Electric quantity abnormity determination method and device, equipment and medium

By receiving the user's actual electricity consumption, temperature and holiday data, and using the prediction model to determine the power abnormality, the measurement error problem in electricity bill settlement is solved, and the accuracy and reliability of power metering is improved.

CN119066394APending Publication Date: 2024-12-03STATE GRID BEIJING ELECTRIC POWER CO +1
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202411202639.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-29
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

In the prior art, there is an error in the electricity metering of users, resulting in an error in the settlement of electricity bills, and the abnormal electricity cannot be discovered in time, affecting the accuracy of electricity bills.

Method used

By receiving the determination request, the user's actual electricity consumption, temperature data set and holiday data set are obtained, and the pre-trained prediction model is used to determine the predicted maximum electricity consumption and predict the minimum electricity consumption, and compare it with the actual electricity consumption to judge the use of Is the electricity abnormal?

Benefits of technology

It realizes accurate and effective identification of electricity consumption abnormalities, reduces electricity bill settlement errors, and improves the accuracy and reliability of power metering.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119066394A_ABST
    Figure CN119066394A_ABST
Patent Text Reader

Abstract

The embodiment of the invention provides an electric quantity abnormity determination method and device, equipment and a medium, and is used for solving the problem that electric quantity abnormity cannot be determined in the prior art. According to the embodiment of the invention, after the electronic equipment receives the determination request, the electronic equipment obtains the identification of the to-be-determined month and the identification of the to-be-predicted user carried in the determination request, obtains the actual electricity consumption of the to-be-predicted user in the to-be-determined month, and obtains the temperature data set and the holiday data set of the to-be-determined month in each historical year; and based on a pre-trained prediction model, the temperature data set and the holiday and festival data set, determining predicted maximum power consumption and predicted minimum power consumption of the to-be-determined month, and based on the predicted maximum power consumption, the predicted minimum power consumption and actual power consumption, determining whether the power consumption of the to-be-predicted user is abnormal or not. Therefore, whether the electricity utilization is abnormal or not can be accurately and effectively determined.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, equipment and medium for determining an abnormal amount of electrical power. Background Art

[0002] As the basic data for the settlement between power companies and users, the accuracy of electricity consumption data is crucial for the settlement of user electricity charges. At present, the settlement of user electricity charges mainly takes the natural month as the settlement cycle. If there is an error in the electricity consumption during the monthly electricity charge settlement, it will lead to errors in the user's electricity charge, which is very likely to cause economic losses to the power company or the user. In addition, it will also cause user complaints and social public opinion. In order to ensure the accuracy of user electricity metering, the power company has made a lot of algorithm improvements in the intelligent monitoring of electricity meter errors and electricity meter fault monitoring, which greatly reduced the proportion of electricity meter measurement errors. However, there are still the following situations that lead to user electricity metering errors. First, it takes a certain period of time to complete the abnormal monitoring of electricity meter measurement and the offline replacement of faulty electricity meters. The electricity bill settlement is carried out at the beginning of each month. It is easy for abnormal electricity meters to be not managed during the electricity bill settlement cycle, which leads to errors in the issued electricity charges. Second, users need to read meters when applying for electricity consumption change services. Meter reading data is manually entered, and human errors can easily lead to errors in electricity data entry, which in turn affects the accuracy of electricity charges. Third, when adjusting the user profile, the relationship between the receiving point and the metering point and the field data required for the calculation of electricity charges may be changed by mistake, resulting in errors in the basic data for calculating the user's electricity charges, which in turn leads to errors in electricity charges. Fourth, there are power failures within the user, such as leakage, which can also cause abnormal electricity, but the abnormality cannot be detected at the electricity meter terminal. Summary of the invention

[0003] The present application provides a method, device, equipment and medium for determining an abnormal amount of electric power, so as to solve the problem that an abnormal amount of electric power cannot be determined in the prior art.

[0004] The present application provides a method for determining an abnormal amount of power, the method comprising:

[0005] receiving a determination request, and obtaining the identifier of the month to be determined and the user to be predicted carried in the determination request;

[0006] Obtain the actual power consumption of the user to be predicted in the month to be determined; and obtain the temperature data set and holiday data set corresponding to the month to be determined;

[0007] Determine the predicted maximum power consumption and the predicted minimum power consumption of the to-be-determined month based on the pre-trained prediction model, the temperature data set, and the holiday data set;

[0008] Based on the predicted maximum power consumption, the predicted minimum power consumption and the actual power consumption, it is determined whether the power consumption is abnormal.

[0009] Further, the determining the predicted maximum power consumption and the predicted minimum power consumption of the to-be-determined month based on the pre-trained prediction model, the temperature data set, and the holiday data set includes:

[0010] Inputting the temperature data set and the holiday data set into a pre-trained prediction model to obtain a load trend prediction curve output by the prediction model;

[0011] and obtaining a set of each historical load curve corresponding to the to-be-determined month of each year; and obtaining a load fluctuation curve corresponding to the set;

[0012] Obtaining a load prediction upper limit curve and a load prediction lower limit curve according to the fusion of the load trend prediction curve and the load fluctuation curve;

[0013] The predicted maximum power consumption and the predicted minimum power consumption of the to-be-determined month are determined according to the load prediction upper limit curve and the load prediction lower limit curve.

[0014] Further, the obtaining of the load fluctuation curve corresponding to the set includes:

[0015] Performing a dispersion analysis on the monthly load curve elements in the set, two by two, to obtain a set of load curves with the largest dispersion;

[0016] Extract the fluctuation characteristic curve between a group of load curves with the largest discreteness.

[0017] Further, the step of obtaining a load prediction upper limit curve and a load prediction lower limit curve by fusing the load trend prediction curve and the load fluctuation curve includes:

[0018] Determine a load prediction upper limit curve according to the sum of the load trend prediction curve and the load fluctuation curve;

[0019] And according to the difference between each point on the load trend prediction curve and the load fluctuation curve, a load prediction lower limit curve is determined.

