User side electric leakage judgment method and device, equipment and medium

Abstract

The invention discloses a user side electric leakage judgment method and device, equipment and a medium. The method comprises the following steps: acquiring power data of a user side in a set time period of a current month and a previous month; wherein the electric power data are acquired in real time through electric power metering equipment installed on a user side; based on a predetermined target electric leakage characteristic of a user side, extracting a data value of the electric power data corresponding to the target electric leakage characteristic; wherein the target electric leakage characteristic at least comprises an electric quantity trend decrease rate, a line loss rate, a current fluctuation rate and a power factor; and inputting the data value of the target electric leakage characteristic into a pre-trained electric leakage judgment model, and judging whether electric leakage exists on the user side or not according to an output result of the electric leakage judgment model. According to the technical scheme, the intelligent level of the electric leakage monitoring process is improved, and the electric leakage condition is judged more efficiently and accurately.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power monitoring, and in particular to a user-side leakage judgment method, device, equipment and medium. Background Art

[0002] Leakage detection is widely used in various fields. It is a necessary means to ensure the safety of electrical equipment and lines, protect personnel safety, increase equipment life, save energy and reduce emissions, and improve system stability. Therefore, regular leakage detection is an indispensable part of electrical equipment and line maintenance.

[0003] In the existing technology, the monitoring of leakage on the user side usually relies mainly on manual inspections and traditional simple equipment detection, and the power parameters concerned are also relatively single, which is not only time-consuming and labor-intensive, but also has a high risk of missed detection and false alarm. Summary of the invention

[0004] The present invention provides a user-side leakage judgment method, device, equipment and medium to improve the intelligence level of the leakage monitoring process and achieve more efficient and accurate judgment of the leakage situation.

[0005] According to one aspect of the present invention, a method for determining leakage at a user side is provided, the method comprising:

[0006] Obtaining the power data of the user side within a set time period of the current month and the previous month; wherein the power data is collected in real time by the power metering equipment installed on the user side;

[0007] Based on a predetermined target leakage characteristic of the user side, extracting a data value of the power data corresponding to the target leakage characteristic; wherein the target leakage characteristic includes at least a power trend decrease rate, a line loss rate, a current fluctuation rate and a power factor;

[0008] The data value of the target leakage characteristic is input into a pre-trained leakage judgment model, and based on the output result of the leakage judgment model, it is judged whether there is leakage on the user side.

[0009] According to another aspect of the present invention, a user-side leakage judgment device is provided, the device comprising:

[0010] The power data acquisition module is used to acquire the power data of the user side within a set time period of the current month and the previous month; wherein the power data is collected in real time by the power metering equipment installed on the user side;

[0011] A data value extraction module, configured to extract a data value of the power data corresponding to the target leakage feature based on a predetermined target leakage feature of the user side; wherein the target leakage feature includes at least a power trend decrease rate, a line loss rate, a current fluctuation rate and a power factor;

[0012] The leakage judgment module is used to input the data value of the target leakage feature into a pre-trained leakage judgment model, and judge whether there is leakage on the user side according to the output result of the leakage judgment model.

[0013] According to another aspect of the present invention, there is provided an electronic device, the electronic device comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the user-side leakage judgment method described in any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the user-side leakage judgment method described in any embodiment of the present invention when executed.

[0018] According to another aspect of the present invention, a computer program product is provided, comprising a computer program / instruction, wherein when the computer program / instruction is executed by a processor, the user-side leakage determination method as described in any embodiment of the present invention is implemented.

[0019] The technical solution of the embodiment of the present invention obtains the user's power data in the set time period of the current month and the previous month through real-time collection of power metering equipment installed on the user side, and extracts the data value of each target leakage feature in the power data based on the predetermined multi-dimensional target leakage feature as the input of the trained leakage judgment model, so that the judgment of whether there is leakage on the user side can be realized according to the input result of the leakage judgment model, thereby avoiding the risk of missed detection and false alarm caused by manual inspection and simple equipment detection, significantly improving the intelligence level of corresponding leakage monitoring, and at the same time helping to realize more efficient and accurate judgment of corresponding leakage situations.

[0020] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 This is a flow chart of a method for determining leakage at a user side provided according to Embodiment 1 of the present invention.

[0023] Figure 2 This is a flow chart of another method for determining leakage at a user side provided according to the second embodiment of the present invention.

