CN116664110B

CN116664110B - Electric power marketing digitizing method and system based on business center

Info

Publication number: CN116664110B
Application number: CN202310684577.8A
Authority: CN
Inventors: 李娜; 潘麟; 明成昆; 程欢; 王晓峰; 龚艳丽
Original assignee: Hubei Central China Technology Development Of Electric Power Co ltd
Current assignee: Hubei Central China Technology Development Of Electric Power Co ltd
Priority date: 2023-06-08
Filing date: 2023-06-08
Publication date: 2024-03-29
Anticipated expiration: 2043-06-08
Also published as: CN116664110A

Abstract

The embodiment of the specification discloses a business center-based power marketing digitizing method and system, wherein the system comprises the following steps: the system comprises a metering module, a historical electricity utilization module, a device operation and maintenance module, an instruction processing module and a processor; the metering module is used for monitoring metering data of at least one metering device at least one position in the power grid and sending the metering data to the historical electricity utilization module for storage; the historical electricity utilization module is used for storing historical electricity utilization data; the equipment operation and maintenance module is used for storing historical overhaul data of the metering equipment; the instruction processing module is used for receiving the detection instruction and the detection route sent by the processor and displaying the detection instruction and the detection route; the processor is used for: acquiring target data, wherein the target data comprises at least one of metering data, historical electricity consumption data and historical maintenance data; judging whether the failure occurrence rate of at least one metering device meets a preset detection condition or not based on the target data; and responding to the failure occurrence rate of at least one metering device to meet a preset detection condition, and sending out a detection instruction.

Description

Electric power marketing digitizing method and system based on business center

Technical Field

The specification relates to the field of electric power marketing, in particular to an electric power marketing digitizing method and system based on a business center.

Background

The electric power marketing is that electric power enterprises provide electric power products and corresponding services meeting the consumption needs through a series of operation activities related to the market of the electric power enterprises in the changing market environment so as to meet the electric power consumption needs of people, thereby realizing the targets of the enterprises. As a metering device of one of the grid base devices, metering data of different locations of the grid needs to be acquired in real time. When any metering device fails, the failed metering device needs to be detected as soon as possible, so that the electricity fee loss possibly caused by the equipment problem is avoided.

In order to monitor the fault condition of the metering equipment, CN102103198A discloses an automatic fault checking system and a checking method for the metering equipment, a setting module is used for setting a judging standard of the fault of the metering equipment, the state of the metering equipment on site of a communication module is collected and transmitted to an analysis module, and the analysis module calculates and analyzes the fault type and the fault cause of the metering equipment according to the collected state of the equipment. In the method, state data of all metering devices are required to be collected and analyzed one by one so as to judge the fault condition of the metering devices, and the calculation process is too complicated.

Therefore, there is a need to provide a business center-based power marketing digitizing method and system that can quickly locate and detect a potentially malfunctioning metering device.

Disclosure of Invention

One of the embodiments of the present specification provides a business center-based power marketing digitizing system, the system comprising: the device comprises a metering module, a historical electricity consumption module, a device operation and maintenance module, an instruction processing module and a processor, wherein the historical electricity consumption module, the device operation and maintenance module, the instruction processing module and the processor are in communication connection; the metering module is deployed at the front end of the system and is used for monitoring metering data of at least one metering device at least one position in the power grid and sending the metering data to the historical electricity utilization module for storage; the historical electricity utilization module is deployed at the rear end of the system and is used for storing historical electricity utilization data; the equipment operation and maintenance module is deployed at the rear end of the system and is used for storing historical overhaul data of the metering equipment; the instruction processing module is used for receiving a detection instruction and a detection route sent by the processor and displaying the detection instruction and the detection route; the processor is configured to: acquiring target data, wherein the target data comprises at least one of the metering data, the historical electricity consumption data and the historical overhaul data; judging whether the failure occurrence rate of the at least one metering device meets a preset detection condition or not based on the target data; and responding to the failure occurrence rate of the at least one metering device to meet a preset detection condition, and sending out the detection instruction.

One of the embodiments of the present disclosure provides a business center-based power marketing digitizing method, which is implemented by a business center-based power marketing digitizing system, the system comprising: the device comprises a metering module, a historical electricity consumption module, a device operation and maintenance module, an instruction processing module and a processor, wherein the historical electricity consumption module, the device operation and maintenance module, the instruction processing module and the processor are in communication connection; the method is performed by the processor and includes: acquiring target data, wherein the target data comprises at least one of metering data, historical electricity consumption data and historical overhaul data; judging whether the failure occurrence rate of the at least one metering device meets a preset detection condition or not based on the target data; and responding to the failure occurrence rate of the at least one metering device to meet a preset detection condition, and sending out the detection instruction.

One of the embodiments of the present specification provides a business center based power marketing digitizing apparatus comprising at least one processor for performing a business center based power marketing digitizing method as described above.

One of the embodiments of the present description provides a computer-readable storage medium storing computer instructions that, when executed by a processor, implement a business center-based power marketing digitizing method as described above.

Drawings

The present specification will be further elucidated by way of example embodiments, which will be described in detail by means of the accompanying drawings. The embodiments are not limiting, in which like numerals represent like structures, wherein:

FIG. 1 is a block diagram of a business center based power marketing digitizing system according to some embodiments of the present description;

FIG. 2 is an exemplary flow chart of a business center-based power marketing digitizing method according to some embodiments of the present description;

fig. 3 is a schematic diagram of a predictive model according to some embodiments of the present disclosure.