[0020] Further, after determining the predicted maximum power consumption and the predicted minimum power consumption of the to-be-determined month, and before determining whether the power consumption is abnormal based on the predicted maximum power consumption, the predicted minimum power consumption and the actual power consumption, the method further includes:

[0021] Obtaining the non-metered basic electricity consumption of the user to be predicted;

[0022] Based on the sum of the predicted maximum power consumption and the non-metered basic power consumption, updating the predicted maximum power consumption;

[0023] and updating the predicted minimum power consumption based on the sum of the predicted minimum power consumption and the non-metered basic power consumption;

[0024] For the updated predicted maximum power consumption and predicted minimum power consumption, a subsequent step of determining whether power consumption is abnormal based on the predicted maximum power consumption, the predicted minimum power consumption and the actual power consumption is performed.

[0025] Furthermore, the prediction model is trained in the following manner:

[0026] Performing J-layer wavelet decomposition on each element in the set to obtain a set of load trend curves;

[0027] The prediction model is trained based on the set of load trend curves, the historical temperature data set of the to-be-determined month of each historical year, and the historical holiday data set.

[0028] Furthermore, the method further comprises:

[0029] If it is determined that the electricity consumption is normal, the actual electricity consumption is issued;

[0030] If it is determined that the power consumption is abnormal, the actual power consumption and the identifier of the user to be predicted are sent to a preset device. If a confirmation instruction returned by the preset device is received, the actual power consumption is issued.

[0031] The embodiment of the present application also provides a product for determining abnormal power consumption, the product comprising:

[0032] A receiving module, used for receiving a determination request, and obtaining the identifier of the month to be determined and the user to be predicted carried in the determination request;

[0033] An acquisition module, used to acquire the actual power consumption of the user to be predicted in the month to be determined; and to acquire a temperature data set and a holiday data set corresponding to the month to be determined;

[0034] A processing module is used to determine the predicted maximum power consumption and the predicted minimum power consumption of the to-be-determined month based on the pre-trained prediction model and the temperature data set and the holiday data set; and to determine whether the power consumption is abnormal based on the predicted maximum power consumption, the predicted minimum power consumption and the actual power consumption.

[0035] Furthermore, the processing module is specifically used to input the temperature data set and the holiday data set into a pre-trained prediction model to obtain a load trend prediction curve output by the prediction model;

[0036] and obtaining a set of each historical load curve corresponding to the to-be-determined month of each year; and obtaining a load fluctuation curve corresponding to the set;

[0037] Obtaining a load prediction upper limit curve and a load prediction lower limit curve according to the fusion of the load trend prediction curve and the load fluctuation curve;

[0038] The predicted maximum power consumption and the predicted minimum power consumption of the to-be-determined month are determined according to the load prediction upper limit curve and the load prediction lower limit curve.

[0039] Furthermore, the processing module is specifically used to perform a discreteness analysis on the monthly load curve elements in the set, and obtain a set of load curves with the largest discreteness;

[0040] Extract the fluctuation characteristic curve between a group of load curves with the largest discreteness.

[0041] Furthermore, the processing module is specifically used to determine the load prediction upper limit curve according to the sum of the load trend prediction curve and the points on the load fluctuation curve;

[0042] And according to the difference between each point on the load trend prediction curve and the load fluctuation curve, a load prediction lower limit curve is determined.

[0043] Furthermore, the processing module is further used to obtain the non-metered basic electricity consumption of the user to be predicted;

[0044] Based on the sum of the predicted maximum power consumption and the non-metered basic power consumption, updating the predicted maximum power consumption;

[0045] and updating the predicted minimum power consumption based on the sum of the predicted minimum power consumption and the non-metered basic power consumption;

[0046] For the updated predicted maximum power consumption and predicted minimum power consumption, a subsequent step of determining whether power consumption is abnormal based on the predicted maximum power consumption, the predicted minimum power consumption and the actual power consumption is performed.

[0047] Furthermore, the processing module is further used to train the prediction model in the following manner:

[0048] Performing J-layer wavelet decomposition on each element in the set to obtain a set of load trend curves;

[0049] The prediction model is trained based on the set of load trend curves, the historical temperature data set of the to-be-determined month of each historical year, and the historical holiday data set.

[0050] Furthermore, the processing module is further configured to issue the actual power consumption if it is determined that the power consumption is normal;

[0051] If it is determined that the power consumption is abnormal, the actual power consumption and the identifier of the user to be predicted are sent to a preset device. If a confirmation instruction returned by the preset device is received, the actual power consumption is issued.

[0052] An embodiment of the present application also provides an electronic device, which includes at least a processor and a memory, and the processor is used to implement the steps of the method for determining power abnormality as described in any one of the above items when executing a computer program stored in the memory.

[0053] An embodiment of the present application further provides a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the steps of the method for determining an abnormal power quantity as described in any one of the above items are implemented.

[0054] Because in the embodiment of the present application, after receiving the determination request, the electronic device obtains the identifiers of the to-be-determined month and the to-be-predicted user carried in the determination request, obtains the actual power consumption of the to-be-predicted user in the to-be-determined month, and obtains the temperature data set and holiday data set of the to-be-determined month in history each year, and determines the predicted maximum power consumption and the predicted minimum power consumption of the to-be-determined month based on the pre-trained prediction model and the temperature data set and the holiday data set, and determines whether the power consumption of the to-be-predicted user is abnormal based on the predicted maximum power consumption and the predicted minimum power consumption as well as the actual power consumption, thereby accurately and effectively determining whether the power consumption is abnormal. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The drawings constituting part of the present application are used to provide a further understanding of the present application. The exemplary embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0056] Figure 1 A schematic diagram of a process for determining an abnormal amount of power provided in an embodiment of the present application;

[0057] Figure 2 A schematic diagram of a process for determining non-metered basic electricity consumption provided in an embodiment of the present application;

[0058] Figure 3 A schematic diagram of a process for determining a predicted maximum power consumption and a predicted minimum power consumption provided in an embodiment of the present application;

[0059] Figure 4 A schematic diagram of a detailed process for determining abnormal power consumption provided in an embodiment of the present application;

[0060] Figure 5A schematic diagram of a product structure for determining power anomaly provided in an embodiment of the present application;

[0061] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0062] The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0063] The following detailed descriptions are all exemplary descriptions, and are intended to provide further detailed descriptions of the present application. Unless otherwise specified, all technical terms used in the present application have the same meanings as those generally understood by those skilled in the art to which the present application belongs. The terms used in the present application are only for describing specific embodiments, and are not intended to limit the exemplary embodiments according to the present application.

