Power consumption anomaly detection method, power consumption anomaly detection device, and electronic device

Abstract

The application provides a power consumption anomaly detection method, a power consumption anomaly detection device and an electronic device. The method comprises the following steps: calculating a power consumption reference value of a target user according to a new energy influence coefficient, first historical data and second historical data; obtaining actual power consumption data of the target user at a current time, and calculating an absolute value of a difference between the power consumption reference value and the actual power consumption data of the target user at the current time to obtain a target difference value; and determining that the target user has a power consumption anomaly in the case that the target difference value is greater than a second threshold value. The method solves the problem of poor power consumption anomaly detection effect in the case of new energy access.

Description

Technical Field

[0001] This application relates to the field of new energy, and more specifically, to a method for detecting abnormal electricity consumption, a device for detecting abnormal electricity consumption, a computer-readable storage medium, and an electronic device. Background Technology

[0002] High-energy-consuming industrial parks are widely introducing new energy power generation systems such as photovoltaic and wind power. Under normal circumstances, enterprises will give priority to using clean and low-cost electricity from photovoltaic and wind power, and purchase electricity from the grid to meet the full load demand for the remaining amount.

[0003] Currently, the detection of abnormal electricity consumption by users is mostly based on the analysis of the user's historical electricity consumption sequences. Load reference values ​​are obtained through methods such as load forecasting, and then the actual load values ​​are compared to determine whether abnormal electricity consumption has occurred. However, because the impact of renewable energy access and fluctuations in renewable energy output on load anomaly detection is not taken into account, the detection effect is unsatisfactory when renewable energy is connected.

[0004] Therefore, there is an urgent need for a detection method that can solve the problem of poor detection results for abnormal electricity use. Summary of the Invention

[0005] The main objective of this application is to provide a method, device, computer-readable storage medium, and electronic device for detecting abnormal electricity consumption, so as to at least solve the problem of poor detection effect of abnormal electricity consumption in the case of new energy access in the prior art.

[0006] According to one aspect of this application, a method for detecting abnormal electricity consumption is provided, comprising: calculating a reference value for the electricity consumption of a target user based on a new energy influence coefficient, first historical data, and second historical data, wherein the new energy influence coefficient characterizes the power generation intensity of the new energy system, the first historical data are historical electricity consumption data of the target user at multiple first predetermined times prior to the current time, the second historical data are historical electricity consumption data of similar users at multiple first predetermined times prior to the current time, the reference value for the electricity consumption of the target user is the electricity consumption of the target user under normal electricity consumption conditions, and the similar users have the same electricity consumption characteristics as the target user; obtaining the actual electricity consumption data of the target user at the current time, and calculating the absolute value of the difference between the reference value for electricity consumption and the actual electricity consumption data of the target user at the current time to obtain a target difference; and determining that the target user's electricity consumption is abnormal if the target difference is greater than a second threshold.

[0007] Optionally, calculating the new energy impact coefficient includes: obtaining the intensity values ​​of power generation influencing factors at multiple predetermined test points of the target user's new energy power station at the current time, wherein the intensity values ​​of the power generation influencing factors include at least the light intensity and wind speed of the target user's new energy power station at the current time; calculating the average of the intensity values ​​of the power generation influencing factors at multiple predetermined test points to obtain the current intensity value; determining the power generation intensity of the new energy system based on the current intensity value and historical intensity values, wherein the historical intensity values ​​are the intensity values ​​of the power generation influencing factors at multiple predetermined test points of the target user's new energy power station at multiple second predetermined times prior to the current time; and determining the new energy impact coefficient based on the mapping relationship between the power generation intensity of the new energy system and the new energy impact coefficient.

[0008] Optionally, determining the power generation intensity of the new energy system based on the current intensity value and historical intensity values ​​includes: sorting the historical intensity values ​​to obtain a target sequence; and determining the power generation intensity of the new energy system based on the position of the current intensity value in the target sequence.

[0009] Optionally, calculating a reference value for the electricity consumption of the target user based on the new energy impact coefficient, first historical data, and second historical data includes: determining a first reference value based on the first historical data, wherein the first reference value is the predicted electricity consumption data of the target user at the current moment obtained based on the first historical data; calculating a second reference value based on the second historical data, wherein the second reference value is the predicted electricity consumption data of similar users at the current moment obtained based on the second historical data; calculating the average value of the second historical data to obtain a third reference value; and calculating the reference value for the electricity consumption of the target user based on the new energy impact coefficient, the first reference value, the second reference value, and the third reference value.

[0010] Optionally, calculating a first reference value based on the first historical data includes: inputting the first historical data into an electricity consumption prediction model to obtain the first reference value, wherein the electricity consumption prediction model is trained using historical electricity consumption data of the target user at multiple third predetermined times before the current time and at the time after the third predetermined time.

[0011] Optionally, the second reference value is calculated based on the second historical data, including: according to the formula Calculate the multiple coefficient of the similar users to the target users. ,in, The data represents the electricity consumption of the m-th similar user from time i-1 to time i. The electricity consumption data of the target user from time i-1 to time i. For the current time, The time window length is the multiplier coefficient; according to the formula For the predicted value The predicted value is obtained by processing. ,in, The predicted electricity consumption data of the m-th similar user at time k is obtained based on the electricity consumption prediction model; the average of the multiple processed predicted values ​​is calculated to obtain the second reference value.

[0012] Optionally, the electricity consumption reference value for the target user is calculated based on the new energy impact coefficient, the first reference value, the second reference value, and the third reference value, including: according to the formula Calculate the reference value of electricity consumption for the target user. ,in, The influence coefficient of the new energy source is... The first reference value, The second reference value, This is the third reference value.

