CN112749465A - Method, processor, storage medium, and detection system for detecting electricity theft - Google Patents
Method, processor, storage medium, and detection system for detecting electricity theft Download PDFInfo
- Publication number
- CN112749465A CN112749465A CN202110071268.4A CN202110071268A CN112749465A CN 112749465 A CN112749465 A CN 112749465A CN 202110071268 A CN202110071268 A CN 202110071268A CN 112749465 A CN112749465 A CN 112749465A
- Authority
- CN
- China
- Prior art keywords
- electricity
- detection
- low
- voltage
- electricity stealing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 189
- 230000005611 electricity Effects 0.000 title claims abstract description 175
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000003860 storage Methods 0.000 title claims abstract description 21
- 238000009826 distribution Methods 0.000 claims abstract description 109
- 238000004891 communication Methods 0.000 claims description 22
- 238000012549 training Methods 0.000 claims description 20
- 230000008569 process Effects 0.000 claims description 12
- 238000012795 verification Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 10
- 238000005516 engineering process Methods 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 abstract description 11
- 238000013135 deep learning Methods 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 15
- 238000004590 computer program Methods 0.000 description 14
- 238000012544 monitoring process Methods 0.000 description 13
- 230000006870 function Effects 0.000 description 10
- 230000006399 behavior Effects 0.000 description 6
- 238000009434 installation Methods 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008014 freezing Effects 0.000 description 1
- 238000007710 freezing Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/18—Network design, e.g. design based on topological or interconnect aspects of utility systems, piping, heating ventilation air conditioning [HVAC] or cabling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/04—Power grid distribution networks
Abstract
The embodiment of the invention provides a method, a processor, a storage medium and a detection system for detecting electricity stealing, belonging to the technical field of electricity stealing detection, wherein the method comprises the following steps: acquiring a trained electricity stealing detection model; acquiring power consumption parameters of all levels of lines in a low-voltage distribution area; determining a detection characteristic value according to the power consumption parameters of the lines at all levels; and inputting the detection characteristic value into the electricity stealing detection model to detect whether the electricity stealing phenomenon occurs in the low-voltage distribution station area. According to the embodiment of the invention, the detection characteristic value with strong power stealing detection pertinence is constructed according to the power consumption parameters of all levels of lines in the low-voltage power distribution area, and the power stealing detection is carried out by utilizing the intelligent deep learning algorithm according to the detection characteristic value, so that whether the power stealing phenomenon occurs in the low-voltage power distribution area can be effectively detected, the detection accuracy is high, and the detection speed is high.
Description
Technical Field
The invention relates to the technical field of electricity stealing detection, in particular to a method, a processor, a storage medium and a detection system for detecting electricity stealing.
Background
At present, two main electricity stealing methods exist in a low-voltage distribution network. The under-voltage method or under-current method is mainly characterized by that the connection mode of voltage or current loop is changed to make the loop under-voltage or under-current so as to make the electric energy meter less measure electric quantity. The other method is called phase shifting method, which mainly changes the phase relation between the voltage and the current in the metering element by changing the wiring mode of the electric meter, injecting the current or using a phase shifter and the like under the condition of not changing the current or the voltage amplitude, thereby enabling the electric meter to rotate slowly, reverse or stop rotating. For the electricity stealing behavior of the low-voltage distribution network, the current detection means are limited, and the detection accuracy is low, so that in the related technology, a larger improvement space exists for the detection of the electricity stealing behavior of the low-voltage distribution network.
Disclosure of Invention
It is an object of embodiments of the present invention to provide a method, processor, storage medium and detection system for detecting theft of electricity.
In order to achieve the above object, a first aspect of the present invention provides a method for detecting electricity theft, applied to a low-voltage distribution substation, the method comprising:
acquiring a trained electricity stealing detection model;
acquiring power consumption parameters of all levels of lines in a low-voltage distribution area, wherein the power consumption parameters of all levels of lines comprise current values, voltage values and power of all levels of lines;
determining detection characteristic values according to the power consumption parameters of all levels of circuits, wherein the detection characteristic values comprise line loss rate, current unbalance and voltage unbalance of a low-voltage distribution area;
and inputting the detection characteristic value into the electricity stealing detection model to detect whether the electricity stealing phenomenon occurs in the low-voltage distribution station area.