[0064] In order to accurately determine whether the power quantity is abnormal, the embodiments of the present application provide a method, device, equipment and medium for determining power quantity abnormality.

[0065] In an embodiment of the present application, an electronic device receives a determination request, obtains the identifiers of the month to be determined and the user to be predicted carried in the determination request; obtains the actual power consumption of the user to be predicted in the month to be determined; and obtains the temperature data set and holiday data set corresponding to the month to be determined in each year of history; determines the predicted maximum power consumption and the predicted minimum power consumption of the month to be determined based on a pre-trained prediction model and the temperature data set and the holiday data set; determines whether the power consumption is abnormal based on the predicted maximum power consumption, the predicted minimum power consumption and the actual power consumption.

[0066] Embodiment 1:

[0067] Figure 1 A schematic diagram of a process for determining an abnormal amount of power provided in an embodiment of the present application, the process comprising the following steps:

[0068] S101: receiving a determination request, and obtaining the identifiers of the month to be determined and the user to be predicted carried in the determination request.

[0069] The method for determining power anomaly provided in the embodiment of the present application is applied to an electronic device, which may be an intelligent device such as a PC or a server.

[0070] In order to accurately determine whether the power consumption is abnormal, after receiving the determination request, the electronic device can first parse and verify the validity of the request to ensure that the data is complete and in the correct format. Next, two key information is extracted from the determination request: the month to be determined (usually refers to a specific month that needs to be analyzed or predicted, such as "April 2023") and the identifier of the user to be predicted (this is a unique identification code used to accurately locate a specific user in the system, such as user ID "U1234567").

[0071] After obtaining this information, the electronic device can perform a series of subsequent processing steps:

[0072] User information verification: First, the electronic device will use the identification of the user to be predicted to query the user database, verify whether the user exists, and obtain his or her basic information and historical data (such as historical consumption records, behavior patterns, etc.) for subsequent analysis.

[0073] S102: Acquire the actual power consumption of the user to be predicted in the month to be determined; and acquire the temperature data set and holiday data set corresponding to the month to be determined.

[0074] After receiving the confirmation request, the electronic device can obtain the actual power consumption of the user to be predicted in the month to be determined according to the month to be determined. Specifically, the electronic device uses the identifier of the user to be predicted and the month to be determined as query conditions to initiate a request to the power database or related service interface to obtain the actual power consumption of the user in the month to be determined. This data is crucial for evaluating the user's power consumption habits, changing trends, and making future predictions.

[0075] In order to analyze the impact of external environmental factors on the user's electricity consumption, the electronic device will retrieve and collect the temperature data set corresponding to the month to be determined. This data set will be used to analyze the correlation between temperature changes and user electricity consumption, and then consider this important factor in the forecast.

[0076] Holidays are important time points when people's daily life rhythm changes, which often have a significant impact on electricity consumption. Therefore, the electronic device will collect the holiday data set corresponding to the month to be determined, where the set corresponding to whether each day in the month to be determined is a holiday can be determined as the holiday data set.

[0077] S103: Determine the predicted maximum power consumption and the predicted minimum power consumption of the to-be-determined month based on the pre-trained prediction model, the temperature data set, and the holiday data set.

[0078] In order to accurately determine whether the power consumption is abnormal, the electronic device locally stores a pre-trained prediction model. The electronic device can determine the predicted maximum power consumption and the predicted minimum power consumption for the month to be determined based on the pre-trained prediction model and the temperature data set and the holiday data set.

[0079] In a possible implementation, the electronic device may input the temperature data set and the holiday data set into the prediction model to obtain the predicted maximum power consumption and the predicted minimum power consumption of the to-be-determined month output by the prediction model.

[0080] S104: Determine whether the power consumption is abnormal based on the predicted maximum power consumption, the predicted minimum power consumption and the actual power consumption.

[0081] After obtaining the predicted maximum power consumption and the predicted minimum power consumption, the electronic device can determine whether the actual power consumption of the user to be predicted is between the predicted maximum power consumption and the predicted minimum power consumption, that is, determine whether the actual power consumption of the user to be predicted is greater than the predicted minimum power consumption and less than the predicted maximum power consumption. If so, it is determined that the power consumption is normal; if not, it is determined that the power consumption is abnormal.

[0082] Because in the embodiment of the present application, after receiving the determination request, the electronic device obtains the identifiers of the to-be-determined month and the to-be-predicted user carried in the determination request, obtains the actual power consumption of the to-be-predicted user in the to-be-determined month, and obtains the temperature data set and holiday data set of the to-be-determined month in history each year, and determines the predicted maximum power consumption and the predicted minimum power consumption of the to-be-determined month based on the pre-trained prediction model and the temperature data set and the holiday data set, and determines whether the power consumption of the to-be-predicted user is abnormal based on the predicted maximum power consumption and the predicted minimum power consumption as well as the actual power consumption, thereby accurately and effectively determining whether the power consumption is abnormal.

[0083] Embodiment 2:

[0084] In order to accurately determine the predicted maximum power consumption and the predicted minimum power consumption, based on the above embodiments, in the embodiment of the present application, the predicted maximum power consumption and the predicted minimum power consumption of the to-be-determined month are determined based on the pre-trained prediction model, the temperature data set, and the holiday data set, including:

[0085] Inputting the temperature data set and the holiday data set into a pre-trained prediction model to obtain a load trend prediction curve output by the prediction model;

[0086] and obtaining a set of each historical load curve corresponding to the to-be-determined month of each year; and obtaining a load fluctuation curve corresponding to the set;

[0087] Obtaining a load prediction upper limit curve and a load prediction lower limit curve according to the fusion of the load trend prediction curve and the load fluctuation curve;

[0088] The predicted maximum power consumption and the predicted minimum power consumption of the to-be-determined month are determined according to the load prediction upper limit curve and the load prediction lower limit curve.

[0089] In the embodiment of the present application, the electronic device inputs the temperature data set and the holiday data set into the trained model to obtain the load trend prediction curve output by the prediction model. This curve reflects the overall change trend of the power load under given conditions.

[0090] The electronic device reviews historical data and collects historical load curves for the month to be determined and the same month in previous years. These curves show the load fluctuations of the month in different years. The statistics of these historical load curves (such as mean, standard deviation, maximum value, minimum value, etc.) are calculated to construct a load fluctuation curve. This curve reflects the natural fluctuation range of the load in that month.

[0091] Among them, for the X month that needs to be analyzed for power anomaly, the load curve of the user in the Xth month of all historical electricity consumption years is counted to form a set of historical load curves for X month in X represents the month X∈(1,2,...,6,...,11,12), Representative year Monthly load curve for month X of year 1, Represents the Npth power data of the load curve in month X of year n.

[0092] The load trend forecast curve is merged with the load fluctuation curve. This usually involves considering the trend forecast curve as the center line, and then determining the upper and lower limits based on the statistical characteristics of the fluctuation curve (such as the standard deviation multiple). Specifically, the standard deviation of the trend forecast curve plus or minus a certain multiple (or other statistics adjusted according to actual demand) can be taken as the upper and lower limit curves of the load forecast.

[0093] According to the load forecast upper limit curve and the load forecast lower limit curve, the predicted maximum power consumption and the predicted minimum power consumption of the month to be determined can be intuitively determined.

[0094] Specifically, the electronic device can determine the predicted maximum power consumption and the predicted minimum power consumption by the following formula:

[0095]

[0096] in, To predict the maximum power consumption, To predict the minimum power consumption, is the load forecast upper limit curve, is the load forecast lower limit curve, and Np is the maximum time between the load forecast upper limit curve and the load forecast lower limit curve.

[0097] These forecasts are of great significance for power dispatching, energy planning and demand-side management. They can help grid operators prepare in advance to ensure the stability and reliability of power supply; at the same time, they also provide energy consumers with a reference for their electricity consumption behavior.

[0098] It should be noted that in the related technologies for judging abnormal power consumption, machine learning algorithms are usually used to analyze the user's historical monthly power consumption and historical monthly power consumption fluctuation rate. However, production-oriented industrial and commercial users have the problem of large randomness in production plans and many influencing factors, so the above methods have the disadvantages of unstable results and large errors. In order to further reduce the number of electricity bill errors caused by abnormal power consumption, it is necessary to use machine learning algorithms to analyze the user's multi-dimensional and refined historical power consumption data and user profile data, and adaptively judge the user's reasonable monthly power consumption range based on conditions such as temperature and holidays, and then accurately identify users with abnormal power consumption during the electricity bill settlement process, and intercept the issuance of electricity bills for users with abnormal power consumption and electricity bills.

[0099] Embodiment 3:

[0100] In order to accurately determine the load fluctuation curve, based on the above embodiments, in the embodiment of the present application, the step of obtaining the load fluctuation curve corresponding to the set includes:

[0101] Performing a dispersion analysis on the monthly load curve elements in the set, two by two, to obtain a set of load curves with the largest dispersion;

[0102] Extract the fluctuation characteristic curve between a group of load curves with the largest discreteness.

[0103] In an embodiment of the present application, the electronic device can perform discreteness analysis on the monthly load curve elements in a set of each historical load curve corresponding to the month to be determined each year, and obtain a set of load curves with the largest discreteness.

[0104] In a possible implementation, the electronic device may use the following formula to determine a set of load curves with the largest dispersion:

[0105]

[0106] in in It represents the load curve of month X in year n. Indicates the load value of the i-th day in month X of year 1. and Represents the pair with the largest dispersion in the monthly load curves of historical month X.

[0107] After obtaining a group of load curves with the largest discreteness, the electronic device can extract a fluctuation characteristic curve between the group of load curves with the largest discreteness.

[0108] In a possible implementation, the electronic device may use the following formula to determine the point set of the fluctuation characteristic curve:

[0109]

[0110] in, It represents the load value of the Npth day of month X in yearmax1. Indicates the load value of the Npth day in month X of year yearmax2.

[0111] It should be noted that a fluctuation characteristic curve can be generated based on the point set.

[0112] Embodiment 4:

[0113] In order to accurately determine the load forecast upper limit curve and the load forecast lower limit curve, on the basis of the above embodiments, in the embodiment of the present application, the load forecast upper limit curve and the load forecast lower limit curve are obtained by fusing the load trend forecast curve and the load fluctuation curve, including:

[0114] Determine a load prediction upper limit curve according to the sum of the load trend prediction curve and the load fluctuation curve;

[0115] And according to the difference between each point on the load trend prediction curve and the load fluctuation curve, a load prediction lower limit curve is determined.

[0116] In an embodiment of the present application, the electronic device can determine the load prediction upper limit curve based on the sum of the points on the load trend prediction curve and the load fluctuation curve.

[0117] In a possible implementation, the electronic device may use the following formula to determine the point set corresponding to the load prediction upper limit curve:

[0118]

[0119] in, is the Npth load value in the load trend prediction curve, It represents the load value of the Npth day of month X in yearmax1. Indicates the load value of the Npth day in month X of year yearmax2.

[0120] It should be noted that a prediction upper limit curve can be generated based on the point set.

[0121] The electronic device can also determine the load prediction lower limit curve based on the difference between each point on the load trend prediction curve and the load fluctuation curve.

[0122] In a possible implementation, the electronic device may use the following formula to determine the point set corresponding to the load forecast lower limit curve:

[0123]

[0124] in, is the Npth load value in the load trend prediction curve, It represents the load value of the Npth day of month X in yearmax1. Indicates the load value of the Npth day in month X of year yearmax2.

[0125] It should be noted that a prediction lower limit curve can be generated based on the point set.

[0126] Embodiment 5:

[0127] After determining the predicted maximum power consumption and the predicted minimum power consumption of the to-be-determined month, and before determining whether power consumption is abnormal based on the predicted maximum power consumption, the predicted minimum power consumption and the actual power consumption, the method further includes:

[0128] Obtaining the non-metered basic electricity consumption of the user to be predicted;

[0129] Based on the sum of the predicted maximum power consumption and the non-metered basic power consumption, updating the predicted maximum power consumption;

[0130] and updating the predicted minimum power consumption based on the sum of the predicted minimum power consumption and the non-metered basic power consumption;

[0131] For the updated predicted maximum power consumption and predicted minimum power consumption, a subsequent step of determining whether power consumption is abnormal based on the predicted maximum power consumption, the predicted minimum power consumption and the actual power consumption is performed.

[0132] In actual scenarios, the user's electricity consumption also includes non-metered basic electricity consumption, which refers to the electricity consumption caused by line loss, etc. Therefore, after obtaining the predicted maximum electricity consumption and the predicted minimum electricity consumption, the predicted maximum electricity consumption and the predicted minimum electricity consumption can also be adjusted based on the non-metered basic electricity consumption of the user to be predicted.

[0133] Specifically, the electronic device may obtain the non-metered basic electricity consumption of the user to be predicted.

[0134] In a possible implementation, the electronic device can calculate the non-metered basic power consumption of the user to be predicted based on the predicted user profile, and extract the active no-load loss coefficient of the transformer using the high supply and low metering method in the system profile of the user to be predicted. Transformer operation days in this month Extract the active no-load loss coefficient of the dedicated transmission line in the user profile to be predicted Number of days the line is in operation this month

[0135] Fixed power loss of non-metering transformer:

[0136] Unmetered Line Loss:

[0137] Non-metered basic electricity consumption: W base =W trans +W line

[0138] Furthermore, the electronic device may update the predicted maximum power consumption based on the sum of the predicted maximum power consumption and the non-metered basic power consumption; and update the predicted minimum power consumption based on the sum of the predicted minimum power consumption and the non-metered basic power consumption.

[0139] Specifically, the electronic device may use the following formula to determine the updated predicted maximum power consumption and predicted minimum power consumption:

[0140]

[0141] in, is the updated predicted maximum power consumption, is the updated predicted minimum power consumption, W base + is the non-metered basic electricity consumption, is the predicted maximum power consumption before updating, It is the predicted minimum power consumption before updating.

[0142] Figure 2 A schematic diagram of a process for determining non-metered basic electricity consumption provided in an embodiment of the present application.

[0143] Depend on Figure 2 It can be seen that the non-metered transformer fixed loss electricity = transformer active no-load loss * transformer operating days in the month * 24, non-metered line loss = line active no-load loss * operating days in the month * 24. The non-metered transformer fixed loss electricity and non-metered line loss are added together to obtain the non-metered basic electricity consumption calculated based on user files.

[0144] Embodiment 6:

[0145] In order to accurately determine whether the power is abnormal, based on the above embodiments, in the embodiment of the present application, the prediction model is trained in the following manner:

[0146] Performing J-layer wavelet decomposition on each element in the set to obtain a set of load trend curves;

[0147] The prediction model is trained based on the set of load trend curves, the historical temperature data set of the to-be-determined month of each historical year, and the historical holiday data set.

[0148] In the embodiment of the present application, the electronic device can use the Haar wavelet function right Perform J-layer wavelet decomposition on each element in to obtain a set of load trend curves in Represents the monthly load curve for month X in year yearn The low-frequency scale signal after J-layer wavelet decomposition.

[0149] The electronic device also obtains a historical temperature data set for each X month and a historical holiday data set for each X month, wherein the historical temperature data set for each X month can be expressed as: in represents the temperature data subset for month X in year n. in, Represents the temperature data of the Ntth day of month X in year n. The historical holiday data set of each year in month X can be expressed as: in Represents the holiday data subset for month X of year n. in, Indicates whether the Nh-th day of month X in year n is a holiday.

[0150] Electronic equipment will be a collection of load trend curves corresponding to the timing Historical temperature dataset for each month to be determined Historical holiday dataset for each month to be determined Input into the support vector machine algorithm, optimize the load trend prediction model parameters under the Xth month, and generate a load trend prediction model.

[0151] Figure 3 A schematic diagram of a process for determining predicted maximum power consumption and predicted minimum power consumption provided in an embodiment of the present application.

[0152] Depend on Figure 3It can be seen that we can first obtain a set of historical load curves of the user to be predicted in month X, perform a discreteness analysis on the set, obtain a set of load curves with the largest discreteness in the set, and obtain the load fluctuation curve of the predicted month by data reconstruction.

[0153] The electronic device also performs wavelet multi-scale decomposition on the set of historical load curves in month X to obtain a set of load trend curves in month X, trains a support vector machine algorithm based on the set of load trend curves, a historical temperature data set corresponding to the load trend curves in the same period, and a historical holiday data set corresponding to the load trend curves in the same period to obtain a trained prediction model, inputs the temperature data set and the holiday data set of the month to be determined into the prediction model, and obtains the load trend curve output by the prediction model.

[0154] The load trend curve and the load fluctuation curve are merged to obtain the load forecast upper limit curve and the load forecast lower limit curve of the month to be forecasted, that is, the extreme value curve. According to the load forecast upper limit curve and the load forecast lower limit curve, the predicted maximum power consumption and the predicted minimum power consumption of the month to be determined are determined.

[0155] Embodiment 7:

[0156] In order to improve the user experience, based on the above embodiments, in the embodiment of the present application, the method further includes:

[0157] If it is determined that the electricity consumption is normal, the actual electricity consumption is issued;

[0158] If it is determined that the power consumption is abnormal, the actual power consumption and the identifier of the user to be predicted are sent to a preset device. If a confirmation instruction returned by the preset device is received, the actual power consumption is issued.

[0159] In the embodiment of the present application, the monthly power distribution of the user to be predicted is compared with the upper and lower limits of the reasonable power consumption of the month. If the monthly electricity consumption is not within the reasonable electricity consumption range, The system will be intercepted and the staff will verify the power quantity on site. If it is verified to be correct, it can be issued normally. If it is verified that there is an abnormality in the power quantity, it will be issued according to the correct power quantity.

[0160] Figure 4 A detailed process diagram for determining abnormal power consumption is provided in an embodiment of the present application.

[0161] Depend on Figure 4It can be seen that the monthly reasonable electricity consumption interval can be calculated first. First, based on the user's current non-metered basic electricity consumption calculation method, the non-metered basic electricity consumption is calculated, and the predicted maximum electricity consumption and the predicted maximum electricity consumption are determined based on the data reconstruction and support vector machine monthly electricity consumption interval prediction method. Through the electricity superposition, the predicted maximum electricity consumption and the predicted maximum electricity consumption are updated to obtain the user's monthly reasonable electricity consumption interval. And the system calculates the monthly electricity consumption that the user should issue, that is, the actual electricity consumption, and judges whether the issued electricity consumption is within the reasonable electricity consumption interval. If so, the user's issued electricity is normal, and the user's electricity is issued. If not, the user's issued electricity is abnormal and transferred to manual on-site verification. If there is no objection to the manual verification, the user's electricity is issued. If there is an objection to the manual verification, the actual electricity consumption is verified on-site for issuance.

[0162] The method for judging user power anomalies based on power range prediction provided in the embodiment of the present application adopts a method combining theoretical power consumption with an artificial intelligence prediction algorithm to predict the user's reasonable power consumption range for the current month. This method is more accurate and stable than the conventional method of judging anomalies by analyzing the user's historical power consumption and power fluctuation rate in historical months. At the same time, the use of artificial intelligence algorithms has solved the problem of large randomness in power consumption among production-type industrial and commercial users to a certain extent.

[0163] The embodiment of the present application provides a method for analyzing and judging user power anomalies based on power interval prediction. The improvement lies in the fine division of user power consumption into two parts. The first part is the physical minimum power consumption calculated based on the user's power file, and the second part is to extract the fluctuation characteristics, analyze and reorganize the user's historical power consumption data, and use a machine learning algorithm to correlate the fluctuation characteristics with the influencing factors to generate a power interval prediction model, and then calculate the user's power consumption interval. By comparing the prediction of the user's reasonable power consumption interval with the user's actual power consumption, it is determined whether there is a user power anomaly. It can effectively solve the problem of inaccurate abnormal analysis caused by methods such as user power consumption fluctuation rate and user power consumption theoretical extreme value.

[0164] Embodiment 8:

[0165] Figure 5 A schematic diagram of a product structure for determining power anomaly provided in an embodiment of the present application, the device includes:

[0166] The receiving module 501 is used to receive a determination request and obtain the identifier of the month to be determined and the user to be predicted carried in the determination request;

[0167] The acquisition module 502 is used to acquire the actual power consumption of the user to be predicted in the month to be determined; and acquire the temperature data set and holiday data set corresponding to the month to be determined;

[0168] Processing module 503 is used to determine the predicted maximum power consumption and the predicted minimum power consumption of the to-be-determined month based on the pre-trained prediction model and the temperature data set and the holiday data set; and determine whether the power consumption is abnormal based on the predicted maximum power consumption, the predicted minimum power consumption and the actual power consumption.

[0169] Furthermore, the processing module 503 is specifically used to input the temperature data set and the holiday data set into a pre-trained prediction model to obtain a load trend prediction curve output by the prediction model;

[0170] and obtaining a set of each historical load curve corresponding to the to-be-determined month of each year; and obtaining a load fluctuation curve corresponding to the set;

[0171] Obtaining a load prediction upper limit curve and a load prediction lower limit curve according to the fusion of the load trend prediction curve and the load fluctuation curve;

[0172] The predicted maximum power consumption and the predicted minimum power consumption of the to-be-determined month are determined according to the load prediction upper limit curve and the load prediction lower limit curve.

[0173] Furthermore, the processing module 503 is specifically used to perform a discreteness analysis on the monthly load curve elements in the set, and obtain a set of load curves with the largest discreteness;

[0174] Extract the fluctuation characteristic curve between a group of load curves with the largest discreteness.

[0175] Furthermore, the processing module 503 is specifically used to determine the load prediction upper limit curve according to the sum of the load trend prediction curve and each point on the load fluctuation curve;

[0176] And according to the difference between each point on the load trend prediction curve and the load fluctuation curve, a load prediction lower limit curve is determined.

[0177] Furthermore, the processing module 503 is further used to obtain the non-metered basic electricity consumption of the user to be predicted;

[0178] Based on the sum of the predicted maximum power consumption and the non-metered basic power consumption, updating the predicted maximum power consumption;

[0179] and updating the predicted minimum power consumption based on the sum of the predicted minimum power consumption and the non-metered basic power consumption;

[0180] For the updated predicted maximum power consumption and predicted minimum power consumption, a subsequent step of determining whether power consumption is abnormal based on the predicted maximum power consumption, the predicted minimum power consumption and the actual power consumption is performed.

[0181] Furthermore, the processing module 503 is further configured to train the prediction model in the following manner:

[0182] Performing J-layer wavelet decomposition on each element in the set to obtain a set of load trend curves;

[0183] The prediction model is trained based on the set of load trend curves, the historical temperature data set of the to-be-determined month of each historical year, and the historical holiday data set.

[0184] Furthermore, the processing module 503 is further configured to issue the actual power consumption if it is determined that the power consumption is normal;

[0185] If it is determined that the power consumption is abnormal, the actual power consumption and the identifier of the user to be predicted are sent to a preset device. If a confirmation instruction returned by the preset device is received, the actual power consumption is issued.

[0186] Embodiment 8:

[0187] Figure 6 The present invention provides a schematic diagram of an electronic device structure according to an embodiment of the present invention. Based on the above embodiments, the present invention further provides an electronic device, such as Figure 6 As shown, it includes: a processor 601, a communication interface 602, a memory 603 and a communication bus 604, wherein the processor 601, the communication interface 602, and the memory 603 communicate with each other through the communication bus 604;

[0188] The memory 603 stores a computer program. When the program is executed by the processor 601, the processor 601 performs the following steps:

[0189] receiving a determination request, and obtaining the identifier of the month to be determined and the user to be predicted carried in the determination request;

[0190] Obtain the actual power consumption of the user to be predicted in the month to be determined; and obtain the temperature data set and holiday data set corresponding to the month to be determined;

[0191] Determine the predicted maximum power consumption and the predicted minimum power consumption of the to-be-determined month based on the pre-trained prediction model, the temperature data set, and the holiday data set;

[0192] Based on the predicted maximum power consumption, the predicted minimum power consumption and the actual power consumption, it is determined whether the power consumption is abnormal.

[0193] Further, the determining the predicted maximum power consumption and the predicted minimum power consumption of the to-be-determined month based on the pre-trained prediction model, the temperature data set, and the holiday data set includes:

[0194] Inputting the temperature data set and the holiday data set into a pre-trained prediction model to obtain a load trend prediction curve output by the prediction model;

[0195] and obtaining a set of each historical load curve corresponding to the to-be-determined month of each year; and obtaining a load fluctuation curve corresponding to the set;

[0196] Obtaining a load prediction upper limit curve and a load prediction lower limit curve according to the fusion of the load trend prediction curve and the load fluctuation curve;

[0197] The predicted maximum power consumption and the predicted minimum power consumption of the to-be-determined month are determined according to the load prediction upper limit curve and the load prediction lower limit curve.

[0198] Further, the obtaining of the load fluctuation curve corresponding to the set includes:

[0199] Performing a dispersion analysis on the monthly load curve elements in the set, two by two, to obtain a set of load curves with the largest dispersion;

[0200] Extract the fluctuation characteristic curve between a group of load curves with the largest discreteness.

[0201] Further, the step of obtaining a load prediction upper limit curve and a load prediction lower limit curve by fusing the load trend prediction curve and the load fluctuation curve includes:

[0202] Determine a load prediction upper limit curve according to the sum of the load trend prediction curve and the load fluctuation curve;

[0203] And according to the difference between each point on the load trend prediction curve and the load fluctuation curve, a load prediction lower limit curve is determined.

[0204] Further, after determining the predicted maximum power consumption and the predicted minimum power consumption of the to-be-determined month, and before determining whether the power consumption is abnormal based on the predicted maximum power consumption, the predicted minimum power consumption and the actual power consumption, the method further includes:

[0205] Obtaining the non-metered basic electricity consumption of the user to be predicted;

[0206] Based on the sum of the predicted maximum power consumption and the non-metered basic power consumption, updating the predicted maximum power consumption;

[0207] and updating the predicted minimum power consumption based on the sum of the predicted minimum power consumption and the non-metered basic power consumption;

[0208] For the updated predicted maximum power consumption and predicted minimum power consumption, a subsequent step of determining whether power consumption is abnormal based on the predicted maximum power consumption, the predicted minimum power consumption and the actual power consumption is performed.

[0209] Furthermore, the prediction model is trained in the following manner:

[0210] Performing J-layer wavelet decomposition on each element in the set to obtain a set of load trend curves;

[0211] The prediction model is trained based on the set of load trend curves, the historical temperature data set of the to-be-determined month of each historical year, and the historical holiday data set.

[0212] Furthermore, the method further comprises:

[0213] If it is determined that the electricity consumption is normal, the actual electricity consumption is issued;

[0214] If it is determined that the power consumption is abnormal, the actual power consumption and the identifier of the user to be predicted are sent to a preset device. If a confirmation instruction returned by the preset device is received, the actual power consumption is issued.

[0215] The communication bus mentioned in the above server can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0216] The communication interface is used for communication between the above electronic device and other devices.

[0217] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0218] The above-mentioned processor can be a general-purpose processor, including a central processing unit, a network processor (Network Processor, NP), etc.; it can also be a digital signal processing processor (Digital Signal Processing, DSP), an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, etc.

[0219] Embodiment 9:

[0220] On the basis of the above embodiments, an embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program executable by an electronic device, and when the program is run on the electronic device, the electronic device implements the following steps when executing:

[0221] receiving a determination request, and obtaining the identifier of the month to be determined and the user to be predicted carried in the determination request;

[0222] Obtain the actual power consumption of the user to be predicted in the month to be determined; and obtain the temperature data set and holiday data set corresponding to the month to be determined;

[0223] Determine the predicted maximum power consumption and the predicted minimum power consumption of the to-be-determined month based on the pre-trained prediction model, the temperature data set, and the holiday data set;

[0224] Based on the predicted maximum power consumption, the predicted minimum power consumption and the actual power consumption, it is determined whether the power consumption is abnormal.

[0225] Further, the determining the predicted maximum power consumption and the predicted minimum power consumption of the to-be-determined month based on the pre-trained prediction model, the temperature data set, and the holiday data set includes:

[0226] Inputting the temperature data set and the holiday data set into a pre-trained prediction model to obtain a load trend prediction curve output by the prediction model;

[0227] and obtaining a set of each historical load curve corresponding to the to-be-determined month of each year; and obtaining a load fluctuation curve corresponding to the set;

[0228] Obtaining a load prediction upper limit curve and a load prediction lower limit curve according to the fusion of the load trend prediction curve and the load fluctuation curve;

[0229] The predicted maximum power consumption and the predicted minimum power consumption of the to-be-determined month are determined according to the load prediction upper limit curve and the load prediction lower limit curve.

[0230] Further, the obtaining of the load fluctuation curve corresponding to the set includes:

[0231] Performing a dispersion analysis on the monthly load curve elements in the set, two by two, to obtain a set of load curves with the largest dispersion;

[0232] Extract the fluctuation characteristic curve between a group of load curves with the largest discreteness.

[0233] Further, the step of obtaining a load prediction upper limit curve and a load prediction lower limit curve by fusing the load trend prediction curve and the load fluctuation curve includes:

[0234] Determine a load prediction upper limit curve according to the sum of the load trend prediction curve and the load fluctuation curve;

[0235] And according to the difference between each point on the load trend prediction curve and the load fluctuation curve, a load prediction lower limit curve is determined.

[0236] Further, after determining the predicted maximum power consumption and the predicted minimum power consumption of the to-be-determined month, and before determining whether the power consumption is abnormal based on the predicted maximum power consumption, the predicted minimum power consumption and the actual power consumption, the method further includes:

[0237] Obtaining the non-metered basic electricity consumption of the user to be predicted;

[0238] Based on the sum of the predicted maximum power consumption and the non-metered basic power consumption, updating the predicted maximum power consumption;

[0239] and updating the predicted minimum power consumption based on the sum of the predicted minimum power consumption and the non-metered basic power consumption;

[0240] For the updated predicted maximum power consumption and predicted minimum power consumption, a subsequent step of determining whether power consumption is abnormal based on the predicted maximum power consumption, the predicted minimum power consumption and the actual power consumption is performed.

[0241] Furthermore, the prediction model is trained in the following manner:

[0242] Performing J-layer wavelet decomposition on each element in the set to obtain a set of load trend curves;

[0243] The prediction model is trained based on the set of load trend curves, the historical temperature data set of the to-be-determined month of each historical year, and the historical holiday data set.

[0244] Furthermore, the method further comprises:

[0245] If it is determined that the electricity consumption is normal, the actual electricity consumption is issued;

[0246] If it is determined that the power consumption is abnormal, the actual power consumption and the identifier of the user to be predicted are sent to a preset device. If a confirmation instruction returned by the preset device is received, the actual power consumption is issued.

[0247] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0248] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0249] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0250] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0251] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present application rather than to limit it. Although the present application has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present application can still be modified or replaced by equivalents, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present application should be included in the scope of protection of the claims of the present application.

Claims

1. A method for determining abnormal power consumption, characterized in that: The method comprises: receiving a determination request, and obtaining the identifier of the month to be determined and the user to be predicted carried in the determination request; Obtain the actual power consumption of the user to be predicted in the month to be determined; and obtain the temperature data set and holiday data set corresponding to the month to be determined; Determine the predicted maximum power consumption and the predicted minimum power consumption of the to-be-determined month based on the pre-trained prediction model, the temperature data set, and the holiday data set; Based on the predicted maximum power consumption, the predicted minimum power consumption and the actual power consumption, it is determined whether the power consumption is abnormal.

2. The method according to claim 1, characterized in that: The determining of the predicted maximum power consumption and the predicted minimum power consumption of the to-be-determined month based on the pre-trained prediction model, the temperature data set, and the holiday data set includes: Inputting the temperature data set and the holiday data set into a pre-trained prediction model to obtain a load trend prediction curve output by the prediction model; and obtaining a set of each historical load curve corresponding to the to-be-determined month of each year; and obtaining a load fluctuation curve corresponding to the set; Obtaining a load prediction upper limit curve and a load prediction lower limit curve according to the fusion of the load trend prediction curve and the load fluctuation curve; The predicted maximum power consumption and the predicted minimum power consumption of the to-be-determined month are determined according to the load prediction upper limit curve and the load prediction lower limit curve.

3. The method according to claim 2, characterized in that The obtaining of the load fluctuation curve corresponding to the set includes: Performing a dispersion analysis on the monthly load curve elements in the set, two by two, to obtain a set of load curves with the largest dispersion; Extract the fluctuation characteristic curve between a group of load curves with the largest discreteness.

4. The method according to claim 2, characterized in that: The step of obtaining a load prediction upper limit curve and a load prediction lower limit curve according to the fusion of the load trend prediction curve and the load fluctuation curve includes: Determine a load prediction upper limit curve according to the sum of the load trend prediction curve and the load fluctuation curve; And according to the difference between each point on the load trend prediction curve and the load fluctuation curve, a load prediction lower limit curve is determined.

5. The method according to claim 1 or 2, characterized in that: After determining the predicted maximum power consumption and the predicted minimum power consumption of the to-be-determined month, and before determining whether power consumption is abnormal based on the predicted maximum power consumption, the predicted minimum power consumption and the actual power consumption, the method further includes: Obtaining the non-metered basic electricity consumption of the user to be predicted; Based on the sum of the predicted maximum power consumption and the non-metered basic power consumption, updating the predicted maximum power consumption; and updating the predicted minimum power consumption based on the sum of the predicted minimum power consumption and the non-metered basic power consumption; For the updated predicted maximum power consumption and predicted minimum power consumption, a subsequent step of determining whether power consumption is abnormal based on the predicted maximum power consumption, the predicted minimum power consumption and the actual power consumption is performed.

6. The method according to claim 2, characterized in that The prediction model is trained in the following way: Performing J-layer wavelet decomposition on each element in the set to obtain a set of load trend curves; The prediction model is trained based on the set of load trend curves, the historical temperature data set of the to-be-determined month of each historical year, and the historical holiday data set.

7. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: If it is determined that the electricity consumption is normal, the actual electricity consumption is issued; If it is determined that the power consumption is abnormal, the actual power consumption and the identifier of the user to be predicted are sent to a preset device. If a confirmation instruction returned by the preset device is received, the actual power consumption is issued.

8. A product for determining abnormal power consumption, characterized in that: The products include: A receiving module, used for receiving a determination request, and obtaining the identifier of the month to be determined and the user to be predicted carried in the determination request; An acquisition module is used to acquire the actual power consumption of the user to be predicted in the month to be determined; and acquire the temperature data set and holiday data set corresponding to the month to be determined; A processing module is used to determine the predicted maximum power consumption and the predicted minimum power consumption of the to-be-determined month based on the pre-trained prediction model and the temperature data set and the holiday data set; and to determine whether the power consumption is abnormal based on the predicted maximum power consumption, the predicted minimum power consumption and the actual power consumption.

9. An electronic device, characterized in that: The electronic device comprises at least a processor and a memory, and the processor is used to implement the steps of the method for determining an abnormal power quantity as described in any one of claims 1 to 7 when executing a computer program stored in the memory.

10. A computer-readable storage medium, characterized in that: It stores a computer program, which, when executed by a processor, implements the steps of the method for determining an abnormality in electrical quantity as described in any one of claims 1 to 7.

Citation Information

Patent Citations

  • Material supplier production capacity monitoring and abnormity early warning method based on electricity consumption analysis

    CN110135612A

  • Meter reading data exception analysis method based on deep learning algorithm

    CN111047094A

  • Device, method and program for prediction of power demand peak

    JP2015139283A