[0013] According to another aspect of this application, an electricity consumption anomaly detection device is provided, comprising: a first calculation unit, configured to calculate a reference value for the electricity consumption of a target user based on a new energy influence coefficient, first historical data, and second historical data, wherein the new energy influence coefficient characterizes the power generation intensity of the new energy system, the first historical data are historical electricity consumption data of the target user at multiple first predetermined times prior to the current time, the second historical data are historical electricity consumption data of similar users at multiple first predetermined times prior to the current time, and the reference value for the electricity consumption of the target user is the electricity consumption of the target user under normal electricity consumption conditions, wherein the similar users have the same electricity consumption characteristics as the target user; a second calculation unit, configured to acquire the actual electricity consumption data of the target user at the current time, and calculate the absolute value of the difference between the reference value for electricity consumption and the actual electricity consumption data of the target user at the current time to obtain a target difference; and a determination unit, configured to determine that the target user's electricity consumption is abnormal if the target difference is greater than a second threshold.

[0014] According to another aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform any of the methods described.

[0015] According to another aspect of this application, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to execute any of the methods described by the computer program.

[0016] Applying the technical solution of this application, firstly, a reference value for the electricity consumption of the target user is calculated based on the new energy influence coefficient, first historical data, and second historical data; then, the actual electricity consumption data of the target user at the current moment is obtained, and the absolute value of the difference between the reference value and the actual electricity consumption data of the target user at the current moment is calculated to obtain the target difference; finally, if the target difference is greater than a second threshold, the electricity consumption of the target user is determined to be abnormal. By introducing a new energy influence coefficient that characterizes the power generation intensity of the new energy system, and calculating a normal electricity consumption reference value based on the new energy influence coefficient, first historical data, and second historical data, this value is used as a reference value for feedback-guided judgment of electricity consumption anomaly detection. This method considers the impact of new energy access and new energy output fluctuations on load anomaly detection, thus solving the technical problem of poor electricity consumption anomaly detection effect under the condition of new energy access. Attached Figure Description

[0017] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0018] Figure 1 A hardware structure block diagram of a mobile terminal for performing an abnormal power consumption detection method according to an embodiment of this application is shown;

[0019] Figure 2 A schematic flowchart of an electricity anomaly detection method according to an embodiment of this application is shown;

[0020] Figure 3 A schematic diagram is shown illustrating an embodiment of the present application for obtaining the intensity value of a power generation influencing factor.

[0021] Figure 4 A detailed flowchart of a power consumption anomaly detection method according to an embodiment of this application is shown.

[0022] Figure 5 A structural block diagram of an electrical anomaly detection device according to an embodiment of this application is shown.

[0023] The above figures include the following reference numerals:

[0024] 102. Processor; 104. Memory; 106. Transmission device; 108. Input / output device. Detailed Implementation

[0025] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0026] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] As described in the background section, the detection effect of power consumption anomalies is not good when new energy sources are connected in the prior art. In order to solve the above problems, the embodiments of this application provide a power consumption anomaly detection method, a power consumption anomaly detection device, a computer-readable storage medium, and an electronic device.

[0029] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0030] The methods and embodiments provided in this application can be executed on a mobile terminal, computer terminal, or similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a power consumption anomaly detection method according to an embodiment of the present invention. Figure 1 As shown, a mobile terminal may include one or more ( Figure 1Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0031] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the power consumption anomaly detection method in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the aforementioned networks may include wireless networks provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0032] This embodiment provides a method for detecting abnormal power consumption that runs on a mobile terminal, computer terminal, or similar computing device. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0033] Figure 2 This is a flowchart of an electricity anomaly detection method according to an embodiment of this application. Figure 2 As shown, the method includes the following steps:

[0034] Step S201: Calculate the reference value of electricity consumption for the target user based on the new energy impact coefficient, the first historical data, and the second historical data. The new energy impact coefficient represents the power generation intensity of the new energy system. The first historical data refers to the historical electricity consumption data of the target user at multiple first predetermined times before the current time. The second historical data refers to the historical electricity consumption data of similar users at multiple first predetermined times before the current time. The reference value of electricity consumption for the target user is the electricity consumption of the target user under normal electricity conditions. The similar users produce the same type of industrial products as the target user.

[0035] Specifically, existing methods for detecting abnormal electricity consumption by users largely rely on analyzing the user's historical electricity usage sequences. Load reference values ​​are derived through load forecasting, and then compared with actual load values ​​to determine if abnormal electricity consumption has occurred. By introducing a renewable energy impact coefficient, considering the influence of renewable energy access and output fluctuations on load anomaly detection, the detection effectiveness is improved when renewable energy access is available. Industrial parks typically house several different types of enterprises, such as electrolytic aluminum companies and polysilicon production companies. The aforementioned similar users can be those producing the same industrial products as the target user, sharing similar production processes and load characteristics. For example, when detecting abnormal electricity consumption by electrolytic aluminum company A, electrolytic aluminum companies B and C can be used as similar users to collect secondary historical data, further improving the accuracy of the detection results.

[0036] Step S202: Obtain the actual electricity consumption data of the target user at the current moment, and calculate the absolute value of the difference between the electricity consumption reference value and the actual electricity consumption data of the target user at the current moment to obtain the target difference;

[0037] Specifically, the above-mentioned actual electricity consumption data is the actual electricity consumption data of the target user collected at the current moment, thereby determining the difference between the target user's actual electricity consumption and the normal electricity consumption reference value.

[0038] Step S203: If the target difference is greater than the second threshold, the target user's electricity consumption is determined to be abnormal.

[0039] Specifically, the aforementioned second threshold is a pre-set judgment threshold. If the target difference is greater than the second threshold, the target user is determined to have an abnormal power consumption. If the target difference is less than or equal to the second threshold, the target user is determined not to have an abnormal power consumption.

