Electric energy meter error detection method and device for predicting transformer area line loss and medium

Abstract

The invention relates to the technical field of electric energy meter error detection, in particular to an electric energy meter error detection method and device for predicting transformer area line loss and a medium, and the method comprises the following steps: S1, data preprocessing: processing noise data in line loss influence variables; s2, constructing a transformer area line loss prediction model: constructing the transformer area line loss prediction model by using a kernel partial least squares algorithm, inputting the data processed in S1, and calculating a transformer area line loss prediction value; s3, constructing an energy conservation formula equation set, and iteratively solving the energy conservation formula equation set by using a least square method; s4, outputting a user error value; and positioning an abnormal electric energy meter according to a calculation result in S3. According to the method, multi-dimensional indexes are used for analysis and calculation, objective analysis is achieved, the method is close to reality, and the accuracy rate of the calculation effect reaches 90% or above through on-site verification results and electric energy meter abnormity recognition and verification.

Description

Technical Field

[0001] The present invention relates to the technical field of electric energy meter error detection, and more specifically, to an electric energy meter error detection method, device and medium for predicting line loss in an area. Background Art

[0002] Smart meters are mandatory inspection equipment and require replacement upon expiration. However, with the accelerated development of smart grids, the demand for replacement will continue to increase. The current meter verification model is increasingly unable to meet the requirements of modern smart meter condition-based inspection and replacement. To achieve a transition from periodic replacement to condition-based replacement of smart meters and ensure metering accuracy, an efficient and accurate method for detecting out-of-tolerance smart meter operation is needed. Traditional methods for solving out-of-tolerance smart meter operation using the generalized law of conservation of energy, including singular value decomposition and least squares (OLS), are prone to ill-posed equations. Later, a method was developed to predict out-of-tolerance energy meter conditions by building and solving predictive models that factor in temperature, humidity, load, verification results, and the cumulative effects of time. However, the extensive initial preparation required makes this method difficult to implement widely. In addition, since the substation line loss is usually regarded as an unknown quantity in the model when constructing the substation line loss, and the factors affecting the substation line loss are complex, there is a nonlinear relationship between the unknown quantities in the constructed equation group. The traditional method treats the line loss as an unknown quantity or uses the BP neural network optimized by the LM algorithm to estimate the substation line loss, and the error value obtained is relatively large.

[0003] The above shortcomings need to be improved. Summary of the Invention

[0004] In order to solve or alleviate the problem of poor balance between practicality and accuracy in the above-mentioned prior art methods for predicting electric energy meter out-of-tolerance, the present invention provides an electric energy meter error detection method, device and medium for predicting line loss in an area.

[0005] The technical solution of the present invention is as follows:

[0006] A method for detecting an electric energy meter error for predicting line loss in a transformer area comprises the following steps:

[0007] S1. Data preprocessing: Processing the noise data in the line loss influencing variables;

[0008] S2. Constructing a line loss prediction model for the substation area: Using the kernel partial least squares algorithm to construct a line loss prediction model for the substation area,

[0009]

[0010] Input the data processed by S1 and calculate the predicted value of line loss in the substation area.

[0011] Among them, U={u i}、T={ti},u i , t i is the i-th extraction component of partial least squares, K and K t Identify the regression matrix and test matrix respectively, whose elements K j =(x t ,x j ), {x j} is sample data, j = 1, 2, ..., n;

[0012] S3. Construct the energy conservation equations.

[0013]

[0014] The energy conservation equations are solved iteratively using the least squares method.

[0015] Among them, y is the total power supply of the substation, e j is the inaccuracy rate of the jth user's electric energy meter, is the electricity consumption of the jth user's electricity meter, e y Refers to line loss rate, e0 refers to fixed loss, (e y y+e0) is replaced by the line loss predicted by the kernel partial least squares in S2;

[0016] S4. Output user error value: locate the abnormal electric energy meter according to the calculation result in S3.

[0017] 2. The method for detecting electric energy meter errors for predicting line loss in a substation according to claim 1 is characterized in that, in S1, the line loss influencing variables include the total number of users in the substation, the total number of data days, the daily electricity consumption of the total meter in the substation, and the daily electricity consumption of the user meter in the substation.

