper boundary value is determined based on the upper quartile and the interquartile range.

[0078] S2120, removing the abnormal sample data with the statistical line loss rate greater than the abnormal upper boundary value and the abnormal sample data with the statistical line loss rate less than the abnormal lower boundary value from the classification line loss samples to obtain the target line loss samples.

[0079] The statistical line loss rate corresponding to each classification line loss sample is compared with the abnormal upper boundary value and the abnormal lower boundary value, and the abnormal sample data with a statistical line loss rate greater than the abnormal upper boundary value is removed from the classification line loss sample, and the abnormal sample data with a statistical line loss rate less than the abnormal lower boundary value is removed from the classification line loss sample, to obtain a target line loss sample.

[0080] S2130, determine the power curve correlation between the power curve of each user in the target line loss sample and the power curve of another single user.

[0081] In an example, the power curve of each user in the target line loss sample and the power curve of another single user can be plotted in the same coordinate system, and the trend and change trend of the two curves can be intuitively analyzed. If the trend of the power curves of the two users is similar, it indicates that the power curves of the two users have a certain correlation.

[0082] S2140, find another user with the highest correlation with the power curve of a user and the corresponding correlation coefficient.

[0083] In an example, if the power curves of the two users are in a linear relationship, the Pearson correlation coefficient can be selected for calculation; if the curve relationship is more complex, the Spearman correlation coefficient can be more suitable. In an embodiment, the correlation coefficient between the power curves of the two users can be calculated according to the selected correlation coefficient calculation method; if the correlation coefficient is in the range of -1 to 1, and the absolute value is closer to 1, the correlation is stronger; otherwise, the absolute value is closer to 0, and the correlation is weaker.

[0084] In an embodiment, another user with the highest correlation with the power curve of a user is found, and the correlation coefficient between the power curve of the user and the power curve of another user is determined.

[0085] S2150, merge two users with a correlation coefficient reaching a correlation coefficient threshold into a user group.

[0086] The correlation coefficient threshold is used to represent a threshold value for determining whether to merge two users; if the correlation coefficient reaches the correlation coefficient threshold, it can be considered that the power curves of the two users are similar, and the two users can be directly merged into one power curve and regarded as a user group.

[0087] The user merging according to the correlation of the power curves is to reduce the multicollinearity problem of the independent variables and realize the dimension reduction of the independent variables of the model. The merging may cause the actual abnormal independent variable features to be unable to be presented and finally unable to be detected. Generally, the users with high correlation of the power curves have high similarity of the power consumption features. The two users with high similarity of the power consumption features are merged to ensure that the overall features are maintained after the merging, and thus the detection of the abnormal independent variables can be ensured.

[0088] S2160, if the number of users composed of the user group and the unmerged single user does not satisfy the preset sample margin, the users are merged according to the power levels of the unmerged single users to obtain the target users after the merging.

[0089] In the formula, the power of the meter in the abnormal metering state is mostly at a medium or low level. The users with low correlation are merged according to the similar load levels to avoid the features of the low-power abnormal users and the users with high power consumption loads being masked after the merging and being unable to be detected.

[0090] S2170, the total power supply and the actual power consumption of each target user in the target line loss sample are obtained.

[0091] In the formula, the total power supply refers to the total power supplied to the object to be counted in the line loss counting period; and the actual power consumption refers to the power consumed by each target user in the target line loss sample in the line loss counting period.

[0092] S2180, the actual line loss value is determined according to the total power supply and the actual power consumption of each target user.

[0093] In an example, the actual power consumptions of all the target users in the target line loss sample are counted to obtain the total actual power consumption; and then the difference between the total power supply and the total actual power consumption is taken as the actual line loss value. Exemplarily, the calculation formula of the actual line loss value can be as follows: In the formula, y represents the actual line loss value; S represents the total power supply; u i represents the actual power consumption of the i-th user; and n represents the total number of the target users included in the target line loss sample.

[0094] S2190, the actual line loss value, the actual power consumption and the technical line loss value are input into the solving formula of the multivariate linear regression model of the statistical line loss pre-constructed to obtain the corresponding model regression coefficients.