[0024] Figure 3 It is a structural schematic diagram of a user-side leakage judgment device provided according to Embodiment 3 of the present invention.

[0025] Figure 4 It is a structural schematic diagram of an electronic device for implementing the user-side leakage judgment method of an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] Figure 1This is a flow chart of a method for judging leakage on the user side provided in the first embodiment of the present invention. This embodiment can be applied to the case where leakage judgment is performed based on multi-dimensional features corresponding to the power data on the user side. The method can be performed by a device for judging leakage on the user side. The device can be implemented in the form of hardware and / or software, and the device can be configured in an electronic device. Figure 1 Said method comprises:

[0029] S110, obtaining power data of the user side within a set time period of the current month and the previous month; wherein the power data is collected in real time by a power metering device installed on the user side.

[0030] Among them, the user side may be an end user or unit that uses electricity, such as residential households, commercial institutions, and industrial enterprises. The current month may be the month to which the current leakage detection date belongs, and the current leakage detection date may be the date on which the leakage detection is currently being performed. The set time period may be the number of days corresponding to the dates before the date to which the current leakage detection date belongs in the current month or the previous month. For example, the current leakage detection date may be the 14th of the current month, and accordingly, the set time period may be the 13 days corresponding to the 1st to the 13th before the 14th in the current month or the previous month. The power data may include at least one of the data types such as voltage data, current data, power data, and power consumption data. The power metering device may include current sensors and voltage sensors, etc.

[0031] S120. Based on a predetermined target leakage characteristic of the user side, extract the data value of the power data corresponding to the target leakage characteristic; wherein the target leakage characteristic includes at least a power trend decrease rate, a line loss rate, a current fluctuation rate and a power factor.

[0032] Among them, the target leakage characteristic can be selected and determined in advance based on experience or needs. The target leakage characteristic can be used to characterize whether there is leakage on the corresponding user side. The power trend decline rate can be used to characterize the changing trend of power consumption on the user side. When the power trend decline rate is greater than the first set threshold, it can indicate that there may be leakage on the user side. The line loss rate can be used to characterize the power loss in the area where the user side is located within a set time period. The current fluctuation rate can be used to characterize the degree of fluctuation of the current value. If the current fluctuation rate exceeds the second set threshold, it can indicate that there may be leakage or other abnormal conditions on the user side. The power factor can be used to characterize the efficiency of the user side for electrical equipment. Under normal circumstances, the power factor can be a set value, which can be 1 or in a neighboring value interval of 1. The corresponding neighboring value interval can be set according to experience or needs, for example, it can be a value interval [0.9,1] less than 1. If the difference between the corresponding set value and the power factor is greater than the third set threshold, it can indicate that there may be leakage or insufficient reactive power compensation on the user side. The above-mentioned first set threshold, the second set threshold and the third set threshold can all be set according to experience or needs.

[0033] Specifically, the determined target leakage characteristics and corresponding power data can be used as inputs to a pre-trained network model, and the data values ​​of each target leakage characteristic corresponding to the power data can be output. The network model can be a neural network model or a machine learning model.

[0034] S130: Input the data value of the target leakage characteristic into a pre-trained leakage judgment model, and judge whether there is leakage on the user side according to the output result of the leakage judgment model.

[0035] The output result of the leakage judgment model may be leakage or no leakage. Accordingly, when the output result of the leakage judgment model is leakage, it can be determined that there is leakage on the user side; when the output result of the leakage judgment model is no leakage, it can be determined that there is no leakage on the user side.

[0036] The technical solution of the embodiment of the present invention obtains the user's power data in the set time period of the current month and the previous month through real-time collection of power metering equipment installed on the user side, and extracts the data value of each target leakage feature in the power data based on the predetermined multi-dimensional target leakage feature as the input of the trained leakage judgment model, so that the judgment of whether there is leakage on the user side can be realized according to the input result of the leakage judgment model, thereby avoiding the risk of missed detection and false alarm caused by manual inspection and simple equipment detection, significantly improving the intelligence level of corresponding leakage monitoring, and at the same time helping to realize more efficient and accurate judgment of corresponding leakage situations.

[0037] Figure 2 This is a flow chart of a user-side leakage judgment method provided in Embodiment 2 of the present invention. This embodiment is further optimized based on the above embodiments. It should be noted that for the parts not described in detail in this embodiment, please refer to the relevant descriptions in other embodiments.