Detailed Description

In order to more clearly illustrate the technical solutions of the embodiments of the present specification, the drawings that are required to be used in the description of the embodiments will be briefly described below. It is apparent that the drawings in the following description are only some examples or embodiments of the present specification, and it is possible for those of ordinary skill in the art to apply the present specification to other similar situations according to the drawings without inventive effort. Unless otherwise apparent from the context of the language or otherwise specified, like reference numerals in the figures refer to like structures or operations.

It will be appreciated that "system," "apparatus," "unit" and/or "module" as used herein is one method for distinguishing between different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

As used in this specification and the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.

A flowchart is used in this specification to describe the operations performed by the system according to embodiments of the present specification. It should be appreciated that the preceding or following operations are not necessarily performed in order precisely. Rather, the steps may be processed in reverse order or simultaneously. Also, other operations may be added to or removed from these processes.

Fig. 1 is a block diagram of a business center based power marketing digitizing system, according to some embodiments of the present description.

In some embodiments, a business center-based power marketing digitizing system 100 (hereinafter referred to as system 100) may include a metering module 110, a historical electricity usage module 120, a device operation and maintenance module 130, an instruction processing module 140, and a processor 150. The metering module 110, the historical electricity consumption module 120, the equipment operation and maintenance module 130 and the instruction processing module 140 are respectively connected with the processor 150 in a communication manner.

Metering module 110 may be deployed at the front end of system 100 for monitoring metering data of at least one metering device at least one location in the grid and sending the metering data to a historical electricity usage module for storage.

The metering device is a device arranged in the power grid and used for counting the power consumption of the power grid users. The metering device may be arranged at least one location in the electrical network. Metering devices may be classified according to different locations in the power grid. In some embodiments, the metering device may be disposed at the user side, where the metering device is a first type of metering device and is used for counting the electricity consumption of the user side. The user side is located on a sub-line of the power grid, and first metering devices on different sub-lines are in parallel relation. In some embodiments, the metering device may be disposed at the management end, where the metering device is a second type of metering device, and is configured to count the power supply amount of the management end. Wherein the management end is positioned on a bus of the power grid.

In some embodiments, the number of configurations of the metering device is related to the number of users and/or the area. By way of example only, each user side may set a corresponding metering device, and the number of the first type of metering devices may be the same as the number of users; the management end of each area can be provided with at least two serially connected second-type metering devices for judging whether the summarized data (namely the total electricity consumption of the area) is accurate or not.

In some embodiments, metering module 110 may acquire metering data for at least one metering device in real time, or may acquire metering data for a metering device at regular time intervals.

The historical electricity usage module 120 may be deployed at the back end of the system 100 for storing historical electricity usage data. In some embodiments, after metering module 110 obtains metering data for different locations, it may be sent to historical electricity usage module 120 for storage. Other modules (e.g., processors) in the system 100 may access the historical electricity usage data stored in the historical electricity usage module 120.

The equipment operation and maintenance module 130 is disposed at the back end of the system 100 and is configured to store historical overhaul data of the metering equipment. In some embodiments, historical overhaul data for the metering device may be sent to the device operation and maintenance module 130 for storage by way of user input, processor issue, and the like. Other modules (e.g., processors) in the system 100 may access the historical overhaul data stored in the device operation and maintenance module 130.

The instruction processing module 140 may be configured to receive the detection instruction and the detection route sent by the processor 150, and display the detection instruction and the detection route. In some embodiments, the instruction processing module may be coupled to a display device (e.g., a display) and send the detection instructions and the detection route to the display device for display. In some embodiments, the detection instructions and detection routes may be presented to the relevant staff and a determination made by the relevant staff as to whether to execute.

Processor 150 may be used to perform the business center station based power marketing digitizing method described in some embodiments of the present description. In some embodiments, the processor 150 may be configured to obtain target data including at least one of metering data, historical electricity usage data, historical overhaul data. In some embodiments, the processor 150 may be configured to determine whether at least one metering device is malfunctioning based on the target data. In some embodiments, processor 150 may issue a detection instruction in response to at least one metering device failing.

The above partial modules can establish data connection in a wired or wireless manner.

It should be noted that the above description of the business center-based power marketing digitizing system and its modules is for convenience of description only and should not be construed as limiting the present description to the scope of the illustrated embodiments. It will be appreciated by those skilled in the art that, given the principles of the system, various modules may be combined arbitrarily or a subsystem may be constructed in connection with other modules without departing from such principles. In some embodiments, the metering module, the historical electricity module, the equipment operation and maintenance module, the instruction processing module and the processor disclosed in fig. 1 may be different modules in one system, or may be one module to implement the functions of two or more modules. For example, each module may share one memory module, or each module may have a respective memory module. Such variations are within the scope of the present description.

Fig. 2 is an exemplary flow chart of a business center-based power marketing digitizing method according to some embodiments of the present description.

In some embodiments, the business center-based power marketing digitizing method described in the embodiments of the present description may be implemented by the system 100, and the process 200 may be performed by the processor 150. As shown in fig. 1, the process 200 may include the steps of:

step 210, obtaining target data.

