An abnormal determination method for an electric energy metering device and an evaluation method for electricity charge refund and compensation

Abstract

The present invention provides a method for abnormal determination of an electric energy metering device and evaluation of electricity refund and compensation, belonging to the technical field of electric energy metering, specifically including: obtaining the failure rate, installation method of the electric energy metering device, and the monthly average electricity consumption of the user in the recent year to obtain an evaluation value of the reliability requirement, and determining the monitoring frequency of the electric energy metering device based on the evaluation value of the reliability requirement; obtaining the electric energy metering data of the electric energy metering device based on the monitoring frequency, and obtaining a fault diagnosis value based on the electric energy metering data, historical electric energy metering data, and weather temperature. When the fault diagnosis value is greater than the first threshold, determining the fault type of the electric energy metering device based on the electric energy metering data, current waveform, voltage waveform, and power factor, calculating the abnormal electricity quantity of the electric energy metering device based on the start and end dates of the fault and the fault type to obtain a calculation result, and outputting the electricity refund and compensation result according to the calculation result, thereby further improving the efficiency of abnormal determination and the accuracy of refund and compensation.

Description

Technical Field

[0001] The present invention belongs to the technical field of electric energy metering, and particularly relates to a method for determining abnormality of an electric energy metering device and evaluating electricity charge refund and compensation. Background Art

[0002] In order to identify an abnormal electric energy metering device, in the authorized invention patent with the authorization announcement number CN110865329B, "A Method and System for Electric Energy Metering Based on Big Data Self-Diagnosis", by obtaining electric energy metering data and intelligent meter information data, and performing statistical analysis and feature quantity extraction based on a big data platform, abnormal data is calculated through feature quantities, and the corresponding intelligent meter is found according to the abnormal data for early warning. However, there are the following technical problems:

[0003] 1. The diagnosis of the fault monitoring frequency is not considered in combination with the installation status of the electric energy metering device and the fault conditions of the model. For different models, their failure rates are different, and the failure probabilities of electric energy metering devices installed outdoors and indoors are also different. Therefore, if the above factors cannot be combined to determine the fault monitoring frequency, the efficiency of the fault diagnosis of the electric energy metering device may be affected to a certain extent.

[0004] 2. The diagnosis of the fault type of the electric energy metering device is not considered. For different fault types, the methods of fault repair and electricity charge refund and compensation are also different. Therefore, if the fault type cannot be diagnosed, the efficiency of subsequent fault repair and the accuracy of electricity charge refund and compensation will be affected.

[0005] In view of the above technical problems, the present invention provides a method for determining abnormality of an electric energy metering device and evaluating electricity charge refund and compensation. Summary of the Invention

[0006] To achieve the purpose of the present invention, the present invention adopts the following technical solutions:

[0007] According to one aspect of the present invention, there is provided a method for determining abnormality of an electric energy metering device and evaluating electricity charge refund and compensation.

[0008] A method for determining abnormality of an electric energy metering device and evaluating electricity charge refund and compensation is characterized by specifically including:

[0009] S11 Obtain the model of the electric energy metering device, and determine the failure rate of the electric energy metering device according to the model. Based on the failure rate, the installation method of the electric energy metering device, and the average monthly electricity consumption of the user of the electric energy metering device in the past year, an evaluation model based on a machine learning algorithm is used to obtain the evaluation value of the reliability requirement of the electric energy metering device, and the monitoring frequency of the electric energy metering device is determined based on the evaluation value of the reliability requirement;

[0010] S12 Based on the monitoring frequency, obtain the power metering data of the power metering device, and based on the power metering data, historical power metering data, and weather temperature, use a fault diagnosis model based on an intelligent algorithm to obtain the fault diagnosis value of the power metering device, and determine whether the fault diagnosis value is greater than the first threshold. If so, proceed to step S13; if not, return to step S11;

[0011] S13 Based on the power metering data, current waveform, voltage waveform, and power factor, determine the fault type of the power metering device, and based on the fault type of the power metering data and historical power metering data, determine the start and end dates of the fault of the power metering device;

[0012] S14 Based on the start and end dates of the fault and the fault type, calculate the abnormal electricity quantity of the power metering device to obtain a calculation result, and output the electricity refund result according to the calculation result.

