CN117493857A - Electric energy metering abnormality judging method, system, equipment and medium - Google Patents
Electric energy metering abnormality judging method, system, equipment and medium Download PDFInfo
- Publication number
- CN117493857A CN117493857A CN202311526900.5A CN202311526900A CN117493857A CN 117493857 A CN117493857 A CN 117493857A CN 202311526900 A CN202311526900 A CN 202311526900A CN 117493857 A CN117493857 A CN 117493857A
- Authority
- CN
- China
- Prior art keywords
- electric energy
- data
- energy metering
- sequence
- time sequence
- 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
- 230000005856 abnormality Effects 0.000 title claims abstract description 67
- 238000000034 method Methods 0.000 title claims abstract description 38
- 230000002159 abnormal effect Effects 0.000 claims abstract description 37
- 238000010586 diagram Methods 0.000 claims abstract description 28
- 238000012545 processing Methods 0.000 claims abstract description 28
- 230000011218 segmentation Effects 0.000 claims description 19
- 238000013144 data compression Methods 0.000 claims description 14
- 238000005259 measurement Methods 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 4
- 238000012850 discrimination method Methods 0.000 claims description 4
- 230000002776 aggregation Effects 0.000 claims description 3
- 238000004220 aggregation Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 239000012634 fragment Substances 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 10
- 239000000463 material Substances 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
Classifications
-
- 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
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2132—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on discrimination criteria, e.g. discriminant analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention discloses a method, a system, equipment and a medium for distinguishing an electric energy metering abnormality, which are used for carrying out sectional processing on electric energy metering data based on time sequence, so that the dimension of the electric energy metering data is reduced, the influence of noise in the measuring process is reduced, and accurate, reliable and easy-to-process data are provided for subsequent abnormality distinguishing; the time sequence data with the same power characteristics are divided into the same class by calculating the information gain value of each subsequence of the time sequence data, so that the data with the same power characteristics can be subjected to abnormal judgment later, and the data processing efficiency is improved; by constructing an anomaly discrimination model to perform anomaly discrimination on the electric energy power state diagram with the same electric power characteristic, the time period of the electric energy metering data anomaly can be determined and fed back to the electric power staff through the system, so that the problem of low working efficiency caused by long time consumption of operators when metering anomaly discrimination is performed due to the complexity and the variability of the electric energy metering data is solved.
Description
Technical Field
The invention relates to the technical field of electric energy metering abnormality discrimination, in particular to an electric energy metering abnormality discrimination method, an electric energy metering abnormality discrimination system, an electric energy metering abnormality discrimination device and an electric energy metering abnormality discrimination medium.
Background
The prior method for monitoring the abnormal electric energy metering is single, the investigation technology is not skilled, and the problem is not timely processed. The measurement abnormality judging process involves a plurality of factors, the data are complex, a large amount of manpower and material resources are consumed, and the risk of inaccurate judgment exists. How to analyze, arrange and collect the electricity consumption based on the existing equipment and combine the new technology means, which is a urgent problem to be solved. In the prior art, the device for measuring the electric energy cannot alarm abnormal conditions and analyze reasons of inaccurate measurement, meanwhile, when the device for monitoring the electric energy in the prior art collects data information, all collected data can be simultaneously transmitted to a data platform center, and due to the complexity and the variability of a plurality of data, the time for operators to use when judging measuring abnormality is long, unnecessary troubles are caused by processing, and the working efficiency is reduced.
Disclosure of Invention
Based on the technical problems set forth in the background art, the invention aims to provide an electric energy metering abnormality judging method, an electric energy metering abnormality judging system, an electric energy metering abnormality judging device and a medium, wherein the abnormality judging method can be used for judging the abnormality from electric energy metering data, the electric energy metering abnormality judging method is integrated into the electric energy metering abnormality judging system, the electric energy metering abnormality judging device and the medium, the metering data is input through the system, the equipment and the medium, and the system automatically outputs metering abnormality results, so that the problem of low working efficiency caused by long time consumption of operators when the operators judge metering abnormality due to complexity and variability of the electric energy metering data is solved.
The invention is realized by the following technical scheme:
the first aspect of the invention provides a method for judging the abnormality of electric energy metering, which comprises the following steps:
step S1, acquiring electric energy metering data, and carrying out sectional processing on the electric energy metering data based on time sequence to obtain time sequence data of electric energy metering;
s2, selecting a subsequence of the time sequence data, calculating an information gain value of the subsequence, classifying the time sequence data through the information gain value, and generating an electric energy metering state diagram;
and S3, constructing an abnormality judgment model, and judging the electric energy metering state diagram through the abnormality judgment model to obtain an electric energy metering abnormal result.