[0038] Furthermore, before "based on the predetermined target leakage feature on the user side, extracting the data value of the power data corresponding to the target leakage feature", add "determining whether there is a missing actual daily power consumption in the power data; wherein the actual power consumption is the daily power consumption on the user side within the set time period counted by the power metering device; if so, determining the date on which the actual power consumption is missing, and setting the actual power consumption corresponding to the date to a specified value; wherein the specified value is 0 or a null value; determining the theoretical daily power consumption within the set time period corresponding to the power data based on the current data and voltage data in the power data, and calculating the difference between the theoretical power consumption and the actual power consumption on the corresponding date counted by the power metering device; if the difference is greater than a preset power consumption abnormality judgment threshold, determining the actual power consumption on the corresponding date as an abnormal value, and adopting a preset correction algorithm to correct the abnormal value" to achieve preprocessing of the acquired power data.

[0039] refer to Figure 2 , the method specifically comprises the following steps:

[0040] S210, obtaining power data of the user side within a set time period of the current month and the previous month; wherein the power data is collected in real time by a power metering device installed on the user side.

[0041] S220. Determine whether there is a missing amount of actual daily power consumption in the power data; wherein the actual power consumption is the daily power consumption of the user side within the set time period counted by the power metering device.

[0042] S230: If yes, determine that there is a date on which the actual power consumption is missing, and set the actual power consumption corresponding to the date to a specified value; wherein the specified value is 0 or a null value.

[0043] Specifically, if it is determined that there is no missing actual daily power consumption in the corresponding power data, you can choose to continue to execute the following step 240.

[0044] For example, if it is determined that there are missing values ​​in the actual daily power consumption in the power data, interpolation, average filling or deletion can be used.

[0045] S240. Determine theoretical power consumption per day within a set time period corresponding to the power data based on current data and voltage data in the power data, and calculate the difference between the theoretical power consumption and actual power consumption on the corresponding date counted by the power metering device.

[0046] The theoretical power consumption may be a theoretical calculated value of the daily power consumption in the area where the user is located, determined based on the current data and voltage data measured by the power metering equipment.

[0047] Specifically, the daily current average value and the daily voltage average value corresponding to each day can be determined based on the daily current data and voltage data included in the power data. Accordingly, the daily theoretical power consumption can be calculated based on the daily current average value and the daily voltage average value.

[0048] S250: If the difference is greater than a preset power consumption abnormality judgment threshold, the actual power consumption on the corresponding date is determined to be an abnormal value, and a preset correction algorithm is used to correct the abnormal value.

[0049] The power abnormality judgment threshold can be set according to needs or experience, for example, it can be twice the actual power consumption on the corresponding date.

[0050] Specifically, the month to which the date corresponding to the abnormal value belongs can be determined, and the average or median of the actual power consumption of other dates in the set time period corresponding to the month except the date corresponding to the abnormal value can be determined. Accordingly, the corresponding abnormal value can be corrected based on the average or median.

[0051] S260. Based on a predetermined target leakage characteristic on the user side, extract the data value of the power data corresponding to the target leakage characteristic; wherein the target leakage characteristic includes at least a power trend decrease rate, a line loss rate, a current fluctuation rate and a power factor.

[0052] In an optional embodiment, the corresponding method may further include: converting each data type in the corresponding power data into a unified format and unit.

[0053] In an optional embodiment, the corresponding target leakage characteristic may be determined by:

[0054] Based on the historical leakage data and the historical non-leakage data, the candidate leakage feature of the user side is determined; wherein the candidate leakage feature is a feature type in which the difference between the value when leakage occurs and the value when no leakage occurs is greater than a preset feature determination threshold; based on the value of the candidate leakage feature when leakage occurs on the user side and the corresponding leakage amount, the correlation between the candidate leakage feature and the leakage on the user side is determined, and the candidate leakage feature that meets the set correlation threshold corresponding to the correlation is used as the target leakage feature.

[0055] Among them, the historical leakage data may be the power data corresponding to the existence of leakage on the user side determined before the current leakage detection date, and the historical no-leakage data may be the power data corresponding to the existence of leakage on the user side before the current leakage detection date. The candidate leakage features may include at least one of the feature types such as the power trend decline rate, line loss rate, current fluctuation rate and power factor. The preset feature determination threshold and the set correlation threshold may be set according to experience or needs. The candidate leakage feature that meets the set correlation threshold corresponding to the correlation may be a candidate leakage feature whose correlation is greater than the set correlation threshold.