[0013] By determining the reliability requirement evaluation value, the determination of the reliability requirements of the power metering device is realized from two aspects: the fault possibility and the electricity consumption of the power metering device, which lays a foundation for setting the monitoring frequency of the power metering device differentially, and also lays a foundation for timely and accurately discovering the problematic power metering device.

[0014] By determining the fault diagnosis value, the diagnosis of the fault condition of the power metering device is realized from multiple aspects such as power metering data, historical power metering data, and weather temperature, which ensures the accuracy of the fault state diagnosis and also lays a foundation for accurately determining the fault type.

[0015] By determining the fault type, the fault condition of the power metering device is further refined, which ensures the refinement and accuracy of the fault condition of the power metering device, and also lays a foundation for targeted maintenance and electricity refund, improving the efficiency of fault maintenance and electricity refund calculation.

[0016] A further technical solution is that the failure rate of the power metering device is determined according to the failure rate of the same model and the same batch of power metering devices from the same manufacturer.

[0017] A further technical solution is that the installation methods of the power metering device include outdoor and indoor.

[0018] A further technical solution is that the specific steps for constructing the reliability requirement evaluation value are as follows:

[0019] S21 Based on the failure rate and the installation method of the power metering device, use a basic evaluation model based on a machine learning algorithm to obtain the basic reliability requirement evaluation value of the power metering device;

[0020] S22 Determine whether the evaluated value of the basic reliability requirement is greater than the second threshold. If so, set the evaluated value of the reliability requirement of the electric energy metering device to 1. If not, proceed to step S23;

[0021] S23 Based on the evaluated value of the basic reliability requirement and the average monthly power consumption of the users of the electric energy metering device in the past year, use an evaluation model based on a machine learning algorithm to obtain the evaluated value of the reliability requirement of the electric energy metering device.

[0022] A further technical solution is that when the evaluated value of the reliability requirement of the electric energy metering device is greater than the first reliability threshold, set the monitoring frequency of the electric energy metering device to the first monitoring frequency; when the evaluated value of the reliability requirement of the electric energy metering device is greater than the second reliability threshold, set the monitoring frequency of the electric energy metering device to the second monitoring frequency; when the evaluated value of the reliability requirement of the electric energy metering device is less than or equal to the second reliability threshold, set the monitoring frequency of the electric energy metering device to the third monitoring frequency, where the first reliability threshold is greater than the second reliability threshold.

[0023] A further technical solution is that the first monitoring frequency is greater than the second monitoring frequency; the second monitoring frequency is greater than the third monitoring frequency, where the first monitoring frequency, the second monitoring frequency, and the third monitoring frequency are determined according to the number of electric energy metering devices in the area where the electric energy metering device to be monitored is located and the power consumption of the electric energy metering devices in the area where the electric energy metering device to be monitored is located. The more the number of electric energy metering devices in the area where the electric energy metering device to be monitored is located and the greater the power consumption of the electric energy metering devices in the area where the electric energy metering device to be monitored is located, the greater the first monitoring frequency, the second monitoring frequency, and the third monitoring frequency.

[0024] A further technical solution is that the specific steps for constructing the fault diagnosis value are as follows:

[0025] S31 Based on the weather temperature on the current day, obtain similar days with a temperature difference less than the first temperature threshold from the weather temperature, and use the historical electric energy metering data of the similar days as the historical electric energy metering data of the similar days;

[0026] S32 Determine whether the ratio of the electric energy metering data to the minimum value of the historical electric energy metering data of the similar days is less than the first ratio threshold or the ratio of the electric energy metering data to the maximum value of the historical electric energy metering data of the similar days is greater than the second ratio threshold. If so, determine that the fault diagnosis value of the electric energy metering device is 1 and there is a suspected fault. If not, proceed to step S32;

[0027] S33 Based on the ratio of the power metering data to the minimum value of the similar-day historical power metering data, the ratio of the power metering data to the maximum value of the similar-day historical power metering data, the power metering data, and the weather temperature, a fault diagnosis model based on a machine learning algorithm is used to obtain the fault diagnosis value of the power metering device.

[0028] A further technical solution is that the value range of the fault diagnosis value is between 0 and 1, where the larger the value of the fault diagnosis value, the greater the possibility that the power metering device has a fault.

[0029] A further technical solution is that the specific steps for determining the fault type of the power metering device are as follows:

[0030] S41 Feature extraction is performed based on the current waveform and the voltage waveform to obtain the current waveform features of the current waveform and the voltage waveform features of the voltage waveform;

[0031] S42 An input set is constructed based on the current waveform features, the voltage waveform features, the power metering data, and the power factor;

[0032] S43 The input set is fed into a classification model based on the SVM algorithm to obtain the fault type of the power metering device.

[0033] A further technical solution is that the specific steps for constructing the measurement result are as follows:

[0034] S51 Based on the fault type of the power metering device, the error coefficient of the power metering data is determined, and the basic measurement result of the power metering device is obtained based on the error coefficient and the power metering data;

[0035] S52 Determine whether the basic measurement result of the power metering device is less than the minimum value of the similar-day historical power metering data. If so, go to step S53; if not, the measurement result is obtained based on the basic measurement result and the average value of the similar-day historical power metering data;

[0036] S53 The measurement result is obtained based on the average value of the similar-day historical power metering data.

[0037] Other features and advantages will be described in the following specification, and part of them will become obvious from the specification or be understood by implementing the present invention. The objectives and other advantages of the present invention are achieved and obtained by the structures specifically pointed out in the specification and the drawings.

[0038] To make the above objectives, features, and advantages of the present invention more obvious and understandable, the following specific preferred embodiments are given, and in conjunction with the accompanying drawings, the detailed description is as follows. Description of the Drawings

[0039] By describing its exemplary embodiments in detail with reference to the drawings, the above and other features and advantages of the present invention will become more apparent.

[0040] Figure 1 is a flowchart of a method for determining anomalies and evaluating electricity refund and compensation of an electricity metering device according to Embodiment 1;

[0041] Figure 2 is a flowchart of the specific steps for constructing the evaluation value of the reliability requirement according to Embodiment 1;

[0042] Figure 3 is a flowchart of the specific steps for constructing the fault diagnosis value according to Embodiment 1. Detailed Embodiments

[0043] Exemplary embodiments will now be described more fully with reference to the drawings. However, the exemplary embodiments can be implemented in various forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this invention will be thorough and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. Like reference numerals in the figures denote the same or similar structures, and thus their detailed description will be omitted.

[0044] The terms "a", "an", "the", and "said" are used to denote the presence of one or more elements / components / etc.; the terms "comprising" and "having" are used to mean an open inclusion and mean that in addition to the listed elements / components / etc., there may be additional elements / components / etc.

[0045] Embodiment 1

[0046] Embodiment 1

[0047] To solve the above problems, according to one aspect of the present invention, as Figure 1 shown, there is provided a method for determining anomalies and evaluating electricity refund and compensation of an electricity metering device, characterized in that it specifically includes:

[0048] S11 Obtain the model of the electricity metering device, and determine the failure rate of the electricity metering device according to the model. Based on the failure rate, the installation method of the electricity metering device, and the average monthly electricity consumption of the user of the electricity metering device in the past year, use an evaluation model based on a machine learning algorithm to obtain the evaluation value of the reliability requirement of the electricity metering device, and determine the monitoring frequency of the electricity metering device based on the evaluation value of the reliability requirement;

[0049] Specifically, the failure rate of the electricity metering device is determined according to the failure rate of the same model and the same batch of electricity metering devices of the same manufacturer.