The target data is relevant data that can be used to determine whether the metering device is malfunctioning. In some embodiments, the target data may include at least one of metering data, historical electricity usage data, historical overhaul data. Processor 150 may obtain target data from other modules of system 100.

The metering data is the electricity consumption of the grid users counted by the metering equipment. In some embodiments, the metering data may include a first type of metering data and a second type of metering data. The first type of metering data may be a sum of metering data of at least one first type of metering device. The second type of metering data is metering data of any second type of metering device. The first type of metering data has a corresponding relationship with the second type of metering data, for example, the second type of metering data can be metering data of any second type of metering device on a bus, and the first type of metering data can be the sum of metering data of at least one first type of metering device on different sub-lines under the bus. See fig. 1 for more description of the metering device.

The historical electricity usage data is metering data for at least one location in the grid for a historical period. In some embodiments, the historical electricity usage data may include historical first-type metering data and historical second-type metering data.

The historical service data is data related to the performance of historical service on the metering device. In some embodiments, the historical service data may include related information such as metering device number, number of service, type of fault, service time, etc.

Step 220, based on the target data, it is determined whether the failure occurrence rate of at least one metering device satisfies a preset detection condition.

The preset detection condition is a judgment condition related to the failure occurrence rate. In some embodiments, the preset detection condition may be that the failure occurrence rate is greater than an occurrence rate threshold. The occurrence threshold may be a system preset value, an artificial preset value, or the like. The preset detection conditions may also be in other various forms, and are not limited herein.

The processor 150 may determine whether the failure occurrence rate of the at least one metering device satisfies the preset detection condition in various ways based on the target data.

In some embodiments, the processor 150 may determine whether at least one metering device is malfunctioning by comparing metering data of a plurality of metering devices of a second type on a bus. For example, if the metering data of the plurality of metering devices of the second type are inconsistent or the metering difference is greater than the difference threshold, it may be determined that the failure occurrence rate of at least one metering device meets the preset detection condition.

In some embodiments, the processor 150 may initially determine that the failure occurrence rate of the metering device satisfies the preset detection condition by a metering difference between metering data of at least one metering device. In some embodiments, the processor 150 may determine that the failure rate of the at least one metering device satisfies the preset detection condition by determining a metering difference between the second type of metering data and the first type of metering data, and comparing the metering difference to a first threshold. And when the metering difference value is greater than or equal to the first threshold value, determining that the failure occurrence rate of at least one metering device meets the preset detection condition as a judging result.

The first threshold may be a threshold condition for judging that the failure occurrence rate of the at least one metering device satisfies a preset detection condition. In some embodiments, the first threshold may be manually determined based on a priori knowledge or historical data.

In some embodiments, the first threshold may be related to circuit loss. For example, the first threshold may be positively correlated to circuit loss. In some embodiments, the processor 150 may determine the first threshold based on the circuit loss and the floating threshold. For example, the sum of the circuit loss and the floating threshold is taken as the first threshold. Where the float threshold is a range of metering difference values that may be allowed to float, the float threshold may be used to avoid misjudgments due to the first threshold being too small. In some embodiments, the floating threshold may be determined based on a priori knowledge or historical data. In some embodiments, the floating threshold may also be determined based on the accuracy of the loss model, for more description below.

In some embodiments, circuit loss may be determined by a loss model. The loss model may be a machine learning model for determining circuit loss, e.g., a neural network model, etc.

In some embodiments, the input of the loss model may include environmental factors, length of lines in the power grid, power grid voltage, etc., and the output of the loss model may include circuit losses of the power grid. The environmental factors may include humidity, temperature, and other external environmental conditions of the environment where the power grid is located. The length of a line in the power grid refers to the total length of all lines in the power grid of one segment, including the total length of at least one bus and at least one sub-line. Grid voltage refers to the voltage measured at a plurality of preset locations in the grid.

In some embodiments, the loss model may be trained from a plurality of first training samples having first tags. In some embodiments, the first training sample may include at least a sample environmental factor in the absence of a fault in the metering device, a length of a line in the sample grid, a voltage, etc., and the first training sample may be determined based on historical data. In some embodiments, the first tag may be the actual circuit loss corresponding to the first training sample. The first tag may be manually identified. For example, a measurement difference between the historical measurement data (i.e., the historical power supply amount) of any second type of measurement device on the bus and the sum of the historical measurement data (i.e., the sum of the historical power consumption amounts) of the first type of measurement devices on the corresponding plurality of sub-lines may be determined under the first training sample, and the measurement difference may be determined as the actual circuit loss corresponding to the first training sample.

In some embodiments, the accuracy of the model may be further counted as the loss model is trained. Wherein the accuracy of the loss model may be determined by comparing the output of the loss model with the first tag. For example, the number of predictions when the difference between the output of the loss model and the prediction of the first tag is less than a preset threshold may be determined, and the ratio of the number of predictions to the total number of predictions may be used as the accuracy of the loss model. In some embodiments the accuracy of the loss model may be used to determine a floating threshold for the first threshold, e.g., a correspondence of the floating threshold to the accuracy of the loss model may be preset based on a priori knowledge or historical data, and the floating threshold may be determined based on the accuracy of the loss model and the correspondence.

In the embodiment of the specification, the circuit loss is determined through the loss model, so that the calculation result of the circuit loss is more accurate, the influence of environmental factors, the length of a line in a power grid, the voltage of the power grid and other factors on the circuit loss is fully considered, and the accuracy of judging whether the metering equipment has faults or not is improved.