[0095] In an example, the solving formula of the multivariate linear regression model of the statistical line loss is as follows: y = x b + u1 * x1 + u2 * x2 + u3 * x3 + … + u n * x n + S * x s + w t*x t Where y represents the actual value of statistical line loss; S represents the total power supply; u n This represents the actual electricity consumption of the nth user; x b Indicates fixed losses; x n w represents the user regression coefficients corresponding to n users; t Indicates variable line loss; x t This represents the variable linear loss regression coefficient.

[0096] The target users after the above processing (including merged user groups and unmerged individual users) are solved using the aforementioned multiple linear regression model for statistical line loss; then, the multiple linear regression model is solved using the least squares method, as shown in the following formula: X=(U T U) -1 U T Y can be equivalent to the following formula:

[0097]

[0098] Where X is a column vector and x is the regression coefficient. b x n x s and x t The solution result; U consists of a constant term and the independent variable u n 、S、w t The parameter matrix composed of samples, with constant term x b The coefficient of is 1, and the independent variable u n For each user's actual electricity consumption (e.g., u 11 This refers to the actual electricity consumption of the first user on the first day, u 1n This refers to the actual electricity consumption of the nth user on the first day. The independent variable S is the total electricity supplied to the target object, and the independent variable w t Y represents the technical line loss value; Y is a column vector composed of lost electricity; m is the number of target line loss samples. If the line loss statistical period is 1 day, m can also be understood as the number of days. Correspondingly, u m1 This refers to the actual electricity consumption of the first user on day m, u mn This refers to the actual electricity consumption of the nth user on day m.

[0099] In an embodiment, it can be achieved through... The calculated y value, and u1, u2...u n S and w t Substituting into the solution formula of the multiple linear regression model for statistical line loss, X = (U T U) -1 U T Y can be used to obtain x bx1, x2, … x n x s and x t .

[0100] S2200, classifying the user regression coefficients according to positive and negative values to obtain first-class user regression coefficients and second-class user regression coefficients.

[0101] In an example, the positive and negative of the first-class user regression coefficients and the second-class user regression coefficients are different, for example, if the first-class user regression coefficient is a value greater than 0; correspondingly, the second-class user regression coefficient is a value less than 0. In an example, the solution value of the user regression coefficient is divided into two categories according to the positive and negative values, that is, it is judged whether the solution value of the user regression coefficient is greater than 0, if it is greater than 0, it is classified as the first-class user regression coefficient; if it is less than 0, it is classified as the second-class user regression coefficient.

[0102] S2210, using the Laplace criterion to cyclically detect a group of data composed of the first-class user regression coefficients and a group of data composed of the second-class user regression coefficients respectively, and screening to obtain abnormal user regression coefficients.

[0103] In an example, the Laplace criterion is referred to as the 3σ criterion. After detecting the abnormal value in the user regression coefficient x n as the independent variable in the group of data composed of the first-class user regression coefficients using the 3σ criterion, the value is removed and the abnormal value in the group of data composed of the first-class user regression coefficients is retested until no abnormal value is detected in the first-class user regression coefficient. Similarly, after detecting the abnormal value in the user regression coefficient x n as the independent variable in the group of data composed of the second-class user regression coefficients using the 3σ criterion, the value is removed and the abnormal value in the group of data composed of the second-class user regression coefficients is retested until no abnormal value is detected in the second-class user regression coefficient.

[0104] S2220, taking the electric energy meter of the user associated with the abnormal user regression coefficient as an abnormal electric energy meter.

[0105] In an example, the abnormal electric energy meter outputting the positive error measurement state in the low-loss abnormal sample; the abnormal electric energy meter outputting the negative error measurement state in the high-loss abnormal sample.

[0106] In an embodiment, in the case that the abnormal user corresponding to the abnormal electric energy meter is a group of abnormal users, the method further comprises: taking each user in the group of abnormal users as a single user, returning to the step of determining the technical line loss value of the to-be-counted object in the online loss counting period, and screening to obtain the abnormal user in the group of abnormal users. In the case that the abnormal user is a group of abnormal users, it is not clear which user in the group of abnormal users is abnormal. At this time, the group of abnormal users is decomposed into single users to solve again. The single abnormal users detected in the first solving and the single users decomposed from the group of abnormal users in the second solving are taken as single users, i.e., not combined with other users into a group of users, and the data processing and solving manner are the same as above. The electric energy meters whose results of both solving are abnormal are confirmed as the electric energy meters with abnormal metering state.

[0107] In an embodiment, the electric energy metering state evaluation method further comprises: inputting the model regression coefficient, the electric quantity related parameter, and the actual power consumption of each target user into the multivariate linear regression model of statistical line loss to obtain a statistical line loss prediction value; determining a statistical line loss average value according to the actual value of the statistical line loss in the target line loss sample and the sample quantity; determining a regression sum of squares according to the statistical line loss prediction value and the statistical line loss average value; determining a total sum of squares according to the actual value of the statistical line loss and the statistical line loss average value; and determining a model evaluation value of the multivariate linear regression model of statistical line loss according to the regression sum of squares and the total sum of squares.

[0108] In an example, the electric quantity related parameter comprises: an actual statistical line loss value, a technical line loss value, and a total power supply quantity. The statistical line loss prediction value refers to a statistical line loss value obtained by using the multivariate linear regression model of statistical line loss, i.e., by using the multivariate linear regression model of statistical line loss y = x b +u1*x1+u2*x2+u3*x3+…+u n *x n +S*x s +w t *x t , it is to be noted that y in the multivariate linear regression model of statistical line loss is to be solved, and other parameters are known, i.e., y at this time represents the statistical line loss prediction value; the actual value of the statistical line loss refers to a statistical line loss value obtained by using the difference between the total power supply quantity and the actual power consumption of all users, i.e., by using , the statistical line loss average value refers to the ratio between the actual value of the statistical line loss and the sample quantity. In an example, the difference between the actual value of the statistical line loss and the statistical line loss average value can be determined, and then the square of the difference between the two is taken as the total sum of squares. It is assumed that the actual value of the statistical line loss is denoted as y i , and the statistical line loss average value is denoted as , i.e., the total sum of squares is In an example, the difference between the statistical line loss prediction value and the statistical line loss average value can be determined, and the square of the difference between the two is taken as the regression sum of squares. For example, assuming that the statistical line loss prediction value is denoted as The statistical line loss average value is denoted as That is, the regression sum of squares is In an example, the ratio of the regression sum of squares to the total sum of squares can be taken as the model evaluation value of the multiple linear regression model of the statistical line loss. For example, assuming that the model evaluation value is denoted as R 2 The calculation formula is R 2 = SSR / SST. If the model evaluation value does not reach the preset evaluation value, it indicates that the multiple linear regression model of the statistical line loss is inaccurate, the low-power users with the average power less than the set threshold are output, and the process ends. The model inaccuracy indicates that there are largely unobservable variables, such as user electricity stealing, power meter failure and stop running, etc., which generally cause the user power to be at a low power level. The model inaccuracy makes the solution result unreliable, so the low-power users are output as target users and are not processed in the next step.

[0109] It can be understood that the degree of coincidence of the multiple linear regression model of the statistical line loss is verified through the model evaluation value R 2 If the model evaluation value R 2 reaches the preset evaluation value, it indicates that the degree of coincidence of the multiple linear regression model of the statistical line loss meets the demand, and the model regression coefficient is reliable.

[0110] The technical scheme of the embodiment of the present application takes power supply units such as transformer areas and lines as line loss statistical objects, and constructs a multivariate linear regression model based on line loss components. The properties and weights of each component in line loss are analyzed to determine the abnormal electric energy meter in metering state. First, based on the voltage lossless transmission theory line loss calculation method, the technical line loss is accurately calculated, and the problem that the technical line loss cannot be accurately measured and evaluated by using linear variables or constants is solved. Second, according to the calculated technical line loss value, the line loss properties of the statistical line loss are judged, the initial line loss samples of the statistical line loss are classified, and the line loss sample properties are ensured to be consistent. Third, the data outlier detection method is used to remove the abnormal sample data in the classified line loss samples, and the influence of the possible unstable independent variables on the evaluation results is reduced. Fourth, the independent variables are combined and solved according to the principle that the user power load level is similar and the load curve correlation is the highest, so that the independent variable dimensionality reduction in the multivariate linear regression model is achieved, the problem of multiple collinearity of independent variables is solved, the sample demand is reduced to solve the sample selection difficulty, the sample data time span is reduced to reduce the possibility of model inaccuracy due to changes in independent variable characteristics, and the difficulty of solving the multivariate linear regression model is reduced. Fifth, the data anomaly detection criterion is used to test the significant regression coefficients in the solution results to determine the electric energy meter in abnormal metering state. The solution results of the independent variable regression coefficients of the multivariate linear regression model based on line loss components cannot quantitatively evaluate whether the electric energy meter is in normal metering state, but compared with the electric energy meter in normal metering state, the influence of the abnormal electric energy meter on line loss should be significant, and the regression coefficient should be significantly different from that of the electric energy meter in normal metering state. Sixth, when the independent variable combination test is abnormal, the single independent variable is decomposed and re-solved for test confirmation, and the electric energy meter that passes the re-test confirmation is output, so that the reliability of the electric energy meter metering state evaluation is improved.

[0111] In an embodiment, Figure 3 is a structural schematic diagram of an electric energy meter metering state evaluation device provided by the embodiment of the present application. As Figure 3 shown, the device comprises a line loss value determination module 310, a classification and removal module 320, a detection and removal module 330, a user combination module 340, a coefficient determination module 350, and a state analysis module 360.

[0112] The line loss value determination module 310 is configured to determine the technical line loss value of the statistical object in the line loss statistical period.

[0113] The classification and removal module 320 is configured to classify and remove the initial line loss sample associated with the statistical line loss value according to the technical line loss value, and obtain the classified line loss sample.

[0114] The detection and removal module 330 is configured to remove the abnormal sample data in the classified line loss sample by using the data outlier detection method, and obtain the target line loss sample.

[0115] The user merging module 340 is configured to merge users based on the power level of each user in the target line loss sample and the power curve correlation if the number of samples of the target line loss sample does not meet the preset sample margin of the number of users contained in the object to be counted, to obtain the target users after merging;

[0116] The coefficient determination module 350 is configured to determine the corresponding model regression coefficient by using the pre-created multivariate linear regression model of statistical line loss and the power correlation parameters and the actual power consumption of each target user in the target line loss sample.

[0117] The state analysis module 360 is configured to analyze the metering state of each user by using the abnormality detection criterion and the model regression coefficient, to obtain the abnormal electric energy meter.

[0118] In an embodiment, the line loss value determination module 310 comprises:

[0119] The parameter acquisition unit is configured to acquire the actual active power, the user voltage and the gateway power supply voltage of each user in the object to be counted in each line loss statistical sub-period;

[0120] The theoretical active power determination unit is configured to determine the theoretical active power of the associated user in the line loss statistical sub-period according to the actual active power, the user voltage and the gateway power supply voltage;

[0121] The theoretical power determination unit is configured to determine the user theoretical power of the associated user in the line loss statistical period according to the theoretical active power of each user in each line loss statistical sub-period;

[0122] The theoretical loss power determination unit is configured to determine the theoretical loss power of each user in the line loss statistical period according to the user theoretical power and the measured power of each user in the line loss statistical period;

[0123] The line loss value determination unit is configured to determine the technical line loss value of the object to be counted in the line loss statistical period according to the theoretical loss power of each user and the number of users contained in the object to be counted.

[0124] In an embodiment, the classification and rejection module 320 comprises:

[0125] The threshold determination unit is configured to determine the upper threshold and the lower threshold of the initial line loss sample classification based on the technical line loss value, the total power consumption of the electric energy meter in the object to be counted, the power consumption of the equipment not included in the metering and the accuracy level of the electric energy meter;

[0126] The abnormal sample screening unit is configured to screen the high-loss abnormal sample from the initial line loss sample according to the upper threshold, and screen the low-loss abnormal sample from the initial line loss sample according to the lower threshold;

[0127] The classification line loss sample screening unit is configured to, if the number of high-loss abnormal samples contained in the initial line loss sample is greater than the number of low-loss abnormal samples, remove the low-loss abnormal samples from the initial line loss sample and take the high-loss abnormal samples as the classification line loss sample.

[0128] The classification line loss sample screening unit is further configured to, if the number of high-loss abnormal samples contained in the initial line loss sample is less than the number of low-loss abnormal samples, remove the high-loss abnormal samples from the initial line loss sample and take the low-loss abnormal samples as the classification line loss sample.

[0129] In an embodiment, the data anomaly detection mode includes a quartile method, and the detection removal module 330 includes:

[0130] The statistical line loss rate determination unit is configured to determine a corresponding statistical line loss rate according to the statistical line loss power and the total power supply in the classification line loss sample.

[0131] The boundary value determination unit is configured to determine a corresponding abnormal upper boundary value and an abnormal lower boundary value by using the quartile method and the statistical line loss rate.

[0132] The removal unit is configured to remove, from the classification line loss sample, abnormal sample data with a statistical line loss rate greater than the abnormal upper boundary value and abnormal sample data with a statistical line loss rate less than the abnormal lower boundary value, to obtain the target line loss sample.

[0133] In an embodiment, the user merging module 340 includes:

[0134] The correlation determination unit is configured to determine the power curve correlation between the power curve of each user in the target line loss sample and the power curve of another single user.

[0135] The correlation coefficient lookup unit is configured to look up another user with the highest power curve correlation with the power curve of one user and a corresponding correlation coefficient.

[0136] The merging unit is configured to merge two users with a correlation coefficient reaching a correlation coefficient threshold into one user group.

[0137] The merging unit is further configured to, if the number of users composed of the user group and the unmerged single users does not satisfy a preset sample margin, perform user merging according to the power levels of the unmerged single users, to obtain the merged target user.

[0138] In an embodiment, the power correlation parameters include an actual statistical line loss value, a technical line loss value and a total power supply, and the coefficient determination module 350 includes:

[0139] The actual power consumption acquisition unit is configured to acquire the total power supply in the target line loss sample and the actual power consumption of each target user.

[0140] The statistical line loss actual value determination unit is configured to determine a statistical line loss actual value according to the total power supply amount and the actual power consumption of each target user.

[0141] The coefficient determination unit is configured to input the statistical line loss actual value, the actual power consumption and the technical line loss value into a pre-constructed multiple linear regression model solving formula of the statistical line loss to obtain corresponding model regression coefficients.

[0142] In an embodiment, the electric energy metering state device further comprises:

[0143] The prediction value determination module is configured to input the model regression coefficients, the power consumption related parameters and the actual power consumption of each target user into the multiple linear regression model of the statistical line loss to obtain a statistical line loss prediction value.

[0144] The statistical line loss average value determination module is configured to determine a statistical line loss average value according to the statistical line loss actual values in the target line loss sample and the sample quantity.

[0145] The regression sum of squares determination module is configured to determine a regression sum of squares according to the statistical line loss prediction value and the statistical line loss average value.

[0146] The total sum of squares determination module is configured to determine a total sum of squares according to the statistical line loss actual values and the statistical line loss average value.

[0147] The model evaluation value determination module is configured to determine a model evaluation value of the multiple linear regression model of the statistical line loss according to the regression sum of squares and the total sum of squares.

[0148] In an embodiment, the model regression coefficients comprise user regression coefficients, and the state analysis module 360 comprises:

[0149] The regression coefficient classification unit is configured to classify the user regression coefficients according to positive and negative values to obtain first-type user regression coefficients and second-type user regression coefficients.

[0150] The regression coefficient screening unit is configured to adopt the Wald criterion to cyclically detect a group of data composed of the first-type user regression coefficients and a group of data composed of the second-type user regression coefficients, respectively, and screen to obtain abnormal user regression coefficients.

[0151] The abnormal electric energy meter determination unit is configured to associate the electric energy meter of the abnormal user regression coefficients as an abnormal electric energy meter.

[0152] In an embodiment, in the case that the abnormal user corresponding to the abnormal electric energy meter is an abnormal user group, the electric energy metering state evaluation device further comprises:

[0153] The judgment and analysis module is used to treat each user in the abnormal user group as a single user and return the steps to determine the technical line loss value of the object to be counted within the line loss statistical period, and to filter out the abnormal users in the abnormal user group.

[0154] The electricity meter metering status evaluation device provided in the embodiments of the present invention can execute the electricity meter metering status evaluation method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method.

[0155] In one embodiment, Figure 4 This is a structural block diagram of an electronic device provided in an embodiment of the present invention, such as... Figure 4 The diagram illustrates a schematic representation of an electronic device 10 that can be used to implement embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0156] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0157] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0158] The processor 11 can be various general and / or special purpose processing components having processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs various methods and processes described above, such as the power metering state evaluation method.

[0159] In some embodiments, the power metering state evaluation method can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded onto the RAM 13 and executed by the processor 11, one or more steps of the power metering state evaluation method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the power metering state evaluation method by any other appropriate means, such as by means of firmware.

[0160] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (PLD), a computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0161] Computer programs used to implement the methods of the application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the computer program, when executed by the processor of the machine, implements the functions / acts specified in the flowcharts and / or block diagrams. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, and partially on a machine or a remote machine or a server.

[0162] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer-readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0163] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0164] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0165] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. Servers can be cloud servers, also known as cloud computing servers or cloud hosts, which are a host product in the cloud computing service system to solve the defects of great management difficulty and weak business scalability in traditional physical hosts and VPS services.

[0166] The embodiment of the present application also provides a computer program product comprising a computer program which, when executed by a processor, can implement the electric energy metering state evaluation method provided by any embodiment of the present application.

[0167] The computer program product can be written in one or more programming languages or combinations of languages including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0168] It should be understood that the various forms of flow shown above can be re-ordered, added to, or deleted from without departing from the scope of the present application. For example, the steps recited in the present application can be performed in parallel, in series, or in a different order, and the present application is not limited in this regard.

[0169] The above detailed description does not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A method for evaluating the metering state of an electric energy meter, characterized by, The method comprises the following steps: determining a technical line loss value of a to-be-counted object in a line loss counting period; classifying and removing an initial line loss sample of an associated statistical line loss value according to the technical line loss value, to obtain a classified line loss sample, specifically comprising: determining an upper threshold and a lower threshold of the initial line loss sample classification based on the technical line loss value, and the total power consumption and fixed loss of the to-be-counted object, and the power meter accuracy level; screening a high-loss abnormal sample from the initial line loss sample according to the upper threshold, and screening a low-loss abnormal sample from the initial line loss sample according to the lower threshold; if the number of the high-loss abnormal sample contained in the initial line loss sample is greater than the number of the low-loss abnormal sample, removing the low-loss abnormal sample from the initial line loss sample, and taking the high-loss abnormal sample as the classified line loss sample; if the number of the high-loss abnormal sample contained in the initial line loss sample is less than the number of the low-loss abnormal sample, removing the high-loss abnormal sample from the initial line loss sample, and taking the low-loss abnormal sample as the classified line loss sample; adopting a data abnormal value detection method to remove abnormal sample data in the classified line loss sample, to obtain a target line loss sample, specifically comprising: determining a corresponding statistical line loss rate according to the statistical line loss power and the total power supply in the classified line loss sample; determining a corresponding abnormal upper boundary value and an abnormal lower boundary value by using the quartile method and the statistical line loss rate; removing abnormal sample data with a statistical line loss rate greater than the abnormal upper boundary value, and abnormal sample data with a statistical line loss rate less than the abnormal lower boundary value from the classified line loss sample, to obtain the target line loss sample; if the number of the target line loss sample does not satisfy a preset sample margin set for the number of users contained in the to-be-counted object, merging users based on the power level and power curve correlation of each user in the target line loss sample, to obtain a merged target user; adopting a pre-created multivariate linear regression model of statistical line loss, and the power-related parameters in the target line loss sample and the actual power consumption of each target user, to determine a corresponding model regression coefficient; adopting an abnormality detection criterion and the model regression coefficient to analyze the metering state of each user's power meter, to obtain an abnormal power meter.

2. The method of claim 1, wherein, The method for determining the technical line loss value of the to-be-counted object in the line loss counting period comprises the following steps: obtaining the actual active power, user voltage and gateway power supply voltage of each user in the to-be-counted object in each line loss counting sub-period; determining the theoretical active power of the associated user in the line loss counting sub-period according to the actual active power, user voltage and gateway power supply voltage; determining the user theoretical power of the associated user in the line loss counting period according to the theoretical active power of each user in each line loss counting sub-period; determining the theoretical loss power of each user in the line loss counting period according to the user theoretical power and the measured power of each user in the line loss counting period; determining the technical line loss value of the to-be-counted object in the line loss counting period according to the theoretical loss power of each user and the number of users contained in the to-be-counted object.

3. The method of claim 1, wherein, The user merging based on the power level and the power curve correlation of each user in the target line loss sample obtains the merged target user, and comprises: determining the power curve correlation between the power curve of each user in the target line loss sample and the power curve of other single users; finding another user with the highest power curve correlation with one user and the corresponding correlation coefficient; merging two users with the correlation coefficient reaching the correlation coefficient threshold into one user group; if the number of users composed of the user group and the unmerged single users does not satisfy the preset sample margin, merging the unmerged single users according to the power level to obtain the merged target user.

4. The method of claim 1, wherein, The power correlation parameters include: actual statistical line loss value, technical line loss value and total power supply; the corresponding model regression coefficient is determined by using the pre-created statistical line loss multiple linear regression model and the power correlation parameters and the actual power consumption of each target user in the target line loss sample, and comprises: obtaining the total power supply in the target line loss sample and the actual power consumption of each target user; determining the statistical line loss actual value according to the total power supply and the actual power consumption of each target user; inputting the statistical line loss actual value, the actual power consumption and the technical line loss value into the pre-created statistical line loss multiple linear regression model solving formula to obtain the corresponding model regression coefficient.

5. The method of claim 4, wherein, The method further comprises: inputting the model regression coefficient, the power correlation parameter and the actual power consumption of each target user into the statistical line loss multiple linear regression model to obtain the statistical line loss prediction value; determining the statistical line loss average value according to the statistical line loss actual value and the sample number in the target line loss sample; determining the regression sum of squares according to the statistical line loss prediction value and the statistical line loss average value; determining the total sum of squares according to the statistical line loss actual value and the statistical line loss average value; determining the model evaluation value of the statistical line loss multiple linear regression model according to the regression sum of squares and the total sum of squares.

6. The method of claim 1, wherein, The model regression coefficient includes: user regression coefficient; the model regression coefficient is used to analyze the metering state of each user to obtain the abnormal meter, and comprises: classifying the user regression coefficient according to the positive and negative values to obtain the first type of user regression coefficient and the second type of user regression coefficient; using the Laplace criterion to cyclically detect a group of data composed of the first type of user regression coefficient and a group of data composed of the second type of user regression coefficient, and screening to obtain the abnormal user regression coefficient; associating the meter of the user corresponding to the abnormal user regression coefficient as the abnormal meter.

7. The method according to any one of claims 1 to 6, characterized in that, In the case that the abnormal user corresponding to the abnormal meter is an abnormal user group, the method further comprises: regarding each user in the abnormal user group as a single user, and returning to the step of determining the technical line loss value of the statistical object in the line loss statistical period to screen to obtain the abnormal user in the abnormal user group.

8. An electronic device, comprising: The electronic device comprises: at least one processor; and a memory connected in communication with the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the electric energy metering state evaluation method in any one of claims 1-7.

Images