[0040] In this embodiment, firstly, a reference value for the electricity consumption of the target user is calculated based on the new energy influence coefficient, first historical data, and second historical data. Then, the actual electricity consumption data of the target user at the current moment is obtained, and the absolute value of the difference between the reference value and the actual electricity consumption data is calculated to obtain the target difference. Finally, if the target difference is greater than a second threshold, the target user's electricity consumption is determined to be abnormal. By introducing a new energy influence coefficient that characterizes the power generation intensity of the new energy system, and calculating a normal electricity consumption reference value based on the new energy influence coefficient, first historical data, and second historical data, this value is used as a reference value to guide the detection and judgment of abnormal electricity consumption. This method considers the impact of new energy access and fluctuations in new energy output on load anomaly detection, thus solving the technical problem of poor electricity consumption anomaly detection performance under new energy access conditions.

[0041] In specific implementation, step S201 can be achieved through the following steps: Step S2011, obtaining the intensity values ​​of power generation influencing factors at multiple predetermined test points of the target user's new energy power station at the current time, wherein the intensity values ​​of the power generation influencing factors include at least the light intensity and wind speed of the target user's new energy power station at the current time; Step S2012, calculating the average of the intensity values ​​of the power generation influencing factors at multiple predetermined test points to obtain the current intensity value; Step S2013, determining the power generation intensity of the new energy system based on the current intensity value and historical intensity values, wherein the historical intensity values ​​are the intensity values ​​of the power generation influencing factors at multiple predetermined test points of the target user's new energy power station at multiple second predetermined times prior to the current time; Step S2014, determining the new energy influence coefficient based on the mapping relationship between the power generation intensity of the new energy system and the new energy influence coefficient. This method can further quickly obtain the new energy influence coefficient.

[0042] Specifically, the current new energy systems in industrial parks are mostly photovoltaic systems that generate electricity from solar power and wind power systems that generate electricity from wind power. For example... Figure 3 As shown, Figure 3 This illustrates the pre-deployment of multiple light intensity and wind speed testing points at a new energy power station. These points are evenly distributed among the various power generation devices at the station to obtain the required intensity values, namely light intensity and wind speed. According to the formula... Calculate the current intensity value, where, This is the current intensity value. The number of test points, The values ​​represent the light intensity or wind speed at each test point. Table 1 below shows the mapping relationship between the power generation intensity of the new energy system and the new energy influence coefficient. As the power generation intensity increases, the new energy influence coefficient also increases. The specific value of the new energy influence coefficient can be determined after evaluating the user's installed new energy capacity.

[0043] Table 1. Relationship between power generation intensity and new energy impact coefficient of new energy system

[0044]

[0045] To further determine the power generation intensity of the aforementioned new energy system based on the current and historical intensity values, step S2013 of this application can be implemented through the following steps: Step S20131, sorting the historical intensity values ​​to obtain a target sequence; Step S20132, determining the power generation intensity of the aforementioned new energy system based on the position of the current intensity value in the target sequence. This method can further classify the power generation intensity of the new energy system into different levels.

[0046] Specifically, if the solar intensity / wind speed is in the top 20% of the historical sequence, the output level of the photovoltaic / wind power system is Level I; if it is between 20% and 40%, it is Level II; if it is between 40% and 60%, it is Level III; if it is between 60% and 80%, it is Level IV; and if it is in the bottom 20%, it is Level V. A higher output level indicates a lower intensity of renewable energy generation. The processing level of the current renewable energy system is further determined based on the output levels of the photovoltaic / wind power system. The determination rules are shown in Table 2. If both the photovoltaic system's output level and the wind power system's level are Level I, then the renewable energy system's level is Level I.

[0047] Table 2. Relationship between Photovoltaic System Level, Wind Power System Level, and New Energy System Level

[0048]

[0049] Step S201 above can also be implemented in other ways, for example: Step S2015, determining a first reference value based on the first historical data, wherein the first reference value is the predicted electricity consumption data of the target user at the current moment obtained based on the first historical data; Step S2016, calculating a second reference value based on the second historical data, wherein the second reference value is the predicted electricity consumption data of similar users at the current moment obtained based on the second historical data; Step S2017, calculating the average value of the second historical data to obtain a third reference value; Step S2018, calculating the electricity consumption reference value of the target user based on the new energy impact coefficient, the first reference value, the second reference value, and the third reference value. This method can further determine accurate electricity consumption reference values.

[0050] Specifically, the first reference value is obtained by predicting the target user's electricity consumption data at the current moment, and the second reference value is obtained by predicting the electricity consumption data of similar users at the current moment. Furthermore, the models used to obtain the first and second reference values ​​can be the same, thus eliminating the influence of model differences. By calculating the mean of the second set of historical data, errors caused by outliers and extreme values ​​can be further eliminated. Therefore, by using the predicted data of the target user and similar users at the current moment, as well as the data of similar users, a more accurate reference value for the target user's normal electricity consumption can be determined.

[0051] In some embodiments, step S2015 can be implemented by the following steps: inputting the first historical data into the electricity consumption prediction model to obtain the first reference value, wherein the electricity consumption prediction model is trained using historical electricity consumption data of the target user at multiple third predetermined times before the current time and at the time after the third predetermined time. This method can further obtain an accurate first reference value.

[0052] Specifically, the electricity consumption prediction model described above can employ a data-driven model (BP neural network, support vector machine model, etc.). The variables in the aforementioned first historical data are used as input layer nodes of the model, and the aforementioned first reference value is used as the output layer node of the model.

[0053] The above step S2016 can also be implemented in other ways, for example: step S20161, according to the formula Calculate the multiple of the aforementioned similar users to the aforementioned target users. ,in, For the m-th similar user mentioned above, the electricity consumption data from time i-1 to time i is... The data refers to the electricity consumption of the target user from time i-1 to time i. For the current moment mentioned above, The time window length for the above multiplier coefficient; Step S20162, according to the formula For the predicted value The above predicted values ​​are obtained after processing. ,in, The method provides the predicted electricity consumption data for the m-th similar user at time k, obtained from the aforementioned electricity consumption prediction model. Step S20163 involves calculating the average of the multiple processed predicted values ​​to obtain the second reference value. This method can further eliminate the impact of differences caused by varying production scales among enterprises within the industrial park.

[0054] Specifically, although the target user and similar users have the same electricity consumption characteristics, differences still exist due to variations in enterprise size. For example, electrolytic aluminum enterprise A and electrolytic aluminum enterprise B are the aforementioned target user and similar user, respectively, but electrolytic aluminum enterprise B may be 10 times larger than electrolytic aluminum enterprise A. Based on historical electricity consumption data, the electricity consumption multiple of electrolytic aluminum enterprise B to the target user (i.e., electrolytic aluminum enterprise A) can be approximated as 10. This 10-fold difference should also be considered when calculating the second reference value, thereby eliminating the impact of differences in production scale among enterprises within the industrial park.

[0055] The above step S2018 can also be achieved in other ways, for example: according to the formula Calculate the reference value of electricity consumption for the above target users. ,in, The above-mentioned new energy impact coefficient, The first reference value mentioned above, The second reference value mentioned above, This is the third reference value mentioned above. This method can quickly calculate the reference value for the electricity consumption of the target user.

[0056] To enable those skilled in the art to better understand the technical solution of this application, the implementation process of the power consumption anomaly detection method of this application will be described in detail below with reference to specific embodiments.

[0057] This embodiment relates to a specific method for detecting abnormal electricity usage, such as... Figure 4 As shown, it includes the following steps:

[0058] Step S1: Collect user electricity consumption sequences with time step T;

[0059] Step S2: Construct a user electricity consumption prediction model using j-step time windows, and build a training sample set using historical electricity consumption data to complete the training of the user electricity consumption prediction model. After training is complete, use the latest j-step electricity consumption sequences {x} at the current sampling time.k-j ,x k-j+1 ,…,x k-2 ,x k-1 The predicted electricity consumption value for the user at the current sampling time is obtained. and will Used as the first reference value for power consumption anomalies at the current sampling time;

[0060] Step S3: Obtain the electricity consumption sequences of M users of the same type, and calculate the electricity consumption multiple coefficient of each user of the same type relative to the current user;

[0061] Step S4: Following the method in Step 2, predict the predicted electricity consumption of m users of the same type at the current sampling time, and use the electricity consumption multiple coefficient obtained in Step 3 for standardization to obtain the standardized predicted electricity consumption of the same type of users. In addition, use the electricity consumption multiple coefficient obtained in Step 3 to standardize the measured electricity consumption of m users of the same type at the current sampling time to obtain the standardized measured electricity consumption of the same type of users.

[0062] Step S5: Take the average of the standardized predicted electricity consumption values ​​and the standardized measured electricity consumption values ​​of the m users of the same type obtained in Step 4, and use them as the second and third reference values ​​for electricity consumption anomalies at the current sampling time.

[0063] Step S6: Evaluate the power output level of new energy sources at the current sampling time, and select the power output influence coefficient of new energy sources according to the corresponding relationship table;

[0064] Step S7: Determine the normal power load reference value of the user at the current sampling time based on the reference values ​​of abnormal power consumption and the new energy output influence coefficient in Step 6;

[0065] Step S8: Based on the normal power load reference value obtained in Step 7 and the measured power consumption value of the user at the current sampling time obtained in Step 1, if the formula If the condition is met, it is determined that an abnormal power supply situation has occurred; otherwise, it is determined that no abnormal power supply situation has occurred. This is the measured power consumption at the current sampling time. This is the reference value for normal power load at the current sampling time. The threshold is set in advance.

[0066] This application also provides an electrical anomaly detection device. It should be noted that the electrical anomaly detection device of this application can be used to execute the electrical anomaly detection method provided in this application. This device is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0067] The following describes the power consumption anomaly detection device provided in the embodiments of this application.

[0068] Figure 5 This is a schematic diagram of an electrical anomaly detection device according to an embodiment of this application. Figure 5 As shown, the device includes:

[0069] The first calculation unit 10 is used to calculate the reference value of the electricity consumption of the target user based on the new energy influence coefficient, the first historical data and the second historical data. The new energy influence coefficient represents the power generation intensity of the new energy system. The first historical data is the historical electricity consumption data of the target user at multiple first predetermined times before the current time. The second historical data is the historical electricity consumption data of similar users at multiple first predetermined times before the current time. The reference value of the electricity consumption of the target user is the electricity consumption of the target user under normal electricity consumption conditions. The similar users have the same electricity consumption characteristics as the target user.

[0070] Specifically, existing methods for detecting abnormal electricity consumption by users largely rely on analyzing the user's historical electricity usage sequences. Load reference values ​​are derived through load forecasting, and then compared with actual load values ​​to determine if abnormal electricity consumption has occurred. By introducing a renewable energy impact coefficient, considering the influence of renewable energy access and output fluctuations on load anomaly detection, the detection effectiveness is improved when renewable energy access is available. Industrial parks typically house several different types of enterprises, such as electrolytic aluminum companies and polysilicon production companies. The aforementioned similar users can be those producing the same industrial products as the target user, sharing similar production processes and load characteristics. For example, when detecting abnormal electricity consumption by electrolytic aluminum company A, electrolytic aluminum companies B and C can be used as similar users to collect secondary historical data, further improving the accuracy of the detection results.

[0071] The second calculation unit 20 is used to obtain the actual electricity consumption data of the target user at the current moment, and calculate the absolute value of the difference between the electricity consumption reference value and the actual electricity consumption data of the target user at the current moment to obtain the target difference.

[0072] Specifically, the above-mentioned actual electricity consumption data is the actual electricity consumption data of the target user collected at the current moment, thereby determining the difference between the target user's actual electricity consumption and the normal electricity consumption reference value.

[0073] The determining unit 30 is used to determine that the target user's power consumption is abnormal when the target difference is greater than the second threshold.

[0074] Specifically, the aforementioned second threshold is a pre-set judgment threshold. If the target difference is greater than the second threshold, the target user is determined to have an abnormal power consumption. If the target difference is less than or equal to the second threshold, the target user is determined not to have an abnormal power consumption.

[0075] In this embodiment, the first calculation unit calculates a reference value for the target user's electricity consumption based on the new energy influence coefficient, first historical data, and second historical data. The second calculation unit obtains the target user's actual electricity consumption data at the current moment and calculates the absolute value of the difference between the reference value and the target user's actual electricity consumption data at the current moment to obtain the target difference. The determining unit determines that the target user's electricity consumption is abnormal if the target difference is greater than a second threshold. By introducing a new energy influence coefficient that characterizes the power generation intensity of the new energy system, and calculating a normal electricity consumption reference value based on the new energy influence coefficient, first historical data, and second historical data, this value is used as a reference value to guide the detection and judgment of abnormal electricity consumption. This device considers the impact of new energy access and fluctuations in new energy output on load anomaly detection, thus solving the technical problem of poor electricity consumption anomaly detection performance under new energy access conditions.

[0076] As an optional solution, the first calculation unit includes an acquisition module, a first calculation module, a first determination module, and a second determination module. The acquisition module acquires the intensity values ​​of power generation influencing factors at multiple predetermined test points of the target user's new energy power station at the current time. The intensity values ​​of these power generation influencing factors include at least the light intensity and wind speed of the target user's new energy power station at the current time. The first calculation module calculates the average of the intensity values ​​of the power generation influencing factors at the multiple predetermined test points to obtain the current intensity value. The first determination module determines the power generation intensity of the new energy system based on the current intensity value and historical intensity values. The historical intensity values ​​are the intensity values ​​of the power generation influencing factors at multiple predetermined test points of the target user's new energy power station at multiple second predetermined times prior to the current time. The second determination module determines the new energy influence coefficient based on the mapping relationship between the power generation intensity of the new energy system and the new energy influence coefficient. This device can further rapidly acquire the new energy influence coefficient.

[0077] Specifically, the current new energy systems in industrial parks are mostly photovoltaic systems that generate electricity from solar power and wind power systems that generate electricity from wind power. For example... Figure 3 As shown, Figure 3 This illustrates the pre-deployment of multiple light intensity and wind speed testing points at a new energy power station. These points are evenly distributed among the various power generation devices at the station to obtain the required intensity values, namely light intensity and wind speed. According to the formula... Calculate the current intensity value, where, This is the current intensity value. The number of test points, The values ​​represent the light intensity or wind speed at each test point. Table 1 below shows the mapping relationship between the power generation intensity of the new energy system and the new energy influence coefficient. As the power generation intensity increases, the new energy influence coefficient also increases. The specific value of the new energy influence coefficient can be determined after evaluating the user's installed new energy capacity.

[0078] To further determine the power generation intensity of the new energy system based on the current and historical intensity values, the first determining module of this application includes a first processing submodule and a determining submodule. The first processing submodule is used to sort the historical intensity values ​​to obtain a target sequence; the determining submodule is used to determine the power generation intensity of the new energy system based on the position of the current intensity value in the target sequence. This device can further classify the power generation intensity of the new energy system into different levels.

[0079] Specifically, if the solar intensity / wind speed is in the top 20% of the historical sequence, the output level of the photovoltaic / wind power system is Level I; if it is between 20% and 40%, it is Level II; if it is between 40% and 60%, it is Level III; if it is between 60% and 80%, it is Level IV; and if it is in the bottom 20%, it is Level V. A higher output level indicates a lower intensity of renewable energy generation. The processing level of the current renewable energy system is further determined based on the output levels of the photovoltaic / wind power system. The determination rules are shown in Table 2. If both the photovoltaic system's output level and the wind power system's level are Level I, then the renewable energy system's level is Level I.

[0080] In one optional embodiment, the first calculation unit includes a third determining module, a second calculation module, a third calculation module, and a fourth calculation module. The third determining module determines a first reference value based on the first historical data, wherein the first reference value is the predicted electricity consumption data of the target user at the current moment obtained from the first historical data. The second calculation module calculates a second reference value based on the second historical data, wherein the second reference value is the predicted electricity consumption data of similar users at the current moment obtained from the second historical data. The third calculation module calculates the average value of the second historical data to obtain a third reference value. The fourth calculation module calculates the electricity consumption reference value of the target user based on the new energy impact coefficient, the first reference value, the second reference value, and the third reference value. This device can further determine accurate electricity consumption reference values.

[0081] Specifically, the first reference value is obtained by predicting the target user's electricity consumption data at the current moment, and the second reference value is obtained by predicting the electricity consumption data of similar users at the current moment. Furthermore, the models used to obtain the first and second reference values ​​can be the same, thus eliminating the influence of model differences. By calculating the mean of the second set of historical data, errors caused by outliers and extreme values ​​can be further eliminated. Therefore, by using the predicted data of the target user and similar users at the current moment, as well as the data of similar users, a more accurate reference value for the target user's normal electricity consumption can be determined.

[0082] In some embodiments, the third determining module is further configured to input the first historical data into the electricity consumption prediction model to obtain the first reference value, wherein the electricity consumption prediction model is trained using historical electricity consumption data of the target user at multiple third predetermined times prior to the current time and at the time following the third predetermined time. This allows the device to obtain a more accurate first reference value.

[0083] Specifically, the electricity consumption prediction model described above can employ a data-driven model (BP neural network, support vector machine model, etc.). The variables in the aforementioned first historical data are used as input layer nodes of the model, and the aforementioned first reference value is used as the output layer node of the model.

[0084] In another alternative embodiment, the second calculation module includes a first calculation submodule, a second processing submodule, and a second calculation submodule, wherein the first calculation submodule is used to calculate according to the formula. Calculate the multiple of the aforementioned similar users to the aforementioned target users. ,in, For the m-th similar user mentioned above, the electricity consumption data from time i-1 to time i is... The data refers to the electricity consumption of the target user from time i-1 to time i. For the current moment mentioned above, The time window length is the above-mentioned multiplier coefficient; the second processing submodule is used to process the formula. For the predicted value The above predicted values ​​are obtained after processing. ,in, The second processing submodule is used to calculate the average of the multiple processed predicted values ​​to obtain the second reference value. This device can further eliminate the impact of differences caused by different production scales of enterprises within the industrial park.

[0085] Specifically, although the target user and similar users have the same electricity consumption characteristics, differences still exist due to variations in enterprise size. For example, electrolytic aluminum enterprise A and electrolytic aluminum enterprise B are the aforementioned target user and similar user, respectively, but electrolytic aluminum enterprise B may be 10 times larger than electrolytic aluminum enterprise A. Based on historical electricity consumption data, the electricity consumption multiple of electrolytic aluminum enterprise B to the target user (i.e., electrolytic aluminum enterprise A) can be approximated as 10. This 10-fold difference should also be considered when calculating the second reference value, thereby eliminating the impact of differences in production scale among enterprises within the industrial park.

[0086] In an alternative approach, the second calculation submodule described above is further configured to calculate based on the formula: Calculate the reference value of electricity consumption for the above target users. ,in, The above-mentioned new energy impact coefficient, The first reference value mentioned above, The second reference value mentioned above, This is the third reference value mentioned above. The device can quickly calculate the reference value for the electricity consumption of the target user.

[0087] The aforementioned power consumption anomaly detection device includes a processor and a memory. The first calculation unit, the second calculation unit, and the determination unit are all stored as program units in the memory. The processor executes the program units stored in the memory to achieve the corresponding functions. All of the above modules are located in the same processor; alternatively, the above modules may be located in different processors in any combination.

[0088] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and power anomaly detection can be performed by adjusting kernel parameters.

[0089] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0090] This invention provides a computer-readable storage medium including a stored program, wherein the program, when running, controls the device containing the computer-readable storage medium to execute the power consumption anomaly detection method.

[0091] Specifically, methods for detecting abnormal electricity usage include:

[0092] Step S201: Calculate the reference value of electricity consumption for the target user based on the new energy impact coefficient, the first historical data, and the second historical data. The new energy impact coefficient represents the power generation intensity of the new energy system. The first historical data refers to the historical electricity consumption data of the target user at multiple first predetermined times before the current time. The second historical data refers to the historical electricity consumption data of similar users at multiple first predetermined times before the current time. The reference value of electricity consumption for the target user is the electricity consumption of the target user under normal electricity conditions. The similar users produce the same type of industrial products as the target user.

[0093] Specifically, existing methods for detecting abnormal electricity consumption by users largely rely on analyzing the user's historical electricity usage sequences. Load reference values ​​are derived through load forecasting, and then compared with actual load values ​​to determine if abnormal electricity consumption has occurred. By introducing a renewable energy impact coefficient, considering the influence of renewable energy access and output fluctuations on load anomaly detection, the detection effectiveness is improved when renewable energy access is available. Industrial parks typically house several different types of enterprises, such as electrolytic aluminum companies and polysilicon production companies. The aforementioned similar users can be those producing the same industrial products as the target user, sharing similar production processes and load characteristics. For example, when detecting abnormal electricity consumption by electrolytic aluminum company A, electrolytic aluminum companies B and C can be used as similar users to collect secondary historical data, further improving the accuracy of the detection results.

[0094] Step S202: Obtain the actual electricity consumption data of the target user at the current moment, and calculate the absolute value of the difference between the electricity consumption reference value and the actual electricity consumption data of the target user at the current moment to obtain the target difference;

[0095] Specifically, the above-mentioned actual electricity consumption data is the actual electricity consumption data of the target user collected at the current moment, thereby determining the difference between the target user's actual electricity consumption and the normal electricity consumption reference value.

[0096] Step S203: If the target difference is greater than the second threshold, the target user's electricity consumption is determined to be abnormal.

[0097] Specifically, the aforementioned second threshold is a pre-set judgment threshold. If the target difference is greater than the second threshold, the target user is determined to have an abnormal power consumption. If the target difference is less than or equal to the second threshold, the target user is determined not to have an abnormal power consumption.

[0098] This invention provides a processor for running a program, wherein the program executes the power consumption anomaly detection method.

[0099] Step S201: Calculate the reference value of electricity consumption for the target user based on the new energy impact coefficient, the first historical data, and the second historical data. The new energy impact coefficient represents the power generation intensity of the new energy system. The first historical data refers to the historical electricity consumption data of the target user at multiple first predetermined times before the current time. The second historical data refers to the historical electricity consumption data of similar users at multiple first predetermined times before the current time. The reference value of electricity consumption for the target user is the electricity consumption of the target user under normal electricity conditions. The similar users produce the same type of industrial products as the target user.

[0100] Specifically, existing methods for detecting abnormal electricity consumption by users largely rely on analyzing the user's historical electricity usage sequences. Load reference values ​​are derived through load forecasting, and then compared with actual load values ​​to determine if abnormal electricity consumption has occurred. By introducing a renewable energy impact coefficient, considering the influence of renewable energy access and output fluctuations on load anomaly detection, the detection effectiveness is improved when renewable energy access is available. Industrial parks typically house several different types of enterprises, such as electrolytic aluminum companies and polysilicon production companies. The aforementioned similar users can be those producing the same industrial products as the target user, sharing similar production processes and load characteristics. For example, when detecting abnormal electricity consumption by electrolytic aluminum company A, electrolytic aluminum companies B and C can be used as similar users to collect secondary historical data, further improving the accuracy of the detection results.

[0101] Step S202: Obtain the actual electricity consumption data of the target user at the current moment, and calculate the absolute value of the difference between the electricity consumption reference value and the actual electricity consumption data of the target user at the current moment to obtain the target difference;

[0102] Specifically, the above-mentioned actual electricity consumption data is the actual electricity consumption data of the target user collected at the current moment, thereby determining the difference between the target user's actual electricity consumption and the normal electricity consumption reference value.

[0103] Step S203: If the target difference is greater than the second threshold, the target user's electricity consumption is determined to be abnormal.

[0104] Specifically, the aforementioned second threshold is a pre-set judgment threshold. If the target difference is greater than the second threshold, the target user is determined to have an abnormal power consumption. If the target difference is less than or equal to the second threshold, the target user is determined not to have an abnormal power consumption.

[0105] This invention provides a device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs at least the following steps:

[0106] Step S201: Calculate the reference value of electricity consumption for the target user based on the new energy impact coefficient, the first historical data, and the second historical data. The new energy impact coefficient represents the power generation intensity of the new energy system. The first historical data refers to the historical electricity consumption data of the target user at multiple first predetermined times before the current time. The second historical data refers to the historical electricity consumption data of similar users at multiple first predetermined times before the current time. The reference value of electricity consumption for the target user is the electricity consumption of the target user under normal electricity conditions. The similar users produce the same type of industrial products as the target user.

[0107] Step S202: Obtain the actual electricity consumption data of the target user at the current moment, and calculate the absolute value of the difference between the electricity consumption reference value and the actual electricity consumption data of the target user at the current moment to obtain the target difference;

[0108] Step S203: If the target difference is greater than the second threshold, the target user's electricity consumption is determined to be abnormal.

[0109] The devices mentioned in this article can be servers, PCs, tablets, mobile phones, etc.

[0110] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program having at least the following method steps:

[0111] Step S201: Calculate the reference value of electricity consumption for the target user based on the new energy impact coefficient, the first historical data, and the second historical data. The new energy impact coefficient represents the power generation intensity of the new energy system. The first historical data refers to the historical electricity consumption data of the target user at multiple first predetermined times before the current time. The second historical data refers to the historical electricity consumption data of similar users at multiple first predetermined times before the current time. The reference value of electricity consumption for the target user is the electricity consumption of the target user under normal electricity conditions. The similar users produce the same type of industrial products as the target user.

[0112] Step S202: Obtain the actual electricity consumption data of the target user at the current moment, and calculate the absolute value of the difference between the electricity consumption reference value and the actual electricity consumption data of the target user at the current moment to obtain the target difference;

[0113] Step S203: If the target difference is greater than the second threshold, the target user's electricity consumption is determined to be abnormal.

[0114] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0115] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0116] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0117] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0118] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0119] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0120] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0121] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0122] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0123] As can be seen from the above description, the embodiments of this application achieve the following technical effects:

[0124] 1) The electricity consumption anomaly detection method of this application first calculates a reference value for the electricity consumption of a target user based on the new energy influence coefficient, first historical data, and second historical data; then, it obtains the actual electricity consumption data of the target user at the current moment and calculates the absolute value of the difference between the electricity consumption reference value and the actual electricity consumption data of the target user at the current moment to obtain a target difference value; finally, if the target difference value is greater than a second threshold, the electricity consumption of the target user is determined to be abnormal. By introducing a new energy influence coefficient that characterizes the power generation intensity of the new energy system, and calculating a normal electricity consumption reference value based on the new energy influence coefficient, first historical data, and second historical data, this method is used as a reference value to guide the judgment of electricity consumption anomaly detection. This method considers the impact of new energy access and new energy output fluctuations on load anomaly detection, thus solving the technical problem of poor electricity consumption anomaly detection effect under the condition of new energy access.

[0125] 2) The electricity consumption anomaly detection device of this application comprises: a first calculation unit calculating a reference value for the electricity consumption of a target user based on a new energy influence coefficient, first historical data, and second historical data; a second calculation unit acquiring the actual electricity consumption data of the target user at the current moment and calculating the absolute value of the difference between the electricity consumption reference value and the actual electricity consumption data of the target user at the current moment to obtain a target difference value; and a determination unit determining that the target user's electricity consumption is abnormal if the target difference value is greater than a second threshold value. By introducing a new energy influence coefficient characterizing the power generation intensity of the new energy system, and calculating a normal electricity consumption reference value based on the new energy influence coefficient, first historical data, and second historical data, this device serves as a reference value for feedback-guided electricity consumption anomaly detection judgment. This device considers the impact of new energy access and new energy output fluctuations on load anomaly detection, thus solving the technical problem of poor electricity consumption anomaly detection effect under new energy access conditions.

[0126] The above description is merely a preferred embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for detecting abnormal electricity usage, characterized in that, include: Based on the new energy impact coefficient, first historical data, and second historical data, a reference value for the electricity consumption of the target user is calculated. The new energy impact coefficient represents the power generation intensity of the new energy system. The first historical data consists of the historical electricity consumption data of the target user at multiple first predetermined times before the current time. The second historical data consists of the historical electricity consumption data of similar users at multiple first predetermined times before the current time. The reference value for the electricity consumption of the target user is the electricity consumption of the target user under normal electricity consumption conditions. The similar users have the same electricity consumption characteristics as the target user. Obtain the actual electricity consumption data of the target user at the current moment, and calculate the absolute value of the difference between the electricity consumption reference value and the actual electricity consumption data of the target user at the current moment to obtain the target difference; If the target difference is greater than the second threshold, the target user's electricity consumption is determined to be abnormal. Calculating the new energy impact coefficient includes: obtaining the intensity values ​​of power generation influencing factors at multiple predetermined test points of the target user's new energy power station at the current time, wherein the intensity values ​​of the power generation influencing factors include at least the light intensity and wind speed of the target user's new energy power station at the current time; calculating the average of the intensity values ​​of the power generation influencing factors at multiple predetermined test points to obtain the current intensity value; determining the power generation intensity of the new energy system based on the current intensity value and historical intensity values, wherein the historical intensity values ​​are the intensity values ​​of the power generation influencing factors at multiple predetermined test points of the target user's new energy power station at multiple second predetermined times prior to the current time; and determining the new energy impact coefficient based on the mapping relationship between the power generation intensity of the new energy system and the new energy impact coefficient. Determining the power generation intensity of the new energy system based on the current intensity value and historical intensity values ​​includes: sorting the historical intensity values ​​to obtain a target sequence; and determining the power generation intensity of the new energy system based on the position of the current intensity value in the target sequence. Based on the new energy impact coefficient, first historical data, and second historical data, a reference value for the electricity consumption of the target user is calculated, including: determining a first reference value based on the first historical data, wherein the first reference value is the predicted electricity consumption data of the target user at the current moment obtained based on the first historical data; calculating a second reference value based on the second historical data, wherein the second reference value is the predicted electricity consumption data of similar users at the current moment obtained based on the second historical data; calculating the average value of the second historical data to obtain a third reference value; and calculating the reference value for the electricity consumption of the target user based on the new energy impact coefficient, the first reference value, the second reference value, and the third reference value. Determining a first reference value based on the first historical data includes: inputting the first historical data into an electricity consumption prediction model to obtain the first reference value, wherein the electricity consumption prediction model is trained using historical electricity consumption data of the target user at multiple third predetermined times before the current time and at the time after the third predetermined time; Based on the second historical data, calculate the second reference value, including: according to the formula Calculate the multiple coefficient of the similar users to the target users. ,in, The data represents the electricity consumption of the m-th similar user from time i-1 to time i. The electricity consumption data of the target user from time i-1 to time i. For the current time, The time window length is the multiplier coefficient; according to the formula For the predicted value The predicted value is obtained by processing. ,in, The predicted electricity consumption data of the m-th similar user at time k is obtained based on the electricity consumption prediction model; the mean of multiple processed predicted values ​​is calculated to obtain the second reference value; Based on the new energy impact coefficient, the first reference value, the second reference value, and the third reference value, calculate the electricity consumption reference value for the target user, including: according to the formula Calculate the reference value of electricity consumption for the target user. ,in, The influence coefficient of the new energy source is... The first reference value, The second reference value, This is the third reference value.

2. A device for detecting abnormal electricity usage, characterized in that, include: The first calculation unit is used to calculate the reference value of electricity consumption of the target user based on the new energy influence coefficient, the first historical data, and the second historical data. The new energy influence coefficient represents the power generation intensity of the new energy system. The first historical data is the historical electricity consumption data of the target user at multiple first predetermined times before the current time. The second historical data is the historical electricity consumption data of similar users at multiple first predetermined times before the current time. The reference value of electricity consumption of the target user is the electricity consumption of the target user under normal electricity consumption conditions. The similar users have the same electricity consumption characteristics as the target user. The second calculation unit is used to obtain the actual electricity consumption data of the target user at the current moment, and calculate the absolute value of the difference between the electricity consumption reference value and the actual electricity consumption data of the target user at the current moment to obtain the target difference. The determining unit is configured to determine that the target user's electricity consumption is abnormal when the target difference is greater than a second threshold. The first calculation unit includes an acquisition module, a first calculation module, a first determination module, and a second determination module. The acquisition module acquires the intensity values ​​of power generation influencing factors at multiple predetermined test points of the target user's new energy power station at the current time, wherein the intensity values ​​of the power generation influencing factors include at least the light intensity and wind speed of the target user's new energy power station at the current time. The first calculation module calculates the average of the intensity values ​​of the power generation influencing factors at multiple predetermined test points to obtain the current intensity value. The first determination module determines the power generation intensity of the new energy system based on the current intensity value and historical intensity values, wherein the historical intensity values ​​are the intensity values ​​of the power generation influencing factors at multiple predetermined test points of the target user's new energy power station at multiple second predetermined times prior to the current time. The second determination module determines the new energy influence coefficient based on the mapping relationship between the power generation intensity of the new energy system and the new energy influence coefficient. The first determining module includes a first processing submodule and a determining submodule, wherein the first processing submodule is used to sort the historical intensity values ​​to obtain a target sequence; the determining submodule is used to determine the power generation intensity of the new energy system based on the position of the current intensity value in the target sequence; The first calculation unit includes a third determining module, a second calculation module, a third calculation module, and a fourth calculation module. The third determining module is used to determine a first reference value based on the first historical data, wherein the first reference value is the predicted electricity consumption data of the target user at the current moment obtained from the first historical data. The second calculation module is used to calculate a second reference value based on the second historical data, wherein the second reference value is the predicted electricity consumption data of similar users at the current moment obtained from the second historical data. The third calculation module is used to calculate the average value of the second historical data to obtain a third reference value. The fourth calculation module is used to calculate the electricity consumption reference value of the target user based on the new energy impact coefficient, the first reference value, the second reference value, and the third reference value. The third determining module is further configured to input the first historical data into the electricity consumption prediction model to obtain the first reference value, wherein the electricity consumption prediction model is trained using historical electricity consumption data of the target user at multiple third predetermined times before the current time and at the time after the third predetermined time. The second calculation module includes a first calculation submodule, a second processing submodule, and a second calculation submodule, wherein the first calculation submodule is used to calculate according to the formula. Calculate the multiple coefficient of the similar users to the target users. ,in, The data represents the electricity consumption of the m-th similar user from time i-1 to time i. The electricity consumption data of the target user from time i-1 to time i. For the current time, The time window length is the multiplier coefficient; the second processing submodule is used to process the multiplier coefficient according to the formula. For the predicted value The predicted value is obtained by processing. ,in, The second calculation submodule is used to calculate the mean of multiple processed predicted values ​​to obtain the second reference value. This is the predicted electricity consumption data of the m-th similar user at time k, obtained from the electricity consumption prediction model. The second calculation submodule is also used to calculate according to the formula Calculate the reference value of electricity consumption for the target user. ,in, The influence coefficient of the new energy source is... The first reference value, The second reference value, This is the third reference value.

3. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform the method of claim 1.

4. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to execute the method of claim 1 through the computer program.

Images