And 230, responding to the failure occurrence rate of at least one metering device to meet a preset detection condition, and sending out a detection instruction.

The detection instruction is an instruction for detecting a fault condition of at least one metering device. The detection instructions may include detecting the location of the metering device, the type of fault, the manner of servicing, etc.

In some embodiments, the processor 150 may issue the detection instruction to the instruction processing module 140, and the instruction processing module 140 may present the detection instruction after receiving the detection instruction issued by the processor 150.

In some embodiments, in response to the failure occurrence rate of at least one metering device meeting a preset detection condition, the processor 150 may further determine a target device and issue a detection instruction in accordance with the target device. The target device is a metering device with a probability of failure above a threshold. When the failure occurrence rate of at least one metering device is determined to meet the preset detection condition, as the number of metering devices in the power grid is large, if each metering device is detected, the calculation amount is too large and time is consumed. Therefore, by determining the target apparatus, the range of the metering apparatus to be detected can be narrowed, thereby reducing the calculation amount and improving the detection efficiency.

In some embodiments, in response to the failure occurrence of the at least one metering device meeting a preset detection condition, the processor 150 may determine at least one suspect device based on the target data; and determining the target equipment from the at least one suspicious equipment through a preset method.

A suspect device is a metering device that may fail. Processor 150 may determine the at least one suspect device in a variety of ways based on the target data. In some embodiments, the processor 150 may determine the suspect device by further analysis of the metrology data of the at least one metrology device.

In some embodiments, upon determining that the failure occurrence rate of the at least one metering device meets the preset detection condition, the processor 150 may further determine the at least one suspect device by comparing whether metering data of a plurality of metering devices of the second type on one bus is consistent. When the metering data of a plurality of metering devices of the second type on one bus are inconsistent, the plurality of metering devices of the second type can be determined to be suspicious devices. When metering data of a plurality of metering devices of the second type are consistent on one bus, the metering devices which indicate that faults possibly occur are metering devices of the first type. Since the first type of metering devices are arranged at the user end and are huge in number, at least one suspicious device needs to be further determined from at least one first type of metering devices.

In some embodiments, the processor 150 may determine the user average daily power consumption based on the target data, and determine the suspicious device from the at least one first type of metering device according to a difference between the metering data of each first type of metering device and the user average daily power consumption and a preset condition. The preset condition is that the difference between the metering data of the first metering device and the daily average power consumption of the user is within a preset threshold range.

In some embodiments, the processor 150 may determine that a first type of metering device whose difference between the metering data of the first type of metering device and the user's average daily power usage is not within a preset threshold range is a suspect device. The daily electricity consumption of the users can be used for representing the overall electricity consumption characteristics of all the user terminals in the bus. The daily electricity consumption of the user can be obtained by dividing the metering data of any metering device of the second type on the bus by the number of sub-lines (namely the number of metering devices of the first type).

In the embodiment of the specification, by comparing the metering data of the first type of metering equipment with the daily average electricity consumption of the user, the influence on the judgment of suspicious equipment caused by weather change/electricity utilization arrangement adjustment (for example, power failure) can be avoided while the electricity utilization habit of the user is fully considered, and the range of the metering equipment to be detected can be accurately reduced.

In some embodiments, the preset conditions corresponding to different metering devices of the first type are different, i.e. the preset threshold ranges are different. In some embodiments, the preset threshold range for each first type of metering device may be varied.

In some embodiments, the preset threshold range may be related to the degree of user influence. For example, the greater the degree of user influence, the greater the interval length of the preset threshold range. The user influence degree of the user terminal corresponding to each first type of metering device may be different, and accordingly, the preset threshold range corresponding to each first type of metering device may be variable.

In some embodiments, the preset threshold range may be determined by the differential mean and the regulatory threshold. For example, the preset threshold range may be (differential mean minus regulatory threshold, differential mean plus regulatory threshold). The difference average value refers to an average value of a plurality of differences between metering data of a plurality of metering devices of the first type and daily average power consumption of a user. The regulation threshold value refers to a numerical condition which is set according to the influence degree of a user and used for determining a preset threshold value range. The regulatory threshold may be positively correlated to the degree of user impact.

The degree of user influence is a condition that can be used to measure the influence of different users. In some embodiments, the user influence level may be calculated by the following equation (1):

user influence degree = variance B ++a×100% (1)

The variance A represents the variance of the daily average power consumption of a user of any second type metering device on the bus in a period of time, and the variance B represents the variance of the daily average power consumption of a first type metering device on a certain sub-line on the bus in the period of time.

In the embodiment of the specification, the preset threshold range is determined according to the influence degree of the user, so that suspicious equipment is determined from the first metering equipment according to the preset threshold range, the influence of external factors on different users is considered, and the accuracy of determining the suspicious equipment is improved. When the user's influence degree is larger, the electricity consumption amount representing the user is more influenced by external factors (e.g., weather, etc.), the regulation threshold value regulated by the user's influence degree can be appropriately increased.

In some embodiments, when the difference between the metering data of the first type of metering device and the user's average daily power usage is not within a preset threshold, the processor 150 may also determine the suspect device further based on other power usage data of the user. The suspicious equipment is determined through other electricity data, so that misjudgment caused by special conditions, such as traveling, forgetting to turn off the electric equipment, and the like, can be eliminated, and the accuracy of determining the suspicious equipment is improved.