[0050] Specifically, if the failure rate of power metering devices of the same model in the same batch from the same manufacturer is 1%, and the failure rate when used for more than one year is 2%, then the failure rate is determined according to the service life and model of the power metering device.

[0051] Specifically, the installation methods of the power metering device include outdoor and indoor.

[0052] Specifically, for example, when the installation method is outdoor, the input value to the evaluation model based on the machine learning algorithm is 0, and when the installation method is indoor, the input value to the evaluation model based on the machine learning algorithm is 1.

[0053] Specifically, such as Figure 2 As shown, the specific steps for constructing the reliability requirement evaluation value are as follows:

[0054] S21 Based on the failure rate and the installation method of the power metering device, using a basic evaluation model based on the machine learning algorithm, obtain the basic reliability requirement evaluation value of the power metering device;

[0055] Specifically, for example, the value range of the basic reliability requirement evaluation value is between 0 and 1. The higher the basic reliability requirement evaluation value, the greater the probability of the power metering device having a failure, and the higher the requirement for reliability.

[0056] Specifically, for example, the basic evaluation model based on the machine learning algorithm uses a basic evaluation model based on the improved PSO-SVR algorithm, and the specific steps for its construction are as follows:

[0057] 1) Obtain training samples and perform normalization processing on the data;

[0058] 2) Initialize the improved PSO-SVR model, set the population size of the improved PSO algorithm to 27, the velocity search interval of the particles, the position search interval, the maximum number of iterations T = 200, and wmax = 10;

[0059] 3) Initialize the kernel parameter σ and the penalty factor c of the SVR model as the particle positions of the improved PSO algorithm, and calculate the initial fitness values of the particles according to the fitness function;

[0060] 4) During the algorithm iteration process, each particle updates its own velocity and position, and calculates the updated fitness function value;

[0061] 5) Determine whether the current optimal individual fitness value meets the iteration termination condition, or whether the number of iterations has reached the maximum. If the termination condition is reached, go to the next step; otherwise, go back to step 4) for loop iteration;

[0062] 6) After the improved PSO algorithm iteration terminates, the optimal parameters are output.

[0063] S22 Determine whether the evaluated value of the basic reliability requirement is greater than the second threshold. If so, set the evaluated value of the reliability requirement of the electric energy metering device to 1. If not, proceed to step S23;

[0064] S23 Based on the evaluated value of the basic reliability requirement and the average monthly power consumption of the users of the electric energy metering device in the past year, use an evaluation model based on a machine learning algorithm to obtain the evaluated value of the reliability requirement of the electric energy metering device.

[0065] Specifically, for example, the calculation formula for the inertia factor of the improved PSO algorithm is:

[0066]

[0067] where d is the current iteration number, Wmax is the maximum value of the inertia factor, and T is the maximum number of iterations. is a random function with a value range between and .

[0068] Specifically, when the evaluated value of the reliability requirement of the electric energy metering device is greater than the first reliability threshold, set the monitoring frequency of the electric energy metering device to the first monitoring frequency; when the evaluated value of the reliability requirement of the electric energy metering device is greater than the second reliability threshold, set the monitoring frequency of the electric energy metering device to the second monitoring frequency; when the evaluated value of the reliability requirement of the electric energy metering device is less than or equal to the second reliability threshold, set the monitoring frequency of the electric energy metering device to the third monitoring frequency, where the first reliability threshold is greater than the second reliability threshold.

[0069] Specifically, the first monitoring frequency is greater than the second monitoring frequency; the second monitoring frequency is greater than the third monitoring frequency, where the first monitoring frequency, the second monitoring frequency, and the third monitoring frequency are determined according to the number of electric energy metering devices in the area where the electric energy metering device to be monitored is located and the power consumption of the electric energy metering devices in the area where the electric energy metering device to be monitored is located. The more the number of electric energy metering devices in the area where the electric energy metering device to be monitored is located and the greater the power consumption of the electric energy metering devices in the area where the electric energy metering device to be monitored is located, the greater the first monitoring frequency, the second monitoring frequency, and the third monitoring frequency.

[0070] By determining the evaluation value of the reliability requirement, the determination of the reliability requirement of the electric energy metering device is realized from two aspects: the probability of failure and the power consumption of the electric energy metering device, which lays a foundation for setting the monitoring frequency of the electric energy metering device differentially and also lays a foundation for timely and accurately discovering the problematic electric energy metering device.

[0071] S12 Based on the monitoring frequency, obtain the electric energy metering data of the electric energy metering device, and based on the electric energy metering data, historical electric energy metering data, and weather temperature, use a fault diagnosis model based on an intelligent algorithm to obtain the fault diagnosis value of the electric energy metering device, and determine whether the fault diagnosis value is greater than a first threshold. If so, proceed to step S13; if not, return to step S11.

[0072] Specifically, as Figure 3 shown, the specific steps for constructing the fault diagnosis value are as follows:

[0073] S31 Based on the weather temperature on the current day, obtain similar days with a temperature difference less than a first temperature threshold from the weather temperature, and use the historical electric energy metering data of the similar days as the historical electric energy metering data of the similar days.

[0074] S32 Determine whether the ratio of the electric energy metering data to the minimum value of the historical electric energy metering data of the similar days is less than a first ratio threshold or the ratio of the electric energy metering data to the maximum value of the historical electric energy metering data of the similar days is greater than a second ratio threshold. If so, determine the fault diagnosis value of the electric energy metering device to be 1, indicating a suspected fault; if not, proceed to step S32.

[0075] S33 Based on the ratio of the electric energy metering data to the minimum value of the historical electric energy metering data of the similar days, the ratio of the electric energy metering data to the maximum value of the historical electric energy metering data of the similar days, the electric energy metering data, and the weather temperature, use a fault diagnosis model based on a machine learning algorithm to obtain the fault diagnosis value of the electric energy metering device.

[0076] Specifically, the value range of the fault diagnosis value is between 0 and 1, where the larger the value of the fault diagnosis value, the greater the probability that the electric energy metering device has a fault.

[0077] By determining the fault diagnosis value, the diagnosis of the fault condition of the electric energy metering device is realized from multiple aspects such as electric energy metering data, historical electric energy metering data, and weather temperature, ensuring the accuracy of the fault state diagnosis and also laying a foundation for accurately determining the fault type.

[0078] S13 Determine the fault type of the power metering device based on the power metering data, current waveform, voltage waveform, and power factor, and determine the start and end dates of the fault of the power metering device based on the fault type of the power metering data and historical power metering data;

[0079] Specifically, the specific steps for determining the fault type of the power metering device are as follows:

[0080] S41 Extract features based on the current waveform and voltage waveform to obtain the current waveform features of the current waveform and the voltage waveform features of the voltage waveform;

[0081] S42 Construct an input set based on the current waveform features, voltage waveform features, power metering data, and power factor;

[0082] S43 Send the input set into a classification model based on the SVM algorithm to obtain the fault type of the power metering device.

[0083] S14 Calculate the abnormal power of the power metering device based on the start and end dates of the fault and the fault type to obtain a calculation result, and output the result of power refund and compensation according to the calculation result.

[0084] Specifically, the specific steps for constructing the calculation result are as follows:

[0085] S51 Determine the error coefficient of the power metering data based on the fault type of the power metering device, and obtain the basic calculation result of the power metering device based on the error coefficient and the power metering data;

[0086] S52 Determine whether the basic calculation result of the power metering device is less than the minimum value of the historical power metering data on the similar day. If so, enter step S53; if not, obtain the calculation result based on the average value of the basic calculation result and the historical power metering data on the similar day;

[0087] S53 Obtain the calculation result based on the average value of the historical power metering data on the similar day.

[0088] By determining the fault type, the fault situation of the power metering device is further refined, ensuring the refinement and accuracy of the fault situation of the power metering device, and laying a foundation for targeted maintenance and power refund and compensation, improving the efficiency of fault maintenance and power refund and compensation calculation.

[0089] Embodiment 2

[0090] The present invention provides a terminal device, including a memory, a processor, and a program stored on the memory and executable on the processor. When the processor executes the program, the above-mentioned method for abnormal determination of an electric energy metering device and evaluation of electricity refund and compensation is implemented.

[0091] In several embodiments provided by the present application, it should be understood that the disclosed systems and methods can also be implemented in other ways. The system embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of systems, methods, and computer program products according to multiple embodiments of the present invention. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order from that marked in the accompanying drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0092] In addition, in each embodiment of the present invention, the functional modules can be integrated together to form an independent part, or each module can exist alone, or two or more modules can be integrated to form an independent part.

[0093] If the function is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0094] Taking the ideal embodiments of the present invention described above as an inspiration, through the above description, relevant staff can completely make various changes and modifications without departing from the technical idea of this invention. The technical scope of this invention is not limited to the content in the specification, and its technical scope must be determined according to the scope of the claims.

Claims

1. An abnormal determination method and electricity quantity refund and compensation evaluation method for an electric energy metering device, characterized in that Specifically, it includes: S11 Obtain the model of the electric energy metering device, determine the failure rate of the electric energy metering device according to the model, and based on the failure rate, the installation method of the electric energy metering device, and the average monthly power consumption of the user of the electric energy metering device in the past year, use an evaluation model based on a machine learning algorithm to obtain the evaluation value of the reliability requirement of the electric energy metering device, and determine the monitoring frequency of the electric energy metering device based on the evaluation value of the reliability requirement; S12 Based on the monitoring frequency, obtain the electric energy metering data of the electric energy metering device, and based on the electric energy metering data, historical electric energy metering data, and weather temperature, use a fault diagnosis model based on an intelligent algorithm to obtain the fault diagnosis value of the electric energy metering device, and determine whether the fault diagnosis value is greater than the first threshold. If so, enter step S13; if not, return to step S11; S13 Based on the electric energy metering data, current waveform, voltage waveform, and power factor, determine the fault type of the electric energy metering device, and based on the fault type of the electric energy metering data and historical electric energy metering data, determine the start and end dates of the fault of the electric energy metering device; S14 Based on the start and end dates of the fault and the fault type, calculate the abnormal electricity quantity of the electric energy metering device to obtain a calculation result, and output the electricity refund result according to the calculation result.

2. The abnormal determination and electricity quantity refund and compensation evaluation method for the electric energy metering device according to claim 1, wherein, The failure rate of the electric energy metering device is determined according to the failure rate of the same model and the same batch of electric energy metering devices from the same manufacturer.

3. The abnormal determination and electricity quantity refund and compensation evaluation method for the electric energy metering device according to claim 1, characterized in that, The installation methods of the electric energy metering device include outdoor and indoor.

4. The abnormal determination and electricity quantity refund and compensation evaluation method for the electric energy metering device according to claim 1, characterized in that, The specific steps for constructing the evaluation value of the reliability requirement are as follows: S21 Based on the failure rate and the installation method of the electric energy metering device, use a basic evaluation model based on a machine learning algorithm to obtain the basic evaluation value of the reliability requirement of the electric energy metering device; S22 Determine whether the basic evaluation value of the reliability requirement is greater than the second threshold. If so, set the evaluation value of the reliability requirement of the electric energy metering device to 1; if not, enter step S23; S23 Based on the basic evaluation value of the reliability requirement and the average monthly power consumption of the user of the electric energy metering device in the past year, use an evaluation model based on a machine learning algorithm to obtain the evaluation value of the reliability requirement of the electric energy metering device.

5. The abnormal determination and electricity quantity refund and compensation evaluation method for the electric energy metering device according to claim 4, characterized in that, When the evaluation value of the reliability requirement of the electric energy metering device is greater than the first reliability threshold, set the monitoring frequency of the electric energy metering device to the first monitoring frequency; when the evaluation value of the reliability requirement of the electric energy metering device is greater than the second reliability threshold, set the monitoring frequency of the electric energy metering device to the second monitoring frequency; when the evaluation value of the reliability requirement of the electric energy metering device is less than or equal to the second reliability threshold, set the monitoring frequency of the electric energy metering device to the third monitoring frequency, where the first reliability threshold is greater than the second reliability threshold.

6. The abnormal determination and electricity quantity refund and compensation evaluation method for the electric energy metering device according to claim 5, characterized in that The first monitoring frequency is greater than the second monitoring frequency; the second monitoring frequency is greater than the third monitoring frequency, where the first monitoring frequency, the second monitoring frequency, and the third monitoring frequency are determined according to the number of power metering devices in the area where the power metering device to be monitored is located and the power consumption of the power metering devices in the area where the power metering device to be monitored is located. The more the number of power metering devices in the area where the power metering device to be monitored is located and the greater the power consumption of the power metering devices in the area where the power metering device to be monitored is located, the greater the first monitoring frequency, the second monitoring frequency, and the third monitoring frequency.

7. The abnormal determination and electricity quantity refund and compensation evaluation method for the electric energy metering device according to claim 1, characterized in that The specific steps for constructing the fault diagnosis value are as follows: S31 Based on the weather temperature on the current day, obtain similar days with a temperature difference from the weather temperature less than the first temperature threshold, and use the historical power metering data of the similar days as the historical power metering data of the similar days; S32 Determine whether the ratio of the power metering data to the minimum value of the historical power metering data of the similar days is less than the first ratio threshold or whether the ratio of the power metering data to the maximum value of the historical power metering data of the similar days is greater than the second ratio threshold. If so, determine that the fault diagnosis value of the power metering device is 1 and there is a suspected fault. If not, proceed to step S32; S33 Based on the ratio of the power metering data to the minimum value of the historical power metering data of the similar days, the ratio of the power metering data to the maximum value of the historical power metering data of the similar days, the power metering data, and the weather temperature, use a fault diagnosis model based on a machine learning algorithm to obtain the fault diagnosis value of the power metering device.

8. The abnormal determination and electricity quantity refund and compensation evaluation method for the electric energy metering device according to claim 7, characterized in that, The value range of the fault diagnosis value is between 0 and 1. The larger the value of the fault diagnosis value, the greater the possibility that the power metering device has a fault.

9. The abnormal determination and electricity quantity refund and compensation evaluation method for the electric energy metering device according to claim 1, wherein The specific steps for determining the fault type of the power metering device are as follows: S41 Perform feature extraction based on the current waveform and the voltage waveform to obtain the current waveform features of the current waveform and the voltage waveform features of the voltage waveform; S42 Construct an input set based on the current waveform features, the voltage waveform features, the power metering data, and the power factor; S43 Send the input set into a classification model based on the SVM algorithm to obtain the fault type of the power metering device.

10. The abnormal determination and electricity quantity refund and compensation evaluation method for the electric energy metering device according to claim 1, characterized in that, The specific steps for constructing the measurement result are as follows: S51 Based on the fault type of the power metering device, determine the error coefficient of the power metering data, and based on the error coefficient and the power metering data, obtain the basic measurement result of the power metering device; S52 Determine whether the basic measurement result of the power metering device is less than the minimum value of the historical power metering data of the similar days. If so, proceed to step S53. If not, obtain the measurement result based on the average value of the basic measurement result and the historical power metering data of the similar days; S53 Obtain the measurement result based on the average value of the historical power metering data of the similar days.

Images