Electric energy meter inaccuracy analysis method, device, equipment and medium
Through the self-optimized elastic network regression model and Newton-Raphson iterative algorithm, combined with the accumulated slip deviation curve and the line loss power regression fitting curve, the problem of insufficient linear evaluation and high time synchronization requirements in the power meter misalignment analysis is solved, and the problem of insufficient linear evaluation and high time synchronization requirements is achieved. The accurate and efficient analysis of power meter inaccuracy has improved management level.
Patent Information
- Application Number
- CN202211505308.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-11-28
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2042-11-28
AI Technical Summary
The existing electrical energy meter misalignment analysis methods have problems such as insufficient linear evaluation, high time synchronization requirements, and easy to overfit, resulting in inaccurate analysis results.
Using self-optimized elastic network regression model combined with Newton-Raphson iterative algorithm, the cumulative slip deviation curve and line loss power regression fitting curve are used to calculate the fit mean square error value to determine whether the power meter is inaccurate, simplify data acquisition requirements, and reduce cutoff Error impact.
It improves the accuracy and efficiency of the analysis of power meter misalignment, reduces manpower and material investment, and realizes the continuous management of low-voltage electricity services and the digitalization and intelligence of equipment.
Smart Images

Figure CN115856757B_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the technical field of electric energy meter inaccuracy troubleshooting, and in particular relates to electric energy meter inaccuracy analysis. Background Art
[0002] As the core equipment for the development and construction of smart grids, the accuracy of electricity metering is the focus and difficulty of grid management. With the continuous increase in electricity consumption by residents and industries, the requirements for accurate metering of smart energy meters are getting higher and higher. The energy meters installed on site in the substation have been inaccurate for a long time due to factors such as working environment, equipment aging, and failure. At present, power supply companies often solve the problem of energy meter inaccuracy by regularly replacing all energy meters in the substation that have reached the rotation cycle or regularly spot checking according to abnormal line losses in the substation. This method is inefficient and has high maintenance costs. Therefore, the idea of online detection of energy meter measurement errors has been proposed, and research on energy meter inaccuracy analysis has been conducted. At present, the commonly used methods for analyzing the misalignment of electric energy meters are mainly qualitative correlation analysis methods and quantitative linear regression methods. However, the following problems are encountered in actual use: First, correlation analysis is generally a linear evaluation, while there are a large number of nonlinear characteristics in the medium and low voltage areas in actual scenarios; second, the existing misalignment analysis methods are mostly based on active power curves, which require the collection of active power data of power supply and power consumption equipment at the same time. The time synchronization requirements are high, and there are certain difficulties in actual on-site implementation; third, due to the small number of out-of-tolerance meters, the conventional linear regression method is prone to overfitting. The above three problems will ultimately affect the accuracy of the analysis results. Summary of the invention
[0003] The object of the present invention is to provide an electric energy meter misalignment analysis method, device, equipment and medium to solve the technical problem that the existing electric energy meter misalignment analysis method is inaccurate and difficult to apply in actual field.
[0004] To achieve the above object, the present invention adopts the following technical solutions:
[0005] In a first aspect, a method for analyzing an electric energy meter misalignment comprises the following steps:
[0006] Obtain the sub-meter electric energy data and the total meter electric energy data respectively;
[0007] Calculate the cumulative slip deviation curve based on the sub-meter electric energy data and the total meter electric energy data;
[0008] An iterative formula of a self-optimizing elastic net regression model is established based on the cumulative slip deviation curve;
[0009] Solving the iterative formula of the optimized elastic net regression model to obtain an optimal solution;
[0010] Generate a line loss power regression fitting curve according to the optimal solution;
[0011] Calculate the fitting mean square error value according to the line loss electric quantity regression fitting curve and the cumulative slip deviation curve;
[0012] The inaccuracy of the electric energy meter is determined based on the fitting mean square error value.