In the embodiment of the invention, inputting the detection characteristic value into the electricity stealing detection model to detect whether the electricity stealing phenomenon occurs in the low-voltage distribution station area comprises the following steps:
inputting a main characteristic value and a secondary characteristic value into the electricity stealing detection model, wherein the main characteristic value comprises a line loss rate, and the secondary characteristic value comprises a current unbalance amount and a voltage unbalance amount;
judging whether the low-voltage power distribution station area has the electricity stealing phenomenon or not by using the main characteristic value;
under the condition that the low-voltage power distribution station area is judged to have the electricity stealing phenomenon, the secondary characteristic value is used for verifying whether the low-voltage power distribution station area has the electricity stealing phenomenon again;
and under the condition of verifying that the electricity stealing phenomenon occurs in the low-voltage power distribution area, determining that the electricity stealing phenomenon occurs in the low-voltage power distribution area.
In the embodiment of the invention, inputting the detection characteristic value into the electricity stealing detection model to detect whether the electricity stealing phenomenon occurs in the low-voltage distribution station area comprises the following steps:
inputting the detection characteristic value into a power stealing detection model, and acquiring a first detection result and a second detection result output by the power stealing detection model aiming at the detection characteristic value, wherein the first detection result is obtained by detecting the power stealing detection model aiming at the main line in each stage of line, and the second detection result is obtained by detecting the power stealing detection model aiming at the branch line in each stage of line;
and judging whether the low-voltage distribution area steals electricity according to the first detection result and the second detection result.
In the embodiment of the present invention, acquiring the electricity consumption parameters of each stage of line in the low-voltage distribution substation area includes:
carrying out station area identification, phase identification and physical topology identification on the low-voltage distribution station area;
obtaining the line distribution of the low-voltage distribution area based on the identification result;
and acquiring power consumption parameters of all levels of lines in the low-voltage distribution area according to the line distribution.
In the embodiment of the present invention, determining the detection characteristic value according to the power consumption parameter of each stage of circuit includes:
acquiring a total power consumption parameter corresponding to each main line and a plurality of secondary power consumption parameters corresponding to the distribution of secondary lines contained in each main line;
determining the line loss rate, the current unbalance amount and the voltage unbalance amount of each main line according to the total power consumption parameter and the plurality of secondary power consumption parameters;
and taking the line loss rate, the current unbalance amount and the voltage unbalance amount of all the main lines as detection characteristic values of the low-voltage distribution station area.
In the embodiment of the invention, the training process of the electricity stealing detection model comprises the following steps:
acquiring historical line loss rate, historical current unbalance and historical voltage unbalance of a low-voltage distribution area within a preset period of time;
normalizing the historical line loss rate, the historical current unbalance amount and the historical voltage unbalance amount;
substituting the data after the normalization processing into a learning model for training to obtain a detection model corresponding to the training result when the error is minimum;
and taking the detection model corresponding to the minimum error of the training result as the trained electricity stealing detection model.
In an embodiment of the present invention, the method for detecting electricity stealing further comprises:
verifying the trained electricity stealing detection model;
and after the trained electricity stealing detection model passes the verification, detecting whether the electricity stealing phenomenon occurs in the low-voltage distribution area or not by using the trained electricity stealing detection model.
A second aspect of the invention provides a processor configured to perform any of the above-described methods for detecting theft of electricity.
A third aspect of the present invention provides a detection system, comprising:
intelligent monitor terminal includes:
the detection module is configured to acquire power consumption parameters of all levels of lines in the low-voltage distribution area;
the first carrier communication module is configured to transmit power consumption parameters of all levels of lines through a carrier communication technology; and
an edge computing device, comprising:
the second carrier communication module is configured to receive the power utilization parameter sent by the first carrier communication module;
the processor is configured to receive the power consumption parameter from the second carrier communication module and process the power consumption parameter.
A fourth aspect of the invention provides a storage medium having stored thereon instructions for causing a machine to perform any one of the above-described methods for detecting theft of electricity.
Through the technical scheme, a trained electricity stealing detection model is obtained; acquiring power consumption parameters of all levels of lines in a low-voltage distribution area, wherein the power consumption parameters of all levels of lines comprise current values, voltage values and power of all levels of lines; determining detection characteristic values according to the power consumption parameters of all levels of circuits, wherein the detection characteristic values comprise line loss rate, current unbalance and voltage unbalance of a low-voltage distribution area; and inputting the detection characteristic value into the electricity stealing detection model to detect whether the electricity stealing phenomenon occurs in the low-voltage distribution station area. According to the embodiment of the invention, the detection characteristic value with strong electricity stealing detection pertinence can be constructed according to the electricity consumption parameters of all levels of lines in the low-voltage distribution area, the electricity stealing detection is carried out by utilizing the intelligent deep learning algorithm according to the detection characteristic value, whether the electricity stealing phenomenon occurs in the low-voltage distribution area can be effectively detected, the detection accuracy is high, and the detection speed is high.