[0018] 3. The method for detecting electric energy meter errors for predicting line loss in a substation according to claim 1, wherein in step S1, data preprocessing comprises the following steps:

[0019] S101. Missing value processing: For missing samples, linear interpolation is used to fill them;

[0020] S102, incalculable identification: when the proportion of zero and missing values ​​in the sample data is higher than a first preset ratio, it is determined to be incalculable and the data is deleted;

[0021] S103. Data standardization processing: After the line loss influencing variable data is processed by S101 and S102, the variable data is used as the independent variable and the theoretical line loss value is used as the dependent variable to standardize the data.

[0022] 4. The method for detecting electric energy meter errors for predicting line loss in an area according to claim 1, wherein in step S2,

[0023] S201, using the Gaussian kernel function as the kernel function of the kernel partial least squares algorithm,

[0024] K(x i ,x j )=exp(-||x i -x j || 2 / c)

[0025] Among them, ||x i -x j || represents vector x i and x j The Euclidean distance between c mσ 2 , r c is a constant ranging from 1 to 10, m is the dimension of the input space, σ 2 is the variance of the input data;

[0026] S202, component data determination: by gradually increasing the input data amount i from the number of users m to the total input data amount n, each time the data amount i is used to establish a regression equation according to the partial least squares regression method, so as to obtain the predicted value at the i-th observation point Take it so that The minimum amount of data is used as the model input data;

[0027] S203. Construct a regression model using kernel function:

[0028]

[0029] The line loss prediction model for the substation area is:

[0030]

[0031] 5. The method for detecting electric energy meter errors for predicting line loss in a substation according to claim 1, wherein the data processing in step S3 comprises the following steps:

[0032] S3011. Eliminate abnormal substations: This includes determining whether the total number of meters in the substation is greater than 1 or equal to 0, the number of user meters in the substation is 0, the total meter power or user meter power is the same for P consecutive days, the number of data days is less than Q days, and the comprehensive power meter ratio is inconsistent with the voltage transformer ratio multiplied by the current transformer ratio;

[0033] S3012, eliminating abnormal data: including the substation power supply is 0, the substation power supply is 0, the substation power loss is less than 0, and the substation line loss rate is greater than a second preset ratio;

[0034] S3013. Processing when the data volume is less than the number of users in the substation: The solution must satisfy the requirement that the data volume is greater than the number of users in the substation. If the actual daily power consumption data obtained in the substation is insufficient, the low-power users will be merged. If the requirement is still not met, the users are sorted by their daily power consumption in descending order of mean, median, and standard deviation, and the top (p) users are merged to meet the solution conditions of the equation system.

[0035] S3014, variable-length data merging processing: When the number of low-power users on day T exceeds the third preset ratio of the total number of users in the area, the data of day T and day (T-1) are merged.

[0036] 6. The method for detecting electric energy meter errors for predicting line loss in a transformer area according to claim 1, wherein in step S3,

[0037] S3021. Set M days as a period and construct a matrix using weighted average:

[0038]

[0039] S3022, using an iterative least squares method to solve N equations, where the solution of the equations is the energy meter deviation;

[0040]

[0041] The solution to the system of equations is:

[0042]

[0043] The solution to the equation is:

[0044]

[0045] K k =P k φ k

[0046]

[0047] S3023. For the users merged in S3013, use the error value solved in S3022.

[0048]

[0049] Calculate the user's restored electricity as the input electricity of the combined electricity, decompose and iterate the energy conservation equations again, and solve the error value of the combined electricity user.

[0050] 7. The method for detecting electric energy meter errors for predicting line loss in an electric energy meter area according to claim 1, characterized in that in S4, a suspicious electric energy meter whose absolute value of the error obtained within M days is greater than Z0 is identified as an out-of-tolerance electric energy meter.

[0051] 8. A method for detecting electric energy meter errors for predicting line loss in a substation according to claim 1, characterized in that, in S4, slowly changing abnormal electric energy meters are located: once a month, with a data window set to 1 year, and a suspicious electric energy meter with an absolute value of excess error greater than Z1 within 1 year is identified as an out-of-tolerance electric energy meter.