In some embodiments, the other power usage data may include at least one or more of a type of power usage, a time of power usage of the power usage, a length of power usage, and the like.

In some embodiments, the processor 150 may determine whether the user is at home for the current day based on other electricity usage data of the corresponding user of the first type of metering device. In response to the user being at home the day, the first type of metering device having a difference between the metering data of the first type of metering device and the daily average power consumption of the user exceeding an upper limit of a preset threshold range may be determined to be a suspicious device. In some embodiments, processor 150 may preset the candidate device set in advance and may determine that the user is at home if there are devices in the candidate device set in the user's type of powered device. Otherwise, it may be determined that the user is not at home. Exemplary candidate device sets may include water heaters, cooktops, air conditioners, and the like.

In some embodiments, the processor 150 may also determine a suspicious device based on the associated user when the difference between the metering data for the first type of metering device and the average daily power usage for the user is not within a preset threshold and it is determined that a certain user is at home for the same day. An associated user refers to another user who has a certain correlation with the daily power consumption of the user. For example, when the difference is not within the preset threshold range and it is determined that the user a is at home on the same day, if the power utilization state of the user a associated with the user a is normal, the first type metering device corresponding to the user a may be determined as the suspicious device.

In some embodiments, processor 150 may plot a change in the daily power usage of the users from the metering data corresponding to the different users and determine users with similarities between the change graphs above a similarity threshold as associated users. If there are multiple users with a similarity above the threshold, the user with the highest similarity may be determined to be the associated user.

In the embodiment of the specification, the suspicious equipment is determined by associating the user, so that misjudgment caused by special conditions can be further eliminated, and the accuracy of determining the suspicious equipment is improved.

In some embodiments, the processor 150 may determine the target device from the at least one suspect device by a preset method. The preset method may be various implementable methods for determining the target device from among a plurality of suspicious devices.

In some embodiments, the preset method may be: when it is determined that at least one metering device fails by determining that metering data of a plurality of metering devices of a second type on a bus is inconsistent, the metering devices of the second type, which indicate that the metering device possibly fails, are metering devices of the second type, all metering devices of the second type on the bus can be determined to be target devices, and all metering devices of the second type can be detected. Since the number of the second type of metering devices is significantly smaller than that of the first type of metering devices, the detection cost can be effectively saved.

In some embodiments, the preset method may be: and determining the fault probability of at least one suspicious device, and determining the target device according to the fault probability of the at least one suspicious device.

In some embodiments, processor 150 may analyze the environment, historical overhaul data, etc. in which the at least one suspect device is located to determine a probability of failure of the at least one suspect device. The probability of failure may represent the likelihood of a suspected device failing.

In some embodiments, processor 150 may also determine a fault type and/or probability of the fault for the at least one suspect device based on the predictive model. For more description of the predictive model see fig. 3.

In some embodiments, processor 150 may determine a suspicious device with a probability of failure above a probability threshold as the target device. The probability threshold is a threshold condition for judging whether or not the suspicious device can be regarded as the target device. The probability threshold may be a system preset value, a human preset value, etc., or any combination thereof.

In the embodiment of the specification, the suspicious device is determined through analyzing the target data, and the target device is further determined from the suspicious devices, so that the range of the metering device to be detected can be reduced, the calculated amount is reduced, and the detection efficiency is improved.

In some embodiments, the processor 150 may also be used to determine a detection route for the target device. The detection route is the detection sequence of the target devices located at different positions in the power grid.

In some embodiments, the processor 150 may determine the detection route based on a failure probability of the target device and/or a span length of a preset threshold range of users corresponding to the first type of metering device.

In some embodiments, the detection route may be to detect the target device in order of high-to-low probability of failure.

In some embodiments, the detection route may be based on a sequence of the interval length of the preset threshold range from long to short, and the target device is detected. The larger the interval length of the preset threshold range of the user corresponding to the first type of metering equipment is, the higher the fault probability is, the higher the possibility of abnormality occurrence is and/or the possibility of abnormality is more serious, and the target equipment can be preferentially detected.

In some embodiments, the processor 150 may also comprehensively consider the failure probability of the target device and the interval length of the preset threshold range of the user corresponding to the first type of metering device to rank the detection sequence of the target device.

In some embodiments, processor 150 may determine at least one candidate detection route by way of route simulation based on at least one target device. The route simulation method may be to obtain a candidate detection route including at least one target device based on a preset route simulation algorithm. The preset route simulation algorithm may comprise any algorithm model that can implement route simulation.

In some embodiments, the processor 150 may determine a route redundancy for each of the at least one candidate detected route, and determine the detected route for the target device based on the route redundancy.

Route redundancy may reflect the degree of duplication of the same target device in the detected route. For example, in a detected route, the higher the number of repeated rounds of at least one target device, the higher the route redundancy. In some embodiments, the detected route with the least route redundancy may be taken as the target detected route.

In some embodiments, the processor 150 may determine the route redundancy for each of the at least one candidate detected route based on preset rules.

The preset rule may refer to a correlation rule for determining route redundancy. In some embodiments, the preset rules may be set according to the actual requirements of the inspection, or may be set empirically by one skilled in the art.