Additional features and advantages of embodiments of the invention will be set forth in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the embodiments of the invention without limiting the embodiments of the invention. In the drawings:
FIG. 1 is a schematic flow diagram of a method for detecting electricity theft in accordance with an embodiment of the present invention;
FIG. 2 is a schematic diagram of an installation of power lines and equipment for a power theft detection method according to an embodiment of the present invention;
FIG. 3 is another schematic diagram of an installation of power lines and equipment for detecting electricity theft according to an embodiment of the present invention;
fig. 4 is an internal structural diagram of a computer device according to an embodiment of the present invention.
Detailed Description
The following detailed description of embodiments of the invention refers to the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating embodiments of the invention, are given by way of illustration and explanation only, not limitation.
Currently, in the related art, the detection of the electricity stealing phenomenon is mainly based on real-time monitoring of data such as voltage, current and/or phase of user information. This monitoring method has the following problems: 1) the electrical parameters are simple and cannot clearly judge whether electricity is stolen or not. 2) With the development of computer technology and machine algorithm, similarity analysis methods, data mining algorithms, outlier algorithms, methods based on graph theory, and the like are also applied to detecting electricity stealing behaviors, but the accuracy of extracting characteristic indexes of electricity stealing and identifying electricity stealing behaviors is still to be improved.
Based on the above, the embodiment of the invention constructs the detection characteristic value with strong electricity stealing detection pertinence according to the electricity consumption parameters of all levels of lines in the low-voltage distribution area, and performs electricity stealing detection by using an intelligent deep learning algorithm according to the detection characteristic value, so that whether the electricity stealing phenomenon occurs in the low-voltage distribution area can be effectively detected, the detection accuracy is high, and the detection speed is high.
An embodiment of the present invention provides a method for detecting electricity stealing, which is applied to a low-voltage distribution station, as shown in fig. 1, and the method includes:
step 101: acquiring a trained electricity stealing detection model;
step 102: acquiring power consumption parameters of all levels of lines in a low-voltage distribution area, wherein the power consumption parameters of all levels of lines comprise current values, voltage values and power of all levels of lines;
step 103: determining detection characteristic values according to the power consumption parameters of all levels of circuits, wherein the detection characteristic values comprise line loss rate, current unbalance and voltage unbalance of a low-voltage distribution area;
step 104: and inputting the detection characteristic value into the electricity stealing detection model to detect whether the electricity stealing phenomenon occurs in the low-voltage distribution station area.
In practical application, the electricity stealing detection model comprises a neural network model.
In practical application, the electricity consumption parameters of all levels of circuits can be acquired through the intelligent monitoring terminals installed on all levels of circuits.
During practical application, the intelligent monitoring terminal is provided with the collector, and the collector can collect power consumption parameters of all levels of circuits.
In practical applications, the intelligent monitoring Terminal may include an intelligent circuit breaker, a Low-voltage Terminal Unit (LTU), or an electric energy meter.
In practical application, in order to facilitate equipment installation, the intelligent monitoring terminal can be installed at the switch of each level of physical line.
In practice, the method for detecting electricity stealing may be performed at the edge computing device based on the edge computing method. Wherein the edge computing device may be disposed on a master control device of each low voltage distribution substation. Because edge computing refers to that an open platform integrating network, computing, storage and application core capabilities is adopted on one side close to an object or a data source to provide the nearest service nearby, data analysis and other work is put on edge processing based on an edge computing architecture, response time delay can be reduced, the pressure of a cloud master station is relieved, and bandwidth cost is reduced.
In one embodiment, the acquiring of the electricity consumption parameters of each stage of line in the low-voltage distribution substation area comprises:
carrying out station area identification, phase identification and physical topology identification on the low-voltage distribution station area;
obtaining the line distribution of the low-voltage distribution area based on the identification result;
and acquiring power consumption parameters of all levels of lines in the low-voltage distribution area according to the line distribution.
In practical application, due to power supply requirements, the circuit can be divided into multiple stages of lines, and power is supplied in sequence respectively. Therefore, in order to obtain the distribution of the power supply lines, station identification, phase identification and physical topology identification can be carried out on the low-voltage power distribution station, and the line distribution of the low-voltage power distribution station is determined based on the identification result.
In an embodiment, determining the detection characteristic value according to the power consumption parameters of the lines at each stage includes:
acquiring a total power consumption parameter corresponding to each main line and a plurality of secondary power consumption parameters corresponding to the distribution of secondary lines contained in each main line;
determining the line loss rate, the current unbalance amount and the voltage unbalance amount of each main line according to the total power consumption parameter and the plurality of secondary power consumption parameters;
and taking the line loss rate, the current unbalance amount and the voltage unbalance amount of all the main lines as detection characteristic values of the low-voltage distribution station area.