In the technical scheme, a large amount of manpower and material resources are consumed for the electric energy metering data in the metering abnormality judging process due to the fact that the data are complex, and meanwhile, if the obtained electric energy metering data are directly judged, the risk of inaccurate judgment exists. According to the technical scheme, the electric energy metering data are subjected to sectional processing based on time sequence, so that the dimension of the electric energy metering data is reduced, the influence of noise in the measuring process is reduced, and accurate, reliable and easy-to-process data are provided for subsequent abnormal judgment.
Aiming at the defect of long discrimination time of the existing electric energy metering abnormality discrimination method, the technical scheme divides the time sequence data with the same electric power characteristic into the same class by calculating the information gain value of each subsequence of the time sequence data so as to discriminate the abnormality of the data with the same electric power characteristic.
The abnormal judgment model is constructed to judge the abnormality of the electric energy power state diagram with the same electric power characteristic, the abnormal time period of the electric energy metering data can be determined and fed back to the electric power staff through the system, so that the problems of long time consumption and low working efficiency of operators when metering abnormality judgment is carried out due to the complexity and the variability of the electric energy metering data are solved.
In an alternative embodiment, the step of processing the electric energy metering data in segments based on time sequence includes:
step S11, the electric energy metering data comprise one-to-one corresponding time sequence, state sequence and power data, and a data compression value is obtained through calculation according to the power data;
s12, processing the electric energy metering data by taking the data compression value as a segmentation interval to obtain a segmentation sequence;
s13, calculating the similarity of the time sequence and the segmented sequence by adopting a DTW distance function, and taking the point with the similarity greater than or equal to a similarity threshold value in the segmented sequence as a sequence characteristic point;
and S14, integrating the sequence feature points with the state sequence corresponding to the sequence feature points and the power data to generate time sequence data.
In an alternative embodiment, processing the electric energy metering data with the data compression value as a segmentation interval to obtain a segmentation sequence includes:
step S121, dividing the time sequence at equal intervals by taking the data compression value as a segmentation interval to generate a plurality of sub-time sequences;
step S122, acquiring power data corresponding to the sub-time sequence, and calculating the power data to obtain a voltage fluctuation value;
step S123, connecting a left endpoint value and a right endpoint value of the sub-time sequence, and generating a segmented time sequence of the sub-time sequence;
and step S124, fitting the voltage fluctuation value with the segmentation time sequence to generate a segmentation sequence.
In an alternative embodiment, selecting a sub-sequence of the time series data, and calculating the information gain value of the sub-sequence includes:
s21, dividing the time sequence data into a plurality of subsequences by taking the sequence feature points as dividing points;
step S22, two subsequences are taken from any of the subsequences, euclidean distance of power data of the two subsequences is calculated, and information gain values of the two subsequences are calculated according to the Euclidean distance;
and step S23, repeating the step S22 until the information gain values of any two subsequences in the plurality of subsequences are calculated, and finally generating an information gain set.
In an alternative embodiment, taking two sub-sequences from any of the plurality of sub-sequences, calculating euclidean distances of power data of the two sub-sequences, and calculating information gain values of the two sub-sequences according to the euclidean distances includes:
wherein D is the euclidean distance of the power data of the two subsequences; l (L) 1 ,l 2 The sequence lengths of the two subsequences are respectively; t is t i ，t i ' time points of the two sub-sequences, respectively; v i ，v′ i Respectively two subsequences t i ，t′ i Corresponding power data; im is the information gain value of the two subsequences; s, S' are two subsequences respectively; s is S i ，S′ i Respectively twoSequence fragments of the subsequences; p is p i ，p i The information gain probabilities corresponding to the sequence segments are respectively given.
In an alternative embodiment, the process of classifying the time series data by the information gain value includes:
step S24, sorting the information gain values from big to small;
s25, setting an information gain threshold, and dividing the sorted information gain sets by the information gain threshold to obtain a plurality of classification sets;
and S26, carrying out aggregation treatment on the same classification set to generate an electric energy metering plate, and splicing a plurality of electric energy metering plates to generate an electric energy metering state diagram.
In an alternative embodiment, constructing an anomaly discrimination model, discriminating the electric energy metering state diagram by the anomaly discrimination model, and obtaining an electric energy metering anomaly result includes:
s31, acquiring historical electric energy metering abnormal data, and analyzing current and voltage in the historical electric energy metering abnormal data;
step S32, training and verifying the analysis result as a sample set to generate metering abnormal characteristics;
step S33, any one electric energy metering plate is taken from the electric energy metering state diagram, and electric energy data of the electric energy metering plate are extracted;
step S34, calculating the similarity between the electric energy data and the metering abnormal characteristics, judging that the electric energy metering state is abnormal if the similarity is larger than a similarity threshold value, and recording an electric energy metering abnormal result in a state sequence
The second aspect of the present invention provides an electric energy metering abnormality discrimination system, comprising:
the electric energy metering data processing module is used for acquiring electric energy metering data, and carrying out sectional processing on the electric energy metering data based on time sequence to obtain time sequence data of electric energy metering;
the electric energy metering state module is used for selecting a subsequence of the time sequence data, calculating an information gain value of the subsequence, classifying the time sequence data through the information gain value and generating an electric energy metering state diagram;
and the abnormality judgment module is used for constructing an abnormality judgment model, judging the electric energy metering state diagram through the abnormality judgment model and obtaining an electric energy metering abnormal result.