In some embodiments, the preset rules may include: determining, for each of the at least one candidate detection route, a number of passes per target device traversed by the certain candidate detection route; determining the number of singular point positions based on the number of paths of each target device; route redundancy of the candidate detected route is determined based on the number of singular point positions.

A pathway refers to a line (e.g., a grid line, etc.) that connects between a certain target device and another target device. Each target device may have a path with one or more other target devices, i.e. there is at least one path per target device. The number of paths may be determined based on the grid line graph.

The singular point position refers to the position of the target device whose number of passages is an odd number. The number of singular point positions refers to the number of target devices whose number of paths is an odd number. By judging whether the number of passes of a certain target device in at least one target device is an odd number, it is possible to determine whether the target device is a singular point position, and further it is possible to determine the number of singular point positions in at least one target device.

In some embodiments, when the number of singular point locations is 0 or 2, the processor 150 may determine that the route redundancy is 0.

In some embodiments, when the number of singular point positions is not 0 or 2, the processor 150 may match the other singular point positions except the start point and the end point in a certain candidate detection route by two, and add a repeated line segment based on the original path of the two singular point positions. And determining the route redundancy of the candidate detection route according to the condition of the added line segments. For example, the total length of the added line segments (the total length is determined by adding the respective lengths of the added line segments) is determined as the route redundancy. For another example, the number of added line segments is determined as route redundancy.

In the embodiment of the specification, whether at least one metering device fails or not is judged through the target data, and when the failure is determined, the detection instruction is sent out again, so that whether the metering device fails or not can be monitored in real time by integrating multiple factors, and when the failure is determined, the detection range is timely reduced by determining the target device, so that the detection efficiency is effectively improved, the detected failure device is overhauled, and the electricity fee loss possibly caused by the equipment problem is avoided.

It should be noted that the above description of the flow 200 and the flow 300 is for illustration and description only, and is not intended to limit the scope of applicability of the present description. Various modifications and changes to flow 200 and flow 300 may be made by those skilled in the art under the guidance of this specification. However, such modifications and variations are still within the scope of the present description.

FIG. 3 is an exemplary schematic diagram of an application prediction model shown in accordance with some embodiments of the present description.

In some embodiments, processor 150 may determine a fault type 350 and/or a fault probability 360 for at least one suspect device based on predictive model 300.

The predictive model 300 may be a machine learning model, such as a neural network model, a recurrent neural network model, or the like, or any combination thereof.

Inputs to the predictive model 300 may include grid environmental photographs 311, historical overhaul data 312 for the suspect device, environmental factors 313, metering data 314 for the suspect device, user average daily power 315, etc., and outputs of the predictive model 300 may include fault types 361 and fault probabilities 362 for the suspect device. See fig. 2 for more description of environmental factors, metering data, and user daily average power usage.

In some embodiments, the predictive model 300 may include an environmental feature extraction layer 310, a service feature extraction layer 320, a wear value estimation layer 330, and a fault prediction layer 350. In some embodiments, the environmental feature extraction layer 310, the overhaul feature extraction layer 320 may be a model such as CNN, and the wear value estimation layer 330, the fault prediction layer 350 may be a model such as NN.

In some embodiments, the input of the environmental feature extraction layer 310 is a grid environmental photograph 311 and the output is an environmental feature vector 312. The environmental feature vector 4312 may characterize the impact of the natural environment on the power device. Grid environment photographs 311 may include photographs of the environment surrounding the power devices (e.g., first and second types of metering devices), such as surrounding vegetation photographs, river photographs, hills photographs, and the like. The environmental feature vector 312 is a feature vector related to the surrounding environment of the power device.

In some embodiments, the input to the overhaul feature extraction layer 320 is historical overhaul data 312 for the suspicious device and the output is an overhaul feature vector 342. The historical overhaul data 312 of the suspicious device may include information about the suspicious device number, overhaul times, fault types, overhaul times, etc. The service feature vector 342 is a feature vector associated with historical service data of the suspect device.

In some embodiments, the wear value estimation layer 330 has an input of a service feature vector 342 and an output of estimated wear values 343 for suspected equipment.

In some embodiments, the inputs of the fault prediction layer 350 are the environmental feature vector 341, the predicted wear value 343 of the suspicious device, the environmental factor 313, the metering data 314 of the suspicious device, the daily average power consumption 315 of the user, the fault type 361 of the suspicious device and the fault probability 362.

In some embodiments, the input of the fault prediction layer 350 may further include a user influence level (not shown in fig. 3). The condition that different users are influenced by external factors is considered when the fault probability is judged according to the influence degree of the users, so that the fault probability is determined more accurately. See fig. 2 for a more explanation of the extent of user influence.

In some embodiments, the outputs of the environmental feature extraction layer 310, the overhaul feature extraction layer 320, and the wear value estimation layer 330 may be inputs of the failure prediction layer 350, and the environmental feature extraction layer 310, the overhaul feature extraction layer 320, the wear value estimation layer 330, and the failure prediction layer 350 may be jointly trained.

In some embodiments, the second training samples for joint training may include a sample grid environment photograph, historical overhaul data of the sample suspicious device, sample environmental factors, metering data of the sample suspicious device, daily average power consumption of the sample user, and the second labels corresponding to the second training samples may be actual fault types and/or actual fault probabilities of the sample suspicious device. When the sample suspicious equipment has faults, the actual fault probability is 1.