[0013] A further improvement of the present invention is that: when respectively acquiring the sub-meter electric energy data and the total meter electric energy data, a low-voltage Internet of Things sensing terminal is used to acquire them.
[0014] A further improvement of the present invention is that: when the sub-meter electric energy data and the total meter electric energy data are obtained respectively, the following steps are specifically included:
[0015] Obtain the forward active electric energy hourly frozen data and the reverse active electric energy hourly frozen data of all household meters on the electric energy meter box side, add the forward active electric energy hourly frozen data and the reverse active electric energy hourly frozen data to obtain the sub-meter electric energy data;
[0016] Obtain the forward active electric energy hourly frozen data and the reverse active electric energy hourly frozen data at the incoming line of the electric energy meter box, add the forward active electric energy hourly frozen data and the reverse active electric energy hourly frozen data to obtain the total meter electric energy data.
[0017] A further improvement of the present invention is that after respectively acquiring the sub-meter electric energy data and the total meter electric energy data, abnormal data in the sub-meter electric energy data and the total meter electric energy data are eliminated, and the abnormal data include data with data leakage, data with abnormal collection time, and the first group of data with an interval of more than 4 collection cycles between the previous and next two groups of valid data.
[0018] A further improvement of the present invention is that when the iterative formula of the self-optimizing elastic net regression model is established according to the cumulative slip deviation curve, the following steps are specifically included:
[0019] According to the cumulative slip deviation curve, the objective function is established by using the traditional elastic net regression model;
[0020] The traditional elastic net regression model solution algorithm is combined with the Newton-Raphson iterative algorithm to transform the objective function and obtain the iterative form of the self-optimizing elastic net regression model.
[0021] A further improvement of the present invention is that: when the iterative formula of the optimized elastic net regression model is solved to obtain the optimal solution, the following steps are specifically included:
[0022] Initialize the iterative formula of the optimized elastic net regression model so that the weight coefficient is 0 and obtain the initial solution;
[0023] According to the Newton-Raphson iterative algorithm and the initial solution, all weight coefficients are traversed to obtain the optimal solution of the process under the current conditions with only one weight coefficient variable;
[0024] When the changes of all weight coefficients are within the preset range or the maximum number of iterations is reached, the iteration ends and the optimal solution of the process at this time is output as the optimal solution.
[0025] A further improvement of the present invention is that when judging whether the electric energy meter is inaccurate according to the fitting mean square error value, the following steps are specifically included:
[0026] Compare the fitting mean square error value with the first preset value, and if it is smaller than the first preset value, it is normal;
[0027] Calculate the electric energy meter measurement error estimation coefficient for each fitting mean square error value greater than or equal to a first preset value;
[0028] The electric energy meter whose absolute value of the measurement error estimation coefficient is greater than the second preset value is regarded as an out-of-tolerance table.
[0029] In the second aspect, the electric energy meter misalignment analysis device comprises:
[0030] Data acquisition module: used to obtain sub-meter electric energy data and total meter electric energy data;
[0031] Cumulative slip deviation curve generation module: used to calculate the cumulative slip deviation curve according to the sub-meter electric energy data and the total meter electric energy data;
[0032] Iterative generation module: used to iteratively establish a self-optimizing elastic net regression model based on the cumulative slip deviation curve;
[0033] Optimal solution calculation module: used to solve the iterative formula of the optimized elastic net regression model to obtain the optimal solution;
[0034] Regression fitting curve generation module: generates a line loss power regression fitting curve according to the optimal solution;
[0035] Fitting mean square error value calculation module: used to calculate the fitting mean square error value according to the line loss power regression fitting curve and the cumulative slip deviation curve;
[0036] Output module: used to determine whether the electric energy meter is inaccurate based on the fitted mean square error value.
[0037] In a third aspect, a computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the electric energy meter misalignment analysis method in the first aspect when executing the computer program.
[0038] In a fourth aspect, a computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the electric energy meter misalignment analysis method in the first aspect.