In practical application, the line loss rate, the current unbalance amount and the voltage unbalance amount can be calculated by adopting a common method.
In one embodiment, the training process of the electricity stealing detection model comprises:
acquiring historical line loss rate, historical current unbalance and historical voltage unbalance of a low-voltage distribution area within a preset period of time;
normalizing the historical line loss rate, the historical current unbalance amount and the historical voltage unbalance amount;
substituting the data after the normalization processing into a learning model for training to obtain a detection model corresponding to the training result when the error is minimum;
and taking the detection model corresponding to the minimum error of the training result as the trained electricity stealing detection model.
In practical applications, the preset period of time may be set as needed. Such as 3 months, half a year, etc. Wherein, the longer the time, the larger the data size, and the more accurate the electricity stealing detection model.
In practical application, the historical line loss rate, the historical current unbalance amount and the historical voltage unbalance amount can be obtained through the total historical electricity consumption parameter corresponding to each main line and the plurality of historical secondary electricity consumption parameters corresponding to the secondary line distribution included in each main line.
In practical application, the historical line loss rate, the historical current unbalance amount and the historical voltage unbalance amount can be classified, and the classified data is used for training.
In practical application, the power consumption time can be classified, for example, into historical line loss rate, historical current unbalance amount and historical voltage unbalance amount on working days; historical line loss rate, historical current unbalance and historical voltage unbalance during non-working days. For another example, the line loss rate, the current unbalance amount and the voltage unbalance amount can be divided into a historical line loss rate in a time period from 8 am to 8 pm; historical line loss rate, historical current unbalance amount and historical voltage unbalance amount in the time period from 8 pm to 8 am.
In practical application, the power utilization location can be further classified, for example, the power utilization location can be classified into historical line loss rate, historical current unbalance amount and historical voltage unbalance amount of power utilization in an industrial park, and historical line loss rate, historical current unbalance amount and historical voltage unbalance amount of household power supply.
In practical application, training is carried out based on the classified data, so that the training result is more accurate and more targeted.
In practical application, the data output by the electricity stealing detection model can be compared with the real data result corresponding to the data, and when the data output by the electricity stealing detection model is closest to the real data result corresponding to the data, the error of the training result is judged to be minimum.
In practical application, the error range can be limited, only the error range is within a preset range, and the detection model corresponding to the minimum error is the trained electricity stealing detection model.
In practical application, in order to reduce the generation of errors, the trained electricity stealing detection model can be verified.
In an embodiment, the method for detecting electricity theft further comprises:
verifying the trained electricity stealing detection model;
and after the trained electricity stealing detection model passes the verification, detecting whether the electricity stealing phenomenon occurs in the low-voltage distribution area or not by using the trained electricity stealing detection model.
In practical application, the trained electricity stealing detection model can be verified based on verification data. The verification data can be selected based on needs, for example, only electricity stealing data when electricity stealing behavior occurs by using different electricity stealing modes can be selected. The verification is carried out by only utilizing the electricity stealing data when the electricity stealing behavior occurs, so that the verification process can be accelerated, the verification time can be shortened, and the data acquisition amount can be reduced.
In practical application, various modes can be adopted to judge whether the trained electricity stealing detection model passes verification. For example, the accuracy percentage for verifying the trained electricity stealing detection model can be obtained, and when the accuracy percentage is greater than the preset percentage, the trained electricity stealing detection model is judged to be verified to be passed; and when the accuracy percentage is less than or equal to the preset percentage, judging that the trained electricity stealing detection model fails to verify.
For example, the verification data can be divided into a plurality of sub-data, each sub-data is used for verifying the trained electricity stealing detection model, and when the accuracy percentage of the preset number of sub-data reaches a preset threshold value, the trained electricity stealing detection model is judged to pass the verification; and when the accuracy percentage of the sub-data without the preset number reaches a preset threshold value, judging that the trained electricity stealing detection model fails to verify.
In one embodiment, inputting the detection characteristic value into the electricity stealing detection model to detect whether the electricity stealing phenomenon occurs in the low-voltage distribution station area comprises the following steps:
inputting a main characteristic value and a secondary characteristic value into the electricity stealing detection model, wherein the main characteristic value comprises a line loss rate, and the secondary characteristic value comprises a current unbalance amount and a voltage unbalance amount;
judging whether the low-voltage power distribution station area has the electricity stealing phenomenon or not by using the main characteristic value;
under the condition that the low-voltage power distribution station area is judged to have the electricity stealing phenomenon, verifying whether the low-voltage power distribution station area has the electricity stealing phenomenon or not by using the secondary characteristic value;
and under the condition of verifying that the electricity stealing phenomenon occurs in the low-voltage power distribution area, determining that the electricity stealing phenomenon occurs in the low-voltage power distribution area.