[0052] In order to solve the above problem, the present invention further provides an electronic device, comprising:

[0053] at least one processor; and,

[0054] a memory communicatively connected to the at least one processor; wherein,

[0055] The memory stores computer program instructions that can be executed by the at least one processor, and the computer program instructions are executed by the at least one processor so that the at least one processor can execute the electric energy meter error detection method for predicting line loss in the substation as described above.

[0056] In order to solve the above problems, the present invention also provides a computer-readable storage medium, including a data storage area and a program storage area, the data storage area stores created data, and the program storage area stores a computer program; wherein, when the computer program is executed by a processor, it implements the above-mentioned electric energy meter error detection method for predicting line loss in a substation.

[0057] The present invention according to the above scheme has the following beneficial effects:

[0058] 1. The present invention uses multi-dimensional indicators for analysis and calculation, which is objective and close to reality. The on-site verification results of business personnel and abnormal identification and verification of electricity meters are compared and calculated with an accuracy rate of more than 90% through statistical comparison.

[0059] 2. The present invention combines the substation topology with the principles of power physics and uses the law of conservation of energy to detect meter deviations, which is more in line with the physical principles of electricity meters, closer to power business scenarios, and highly interpretable.

[0060] 3. Before calculating the energy meter deviation, the present invention uses the kernel partial least squares method to predict the line loss in the substation according to the substation topology structure, so that the line loss input into the energy conservation equation group is more consistent with the data set, and uses recursive least squares to solve the equation group to obtain the energy meter error value. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0062] Figure 1 A flow chart of an electric energy meter error detection method for predicting line loss in an area provided by one embodiment of the present invention;

[0063] Figure 2 A schematic diagram of the internal structure of an electronic device for implementing an electric energy meter error detection method based on predicted area line loss provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0064] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0065] The embodiment of the present application provides an electric energy meter error detection method for predicting line loss in an area. The execution subject of the electric energy meter error detection method for predicting line loss in an area includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. Among them, the server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms. In other words, the electric energy meter error detection method for predicting line loss in an area can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0066] like Figure 1 As shown, an electric energy meter error detection method for predicting line loss in an area according to one embodiment of the present invention includes the following steps:

[0067] S1. Data preprocessing: Processing the noise data in the line loss influencing variables;

[0068] S2. Constructing a line loss prediction model for the substation area: Using the kernel partial least squares algorithm to construct a line loss prediction model for the substation area,

[0069]

[0070] Input the data processed by S1 and calculate the predicted value of line loss in the substation area.

[0071] Among them, U={u i}、T={t i},u i , t i is the component extracted by the partial least squares method for the i-th time, K and K t Identify the regression matrix and test matrix respectively, whose elements K j =K(x t ,x j ), {x j} is sample data, j = 1, 2, ..., n;

[0072] S3. Construct the energy conservation equations.

[0073]

[0074] The energy conservation equations are solved iteratively using the least squares method.

[0075] Among them, y is the total power supply of the substation, e j is the inaccuracy rate of the jth user's electric energy meter, is the electricity consumption of the jth user's electricity meter, e y Refers to line loss rate, e0 refers to fixed loss, (e y y+e0) is replaced by the line loss predicted by the kernel partial least squares in S2;

[0076] S4. Output user error value: locate the abnormal electric energy meter according to the calculation result in S3.

[0077] In this embodiment, a data preprocessing step removes noise from line loss-influencing variables, improving the accuracy of the prediction results. Secondly, a kernel partial least squares method is used to predict substation line loss, ensuring that the line loss input into the energy conservation equations is more consistent with the dataset. By inputting the preprocessed data, this method can calculate the predicted value of substation line loss, providing a basis for subsequent error detection. Next, when constructing the energy conservation equations, this method introduces parameters such as the substation's total meter power supply, the inaccuracy rate of user electricity meters, electricity consumption, and line loss rate, and iteratively solves the equations using the least squares method. In particular, this method uses line loss predicted by kernel partial least squares to replace fixed losses, thereby improving the accuracy and efficiency of solving the equations. Finally, the user error value is output. This method can accurately locate abnormal electricity meters, providing strong support for meter maintenance and replacement, reducing power losses caused by meter errors, and improving the overall operational efficiency and stability of the power grid. Based on the on-site verification results of business personnel and the identification and verification of abnormalities in electricity meters, the accuracy of statistical comparison and calculation results reached over 90%.