[0039] Compared with the prior art, the present invention has at least the following beneficial effects:
[0040] 1. The electric energy meter misalignment analysis method based on the self-optimizing elastic net regression algorithm provided by the present invention improves the elastic net regression model through the Newton-Raphson iterative algorithm, optimizes the model parameters, solves the electric energy deviation regression coefficient through the self-optimizing iterative method, and then finally locates the out-of-tolerance meter through the similarity between the fitting curve and the actual electric energy slip deviation value curve and the size of the regression coefficient. The present invention is simple to implement, and only needs to obtain the electric energy data of all sub-meters and the total meter in the meter box.
[0041] 2. The present invention performs cumulative slip processing on the collected total meter and sub-meter electric energy data, which can minimize the impact of the truncation error of the meter box electric energy meter. At the same time, the processing method requires a short cumulative data cycle, which can realize the analysis of the electric energy meter measurement inaccuracy as soon as possible;
[0042] 3. The present invention uses data collection and algorithm analysis to locate out-of-tolerance meters, which can operate continuously for a long time, save manpower and material resources, and ensure the low-voltage electricity service and management level. At the same time, the present invention makes full use of emerging technologies such as the Internet of Things, big data, and artificial intelligence, which is conducive to improving the digitalization, informatization, and intelligence level of terminal equipment.
[0043] 4. Compared with the power curve schemes adopted in other patents, the present invention performs cumulative slip processing on the collected total meter and sub-meter electric energy data, which has the following advantages: first, it can minimize the impact of the truncation error of the meter box electric energy meter and ensure the accuracy of the analysis results; second, it avoids the problem of high time synchronization requirements for power data sampling, and on-site collection is easy to implement; third, the cumulative data cycle required by the processing method is also short, and the analysis of electric energy meter measurement inaccuracies can be realized as soon as possible. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.
[0045] In the attached picture:
[0046] Figure 1 It is a flow chart of the method for analyzing the misalignment of an electric energy meter according to the present invention;
[0047] Figure 2 It is a fitting curve of the meter box end and a curve diagram of the actual electric energy deviation value in an implementation example of the present invention;
[0048] Figure 3 The system block diagram of the electric energy meter misalignment analysis device of the present invention. DETAILED DESCRIPTION
[0049] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present invention can be combined with each other without conflict.
[0050] The following detailed description is an exemplary description, which is intended to provide further detailed description of the present invention. Unless otherwise specified, all technical terms used in the present invention have the same meaning as those generally understood by those skilled in the art to which the present invention belongs. The terms used in the present invention are only for describing specific embodiments, and are not intended to limit the exemplary embodiments according to the present invention.
[0051] like Figure 1 As shown, the electric energy meter misalignment analysis method comprises the following steps:
[0052] S1. Obtain the sub-meter electric energy data and the total meter electric energy data respectively;
[0053] As a preferred embodiment of the present invention, a low-voltage IoT sensing terminal is used in S1 to collect electric energy data of several sub-meters and electric energy data of the total meter;
[0054] S1 specifically includes the following steps:
[0055] S11, obtaining the forward active electric energy hourly frozen data and the reverse active electric energy hourly frozen data of all household meters on the meter box side of the electric energy meter, adding the forward active electric energy hourly frozen data and the reverse active electric energy hourly frozen data to obtain the sub-meter electric energy data;
[0056] S12, obtaining the forward active electric energy hourly frozen data and the reverse active electric energy hourly frozen data at the incoming line of the electric energy meter box, adding the forward active electric energy hourly frozen data and the reverse active electric energy hourly frozen data to obtain the total meter electric energy data;
[0057] S2, eliminating abnormal data in the sub-meter electric energy data and the total meter electric energy data;
[0058] In S2, the abnormal data includes: data with data leakage, data with abnormal collection time, and the interval between the previous and next two groups of valid data is greater than 4 collection cycles.