During practical application, when electricity stealing phenomenon occurs, line loss rate is obviously transformed in the circuit, so that the line loss rate is used as a main characteristic value to preliminarily judge whether the electricity stealing phenomenon occurs in a low-voltage distribution substation area, and then the current unbalance amount and the voltage unbalance amount are used as secondary characteristic values to check a preliminary judgment result, so that the detection of the electricity stealing phenomenon is more accurate.
In one embodiment, inputting the detection characteristic value into the electricity stealing detection model to detect whether the electricity stealing phenomenon occurs in the low-voltage distribution station area comprises the following steps:
inputting the detection characteristic value into a power stealing detection model, and acquiring a first detection result and a second detection result output by the power stealing detection model aiming at the detection characteristic value, wherein the first detection result is obtained by detecting the power stealing detection model aiming at the main line in each stage of line, and the second detection result is obtained by detecting the power stealing detection model aiming at the branch line in each stage of line;
and judging whether the low-voltage distribution area steals electricity according to the first detection result and the second detection result.
In practical application, the judgment can be performed in various ways according to the first detection result and the second detection result. For example, when at least one of the first detection result and the second detection result shows that the electricity stealing phenomenon occurs in the low-voltage power distribution area, the electricity stealing phenomenon in the low-voltage power distribution area is judged; and when the first detection result and the second detection result show that the low-voltage power distribution station area does not have the electricity stealing phenomenon, judging that the low-voltage power distribution station area does not have the electricity stealing phenomenon.
For another example, a mapping relation table may be queried based on the first detection result and the second detection result to obtain a determination result, where the mapping relation table includes the one-to-one correspondence between the first detection result and the second detection result and the determination result, and when the determination result indicates that the electricity stealing phenomenon occurs in the low-voltage distribution substation area, it is determined that the electricity stealing phenomenon occurs in the low-voltage distribution substation area; and when the judgment result shows that the low-voltage power distribution area does not have the electricity stealing phenomenon, judging that the low-voltage power distribution area does not have the electricity stealing phenomenon.
Through the technical scheme, a trained electricity stealing detection model is obtained; acquiring power consumption parameters of all levels of lines in a low-voltage distribution area, wherein the power consumption parameters of all levels of lines comprise current values, voltage values and power of all levels of lines; determining detection characteristic values according to the power consumption parameters of all levels of circuits, wherein the detection characteristic values comprise line loss rate, current unbalance and voltage unbalance of a low-voltage distribution area; and inputting the detection characteristic value into the electricity stealing detection model, and detecting whether the electricity stealing phenomenon occurs in the low-voltage distribution station area. According to the embodiment of the invention, the detection characteristic value with strong electricity stealing detection pertinence can be constructed according to the electricity consumption parameters of all levels of lines in the low-voltage distribution area, the electricity stealing detection is carried out by utilizing the intelligent deep learning algorithm according to the detection characteristic value, whether the electricity stealing phenomenon occurs in the low-voltage distribution area can be effectively detected, the detection accuracy is high, and the detection speed is high.
The present invention will be described in further detail with reference to the following application examples.
The application embodiment provides a low-voltage distribution network electricity stealing detection method based on an artificial intelligence algorithm and edge calculation. The method is based on a deep learning algorithm electricity stealing detection model and is used for detecting electricity stealing of users in a low-voltage distribution station area.
Through analysis, the line loss of the electricity stealing node can be changed greatly when an electricity stealing event occurs in a transformer area, so that the line loss rate is used as a main characteristic for judging electricity stealing in the application embodiment; meanwhile, three-phase current and voltage unbalance of the transformer area can be damaged during electricity stealing, so that the application embodiment takes the three-phase current unbalance and the three-phase voltage unbalance as secondary characteristics. And training by using an artificial intelligence deep learning algorithm on the basis of the three characteristic values, and obtaining a power stealing detection model when the error value reaches the minimum value. And adopting the obtained electricity stealing detection model to carry out electricity stealing detection on the users in the low-voltage distribution station area.
First, the schematic installation diagram of the power lines and the equipment of the low-voltage distribution network electricity stealing detection method of the embodiment of the application can be seen in fig. 2 and fig. 3.