[0078] In a preferred embodiment, in S1, the line loss influencing variables include the total number of users in the substation area, the total number of data days, the total daily electricity consumption of the substation area, and the daily electricity consumption of users in the substation area.

[0079] Total meter daily electricity consumption = sum of user meter daily electricity consumption + substation line loss; substation line loss rate = substation line loss / total meter daily electricity consumption.

[0080] In S1, data preprocessing includes the following steps:

[0081] S101. Missing value processing: For missing samples, linear interpolation is used to fill them;

[0082] S102, incomputable identification: When the proportion of zero and missing values ​​in the sample data exceeds a first preset ratio, which is 80%, the data is determined to be incomputable and deleted;

[0083] S103. Data standardization: After the variable data affecting line loss are processed by S101 and S102, the variable data is used as the independent variable, that is, the total number of users in the substation, the total number of data days, the daily power consumption of the substation total meter, and the daily power consumption of the substation user meter are used as independent variables, and the theoretical line loss value is used as the dependent variable to standardize the data.

[0084] Specifically, Z-Score standardization is used, and the standardization formula is:

[0085]

[0086] Among them, x ij is the original data, is the mean of the original data, σ jis the standard deviation of the original data.

[0087] In practical applications, other data normalization methods can be adopted as needed.

[0088] In a preferred embodiment, in S2,

[0089] S201, using the Gaussian kernel function as the kernel function of the kernel partial least squares algorithm,

[0090] K(x i ,x j )=exp(-||x i -x j || 2 / c)

[0091] Among them, ||x i -x j || represents vector x i and x j The Euclidean distance between c mσ 2 , r c is a constant ranging from 1 to 10, m is the dimension of the input space, σ 2 is the variance of the input data;

[0092] Because line loss has many variables, each user in a substation area experiences some loss on the line. This leads to a certain correlation between each user and the substation area's line loss, which in turn leads to a nonlinear relationship between the variables in the energy conservation equations and the dependent variable. Since the Gaussian kernel function corresponds to an infinite-dimensional feature space, and a finite number of samples in this feature space are linearly separable, the Gaussian kernel function is selected as the kernel function for the kernel partial least squares algorithm.

[0093] S202, component data determination: by gradually increasing the input data amount i from the number of users m to the total input data amount n, each time the data amount i is used to establish a regression equation according to the partial least squares regression method, so as to obtain the predicted value at the i-th observation point Take it so that The minimum amount of data is used as the model input data; therefore, it is not necessary to use all input data to establish the regression equation, reducing the amount of calculation.

[0094] S203. Construct a regression model using kernel function:

[0095]

[0096] The line loss prediction model for the substation area is:

[0097]

[0098] In a preferred embodiment, in S3, data processing includes the following steps:

[0099] S3011. Eliminate abnormal substations: This includes determining whether the total number of meters in the substation is greater than 1 or equal to 0, the number of user meters in the substation is 0, the total meter power or user meter power is the same for P consecutive days, the number of data days is less than Q days, and the comprehensive power meter ratio is inconsistent with the voltage transformer ratio multiplied by the current transformer ratio; specifically, P = 6, Q = 200. In actual applications, P and Q can be set as needed.

[0100] S3012, eliminating abnormal data: including the substation power supply is 0, the substation power supply is 0, the substation power loss is less than 0, and the substation line loss rate is greater than a second preset ratio, the second preset ratio is 40%;

[0101] S3013. Processing when the data volume is less than the number of users in the substation: The solution must satisfy the requirement that the data volume is greater than the number of users in the substation. If the actual daily power consumption data obtained in the substation is insufficient, the low-power users will be merged. If the requirement is still not met, the users are sorted by their daily power consumption in descending order of mean, median, and standard deviation, and the top (p) users are merged to meet the solution conditions of the equation system.

[0102] S3014, Variable-Length Data Merging Processing: When the number of low-battery users on day T exceeds a third preset ratio of the total number of users in the area, the data for day T and day (T-1) are merged. Specifically, if the daily battery count of a low-battery user is less than 1 and the total number of users in the area is greater than 30, the third preset ratio is 80%, which is configured based on the specific circumstances of the dataset.