In some embodiments, the second training sample may be determined based on historical data. The second tag may be determined by manual annotation. For example, the second label may be labeled (a, 0) or (a, 1), where a represents a fault type, 0 represents a fault that did not occur for that fault type, and 1 represents a fault that occurred for that fault type.

An exemplary joint training process includes: inputting the environmental photo of the sample power grid into an initial environmental feature extraction layer to obtain an environmental feature vector output by the initial environmental feature extraction layer; inputting historical overhaul data of the sample suspicious equipment into an initial overhaul feature extraction layer to obtain an overhaul feature vector output by the initial environmental feature extraction layer; the environmental feature vector and the maintenance feature vector are used as training data, and the environmental factors of the sample, the metering data of the sample suspicious equipment and the daily average power consumption of the sample user are input into an initial fault prediction layer to obtain the fault type and the fault probability of the sample suspicious equipment output by the initial fault prediction layer; and updating parameters of the model based on the second label and the output establishment loss function of the initial fault prediction layer until the preset condition is met, and finishing training. Until the preset condition is satisfied, the training is completed.

In some embodiments, the output of the overhaul feature extraction layer 320 may be the input of the wear value estimation layer 330, and the overhaul feature extraction layer 320 and the wear value estimation layer 330 may be separately obtained by performing joint training. In some embodiments, the corresponding third training sample includes historical overhaul data of the sample suspicious device, and the third label corresponding to the third training sample is an estimated wear value of the sample suspicious device. In some embodiments, the third training sample may be determined based on historical data. The third tag may be determined by manual annotation. For example, after multiple overhauls, the appearance of each element (such as copper sheet, inner wire insulation cover, etc.) of the suspicious equipment can be compared with the appearance difference between each element of the metering equipment with the same model when just leaving the factory, and the larger the appearance difference is, the larger the estimated wear value is marked manually.

In the embodiment of the specification, the fault probability and the fault type of the suspicious equipment are determined through the prediction model, so that the target equipment is determined, the suspicious equipment with higher fault probability can be accurately screened out to serve as the target equipment, the detection efficiency is effectively improved, and meanwhile, the fault type output by the prediction model can provide references for related technicians to perform fault rechecking on the metering equipment. The parameters of the prediction model are obtained through the training mode, so that the problem that labels are difficult to obtain when the environment feature extraction layer and the maintenance feature extraction layer are independently trained can be solved, and the environment feature extraction layer and the maintenance feature extraction layer can better reflect the environment features and the maintenance features.

While the basic concepts have been described above, it will be apparent to those skilled in the art that the foregoing detailed disclosure is by way of example only and is not intended to be limiting. Although not explicitly described herein, various modifications, improvements, and adaptations to the present disclosure may occur to one skilled in the art. Such modifications, improvements, and modifications are intended to be suggested within this specification, and therefore, such modifications, improvements, and modifications are intended to be included within the spirit and scope of the exemplary embodiments of the present invention.

Meanwhile, the specification uses specific words to describe the embodiments of the specification. Reference to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the present description. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the present description may be combined as suitable.

Furthermore, the order in which the elements and sequences are processed, the use of numerical letters, or other designations in the description are not intended to limit the order in which the processes and methods of the description are performed unless explicitly recited in the claims. While certain presently useful inventive embodiments have been discussed in the foregoing disclosure, by way of various examples, it is to be understood that such details are merely illustrative and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements included within the spirit and scope of the embodiments of the present disclosure. For example, while the system components described above may be implemented by hardware devices, they may also be implemented solely by software solutions, such as installing the described system on an existing server or mobile device.

Likewise, it should be noted that in order to simplify the presentation disclosed in this specification and thereby aid in understanding one or more inventive embodiments, various features are sometimes grouped together in a single embodiment, figure, or description thereof. This method of disclosure, however, is not intended to imply that more features than are presented in the claims are required for the present description. Indeed, less than all of the features of a single embodiment disclosed above.

In some embodiments, numbers describing the components, number of attributes are used, it being understood that such numbers being used in the description of embodiments are modified in some examples by the modifier "about," approximately, "or" substantially. Unless otherwise indicated, "about," "approximately," or "substantially" indicate that the number allows for a 20% variation. Accordingly, in some embodiments, numerical parameters set forth in the specification and claims are approximations that may vary depending upon the desired properties sought to be obtained by the individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and employ a method for preserving the general number of digits. Although the numerical ranges and parameters set forth herein are approximations that may be employed in some embodiments to confirm the breadth of the range, in particular embodiments, the setting of such numerical values is as precise as possible.

Each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, etc., referred to in this specification is incorporated herein by reference in its entirety. Except for application history documents that are inconsistent or conflicting with the content of this specification, documents that are currently or later attached to this specification in which the broadest scope of the claims to this specification is limited are also. It is noted that, if the description, definition, and/or use of a term in an attached material in this specification does not conform to or conflict with what is described in this specification, the description, definition, and/or use of the term in this specification controls.

Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments of this specification. Other variations are possible within the scope of this description. Thus, by way of example, and not limitation, alternative configurations of embodiments of the present specification may be considered as consistent with the teachings of the present specification. Accordingly, the embodiments of the present specification are not limited to only the embodiments explicitly described and depicted in the present specification.