As shown in fig. 2 and 3, the network is a low-voltage power line electricity information collection system based on a carrier communication technology, and the network is configured with an edge computing device (having a carrier communication function) and an intelligent monitoring terminal (having a carrier communication function). The intelligent monitoring terminal has a carrier communication function and an electric physical quantity (voltage, current, phase angle and the like) acquisition function. The intelligent monitoring terminal can be an electric energy meter (with a carrier communication function), a collector (with a carrier communication function), a switch monitoring device, an intelligent circuit breaker, an LTU and the like. In addition, an intelligent monitoring terminal may be installed at the physical line switch.
Secondly, the specific implementation process of the low-voltage distribution network electricity stealing detection method in the application embodiment is as follows:
step 1: after the networking is successful (namely, after the equipment is successfully installed in the network), the station area identification, the phase identification and the physical topology identification are carried out through the intelligent monitoring terminal equipment. The main purpose of identification is to provide data support for calculating the line loss of the platform area, the split-phase line loss, the branch line loss and the meter box line loss.
Step 2: after the physical topology identification of the transformer area is completed, obtaining the line loss rate of the transformer area, the current unbalance amount and the voltage unbalance amount through load flow calculation; and data freezing and storing are carried out according to the day.
And step 3: and carrying out normalization processing on the obtained historical line loss rate and the three-phase unbalance to obtain three groups of data sets. Wherein, the three sets of data sets may be three index data for each time period (which may be a month or a day) that are respectively recorded.
And 4, step 4: and providing the three groups of electricity stealing detection data for a training network, carrying out circular simulation training until the sample error reaches the minimum value, and stopping network training.
And 5: and testing the trained model, and confirming that the result calculated by the model accords with the actual condition.
Step 6: and (4) carrying out electricity stealing detection on the low-voltage distribution station by using the tested model, and judging whether electricity stealing occurs.
This patent is on selecting the power stealing detection index basis that has strong pertinence, has designed the power stealing detection model based on artificial intelligence degree of depth learning algorithm, utilizes this model to steal the power and detects and can improve the detection rate of accuracy greatly, effectively detects the power stealing action. Meanwhile, based on an edge computing architecture, data analysis and other work are put into edge processing, response time delay is reduced, pressure of a master station is relieved, and bandwidth cost is reduced.
The embodiment of the invention also provides a processor configured to execute the method of any one of the above embodiments.
An embodiment of the present invention further provides a detection system, where the detection system includes:
intelligent monitor terminal includes: the detection module is configured to acquire power consumption parameters of all levels of lines in the low-voltage distribution area; the first carrier communication module is configured to transmit power consumption parameters of all levels of lines through a carrier communication technology; and an edge computing device comprising: the second carrier communication module is configured to receive the power utilization parameter sent by the first carrier communication module; the processor is configured to receive the power consumption parameter from the second carrier communication module and process the power consumption parameter.
In practical application, the intelligent monitoring terminal comprises an intelligent circuit breaker, an LTU and/or an electric energy meter.
During practical application, the intelligent monitoring terminal can be installed at a physical line switch.
An embodiment of the present invention further provides a storage medium, where instructions are stored on the storage medium, and the instructions are used to cause a machine to execute the method according to any one of the above embodiments.
Embodiments of the present invention also provide a computer program product, which includes a computer program, and when the computer program is executed by a processor, the computer program implements the method of any one of the above embodiments.
In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 4. The computer apparatus includes a processor a01, a network interface a02, a display screen a04, an input device a05, and a memory (not shown in the figure) connected through a system bus. Wherein processor a01 of the computer device is used to provide computing and control capabilities. The memory of the computer device comprises an internal memory a03 and a non-volatile storage medium a 06. The nonvolatile storage medium a06 stores an operating system B01 and a computer program B02. The internal memory a03 provides an environment for the operation of the operating system B01 and the computer program B02 in the nonvolatile storage medium a 06. The network interface a02 of the computer device is used for communication with an external terminal through a network connection. The computer program when executed by processor a01 implements a method for detecting theft of electricity. The display screen a04 of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device a05 of the computer device may be a touch layer covered on the display screen, a button, a trackball or a touch pad arranged on a casing of the computer device, or an external keyboard, a touch pad or a mouse.
Those skilled in the art will appreciate that the architecture shown in fig. 4 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
The embodiment of the invention provides equipment, which comprises a processor, a memory and a program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the method for detecting electricity stealing.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include transitory computer readable media (transmyedia) such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A method for detecting the theft of electricity, applied to a low-voltage distribution substation, characterized in that it comprises:
acquiring a trained electricity stealing detection model;
acquiring power consumption parameters of all levels of lines in a low-voltage distribution area, wherein the power consumption parameters of all levels of lines comprise current values, voltage values and power of all levels of lines;
determining detection characteristic values according to the power consumption parameters of all levels of circuits, wherein the detection characteristic values comprise line loss rate, current unbalance and voltage unbalance of a low-voltage power distribution area;
and inputting the detection characteristic value into the electricity stealing detection model to detect whether the electricity stealing phenomenon occurs in the low-voltage distribution station area.