[0059] In S2, if the number of valid data groups is less than twice the total number of household meters, the process returns to S1 to re-acquire the electricity meter energy hour freezing data.
[0060] S3, calculating the cumulative slip deviation curve based on the sub-meter electric energy data excluding abnormal data and the total meter electric energy data;
[0061] When obtaining the cumulative slip deviation curve in S3, the difference between the period data before and after the total meter electric energy data is subtracted from the difference between the period data before and after the total meter electric energy data, that is:
[0062]
[0063] In the formula, s k Indicates the electric energy slip deviation value of the meter box at the kth data collection point, y k represents the total meter electric energy data of the kth data collection point, x ki It represents the electric energy reading of the ith submeter at the kth data collection point, and m represents the total number of submeters.
[0064] S4, establishing an iterative formula of a self-optimizing elastic net regression model according to the cumulative slip deviation curve;
[0065] S4 specifically includes the following steps:
[0066] S41, establishing an objective function using a traditional elastic net regression model based on the cumulative slip deviation curve;
[0067]
[0068] In the formula, δ represents the estimation coefficient of the metering error of the electric energy meter, and its optimal estimation is determined by two parameters: weight coefficient λ and weight coefficient ρ. i is the electric energy slip deviation value of the meter box at the i-th data collection point;
[0069] S42, using the traditional elastic net regression model solution algorithm combined with the Newton-Raphson iterative algorithm to transform the objective function, and obtain the iterative form of the self-optimizing elastic net regression model;
[0070]
[0071] In the formula, represents the measurement error estimation coefficient of the electric energy meter, the matrix X represents the electric energy slip deviation data of all sub-meters in the meter box, the matrix S represents the electric energy slip deviation value calculated in the above steps, k represents the number of iterations, and the matrix ω represents the self-optimization shrinkage coefficient matrix for the Kth iteration.
[0072] S5, solving the iterative formula of the optimized elastic net regression model to obtain the optimal solution;
[0073] In S5, the following steps are specifically included:
[0074] S51, initializing weight coefficients λ and ρ to 0 to obtain an initial solution;
[0075] S52, according to the Newton-Raphson iterative algorithm and the initial solution, traverse all weight coefficients, take one of the weight coefficients as a variable in turn, and fix the other weight coefficients to the result of the last calculation as a constant, and find the optimal solution of the process under the current condition that there is only one weight coefficient variable;
[0076] S53. When the changes of all weight coefficients are within a preset range or the maximum number of iterations is reached, the iteration is terminated and the optimal solution of the process at this time is output as the optimal solution.
[0077] S6. Generate a line loss power regression fitting curve according to the optimal solution;
[0078] S7, calculate the fitting mean square error value according to the line loss power regression fitting curve and the cumulative slip deviation curve; Figure 2 As shown;
[0079] Fitting mean square error
[0080]
[0081]
[0082] In the formula, ω k Represents the fitted value of the i-th point.
[0083] S8. Determine whether the electric energy meter is inaccurate based on the fitting mean square error value.
[0084] S8 specifically includes the following steps:
[0085] Compare the fitting mean square error value with the first preset value, and the value smaller than the first preset value is in compliance with the standard;
[0086] Calculate the electric energy meter measurement error estimation coefficient for each fitting mean square error value greater than or equal to the first preset value, δ = [δ 1 ,δ 2 ,…,δ n ] T A list of out-of-tolerance meters is given according to the estimated error coefficient of the electric energy meter corresponding to each user, and the electric energy meters whose absolute values of the estimated error coefficient of the electric energy meter are greater than the second preset value are positioned as out-of-tolerance meters.
[0087] The first preset value is 0.06, and the second preset value is 0.03.