Claims

1. A business center-based power marketing digitizing system, the system comprising: the device comprises a metering module, a historical electricity consumption module, a device operation and maintenance module, an instruction processing module and a processor, wherein the historical electricity consumption module, the device operation and maintenance module, the instruction processing module and the processor are in communication connection;

the metering module is deployed at the front end of the system and is used for monitoring metering data of at least one metering device at least one position in the power grid and sending the metering data to the historical electricity utilization module for storage;

the historical electricity utilization module is deployed at the rear end of the system and is used for storing historical electricity utilization data;

the equipment operation and maintenance module is deployed at the rear end of the system and is used for storing historical overhaul data of the metering equipment;

The instruction processing module is used for receiving a detection instruction and a detection route sent by the processor and displaying the detection instruction and the detection route;

the processor is configured to:

acquiring target data, wherein the target data comprises at least one of the metering data, the historical electricity consumption data and the historical overhaul data;

based on the target data, judging whether the failure occurrence rate of the at least one metering device meets a preset detection condition, including:

determining a metering difference between the second type of metering data and the first type of metering data; the second type of metering data is metering data of any second type of metering equipment, and the first type of metering data is the sum of metering data of at least one first type of metering equipment; the first type metering equipment is metering equipment arranged at a user end, and the second type metering equipment is equipment arranged at a management end;

judging whether the failure occurrence rate of the at least one metering device meets the preset detection condition or not based on comparison of the metering difference value and a first threshold value; wherein,

the first threshold is related to circuit loss, the circuit loss is determined through a loss model, the loss model is a machine learning model, the input of the loss model comprises environmental factors, the length of a line in a power grid and the power grid voltage, and the output of the loss model comprises the circuit loss; the accuracy of the loss model is determined based on comparing the output of the loss model with a first tag during training;

Responding to the failure occurrence rate of the at least one metering device to meet a preset detection condition, determining a target device and sending out the detection instruction according to the target device; determining the target device includes:

determining the daily average power consumption of the user based on the target data;

determining whether the difference is in a preset threshold range according to the difference between the metering data of each metering device of the first type and the daily average power consumption of the user; the preset threshold range is related to user influence degrees, the user influence degrees of the user sides corresponding to the first type metering devices are different, the preset threshold range is determined based on a difference average value and a regulation threshold value, the difference average value refers to an average value of a plurality of differences between metering data of a plurality of first type metering devices and daily average power consumption of the user, and the regulation threshold value is positively related to the user influence degrees;

determining at least one suspicious device based on the power utilization state of the associated user when the difference is not within the preset threshold range and the user corresponding to the at least one first metering device is judged to be at home;

wherein the associated user is determined based on the similarity between the change graphs of the daily electricity quantity of the user,

The change curve graph of the daily electricity consumption is drawn based on metering data corresponding to a user;

determining a target device from the at least one suspicious device through a preset method;

the processor is further configured to determine a detection route of the target device based on a failure probability of the target device and/or a section length of the preset threshold range of the user corresponding to the first type of metering device, where the detection route includes:

determining a detection sequence of the target equipment based on the fault probability of the target equipment and/or the interval length of the preset threshold range of the user corresponding to the first type metering equipment, and determining the detection route based on the detection sequence; or alternatively

Determining at least one candidate detection route based on at least one of the target devices;

determining, for each of the at least one candidate detection route, a number of passes of each of the target devices traversed by the candidate detection route; the path refers to a line connected between any one of the target devices and another one of the target devices;

determining a number of singular point locations based on the number of passes of each of the target devices; the number of the singular point positions refers to the number of the target devices with the odd number of the paths;

Determining route redundancy of the candidate detection route based on the number of singular point positions; the route redundancy reflects the degree of repetition of the same target device in the candidate detection route;

a detected route of the target device is determined from the at least one candidate detected route based on the route redundancy.

2. The system of claim 1, wherein the determining, by a preset method, the target device from the at least one suspect device comprises:

determining the fault type and/or fault probability of the at least one suspicious device based on a prediction model, wherein the prediction model is a machine learning model;

and determining the target equipment based on the fault probability.

3. The utility model provides a business center based electric power marketing digitalization method which is characterized in that the business center based electric power marketing digitalization method is realized by a business center based electric power marketing digitalization system, the system comprises: the device comprises a metering module, a historical electricity consumption module, a device operation and maintenance module, an instruction processing module and a processor, wherein the historical electricity consumption module, the device operation and maintenance module, the instruction processing module and the processor are in communication connection;

The method is performed by the processor and includes:

acquiring target data, wherein the target data comprises at least one of metering data, historical electricity consumption data and historical overhaul data;

Responding to the failure occurrence rate of the at least one metering device to meet a preset detection condition, determining a target device and sending a detection instruction according to the target device; determining the target device includes:

the method further comprises: determining a detection route of the target device based on the fault probability of the target device and/or the interval length of the preset threshold range of the user corresponding to the first type metering device, including:

4. A method according to claim 3, wherein said determining said target device from said at least one suspect device by a predetermined method comprises:

and determining the target equipment based on the fault probability.

5. A business-board-based power marketing digitizing apparatus, comprising at least one processor for performing the business-board-based power marketing digitizing method of any of claims 3-4.

6. A computer readable storage medium storing computer instructions which, when executed by a processor, implement the business center-based power marketing digitization method of any of claims 3-4.