2. The method for detecting electricity theft according to claim 1, wherein the inputting the detection characteristic value into the electricity theft detection model to detect whether the electricity theft phenomenon occurs in the low voltage distribution substation area comprises:
inputting a primary characteristic value and a secondary characteristic value into the electricity stealing detection model, wherein the primary characteristic value includes the line loss rate, and the secondary characteristic value includes the current unbalance amount and the voltage unbalance amount;
judging whether the low-voltage power distribution station area has an electricity stealing phenomenon or not by using the main characteristic value;
under the condition that the low-voltage power distribution station area is judged to have the electricity stealing phenomenon, verifying whether the low-voltage power distribution station area has the electricity stealing phenomenon or not by using the secondary characteristic value;
and under the condition that the low-voltage power distribution area is verified to steal electricity, determining that the low-voltage power distribution area steals electricity.
3. The method for detecting electricity theft according to claim 1, wherein the inputting the detection characteristic value into the electricity theft detection model to detect whether the electricity theft phenomenon occurs in the low voltage distribution substation area comprises:
inputting the detection characteristic value into the electricity stealing detection model, and acquiring a first detection result and a second detection result output by the electricity stealing detection model aiming at the detection characteristic value, wherein the first detection result is obtained by detecting the electricity stealing detection model aiming at the bus circuit in each stage of circuit, and the second detection result is obtained by detecting the electricity stealing detection model aiming at the branch circuit in each stage of circuit;
and judging whether the low-voltage distribution area has the electricity stealing phenomenon or not according to the first detection result and the second detection result.
4. The method for detecting the theft of electricity according to claim 1, wherein said obtaining of electricity usage quantities of lines of each stage of the low voltage distribution substation area comprises:
carrying out station area identification, phase identification and physical topology identification on the low-voltage distribution station area;
obtaining the line distribution of the low-voltage distribution area based on the identification result;
and acquiring the electricity consumption parameters of all levels of lines of the low-voltage power distribution area according to the line distribution.
5. The method for detecting electricity stealing according to claim 1, wherein the determining of the detection characteristic values according to the electricity consumption parameters of the lines at each stage comprises:
acquiring a total power consumption parameter corresponding to each main line and a plurality of secondary power consumption parameters corresponding to the distribution of secondary lines contained in each main line;
determining the line loss rate, the current unbalance amount and the voltage unbalance amount of each main line according to the total power consumption parameter and the plurality of secondary power consumption parameters;
and taking the line loss rate, the current unbalance amount and the voltage unbalance amount of all the main lines as detection characteristic values of the low-voltage distribution station area.
6. The method for detecting theft of electricity according to claim 1, wherein the training process of the electricity theft detection model comprises:
acquiring historical line loss rate, historical current unbalance and historical voltage unbalance of the low-voltage distribution area within a preset period of time;
normalizing the historical line loss rate, the historical current unbalance amount and the historical voltage unbalance amount;
substituting the data after the normalization processing into a learning model for training to obtain a detection model corresponding to the training result when the error is minimum;
and taking the detection model corresponding to the minimum error of the training result as the trained electricity stealing detection model.
7. The method for detecting theft of electricity according to claim 6, further comprising:
verifying the trained electricity stealing detection model;
and after the trained electricity stealing detection model passes the verification, detecting whether the electricity stealing phenomenon occurs in the low-voltage distribution substation area or not by using the trained electricity stealing detection model.
8. A processor configured to perform the method for detecting theft of electricity according to any one of claims 1 to 7.
9. A detection system, characterized in that the detection system comprises:
intelligent monitor terminal includes:
the detection module is configured to acquire power consumption parameters of all levels of lines in the low-voltage distribution area;
the first carrier communication module is configured to transmit the electricity consumption parameters of the lines at all levels through a carrier communication technology; and
an edge computing device, comprising:
the second carrier communication module is configured to receive the power utilization parameter sent by the first carrier communication module;
the processor of claim 8, configured to receive and process the electricity usage quantity from the second carrier communication module.