[0088] Example 2
[0089] like Figure 3 As shown, the electric energy meter misalignment analysis device, based on the electric energy meter misalignment analysis method in embodiment 1, comprises:
[0090] Data acquisition module: used to obtain the electric energy data of several sub-meters and the total meter electric energy data;
[0091] Preprocessing module: used to remove abnormal data from several sub-meter electric energy data and the total meter electric energy data;
[0092] Cumulative slip deviation curve generation module: used to calculate the cumulative slip deviation curve according to several sub-meter electric energy data and the total meter electric energy data;
[0093] Iterative generation module: used to iteratively establish a self-optimizing elastic net regression model based on the cumulative slip deviation curve;
[0094] Optimal solution calculation module: used to obtain the optimal solution according to the iteration of optimizing elastic net regression model;
[0095] Regression fitting curve generation module: used to generate line loss power regression fitting curve according to the optimal solution;
[0096] Fitting mean square error value calculation module: used to calculate the fitting mean square error value according to the line loss power regression fitting curve and the cumulative slip deviation curve;
[0097] Output module: used to generate an electric energy meter inaccuracy analysis report based on the fitted mean square error value.
[0098] Example 3
[0099] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the electric energy meter misalignment analysis method of embodiment 1 is implemented.
[0100] Example 4
[0101] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the electric energy meter misalignment analysis method of embodiment 1 is implemented.
[0102] It is known from common technical knowledge that the present invention can be implemented by other embodiments that do not deviate from its spirit or essential features. Therefore, the above disclosed embodiments are only illustrative in all respects and are not exclusive. All changes within the scope of the present invention or within the scope equivalent to the present invention are included in the present invention.
[0103] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0104] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0105] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0106] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0107] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.
Claims
1. Analysis method of electric energy meter inaccuracy, It is characterized in that The following steps are involved: The sub-meter electric energy data and the total meter electric energy data are obtained respectively; including: obtaining the forward active electric energy hourly frozen data and the reverse active electric energy hourly frozen data of all household meters on the electric energy meter box side, adding the forward active electric energy hourly frozen data and the reverse active electric energy hourly frozen data to obtain the sub-meter electric energy data; obtaining the forward active electric energy hourly frozen data and the reverse active electric energy hourly frozen data at the electric energy meter box inlet, adding the forward active electric energy hourly frozen data and the reverse active electric energy hourly frozen data to obtain the total meter electric energy data; Calculate the cumulative slip deviation curve based on the sub-meter electric energy data and the total meter electric energy data; including: In the formula, s k Indicates the electric energy slip deviation value of the meter box at the kth data collection point, y k represents the total meter electric energy data of the kth data collection point, x ki represents the electric energy reading of the ith submeter at the kth data collection point, and m represents the total number of submeters; An iterative formula of a self-optimizing elastic net regression model is established based on the cumulative slip deviation curve; Solving the iterative formula of the optimized elastic net regression model to obtain an optimal solution; Generate a line loss power regression fitting curve according to the optimal solution; Calculate the mean square error value of the fitting according to the line loss power regression fitting curve and the cumulative slip deviation curve; including: fitting mean square error value In the formula, ω k represents the fitting value of the i-th point; Judging whether the electric energy meter is inaccurate according to the fitted mean square error value; comprising: comparing the fitted mean square error value with a first preset value, and the value less than the first preset value meets the standard; calculating the electric energy meter measurement error estimation coefficient for each fitted mean square error value greater than or equal to the first preset value, δ=[δ 1 ,δ 2 ,…,δ n ] T The meter error estimation coefficient of the electric energy meter corresponding to each user is used to provide a list of out-of-tolerance meters, and the electric energy meters whose absolute values of the meter error estimation coefficients are greater than a second preset value are positioned as out-of-tolerance meters; The iterative formula of establishing the self-optimizing elastic net regression model according to the cumulative slip deviation curve specifically includes the following steps: According to the cumulative slip deviation curve, the objective function is established by using the traditional elastic net regression model; In the formula, δ represents the estimation coefficient of the metering error of the electric energy meter, and its optimal estimation is determined by two parameters: weight coefficient λ and weight coefficient ρ. i is the electric energy slip deviation value of the meter box at the i-th data collection point; The traditional elastic net regression model solution algorithm is combined with the Newton-Raphson iterative algorithm to transform the objective function and obtain the iterative form of the self-optimizing elastic net regression model. In the formula, represents the measurement error estimation coefficient of the electric energy meter, the matrix X represents the electric energy slip deviation data of all sub-meters in the meter box, the matrix S represents the electric energy slip deviation value calculated in the above steps, k represents the number of iterations, and the matrix ω represents the self-optimization shrinkage coefficient matrix for the Kth iteration; The iterative method of solving the optimized elastic net regression model to obtain the optimal solution specifically includes the following steps: Initialize the iterative formula of the optimized elastic net regression model so that the weight coefficient is 0 and obtain the initial solution; According to the Newton-Raphson iterative algorithm and the initial solution, all weight coefficients are traversed to obtain the optimal solution of the process under the current conditions with only one weight coefficient variable; When the changes of all weight coefficients are within the preset range or the maximum number of iterations is reached, the iteration ends and the optimal solution of the process at this time is output as the optimal solution.
2. The method for analyzing misalignment of an electric energy meter according to claim 1, It is characterized in that When respectively acquiring the sub-meter electric energy data and the total meter electric energy data, a low-voltage Internet of Things sensing terminal is used for acquisition.
3. The method for analyzing misalignment of an electric energy meter according to claim 1, It is characterized in that After respectively acquiring the sub-meter electric energy data and the total meter electric energy data, abnormal data in the sub-meter electric energy data and the total meter electric energy data are eliminated, and the abnormal data include data with data leakage, data with abnormal collection time, and the first group of data with an interval of more than 4 collection cycles between the previous and next two groups of valid data.
4. An electric energy meter misalignment analysis device, used to implement the electric energy meter misalignment analysis method according to any one of claims 1 to 3, It is characterized in that include: Data acquisition module: used to obtain the electric energy data of several sub-meters and the total meter electric energy data; Cumulative slip deviation curve generation module: used to calculate the cumulative slip deviation curve according to the sub-meter electric energy data and the total meter electric energy data; Iterative generation module: used to iteratively establish a self-optimizing elastic net regression model based on the cumulative slip deviation curve; Optimal solution calculation module: used to solve the iterative formula of the optimized elastic net regression model to obtain the optimal solution; Regression fitting curve generation module: generates a line loss power regression fitting curve according to the optimal solution; Fitting mean square error value calculation module: used to calculate the fitting mean square error value according to the line loss power regression fitting curve and the cumulative slip deviation curve; Output module: used to determine whether the electric energy meter is inaccurate based on the fitted mean square error value; The iterative formula of establishing the self-optimizing elastic net regression model according to the cumulative slip deviation curve specifically includes the following steps: According to the cumulative slip deviation curve, the objective function is established by using the traditional elastic net regression model; The traditional elastic net regression model solution algorithm is combined with the Newton-Raphson iterative algorithm to transform the objective function and obtain the iterative form of the self-optimizing elastic net regression model. The iterative method of solving the optimized elastic net regression model to obtain the optimal solution specifically includes the following steps: Initialize the iterative formula of the optimized elastic net regression model so that the weight coefficient is 0 and obtain the initial solution; According to the Newton-Raphson iterative algorithm and the initial solution, all weight coefficients are traversed to obtain the optimal solution of the process under the current conditions with only one weight coefficient variable; When the changes of all weight coefficients are within the preset range or the maximum number of iterations is reached, the iteration ends and the optimal solution of the process at this time is output as the optimal solution.
5. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, the electric energy meter misalignment analysis method according to any one of claims 1 to 3 is implemented.
6. A computer-readable storage medium storing a computer program, It is characterized in that When the computer program is executed by a processor, the method for analyzing misalignment of an electric energy meter according to any one of claims 1 to 3 is implemented.