[0103] In a preferred embodiment, in S3,

[0104] S3021. Set M days as a period and construct a matrix using weighted average:

[0105]

[0106] S3022, using an iterative least squares method to solve N equations, where the solution of the equations is the energy meter deviation;

[0107]

[0108] The solution to the system of equations is:

[0109]

[0110] The solution to the equation is:

[0111]

[0112] K k =P k φk

[0113]

[0114] S3023. For the users merged in S3013, use the error value solved in S3022.

[0115]

[0116] Calculate the user's restored electricity as the input electricity of the combined electricity, decompose and iterate the energy conservation equations again, and solve the error value of the combined electricity user.

[0117] In a preferred embodiment, in S4, when the suspected electricity meter with an absolute value of deviation greater than Z0 within M days is determined to be an out-of-tolerance electricity meter, Z0=0.3.

[0118] In a preferred embodiment, in S4, the slowly changing abnormal electric energy meter is located: once a month, the data window is set to 1 year, and a suspicious electric energy meter with an absolute value of deviation greater than Z1 within 1 year is identified as an out-of-tolerance electric energy meter, Z1∈[0.3, 0.45].

[0119] like Figure 2 FIG. 1 is a schematic diagram of the structure of an electronic device for realizing the electric energy meter error detection method for predicting line loss in an area according to the present invention.

[0120] The electronic device may include a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as an electric energy meter error detection program for predicting line loss in a substation.

[0121] In some embodiments, the processor 10 may be composed of an integrated circuit, such as a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and a combination of various control chips. The processor 10 is the control core (Control Unit) of the electronic device, connecting the various components of the entire electronic device using various interfaces and lines. It executes or executes programs or modules stored in the memory 11 (such as an electric energy meter error detection program for predicting line loss in a substation area) and calls data stored in the memory 11 to perform various functions of the electronic device and process data.

[0122] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of an electronic device, such as a mobile hard disk of the electronic device. In other embodiments, the memory 11 can also be an external storage device of the electronic device, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Furthermore, the memory 11 can also include both an internal storage unit of the electronic device and an external storage device. The memory 11 can not only be used to store application software and various types of data installed in the electronic device, such as the code of the electric energy meter error detection program for predicting line loss in the substation, but can also be used to temporarily store data that has been output or is to be output.

[0123] The communication bus 12 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to enable communication between the memory 11 and at least one processor 10, etc.

[0124] The communication interface 13 is used for communication between the above-mentioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), optionally, the user interface may also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, for displaying information processed in the electronic device and for displaying a visual user interface.

[0125] Figure 2 Only the electronic device with components is shown, and it can be understood by those skilled in the art that Figure 2The structure shown does not limit the electronic device and may include fewer or more components than shown in the figure, or combine some components, or arrange the components differently.

[0126] For example, although not shown, the electronic device may further include a power source (such as a battery) to power various components. Preferably, the power source may be logically connected to at least one processor 10 via a power management device, thereby implementing functions such as charge management, discharge management, and power consumption management through the power management device. The power source may further include any components such as one or more DC or AC power sources, a recharging device, a power failure detection circuit, a power converter or inverter, a power status indicator, etc. The electronic device may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0127] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0128] The electric energy meter error detection program for predicting area line loss stored in the memory 11 of the electronic device is a combination of multiple computer programs. When running in the processor 10, it can achieve the following:

[0129] S1. Data preprocessing: Processing the noise data in the line loss influencing variables;

[0130] S2. Constructing a line loss prediction model for the substation area: Using the kernel partial least squares algorithm to construct a line loss prediction model for the substation area,

[0131]

[0132] Input the data processed by S1 and calculate the predicted value of line loss in the substation area.

[0133] Among them, U={u i}、T={t i},u i , t i is the i-th extraction component of partial least squares, K and K t Identify the regression matrix and test matrix respectively, whose elements K j =(x t ,x j ), {x j} is sample data, j = 1, 2, ..., n;

[0134] S3. Construct the energy conservation equations.

[0135]

[0136] The energy conservation equations are solved iteratively using the least squares method.

[0137] Among them, y is the total power supply of the substation, e j is the inaccuracy rate of the jth user's electric energy meter, is the electricity consumption of the jth user's electricity meter, e y Refers to line loss rate, e0 refers to fixed loss, (e y y+e0) is replaced by the line loss predicted by the kernel partial least squares in S2;

[0138] S4. Output user error value: locate the abnormal electric energy meter according to the calculation result in S3.