10. A storage medium having stored thereon instructions for causing a machine to perform the method for detecting theft of electricity according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110071268.4A CN112749465A (en) | 2021-01-19 | 2021-01-19 | Method, processor, storage medium, and detection system for detecting electricity theft |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110071268.4A CN112749465A (en) | 2021-01-19 | 2021-01-19 | Method, processor, storage medium, and detection system for detecting electricity theft |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112749465A true CN112749465A (en) | 2021-05-04 |
Family
ID=75652573
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110071268.4A Pending CN112749465A (en) | 2021-01-19 | 2021-01-19 | Method, processor, storage medium, and detection system for detecting electricity theft |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112749465A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116701947A (en) * | 2023-08-02 | 2023-09-05 | 成都汉度科技有限公司 | Method and system for detecting electricity stealing behavior |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106771734A (en) * | 2016-12-09 | 2017-05-31 | 国网北京市电力公司 | Electric power monitoring method and device |
| CN110646677A (en) * | 2019-09-11 | 2020-01-03 | 巴祎 | Method for identifying topology and line impedance of distribution room low-voltage power distribution network |
| CN110749784A (en) * | 2019-08-05 | 2020-02-04 | 上海大学 | Line electricity stealing detection method based on electric power data wavelet analysis |
-
2021
- 2021-01-19 CN CN202110071268.4A patent/CN112749465A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106771734A (en) * | 2016-12-09 | 2017-05-31 | 国网北京市电力公司 | Electric power monitoring method and device |
| CN110749784A (en) * | 2019-08-05 | 2020-02-04 | 上海大学 | Line electricity stealing detection method based on electric power data wavelet analysis |
| CN110646677A (en) * | 2019-09-11 | 2020-01-03 | 巴祎 | Method for identifying topology and line impedance of distribution room low-voltage power distribution network |
Non-Patent Citations (3)
| Title |
|---|
| 吴健等: "基于神经网络算法的用户窃电行为检测模型研究", 《电力信息与通信技术》, no. 12, pages 36 - 40 * |
| 许均星等: "基于遗传算法优化BP神经网络的窃电分析", 《软件》, vol. 38, no. 11, pages 18 - 23 * |
| 黄星知等: "基于BP 神经网络的配电网 防窃电降线损研究", 《电力科学与技术学报》, vol. 34, no. 4, pages 143 - 147 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116701947A (en) * | 2023-08-02 | 2023-09-05 | 成都汉度科技有限公司 | Method and system for detecting electricity stealing behavior |
| CN116701947B (en) * | 2023-08-02 | 2023-11-03 | 成都汉度科技有限公司 | Method and system for detecting electricity stealing behavior |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kamwa et al. | Fuzzy partitioning of a real power system for dynamic vulnerability assessment | |
| CN106505557B (en) | Remote measurement error identification method and device | |
| CN108198408B (en) | Self-adaptive anti-electricity-stealing monitoring method and system based on electricity information acquisition system | |
| CN108667005B (en) | Power grid static and dynamic combination vulnerability assessment method considering new energy influence | |
| CN114915546B (en) | Power failure user positioning method, device, equipment and medium | |
| Rashidi et al. | LEs based framework for transient instability prediction and mitigation using PMU data | |
| CN111521867A (en) | System and method for collecting load data | |
| CN112749465A (en) | Method, processor, storage medium, and detection system for detecting electricity theft | |
| Hua et al. | Efficient probabilistic contingency analysis through a stability measure considering wind perturbation | |
| CN116911471B (en) | Transmission performance optimization method and system of power supply system | |
| CN112198375B (en) | Phase identification method, device, equipment and storage medium for single-phase user | |
| CN110334385B (en) | Test method, device and equipment for central controller of comprehensive energy system | |
| CN109557398B (en) | Power distribution network fault diagnosis method and device | |
| CN105701265A (en) | Double-fed wind generator modeling method and apparatus | |
| CN116679151A (en) | Low-voltage transformer area line loss abnormity diagnosis method, device and storage medium | |
| CN104237697A (en) | Testing system for new energy automobile charging equipment | |
| Gomez et al. | Web services framework for power quality monitoring | |
| CN113541126A (en) | Power distribution network simulation system suitable for verifying advanced algorithm and algorithm verification method | |
| CN113283076A (en) | Method and device for researching electricity utilization abnormity and computer readable storage medium | |
| CN109871998B (en) | Power distribution network line loss rate prediction method and device based on expert sample library | |
| Sheng et al. | Frequency deviation peak calculation of sending‐end network in large asynchronous interconnected power grid | |
| CN110879537A (en) | Method and device for processing transient stability of intelligent household energy system | |
| CN113837227B (en) | Load prediction method, load prediction device, chip, electronic equipment and storage medium | |
| Rauma et al. | Optimal location of voltage sensors in low voltage networks for on‐load tap changer application | |
| CN114825647B (en) | Topological relation-based distribution room line loss monitoring method and related equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |