Electric energy metering method, device, equipment, medium and program product

Abstract

The invention relates to an electric energy metering method, device and equipment, a medium and a program product. The electric energy metering method comprises the following steps: for a to-be-estimated moment, acquiring charge attribute data collected at at least one historical moment associated with the to-be-estimated moment; the charge attribute data comprises voltage data and current data; for each historical moment, determining a frequency domain signal at the corresponding historical moment according to the charge attribute data at the historical moment; performing feature extraction on the frequency domain signals at the historical moments to obtain frequency domain features at the corresponding historical moments; and determining a target electric energy value at the to-be-estimated moment according to the frequency domain characteristics at different historical moments. Through the method, the accuracy of electric energy prediction is improved.

Description

Technical Field

[0001] The present application relates to the technical field of electric energy metering, and in particular to an electric energy metering method, device, equipment, medium and program product. Background Art

[0002] With the development of power systems, the importance of electric energy metering and prediction technology has become increasingly prominent, becoming a key factor in ensuring the safe and efficient operation of power grids. By accurately predicting future electric energy values, it provides a scientific basis for the rational allocation of power resources.

[0003] Traditionally, the future power trend is usually predicted based on the historical power of the power system. Although this method can reflect the trend of power changes to a certain extent, the prediction accuracy is relatively low and cannot meet the current power system's demand for higher accuracy. Summary of the invention

[0004] Based on this, it is necessary to provide an electric energy metering method, device, equipment, medium and program product that can improve the accuracy of electric energy prediction in response to the above technical problems.

[0005] In a first aspect, the present application provides an electric energy metering method, comprising:

[0006] For the time to be estimated, acquiring charge attribute data collected at at least one historical time associated with the time to be estimated; wherein the charge attribute data includes voltage data and current data;

[0007] For each historical moment, the frequency domain signal at the corresponding historical moment is determined according to the charge attribute data at the historical moment;

[0008] Extract features of the frequency domain signals at the historical moments to obtain the frequency domain features at the corresponding historical moments;

[0009] According to the frequency domain characteristics at different historical moments, the target electric energy value at the moment to be estimated is determined.

[0010] In one of the embodiments, the target electric energy value at the time to be estimated is determined based on the frequency domain characteristics at different historical moments, including: determining the charge attribute data at the time to be estimated based on the frequency domain characteristics at different historical moments; determining the target electric energy value at the time to be estimated based on the charge attribute data at the time to be estimated and the charge attribute data at different historical moments.

[0011] In one of the embodiments, a target electric energy value at the time to be estimated is determined based on charge attribute data at the time to be estimated and charge attribute data at different historical moments, including: determining an average effective electric energy value at the time to be estimated based on the charge attribute data at the time to be estimated and charge attribute data at different historical moments; correcting the average effective electric energy value at the time to be estimated based on a preset temperature compensation coefficient and / or equipment error coefficient to obtain the target electric energy value at the time to be estimated.

[0012] In one of the embodiments, the charge attribute data at the time to be estimated is determined according to the frequency domain features at different historical moments, including: combining the frequency domain features at different historical moments with the time attribute data at the time to be estimated to obtain the target prediction features; inputting the target prediction features into a pre-trained electric energy estimation model to obtain the charge attribute data at the time to be estimated; wherein the electric energy estimation model is trained in the following manner: obtaining the sample charge attribute data collected at at least one sample historical moment associated with the sample estimation moment and the standard charge attribute data at the sample estimation moment; for each sample historical moment, determining the sample frequency domain signal at the corresponding sample historical moment according to the sample charge attribute data at the sample historical moment; performing feature extraction on the sample frequency signal at the sample historical moment to obtain the sample frequency domain features at the corresponding sample historical moment; combining the sample frequency domain features at each sample historical moment with the time attribute data at the corresponding sample historical moment to generate the target sample features at the corresponding sample historical moment; using the target sample features at different sample historical moments as model input and the standard charge attribute data at the corresponding sample estimation moment as labels to perform model training on the pre-constructed electric energy estimation model.

[0013] In one of the embodiments, a frequency domain signal at a corresponding historical moment is determined based on charge attribute data at the historical moment, including: determining a power element value at the corresponding historical moment based on a voltage signal and a current signal at the historical moment; and performing frequency domain conversion on the power element value at the historical moment to obtain a frequency domain signal at the corresponding historical moment.

[0014] In one of the embodiments, feature extraction is performed on the frequency domain signal at the historical moment to obtain the frequency domain features at the corresponding historical moment, including: determining the center frequency, bandwidth, peak frequency, energy distribution in different frequency bands and signal harmonic components of the corresponding frequency domain signal according to the frequency domain signal at the historical moment; generating the frequency domain features at the corresponding historical moment according to at least one of the center frequency, bandwidth, peak frequency, energy distribution in different frequency bands and signal harmonic components.

[0015] In a second aspect, the present application also provides an electric energy metering device, comprising:

[0016] An acquisition module, for acquiring, for the time to be estimated, charge attribute data collected at at least one historical time associated with the time to be estimated; wherein the charge attribute data includes voltage data and current data;

[0017] A first determination module is used to determine, for each historical moment, a frequency domain signal at the corresponding historical moment according to the charge attribute data at the historical moment;

[0018] An extraction module is used to extract features of frequency domain signals at historical moments to obtain frequency domain features at corresponding historical moments;

[0019] The second determination module is used to determine the target electric energy value at the time to be estimated according to the frequency domain characteristics at different historical moments.

[0020] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0021] For the time to be estimated, acquiring charge attribute data collected at at least one historical time associated with the time to be estimated; wherein the charge attribute data includes voltage data and current data;

[0022] For each historical moment, the frequency domain signal at the corresponding historical moment is determined according to the charge attribute data at the historical moment;

[0023] Extract features of the frequency domain signals at the historical moments to obtain the frequency domain features at the corresponding historical moments;

[0024] According to the frequency domain characteristics at different historical moments, the target electric energy value at the moment to be estimated is determined.

[0025] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0026] For the time to be estimated, acquiring charge attribute data collected at at least one historical time associated with the time to be estimated; wherein the charge attribute data includes voltage data and current data;

[0027] For each historical moment, the frequency domain signal at the corresponding historical moment is determined according to the charge attribute data at the historical moment;

[0028] Extract features of the frequency domain signals at the historical moments to obtain the frequency domain features at the corresponding historical moments;

[0029] According to the frequency domain characteristics at different historical moments, the target electric energy value at the moment to be estimated is determined.

[0030] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0031] For the time to be estimated, acquiring charge attribute data collected at at least one historical time associated with the time to be estimated; wherein the charge attribute data includes voltage data and current data;

[0032] For each historical moment, the frequency domain signal at the corresponding historical moment is determined according to the charge attribute data at the historical moment;

[0033] Extract features of the frequency domain signals at the historical moments to obtain the frequency domain features at the corresponding historical moments;

[0034] According to the frequency domain characteristics at different historical moments, the target electric energy value at the moment to be estimated is determined.

[0035] The above-mentioned electric energy metering method, device, equipment, medium and program product obtains the voltage data and current data collected in at least one historical time associated with the time to be estimated, and determines the frequency domain signal at the corresponding historical time based on the voltage data and current data, so as to more directly and accurately reflect the various characteristics of the complex power system through the frequency domain signal. On this basis, by extracting various frequency domain characteristics at different historical times, the target electric energy value at the time to be estimated can be more accurately predicted. Through the above steps, the accuracy of electric energy prediction is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 is a schematic flow chart of an electric energy metering method in one embodiment;

[0038] Figure 2 A schematic flow chart of a target electric energy value determination step in one embodiment;

[0039] Figure 3 A schematic flow chart of a step of determining charge attribute data at a time to be estimated in one embodiment;

[0040] Figure 4 is a flow chart of an electric energy metering method in another embodiment;

[0041] Figure 5is a structural block diagram of an electric energy metering device in one embodiment;

[0042] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0044] In one embodiment, Figure 1 As shown, an electric energy metering method is provided. This embodiment takes the method applied to a terminal as an example for illustration. It can be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0045] S110. For the time to be estimated, obtain charge attribute data collected at at least one historical time associated with the time to be estimated; wherein the charge attribute data includes voltage data and current data.

[0046] Among them, the time to be estimated refers to the time point when the electric energy of the power system needs to be predicted. Optionally, the voltage data and current data can be the voltage signal and current signal of the power system. Optionally, the voltage signal and the current signal are collected in a wide time-frequency domain, and the wide time-frequency domain range can be 0-100kHz (Hz). By collecting charge attribute data in a wide time-frequency domain, the measurement error caused by harmonics, interharmonics, and nonlinear loads can be effectively reduced. Optionally, the collected charge attribute data can also be filtered to remove noise and interference.

[0047] S120. For each historical moment, determine the frequency domain signal at the corresponding historical moment according to the charge attribute data at the historical moment.

[0048] Among them, the frequency domain signal refers to the signal expressed in the frequency domain, that is, the signal in the time domain is converted into a signal representation in the frequency domain.

[0049] In an optional embodiment, determining the frequency domain signal at the corresponding historical moment based on the charge attribute data at the historical moment includes: determining the power element value at the corresponding historical moment based on the voltage signal and current signal at the historical moment; performing frequency domain conversion on the power element value at the historical moment to obtain the frequency domain signal at the corresponding historical moment.