[0139] Specifically, the specific implementation method of the processor 10 for the above computer program can refer to Figure 1 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0140] Furthermore, if the modules / units integrated into an electronic device are implemented as software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium. Computer-readable storage media can be either volatile or non-volatile. For example, computer-readable media can include any entity or device capable of carrying computer program code, recording media, USB flash drives, mobile hard drives, magnetic disks, optical disks, computer memory, and read-only memory (ROM).

[0141] The present invention further provides a computer-readable storage medium, wherein the computer program is stored in the computer-readable storage medium. When the computer program is executed by a processor of an electronic device, the computer program can achieve:

[0142] S1. Data preprocessing: Processing the noise data in the line loss influencing variables;

[0143] S2. Constructing a line loss prediction model for the substation area: Using the kernel partial least squares algorithm to construct a line loss prediction model for the substation area,

[0144]

[0145] Input the data processed by S1 and calculate the predicted value of line loss in the substation area.

[0146] Among them, U={u i}、T={t i},u i , t i is the i-th extraction component of partial least squares, K and K t Identify the regression matrix and test matrix respectively, whose elements K j =(x t ,x j ), {x j} is sample data, j = 1, 2, ..., n;

[0147] S3. Construct the energy conservation equations.

[0148]

[0149] The energy conservation equations are solved iteratively using the least squares method.

[0150] Among them, y is the total power supply of the substation, e j is the inaccuracy rate of the jth user's electric energy meter, is the electricity consumption of the jth user's electricity meter, e y Refers to line loss rate, e0 refers to fixed loss, (e y y+e0) is replaced by the line loss predicted by the kernel partial least squares in S2;

[0151] S4. Output user error value: locate the abnormal electric energy meter according to the calculation result in S3.

[0152] In the several embodiments provided herein, it should be understood that the disclosed devices, apparatuses, and methods may be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the module division is merely a logical functional division, and actual implementation may employ other division methods.

[0153] Modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, that is, they may be located in one place or distributed across multiple network elements. Some or all of these modules may be selected to achieve the purpose of this embodiment based on actual needs.

[0154] In addition, the functional modules in various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or hardware plus software functional modules.

[0155] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0156] Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the claims are intended to be embraced therein. Any reference to a figure in a claim should not be construed as limiting the claim to which it relates.

[0157] Blockchain, as used in this article, refers to a novel application model for computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Blockchain is essentially a decentralized database, a series of data blocks generated using cryptographic methods. Each block contains information about a batch of online transactions, used to verify the validity of this information (to prevent counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, the platform product service layer, and the application service layer.

[0158] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to achieve optimal results.

[0159] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in a system claim may also be implemented by a single unit or device through software or hardware. Second-order terms are used to indicate names and do not imply any particular order.

[0160] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for detecting electric energy meter errors for predicting line losses in a transformer area, characterized in that: The following steps are involved: S1. Data preprocessing: processing the noise data in the line loss influencing variables; S2. Constructing a line loss prediction model for the substation area: Using the kernel partial least squares algorithm to construct a line loss prediction model for the substation area, Input the data processed by S1 and calculate the predicted value of line loss in the substation area. Among them, U={u i }、T={t i },u i ,t i is the i-th extraction component of partial least squares, K and K t Identify the regression matrix and the test matrix respectively, whose elements K j =(x t ,x j ), {x j } is sample data, j = 1, 2, ..., n; S3, construct the energy conservation formula equation group, The least squares method is used to iteratively solve the energy conservation equations. Among them, y is the total power supply of the area, e j is the inaccuracy rate of the jth user’s electric energy meter, is the power consumption of the jth user's electric energy meter, e y refers to line loss rate, e0 refers to fixed loss, (e y y+e0) is replaced by the line loss predicted by the kernel partial least squares in S2; S4. Output user error value: locate the abnormal electric energy meter according to the calculation result in S3.

2. According to the electric energy meter error detection method for predicting line loss in a transformer area as described in claim 1, it is characterized in that: In S1, the line loss influencing variables include the total number of users in the substation area, the total number of data days, the total daily electricity consumption of the substation area, and the daily electricity consumption of the user tables in the substation area.

3. According to the method for detecting electric energy meter error for predicting line loss in a transformer area as described in claim 1, it is characterized in that: In S1, data preprocessing includes the following steps: S101, missing value processing: For missing samples, use linear interpolation method to fill; S102, incalculable identification: when the proportion of zero missing values ​​in the sample data is higher than a first preset proportion, it is determined to be incalculable and the data is deleted; S103, data standardization processing: After the line loss influencing variable data is processed by S101 and S102, the variable data is used as the independent variable, and the theoretical line loss value is used as the dependent variable to standardize the data.

4. According to the electric energy meter error detection method for predicting line loss in a transformer area as described in claim 1, it is characterized in that: In S2, S201, using the Gaussian kernel function as the kernel function of the kernel partial least squares algorithm, K(x i ,x j )=exp(-||x i -x j || 2 / c) Among them, ||x i -x j || represents vector x i and x j The Euclidean distance between c mσ 2 , r c is a constant with a value between 1 and 10, m is the dimension of the input space, σ 2 is the variance of the input data; S202, component data determination: by gradually increasing the input data volume i from the number of users m to the total input data volume n, each time the data volume i is used to establish a regression equation according to the partial least squares regression method, so as to obtain the predicted value at the i-th observation point Take it so that The minimum amount of data is used as the model input data amount; S203, using kernel function to build regression model: The line loss prediction model of the substation area is:

5. According to the electric energy meter error detection method for predicting line loss in an area as described in claim 1, it is characterized in that: In S3, data processing includes the following steps: S3011, eliminating abnormal areas: including judging that the total number of meters in the area is greater than 1 or equal to 0, the number of user meters in the area is 0, the total meter power or user meter power is the same for P consecutive days, the number of data days is less than Q days, and the comprehensive multiplier of the electric energy meter is inconsistent with the voltage transformer ratio multiplied by the current transformer ratio; S3012, eliminating abnormal data: including the area power supply is 0, the area power supply is 0, the area power loss is less than 0, and the area line loss rate is greater than the second preset ratio; S3013, processing when the amount of data is less than the number of users in the area: the solution needs to satisfy the requirement that the amount of data is greater than the number of users in the area. When the actual daily power data of the area is insufficient, the low-power users will be merged. If it still does not meet the requirement, the mean, median, and standard deviation of the daily power of the users are sorted in descending order, and the top (p) users are selected for power merger to meet the solution conditions of the equation group; S3014, variable length data merging processing: when the number of low-power users on the Tth day exceeds the third preset ratio of the total number of users in the station area, the data of the Tth day and the (T-1)th day are merged.

6. The method for detecting electric energy meter errors for predicting line loss in a transformer area according to claim 1, characterized in that: In S3, S3021. Set M days as a cycle and construct a matrix using weighted average: S3022, using iterative least squares method to solve N sets of equations, the solution of the set of equations being the electric energy meter deviation; The solution to the system of equations is: The solution to the equation is: K k =P k f k S3023. For the users merged in S3013, using the error value solved in S3022, Calculate the user's restored electricity as the input electricity of the combined electricity, decompose and iterate the energy conservation equations again, and solve the error value of the combined electricity user.

7. The method for detecting an electric energy meter error for predicting line loss in an area according to claim 1, characterized in that: In S4, a suspicious meter whose absolute value of the deviation is greater than Z0 within M days is identified as an out-of-tolerance meter.

8. The method for detecting electric energy meter errors for predicting line loss in a transformer area according to claim 1, characterized in that: In S4, the slowly changing abnormal electric energy meter is located: once a month, the data window is set to 1 year, and the suspicious electric energy meter with an absolute value of the deviation greater than Z1 within 1 year is identified as an out-of-tolerance electric energy meter.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores computer program instructions that can be executed by the at least one processor, and the computer program instructions are executed by the at least one processor so that the at least one processor can execute the electric energy meter error detection method for predicting line loss in a substation as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: It includes a data storage area and a program storage area, the data storage area stores created data, and the program storage area stores a computer program; wherein, when the computer program is executed by a processor, an electric energy meter error detection method for predicting line loss in an area as described in any one of claims 1 to 8 is implemented.

Images