[0056] Specifically, a mapping relationship database between the numerical values ​​of different candidate leakage characteristics when leakage occurs on the user side and the corresponding leakage amounts, and the corresponding correlation degrees can be established in advance. Accordingly, when determining the numerical values ​​of the corresponding candidate leakage characteristics when leakage occurs on the user side and the corresponding leakage amounts, the corresponding correlation degrees can be matched by traversing the mapping relationship database, and the matched correlation degrees can be used as the correlation degree between the candidate leakage characteristic and the leakage occurring on the user side.

[0057] It can be understood that by determining the candidate leakage feature on the user side based on the historical leakage data and the historical non-leakage data, and determining the correlation between the candidate leakage feature and the leakage on the user side based on the value of the candidate leakage feature at the user side and the corresponding leakage amount, and then using the candidate leakage feature that meets the set correlation threshold corresponding to the correlation as the target leakage feature, it is possible to achieve the importance and correlation screening of the relevant feature types at the time of leakage, which helps to avoid the situation where the complexity of the leakage judgment model is high due to the poor correlation between the selected target leakage feature and the leakage, and improve the generalization ability of the model.

[0058] In an alternative embodiment, the correlation may be a Pearson correlation coefficient.

[0059] In an optional embodiment, a pre-trained candidate leakage feature determination model can be used to take historical leakage data and historical non-leakage data as input to output corresponding candidate leakage features. The candidate leakage feature determination model can be a neural network model or a machine learning model.

[0060] S270: Input the data value of the target leakage characteristic into a pre-trained leakage judgment model, and judge whether there is leakage on the user side according to the output result of the leakage judgment model.

[0061] In an optional embodiment, the corresponding method may further include:

[0062] Historical leakage data and historical non-leakage data are obtained as a training data set, and the training data set is divided into multiple subsets; any subset of the multiple subsets is used as a verification set, and other subsets outside the verification set are used as corresponding training sets, until each subset of the multiple subsets is used as a verification set at least once; a leakage judgment model is trained based on the training set, and the performance index of the trained leakage judgment model is determined through the verification set, so as to adjust the parameters of the trained candidate leakage judgment model according to the performance index.

[0063] The number of subsets divided from the training data set can be set as needed. The validation set can be used to evaluate the performance of the leakage judgment model after training, and the corresponding performance index can be used to characterize the performance of the leakage judgment model, and the performance index can include at least one of the indicators such as accuracy, recall rate and F1 score. Parameter adjustment can include at least one of increasing the number of layers of the neural network, changing the depth of the decision tree, adjusting the learning rate, adjusting the penalty coefficient C, and adjusting the kernel function type.

[0064] It can be understood that by dividing the dataset into multiple subsets, selecting one of the subsets as the validation set and the remaining subsets as the training set, then using the training set to train the model and using the validation set to evaluate the performance of the model, it helps to improve the accuracy of model evaluation, avoid overfitting, and help select the best model and parameters, while helping to enhance the generalization ability of the model.

[0065] In an optional embodiment, the data values ​​corresponding to the power trend decrease rate, line loss rate, current fluctuation rate and power factor may be determined in the following manner:

[0066] Determine the difference between the first average daily electricity consumption within the set time period of the previous month and the second average daily electricity consumption within the set time period of the current month, and use the percentage corresponding to the ratio of the difference to the first average electricity consumption as the electricity trend decline rate; determine the difference between the total power supply of the power supply area where the user side is located within the set time period of the current month and the actual total power consumption of the user side counted by the power metering equipment, and use the percentage corresponding to the ratio of the difference to the total power supply as the line loss rate; determine the standard deviation and average value of each current value in the power data within the set time period of the current month, and use the percentage corresponding to the ratio of the standard deviation to the average value as the current fluctuation rate; use the ratio of the active power and apparent power of the power equipment on the user side as the power factor.

[0067] Among them, the first average power consumption may be the average value of the actual power consumption corresponding to each day within the set time period of the previous month, and the second average power consumption may be the average value of the actual power consumption corresponding to each day within the set time period of the current month. The power supply area where the user side is located may be pre-divided as needed. The line loss rate can be used to compare with the historical line loss rate corresponding to the historical power data, and determine the corresponding difference. Correspondingly, if the difference is greater than the set line loss rate difference threshold, it can be determined that there is an abnormal increase in the line loss rate. The historical line loss rate may be the line loss rate corresponding to the set time period of the month before the current month. Abnormal growth may indicate that there may be leakage on the user side.

[0068] In an optional embodiment, the leakage judgment model may be a support vector machine model or a neural network model. Optionally, the leakage judgment model may also be a decision tree model or a time series analysis model, and the time series analysis model may be an ARIMA model or an LSTM model.

[0069] It can be understood that by selecting the corresponding support vector machine model or neural network model to train the leakage judgment model, the intelligence level of the corresponding leakage detection process is improved, which helps to achieve more efficient and accurate judgment of the leakage situation.

[0070] In an optional embodiment, the corresponding method may further include:

[0071] If it is determined that there is leakage on the user side, the power supply system will be controlled to send out a warning signal, and a corresponding power consumption plan or treatment measure will be generated and sent to the user.

[0072] It is understandable that when a leakage is detected, the control power supply system will immediately send out an early warning signal, and generate and send to the user a recommended power consumption plan or treatment measure based on the actual situation. This real-time response and intelligent decision-making capabilities help power supply companies quickly respond to leakage events, reduce losses, and improve customer satisfaction.

[0073] In an optional embodiment, the area range and warning threshold for leakage detection can be configured according to actual conditions. The warning threshold can be used to control the power supply system to issue a warning signal when the leakage amount corresponding to the current leakage detection is not exceeded.

[0074] In an embodiment of the present invention, by determining missing values ​​and abnormal values ​​in the corresponding power data and correcting the missing values ​​and abnormal values, data anomalies or data missing caused by data input errors, equipment failures or measurement errors can be avoided, thereby helping to ensure the integrity and accuracy of the data analysis process, and further helping to avoid the impact of noise data on model performance, thereby improving the reliability of the judgment results output by the corresponding leakage judgment model.

[0075] Figure 3 This is a schematic diagram of the structure of a user-side leakage judgment device provided in the third embodiment of the present invention. This embodiment can be applied to the case where leakage judgment is performed based on multi-dimensional features corresponding to user-side power data. The device can be implemented in the form of hardware and / or software, and the device can be configured in an electronic device. Figure 3 Said device comprises:

[0076] The power data acquisition module 310 acquires the power data of the user side within a set time period of the current month and the previous month; wherein the power data is collected in real time by the power metering equipment installed on the user side.

[0077] The data value extraction module 320 is used to extract the data value of the power data corresponding to the target leakage characteristic based on the predetermined user-side target leakage characteristic; wherein the target leakage characteristic includes at least the power trend decrease rate, line loss rate, current fluctuation rate and power factor.

[0078] The leakage judgment module 330 is used to input the data value of the target leakage feature into a pre-trained leakage judgment model, and judge whether there is leakage on the user side according to the output result of the leakage judgment model.

[0079] The technical solution of the embodiment of the present invention obtains the user's power data in the set time period of the current month and the previous month through real-time collection of power metering equipment installed on the user side, and extracts the data value of each target leakage feature in the power data based on the predetermined multi-dimensional target leakage feature as the input of the trained leakage judgment model, so that the judgment of whether there is leakage on the user side can be realized according to the input result of the leakage judgment model, thereby avoiding the risk of missed detection and false alarm caused by manual inspection and simple equipment detection, significantly improving the intelligence level of corresponding leakage monitoring, and at the same time helping to realize more efficient and accurate judgment of corresponding leakage situations.

[0080] Optionally, the target leakage characteristic may be determined by:

[0081] Based on the historical leakage data and the historical non-leakage data, the candidate leakage feature of the user side is determined; wherein the candidate leakage feature is a feature type in which the difference between the value when leakage occurs and the value when no leakage occurs is greater than a preset feature determination threshold; based on the value of the candidate leakage feature when leakage occurs on the user side and the corresponding leakage amount, the correlation between the candidate leakage feature and the leakage on the user side is determined, and the candidate leakage feature that meets the set correlation threshold corresponding to the correlation is used as the target leakage feature.

[0082] Optionally, the corresponding device may further include:

[0083] A subset division module, used for obtaining historical leakage data and historical non-leakage data as a training data set, and dividing the training data set into a plurality of subsets;

[0084] a training set and validation set determination module, configured to use any subset of the plurality of subsets as a validation set, and use other subsets other than the validation set as corresponding training sets, until each subset of the plurality of subsets is used as a validation set at least once;

[0085] The model training and verification module is used to train the leakage judgment model based on the training set, and determine the performance index of the trained leakage judgment model through the verification set, so as to adjust the parameters of the trained candidate leakage judgment model according to the performance index.

[0086] Optionally, the corresponding device may further include:

[0087] A missing determination module is used to determine whether there is a missing actual daily power consumption in the power data before extracting the data value corresponding to the target leakage characteristic of the power data based on the predetermined target leakage characteristic of the user side; wherein the actual power consumption is the daily power consumption of the user side within the set time period counted by the power metering device;

[0088] A missing value setting module, for determining a date on which the actual power consumption is missing, and setting the actual power consumption corresponding to the date to a specified value; wherein the specified value is 0 or a null value;

[0089] Theoretical power consumption determination module, used to determine the theoretical power consumption of each day within a set time period corresponding to the power data according to the current data and voltage data in the power data, and calculate the difference between the theoretical power consumption and the actual power consumption of the corresponding date counted by the power metering device;

[0090] The abnormal value correction module is used to determine that the actual power consumption on the corresponding date is an abnormal value if the difference is greater than a preset power consumption abnormality judgment threshold, and adopt a preset correction algorithm to correct the abnormal value.

[0091] Optionally, the corresponding data values ​​of the corresponding power trend decrease rate, line loss rate, current fluctuation rate and power factor may be determined in the following manner:

[0092] Determine the difference between the first average power consumption per day in the set time period of the previous month and the second average power consumption per day in the set time period of the current month, and use the percentage corresponding to the ratio of the difference to the first average power consumption as the power trend decline rate;

[0093] Determine the difference between the total power supply in the power supply area where the user side is located and the actual total power consumption of the user side counted by the power metering device within the set time period of the current month, and take the percentage corresponding to the ratio of the difference to the total power supply as the line loss rate;

[0094] Determine the standard deviation and average value of each current value in the power data within a set time period of the current month, and use the percentage corresponding to the ratio of the standard deviation to the average value as the current fluctuation rate;

[0095] The ratio of the active power and the apparent power of the electrical equipment applied by the user is used as the power factor.

[0096] Optionally, the leakage judgment model may be a support vector machine model or a neural network model.

[0097] Optionally, the corresponding device may further include:

[0098] The leakage situation processing module is used to control the power supply system to send out an early warning signal if it is determined that there is leakage on the user side, and generate corresponding power consumption plans or processing measures to send to the user.

[0099] The user-side leakage judgment device provided in the embodiment of the present invention can execute any one of the user-side leakage judgment methods provided in the embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing each user-side leakage judgment method. For the contents not described in detail in the embodiment of the present invention, reference can be made to the description in any one of the user-side leakage judgment method embodiments of the present invention.

[0100] According to an embodiment of the present invention, the present invention also provides an electronic device, a readable storage medium and a computer program product.

[0101] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0102] like Figure 4As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0103] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0104] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the user-side leakage judgment method.

[0105] In some embodiments, the user-side leakage determination method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the user-side leakage determination method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the user-side leakage determination method in any other appropriate manner (e.g., by means of firmware).

[0106] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0107] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0108] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0109] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0110] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0111] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0112] Artificial intelligence is a discipline that studies how to use computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.). It includes both hardware-level and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, machine learning / deep learning technology, big data processing technology, knowledge graph technology, and other major directions.

[0113] Cloud computing refers to a technology system that uses network access to elastically scalable shared physical or virtual resource pools. Resources can include servers, operating systems, networks, software, applications, and storage devices, and can be deployed and managed on demand and in a self-service manner. Cloud computing technology can provide efficient and powerful data processing capabilities for technical applications such as artificial intelligence and blockchain, as well as model training.

[0114] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution provided by this disclosure can be achieved, and this document does not limit this.

[0115] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for judging leakage at the user side, characterized in that: include: Obtaining the power data of the user side within a set time period of the current month and the previous month; wherein the power data is collected in real time by the power metering equipment installed on the user side; Based on a predetermined target leakage characteristic of the user side, extracting a data value of the power data corresponding to the target leakage characteristic; wherein the target leakage characteristic includes at least a power trend decrease rate, a line loss rate, a current fluctuation rate and a power factor; The data value of the target leakage characteristic is input into a pre-trained leakage judgment model, and based on the output result of the leakage judgment model, it is judged whether there is leakage on the user side.

2. The method according to claim 1, characterized in that The target leakage characteristic is determined by: Determine the candidate leakage feature of the user side according to the historical leakage data and the historical non-leakage data; wherein the candidate leakage feature is a feature type whose difference between the value when leakage occurs and the value when no leakage occurs is greater than a preset feature determination threshold; According to the value of the candidate leakage feature when leakage occurs on the user side and the corresponding leakage amount, the correlation between the candidate leakage feature and the leakage on the user side is determined, and the candidate leakage feature that meets the set correlation threshold corresponding to the correlation is used as the target leakage feature.

3. The method according to claim 1 or 2, characterized in that: Also includes: Acquire historical leakage data and historical non-leakage data as a training data set, and divide the training data set into multiple subsets; Using any subset of the multiple subsets as a validation set, and using other subsets other than the validation set as corresponding training sets, until each subset of the multiple subsets is used as a validation set at least once; The leakage judgment model is trained based on the training set, and the performance index of the trained leakage judgment model is determined through the verification set, so as to adjust the parameters of the trained candidate leakage judgment model according to the performance index.

4. The method according to claim 1, characterized in that: Before extracting the data value of the power data corresponding to the target leakage feature based on the predetermined target leakage feature of the user side, the method further includes: Based on a preset denoising algorithm, removing noise data from the power data; Determine whether there is a missing actual daily power consumption in the power data; wherein the actual power consumption is the daily power consumption of the user side within the set time period counted by the power metering device; If yes, determine that there is a date on which the actual power consumption is missing, and set the actual power consumption corresponding to the date to a specified value; wherein the specified value is 0 or a null value; Determine the theoretical power consumption of each day within a set time period corresponding to the power data according to the current data and the voltage data in the power data, and calculate the difference between the theoretical power consumption and the actual power consumption of the corresponding date counted by the power metering device; If the difference is greater than a preset power consumption abnormality judgment threshold, the actual power consumption on the corresponding date is determined to be an abnormal value, and a preset correction algorithm is used to correct the abnormal value.

5. The method according to claim 1, characterized in that The method for determining the data values ​​corresponding to the power trend decrease rate, line loss rate, current fluctuation rate and power factor is as follows: Determine the difference between the first average power consumption per day in the set time period of the previous month and the second average power consumption per day in the set time period of the current month, and use the percentage corresponding to the ratio of the difference to the first average power consumption as the power trend decline rate; Determine the difference between the total power supply in the power supply area where the user side is located and the actual total power consumption of the user side counted by the power metering device within the set time period of the current month, and take the percentage corresponding to the ratio of the difference to the total power supply as the line loss rate; Determine the standard deviation and average value of each current value in the power data within a set time period of the current month, and use the percentage corresponding to the ratio of the standard deviation to the average value as the current fluctuation rate; The ratio of the active power and the apparent power of the electrical equipment applied by the user is used as the power factor.

6. The method according to claim 1, characterized in that The leakage judgment model is a support vector machine model or a neural network model.

7. The method according to claim 1, characterized in that The method further comprises: If it is determined that there is leakage on the user side, the power supply system is controlled to send out a warning signal, and a corresponding power consumption plan or treatment measure is generated and sent to the user.

8. A user-side leakage judgment device, characterized in that: include: The power data acquisition module is used to acquire the power data of the user side within a set time period of the current month and the previous month; wherein the power data is collected in real time by the power metering equipment installed on the user side; A data value extraction module, configured to extract a data value of the power data corresponding to the target leakage feature based on a predetermined target leakage feature of the user side; wherein the target leakage feature includes at least a power trend decrease rate, a line loss rate, a current fluctuation rate and a power factor; The leakage judgment module is used to input the data value of the target leakage feature into a pre-trained leakage judgment model, and judge whether there is leakage on the user side according to the output result of the leakage judgment model.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the user-side leakage judgment method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the user-side leakage judgment method according to any one of claims 1 to 7 when executed.

Images