[0050] Exemplarily, the power element value P can be determined by the following formula:

[0051]

[0052] Where P represents the power value; V 0 Represents the DC component of the voltage signal, which is used to reflect the constant part of the voltage signal and provide a reference voltage level; V n It represents the amplitude of the nth harmonic in the voltage signal, represents the size of the nth harmonic in the voltage signal, and describes the intensity of the periodic changing components of different frequencies in the voltage signal; ω represents the angular frequency, which determines the frequency of the harmonic, and is to determine the period and change rate of the harmonic; φ Vn It represents the phase of the nth harmonic in the voltage signal and describes the starting position of the nth harmonic on the time axis. It is of great significance for analyzing the relative relationship between different harmonics and the synthesis of signals. 0 Represents the DC component of the current signal, representing the unchanged part of the current signal; I m Indicates the amplitude of the mth harmonic in the current signal; φ Im It represents the phase of the mth harmonic in the current signal and determines the starting time of the mth harmonic in the current signal.

[0053] Exemplarily, the power element value P can be converted into a frequency domain by the following formula to obtain a frequency domain signal F(ω):

[0054]

[0055] Where F(ω) represents the frequency domain signal; P represents the power value; e -jωt represents a complex exponential function, where ω represents the angular frequency in radians per second, e represents the extension of the exponential function in the real number domain to the complex number domain; dt represents a small change in time, an integral variable; c nφ represents the Fourier coefficient, which describes the amplitude and phase information of different frequency components in the original signal (i.e., the power element value P before frequency domain conversion); (t-nT) represents the time difference, i.e., the distance the signal moves on the time axis; s represents the frequency domain variable.

[0056] S130, extracting features of the frequency domain signal at the historical moment to obtain the frequency domain features at the corresponding historical moment.

[0057] Among them, the frequency domain feature represents the characteristics of the signal in terms of frequency, which describes the behavior of the signal in the frequency domain.

[0058] In an optional embodiment, feature extraction is performed on the frequency domain signal at the historical moment to obtain the frequency domain features at the corresponding historical moment, including: determining the center frequency, bandwidth, peak frequency, energy distribution in different frequency bands and signal harmonic components of the corresponding frequency domain signal according to the frequency domain signal at the historical moment; generating the frequency domain features at the corresponding historical moment according to at least one of the center frequency, bandwidth, peak frequency, energy distribution in different frequency bands and signal harmonic components. Among them, the center frequency represents the main frequency component of the frequency domain signal; the peak frequency represents the frequency range covered by the frequency domain signal; the peak frequency represents the frequency point with the highest amplitude in the spectrum; and the harmonic component represents the integral multiple frequency part of the fundamental frequency contained in the frequency domain signal.

[0059] In an optional embodiment, after obtaining the frequency domain features at the corresponding historical moment, the frequency domain features at the corresponding historical moment are further standardized. The standardization process may be a normalization process or a mean removal process.

[0060] S140. Determine the target electric energy value at the time to be estimated according to the frequency domain characteristics at different historical times.

[0061] In an optional embodiment, determining the target electric energy value at the time to be estimated according to the frequency domain characteristics at different historical moments may include: determining the charge attribute data at the time to be estimated according to the frequency domain characteristics at different historical moments; determining the target electric energy value at the time to be estimated according to the charge attribute data at the time to be estimated and the charge attribute data at different historical moments. Optionally, the frequency domain characteristics at different historical moments may be input into the electric energy estimation model to determine the charge attribute data at the time to be estimated.

[0062] In an optional embodiment, the frequency domain features at different historical moments may be input into a prediction model to determine the target electric energy value at the moment to be estimated.

[0063] In the embodiment of the present application, by obtaining the voltage data and current data collected in at least one history associated with the time to be estimated, and determining the frequency domain signal at the corresponding historical moment based on the voltage data and current data, the various characteristics of the complex power system can be more directly and accurately reflected through the frequency domain signal. On this basis, by extracting various frequency domain characteristics at different historical moments, the target electric energy value at the time to be estimated can be more accurately predicted. Through the above steps, the accuracy of electric energy prediction is improved.

[0064] Based on the technical solutions of the above embodiments, the present application also provides an optional embodiment, in which the step of determining the target electric energy value is refined.

[0065] See also Figure 2The target electric energy value determination steps shown include:

[0066] S210, determining the average effective electric energy value at the time to be estimated based on the charge attribute data at the time to be estimated and the charge attribute data at different historical times.

[0067] S220. Correct the average effective electric energy value at the time to be estimated according to a preset temperature compensation coefficient and / or a device error coefficient to obtain a target electric energy value at the time to be estimated.

[0068] The charge attribute data may include voltage, current and total power factor. Optionally, the charge attribute data may include voltage after harmonics are considered, current after harmonics are considered and total power factor after harmonics are considered.

[0069] In an optional embodiment, the target electric energy value is calculated by the following formula:

[0070]

[0071] Where E represents the target electric energy value, that is, the electric energy prediction result at the estimated time after various corrections and calculations; ϵ represents the device error coefficient of the acquisition device, which is used to consider the impact of the measurement error of the device itself on the target electric energy value; K T represents the preset temperature compensation coefficient, which is used to correct the influence of temperature change on the calculated target electric energy value; p represents the number of sampling times; ∆t represents the time difference between two adjacent samplings; V total，i ,I total，i 、COSφ total，i Represents the charge attribute data at the time to be estimated and at different historical moments; V total，i It represents the total voltage after considering harmonics at the i-th sampling point; I total，i represents the total current after considering harmonics at the i-th sampling point; COSφ total，i It represents the total power factor after considering harmonics at the i-th sampling point, which is used to reflect the impact of the phase relationship between voltage and current on power.

[0072] In an embodiment of the present application, the average effective electric energy value at the time to be estimated is determined by using the charge attribute data at the time to be estimated and the charge attribute data at different historical times, and the average effective electric energy value at the time to be estimated is corrected according to a preset temperature compensation coefficient and / or an equipment error coefficient, thereby improving the accuracy of the prediction of the target electric energy value.

[0073] Based on the technical solutions of the above-mentioned embodiments, the present application also provides an optional embodiment, in which the step of determining the charge attribute data at the time to be estimated is refined.

[0074] See also Figure 3 The step of determining the charge attribute data at the time to be estimated includes:

[0075] S310: Combine the frequency domain features at different historical moments with the time attribute data of the moment to be estimated to obtain target prediction features.

[0076] S320: Input the target prediction features into a pre-trained electric energy estimation model to obtain charge attribute data at the time to be estimated.

[0077] The charge attribute data at the time to be estimated may include the voltage, current and total power factor at the time to be estimated.

[0078] In an optional embodiment, the target prediction features can be sorted and normalized before being input into a pre-trained electric energy estimation model. Exemplarily, the target prediction features can be classified to facilitate the management and understanding of features of different natures. Exemplarily, outliers can be identified and processed by statistical methods, and deletion, replacement or special processing can be selected, while missing values ​​can be filled by means of mean filling, median filling or interpolation. Exemplarily, the target prediction features can be mapped to a specific interval using a data normalization method, such as minimum to maximum normalization or standard deviation standardization, or the data normalization method can be used to make the data mean 0 and the standard deviation 1. Optionally, the target prediction features after sorting and normalization can be verified and evaluated, and the data trend can be observed with the help of visualization means, and the evaluation indicators such as accuracy and recall rate can be used to determine whether the data is suitable for subsequent analysis and processing to ensure the accuracy and completeness of the data. Optionally, according to the input format and requirements of the electric energy estimation model, necessary format conversion and adjustment can be performed on the target prediction features to establish a stable data transmission channel to ensure that the target prediction features can be accurately and timely transmitted to the electric energy estimation model, and the timestamp and source information of the input data can be recorded to facilitate subsequent analysis and traceability, continuously optimize the input process and method, and improve the efficiency and accuracy of data input.

[0079] In an optional embodiment, the electric energy estimation model is trained in the following manner: sample charge attribute data collected at at least one sample historical moment associated with the sample estimation moment and standard charge attribute data at the sample estimation moment are obtained; for each sample historical moment, the sample frequency domain signal at the corresponding sample historical moment is determined based on the sample charge attribute data at the sample historical moment; feature extraction is performed on the sample frequency signal at the sample historical moment to obtain the sample frequency domain feature at the corresponding sample historical moment; the sample frequency domain feature at each sample historical moment is combined with the time attribute data at the corresponding sample historical moment to generate the target sample feature at the corresponding sample historical moment; the target sample features at different sample historical moments are used as model input, and the standard charge attribute data at the corresponding sample estimation moment is used as a label to perform model training on the pre-constructed electric energy estimation model.

[0080] Optionally, before using the target sample features at different sample historical moments as model input, the target sample features may be cleaned and preprocessed to remove possible missing values, outliers, etc. to ensure data quality. The target sample features may also be processed through appropriate encoding or conversion methods to make them meet the input requirements of the model.

[0081] Optionally, after the training of the electric energy estimation model is completed, the trained electric energy estimation model can also be verified. Exemplarily, the target electric energy value at each time to be estimated is calculated through the electric energy prediction model, and the actual electric energy value of the power system is obtained at the corresponding time to be estimated, and the target electric energy value is compared with the corresponding actual electric energy value to verify whether the comparison result meets the expected standard. In the case that the comparison result does not meet the expected standard, it is possible to detect whether the parameters of the electric energy estimation model are reasonable, whether there are errors in the training process, etc., so as to determine whether the model needs to be retrained or the electric energy estimation model needs to be improved and optimized.

[0082] Optionally, when verifying the electric energy estimation model, the target electric energy value and the actual electric energy value under the same time period conditions can be obtained, and the target electric energy value and the actual electric energy value under the same time period conditions can be compared to further explore the electric energy prediction effect of the electric energy estimation model under the conditions of each specific time period.

[0083] Optionally, the error value between the target electric energy value and the actual electric energy value is calculated by the following formula:

[0084]

[0085] Among them, F error represents the error value between the target electric energy value and the actual electric energy value; r represents the number of data points; represents the jth target electric energy value; E jrepresents the jth actual electric energy value; max(E j ) represents the maximum value of all actual electric energy values; min(E j ) represents the minimum value of all actual electrical energy values.

[0086] By calculating the size and changing trend of the error value, it is easy to analyze and explore the influence of different factors on the predicted target electric energy value. The error value is compared with the preset accuracy standard or industry specification to determine the advantages and disadvantages of the electric energy estimation model and correction parameters, and the distribution characteristics and abnormal conditions can be displayed in combination with data visualization to deeply and accurately evaluate the effect of the target electric energy value prediction. In addition, in the process of further adjusting the electric energy estimation model, it is also possible to determine the key parameters in the electric energy estimation model that have a greater impact on the accuracy of the target electric energy value, and gradually adjust the values ​​of the key parameters to improve the prediction accuracy of the electric energy estimation model.

[0087] Based on the technical solutions of the above embodiments, the present application also provides an optional embodiment, in which another specific implementation method of the electric energy metering method is provided.

[0088] See also Figure 4 The electric energy measurement method shown includes:

[0089] S410. For the time to be estimated, obtain charge attribute data collected at at least one historical time associated with the time to be estimated; wherein the charge attribute data includes voltage data and current data.

[0090] S420. For each historical moment, determine the power microelement value at the corresponding historical moment according to the voltage signal and the current signal at the historical moment.

[0091] S430, performing frequency domain conversion on the power element value at the historical moment to obtain the frequency domain signal at the corresponding historical moment.

[0092] S440. Determine, according to the frequency domain signal at the historical moment, the center frequency, bandwidth, peak frequency, energy distribution in different frequency bands, and signal harmonic components of the corresponding frequency domain signal.

[0093] S450, generating frequency domain features at a corresponding historical moment according to at least one of a center frequency, a bandwidth, a peak frequency, energy distribution in different frequency bands, and a signal harmonic component.

[0094] S460: Combine the frequency domain features at different historical moments with the time attribute data of the moment to be estimated to obtain target prediction features.

[0095] S470: Input the target prediction features into a pre-trained electric energy estimation model to obtain charge attribute data at the time to be estimated.

[0096] S480, determining the average effective electric energy value at the time to be estimated based on the charge attribute data at the time to be estimated and the charge attribute data at different historical times.

[0097] S490. According to a preset temperature compensation coefficient and / or a device error coefficient, the average effective electric energy value at the time to be estimated is corrected to obtain a target electric energy value at the time to be estimated.

[0098] The detailed technical contents of the above steps S410 - S490 have been recorded in the above embodiments and will not be repeated here.

[0099] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0100] Based on the same inventive concept, the embodiment of the present application also provides an electric energy metering device for implementing the electric energy metering method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more electric energy metering device embodiments provided below can refer to the limitations of the electric energy metering method above, and will not be repeated here.

[0101] In an exemplary embodiment, Figure 5 As shown, an electric energy metering device is provided, including: an acquisition module 510, a first determination module 520, an extraction module 530 and a second determination module 540, wherein:

[0102] The acquisition module 510 is used to acquire, for the time to be estimated, charge attribute data collected at at least one historical time associated with the time to be estimated; wherein the charge attribute data includes voltage data and current data;

[0103] A first determination module 520 is used to determine, for each historical moment, a frequency domain signal at the corresponding historical moment according to the charge attribute data at the historical moment;

[0104] An extraction module 530 is used to extract features from the frequency domain signal at a historical moment to obtain frequency domain features at the corresponding historical moment;

[0105] The second determination module 540 is used to determine the target electric energy value at the time to be estimated according to the frequency domain characteristics at different historical times.

[0106] In one embodiment, the second determination module 540 includes: a first determination unit, used to determine the charge attribute data at the time to be estimated based on the frequency domain characteristics at different historical moments; a second determination unit, used to determine the target electric energy value at the time to be estimated based on the charge attribute data at the time to be estimated and the charge attribute data at different historical moments.

[0107] In one embodiment, the second determination unit includes: a first determination subunit, used to determine the average effective electric energy value at the time to be estimated based on the charge attribute data at the time to be estimated and the charge attribute data at different historical times; a correction subunit, used to correct the average effective electric energy value at the time to be estimated based on a preset temperature compensation coefficient and / or equipment error coefficient to obtain the target electric energy value at the time to be estimated.

[0108] In one embodiment, the first determination unit includes: a first processing subunit, which is used to combine the frequency domain features at different historical moments with the time attribute data at the time to be estimated to obtain the target prediction feature; a second processing subunit, which inputs the target prediction feature into a pre-trained electric energy estimation model to obtain the charge attribute data at the time to be estimated;

[0109] In one embodiment, the electric energy metering device further includes a training module for training the electric energy estimation model. The training module includes: a first acquisition unit for acquiring sample charge attribute data collected at at least one sample historical moment associated with the sample estimation moment and standard charge attribute data at the sample estimation moment; a third determination unit for determining the sample frequency domain signal at the corresponding sample historical moment according to the sample charge attribute data at the sample historical moment for each sample historical moment; a first extraction unit for performing feature extraction on the sample frequency signal at the sample historical moment to obtain the sample frequency domain feature at the corresponding sample historical moment; a first generation unit for combining the sample frequency domain feature at each sample historical moment with the time attribute data at the corresponding sample historical moment to generate the target sample feature at the corresponding sample historical moment; a training unit for taking the target sample features at different sample historical moments as model input and the standard charge attribute data at the corresponding sample estimation moment as labels to perform model training on the pre-constructed electric energy estimation model.

[0110] In one embodiment, the first determination module 520 includes: a fourth determination unit, used to determine the power element value at the corresponding historical moment based on the voltage signal and the current signal at the historical moment; a conversion unit, used to perform frequency domain conversion on the power element value at the historical moment to obtain the frequency domain signal at the corresponding historical moment.

[0111] In one embodiment, the extraction module 530 includes: a fifth determination unit, which is used to determine the center frequency, bandwidth, peak frequency, energy distribution in different frequency bands and signal harmonic components of the corresponding frequency domain signal according to the frequency domain signal at the historical moment; a second generation unit, which is used to generate the frequency domain characteristics at the corresponding historical moment according to at least one of the center frequency, bandwidth, peak frequency, energy distribution in different frequency bands and signal harmonic components.

[0112] Each module in the above-mentioned electric energy metering device can be implemented in whole or in part by software, hardware or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0113] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 6 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, an electric energy metering method is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0114] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0115] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0116] For the time to be estimated, acquiring charge attribute data collected at at least one historical time associated with the time to be estimated; wherein the charge attribute data includes voltage data and current data;

[0117] For each historical moment, the frequency domain signal at the corresponding historical moment is determined according to the charge attribute data at the historical moment;

[0118] Extract features of the frequency domain signals at the historical moments to obtain the frequency domain features at the corresponding historical moments;

[0119] According to the frequency domain characteristics at different historical moments, the target electric energy value at the moment to be estimated is determined.

[0120] In one embodiment, when the processor executes the computer program, the following steps are also implemented: based on the frequency domain characteristics at different historical moments, the charge attribute data at the moment to be estimated is determined; based on the charge attribute data at the moment to be estimated and the charge attribute data at different historical moments, the target electric energy value at the moment to be estimated is determined.

[0121] In one embodiment, when the processor executes the computer program, the following steps are also implemented: determining the average effective electric energy value at the time to be estimated based on the charge attribute data at the time to be estimated and the charge attribute data at different historical times; correcting the average effective electric energy value at the time to be estimated based on a preset temperature compensation coefficient and / or equipment error coefficient to obtain the target electric energy value at the time to be estimated.

[0122] In one embodiment, when the processor executes the computer program, the following steps are also implemented: combining the frequency domain features at different historical moments with the time attribute data at the moment to be estimated to obtain the target prediction features; inputting the target prediction features into a pre-trained electric energy estimation model to obtain the charge attribute data at the moment to be estimated; wherein the electric energy estimation model is trained in the following manner: obtaining the sample charge attribute data collected at at least one sample historical moment associated with the sample estimation moment and the standard charge attribute data at the sample estimation moment; for each sample historical moment, determining the sample frequency domain signal at the corresponding sample historical moment according to the sample charge attribute data at the sample historical moment; performing feature extraction on the sample frequency signal at the sample historical moment to obtain the sample frequency domain features at the corresponding sample historical moment; combining the sample frequency domain features at each sample historical moment with the time attribute data at the corresponding sample historical moment to generate the target sample features at the corresponding sample historical moment; using the target sample features at different sample historical moments as model input and the standard charge attribute data at the corresponding sample estimation moment as labels to perform model training on the pre-constructed electric energy estimation model.

[0123] In one embodiment, when the processor executes the computer program, the following steps are also implemented: determining the power element value at the corresponding historical moment based on the voltage signal and the current signal at the historical moment; performing frequency domain conversion on the power element value at the historical moment to obtain the frequency domain signal at the corresponding historical moment.

[0124] In one embodiment, when the processor executes the computer program, the following steps are also implemented: based on the frequency domain signal at the historical moment, the center frequency, bandwidth, peak frequency, energy distribution in different frequency bands and signal harmonic components of the corresponding frequency domain signal are determined; based on at least one of the center frequency, bandwidth, peak frequency, energy distribution in different frequency bands and signal harmonic components, the frequency domain characteristics at the corresponding historical moment are generated.

[0125] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0126] For the time to be estimated, acquiring charge attribute data collected at at least one historical time associated with the time to be estimated; wherein the charge attribute data includes voltage data and current data;

[0127] For each historical moment, the frequency domain signal at the corresponding historical moment is determined according to the charge attribute data at the historical moment;

[0128] Extract features of the frequency domain signals at the historical moments to obtain the frequency domain features at the corresponding historical moments;

[0129] According to the frequency domain characteristics at different historical moments, the target electric energy value at the moment to be estimated is determined.

[0130] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: based on the frequency domain characteristics at different historical moments, the charge attribute data at the moment to be estimated is determined; based on the charge attribute data at the moment to be estimated and the charge attribute data at different historical moments, the target electric energy value at the moment to be estimated is determined.

[0131] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: determining the average effective electric energy value at the time to be estimated based on the charge attribute data at the time to be estimated and the charge attribute data at different historical times; correcting the average effective electric energy value at the time to be estimated based on a preset temperature compensation coefficient and / or equipment error coefficient to obtain the target electric energy value at the time to be estimated.

[0132] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: combining the frequency domain features at different historical moments with the time attribute data at the moment to be estimated to obtain the target prediction features; inputting the target prediction features into a pre-trained electric energy estimation model to obtain the charge attribute data at the moment to be estimated; wherein the electric energy estimation model is trained in the following manner: obtaining the sample charge attribute data collected at at least one sample historical moment associated with the sample estimation moment and the standard charge attribute data at the sample estimation moment; for each sample historical moment, determining the sample frequency domain signal at the corresponding sample historical moment according to the sample charge attribute data at the sample historical moment; performing feature extraction on the sample frequency signal at the sample historical moment to obtain the sample frequency domain features at the corresponding sample historical moment; combining the sample frequency domain features at each sample historical moment with the time attribute data at the corresponding sample historical moment to generate the target sample features at the corresponding sample historical moment; using the target sample features at different sample historical moments as model input and the standard charge attribute data at the corresponding sample estimation moment as labels to perform model training on the pre-constructed electric energy estimation model.

[0133] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: determining the power element value at the corresponding historical moment based on the voltage signal and current signal at the historical moment; performing frequency domain conversion on the power element value at the historical moment to obtain the frequency domain signal at the corresponding historical moment.

[0134] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: based on the frequency domain signal at the historical moment, the center frequency, bandwidth, peak frequency, energy distribution in different frequency bands and signal harmonic components of the corresponding frequency domain signal are determined; based on at least one of the center frequency, bandwidth, peak frequency, energy distribution in different frequency bands and signal harmonic components, the frequency domain characteristics at the corresponding historical moment are generated.

[0135] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0136] For the time to be estimated, acquiring charge attribute data collected at at least one historical time associated with the time to be estimated; wherein the charge attribute data includes voltage data and current data;

[0137] For each historical moment, the frequency domain signal at the corresponding historical moment is determined according to the charge attribute data at the historical moment;

[0138] Extract features of the frequency domain signals at the historical moments to obtain the frequency domain features at the corresponding historical moments;

[0139] According to the frequency domain characteristics at different historical moments, the target electric energy value at the moment to be estimated is determined.

[0140] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: based on the frequency domain characteristics at different historical moments, the charge attribute data at the moment to be estimated is determined; based on the charge attribute data at the moment to be estimated and the charge attribute data at different historical moments, the target electric energy value at the moment to be estimated is determined.

[0141] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: determining the average effective electric energy value at the time to be estimated based on the charge attribute data at the time to be estimated and the charge attribute data at different historical times; correcting the average effective electric energy value at the time to be estimated based on a preset temperature compensation coefficient and / or equipment error coefficient to obtain the target electric energy value at the time to be estimated.

[0142] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: combining the frequency domain features at different historical moments with the time attribute data at the moment to be estimated to obtain the target prediction features; inputting the target prediction features into a pre-trained electric energy estimation model to obtain the charge attribute data at the moment to be estimated; wherein the electric energy estimation model is trained in the following manner: obtaining the sample charge attribute data collected at at least one sample historical moment associated with the sample estimation moment and the standard charge attribute data at the sample estimation moment; for each sample historical moment, determining the sample frequency domain signal at the corresponding sample historical moment according to the sample charge attribute data at the sample historical moment; performing feature extraction on the sample frequency signal at the sample historical moment to obtain the sample frequency domain features at the corresponding sample historical moment; combining the sample frequency domain features at each sample historical moment with the time attribute data at the corresponding sample historical moment to generate the target sample features at the corresponding sample historical moment; using the target sample features at different sample historical moments as model input and the standard charge attribute data at the corresponding sample estimation moment as labels to perform model training on the pre-constructed electric energy estimation model.

[0143] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: determining the power element value at the corresponding historical moment based on the voltage signal and current signal at the historical moment; performing frequency domain conversion on the power element value at the historical moment to obtain the frequency domain signal at the corresponding historical moment.

[0144] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: based on the frequency domain signal at the historical moment, the center frequency, bandwidth, peak frequency, energy distribution in different frequency bands and signal harmonic components of the corresponding frequency domain signal are determined; based on at least one of the center frequency, bandwidth, peak frequency, energy distribution in different frequency bands and signal harmonic components, the frequency domain characteristics at the corresponding historical moment are generated.

[0145] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0146] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0147] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for measuring electric energy, characterized in that: include: For the time to be estimated, acquiring charge attribute data collected at at least one historical time associated with the time to be estimated; wherein the charge attribute data includes voltage data and current data; For each historical moment, determining a frequency domain signal at the corresponding historical moment according to the charge attribute data at the historical moment; Extracting features of the frequency domain signal at the historical moment to obtain frequency domain features at the corresponding historical moment; According to the frequency domain characteristics at different historical moments, the target electric energy value at the moment to be estimated is determined.

2. The method according to claim 1, characterized in that The step of determining the target electric energy value at the time to be estimated according to the frequency domain characteristics at different historical moments includes: Determining the charge attribute data at the time to be estimated according to the frequency domain characteristics at different historical moments; The target electric energy value at the time to be estimated is determined according to the charge attribute data at the time to be estimated and the charge attribute data at different historical times.

3. The method according to claim 2, characterized in that The step of determining the target electric energy value at the time to be estimated according to the charge attribute data at the time to be estimated and the charge attribute data at different historical times includes: Determine the average effective electric energy value at the time to be estimated according to the charge attribute data at the time to be estimated and the charge attribute data at different historical times; According to a preset temperature compensation coefficient and / or a device error coefficient, the average effective electric energy value at the time to be estimated is corrected to obtain a target electric energy value at the time to be estimated.

4. The method according to claim 2, characterized in that: The step of determining the charge attribute data at the time to be estimated according to the frequency domain characteristics at different historical moments includes: Combining the frequency domain features at different historical moments with the time attribute data of the moment to be estimated to obtain target prediction features; Inputting the target prediction feature into a pre-trained electric energy estimation model to obtain the charge attribute data at the time to be estimated; The electric energy estimation model is trained in the following way: Acquire sample charge attribute data collected at at least one sample historical moment associated with the sample estimation moment and standard charge attribute data at the sample estimation moment; For each sample historical moment, determining a sample frequency domain signal at the corresponding sample historical moment according to the sample charge attribute data at the sample historical moment; Extracting features of the sample frequency signal at the sample historical moment to obtain the sample frequency domain features at the corresponding sample historical moment; The sample frequency domain features at each sample historical moment and the time attribute data at the corresponding sample historical moment are combined to generate the target sample features at the corresponding sample historical moment; The target sample features at different sample historical moments are used as model input, and the standard charge attribute data at the corresponding sample estimation moment is used as a label to train the pre-built electric energy estimation model.

5. The method according to any one of claims 1 to 4, characterized in that: Determining the frequency domain signal at the corresponding historical moment according to the charge attribute data at the historical moment includes: Determine the power microelement value at the corresponding historical moment according to the voltage signal and the current signal at the historical moment; The power infinitesimal value at the historical moment is converted into a frequency domain to obtain a frequency domain signal at the corresponding historical moment.

6. The method according to any one of claims 1 to 4, characterized in that: The extracting features of the frequency domain signal at the historical moment to obtain the frequency domain features at the corresponding historical moment includes: According to the frequency domain signal at the historical moment, determine the center frequency, bandwidth, peak frequency, energy distribution in different frequency bands and signal harmonic components of the corresponding frequency domain signal; A frequency domain feature at a corresponding historical moment is generated according to at least one of a center frequency, a bandwidth, a peak frequency, energy distribution in different frequency bands, and a signal harmonic component.

7. An electric energy metering device, characterized in that: The device comprises: An acquisition module, for acquiring, for a time to be estimated, charge attribute data collected at at least one historical time associated with the time to be estimated; wherein the charge attribute data includes voltage data and current data; A first determination module is used to determine, for each historical moment, a frequency domain signal at the corresponding historical moment according to the charge attribute data at the historical moment; An extraction module, used to extract features from the frequency domain signal at the historical moment to obtain the frequency domain features at the corresponding historical moment; The second determination module is used to determine the target electric energy value at the time to be estimated according to the frequency domain characteristics at different historical moments.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images