The third aspect of the invention provides an electronic device comprising a memory, a processor and a computer program stored on the memory and operable on the processor, the processor implementing a method of determining anomalies in electrical energy metering when executing the program.
A fourth aspect of the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method of determining an abnormality of electric energy metering.
Compared with the prior art, the invention has the following advantages and beneficial effects:
1. the electric energy metering data is subjected to sectional processing based on time sequence, so that the dimension of the electric energy metering data is reduced, the influence of noise in the measuring process is reduced, and accurate, reliable and easy-to-process data are provided for subsequent abnormal judgment;
2. the time sequence data with the same power characteristics are divided into the same class by calculating the information gain value of each subsequence of the time sequence data, so that the data with the same power characteristics can be subjected to abnormal judgment later, and the data processing efficiency is improved;
3. by constructing an anomaly discrimination model to perform anomaly discrimination on the electric energy metering state diagram with the same electric power characteristic, the time period of the electric energy metering data anomaly can be determined and fed back to the electric power staff through the system, so that the problem of low working efficiency caused by long time consumption of operators when metering anomaly discrimination is performed due to complexity and variability of the electric energy metering data is solved.
Drawings
In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the drawings that are needed in the examples will be briefly described below, it being understood that the following drawings only illustrate some examples of the present invention and therefore should not be considered as limiting the scope, and that other related drawings may be obtained from these drawings without inventive effort for a person skilled in the art. In the drawings:
FIG. 1 is a schematic flow chart of a method for determining abnormality of electric energy measurement according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a system for determining abnormality in electric energy measurement according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
For the purpose of making apparent the objects, technical solutions and advantages of the present invention, the present invention will be further described in detail with reference to the following examples and the accompanying drawings, wherein the exemplary embodiments of the present invention and the descriptions thereof are for illustrating the present invention only and are not to be construed as limiting the present invention.
Example 1
Fig. 1 is a flow chart of a method for determining an abnormality of electric energy measurement according to an embodiment of the present invention, as shown in fig. 1, the method for determining an abnormality of electric energy measurement includes:
step S1, acquiring electric energy metering data, and carrying out sectional processing on the electric energy metering data based on time sequence to obtain time sequence data of electric energy metering;
in an alternative embodiment, the step of processing the electric energy metering data in segments based on time sequence includes:
step S11, the electric energy metering data comprise one-to-one corresponding time sequence, state sequence and power data, and a data compression value is obtained through calculation according to the power data;
s12, processing the electric energy metering data by taking the data compression value as a segmentation interval to obtain a segmentation sequence;
s13, calculating the similarity of the time sequence and the segmented sequence by adopting a DTW distance function, and taking the point with the similarity greater than or equal to a similarity threshold value in the segmented sequence as a sequence characteristic point;
and S14, integrating the sequence feature points with the state sequence corresponding to the sequence feature points and the power data to generate time sequence data.
The electric energy metering data related to the invention is data closely related to time, and has high dimension, large scale and complex structure. In the process of judging metering abnormality of the electric energy metering data, a large amount of manpower and material resources are consumed due to complicated data, and meanwhile, if the obtained electric energy metering data are directly judged, the risk of inaccurate judgment exists.
In this regard, the invention performs the segment processing on the electric energy metering data based on the time sequence, thereby reducing the dimension of the electric energy metering data, reducing the influence of noise in the measuring process, and providing accurate, reliable and easy-to-process data for the subsequent abnormal judgment.
Specifically, in the invention, the data compression value used for dividing the time sequence can be determined by analyzing the voltage curve of the power data, and the data compression value is divided at equal intervals to obtain the segmented sequence.
And calculating the similarity of the time sequence and the segmented sequence by adopting a DTW distance function, and taking the point with the similarity greater than or equal to a similarity threshold value in the segmented sequence as a sequence characteristic point. And acquiring sequence characteristic points from the segmented sequence, discarding other non-important points, and realizing dimension reduction processing of the electric energy metering data, thereby improving the data processing efficiency of subsequent abnormality discrimination.
In an alternative embodiment, processing the electric energy metering data with the data compression value as a segmentation interval to obtain a segmentation sequence includes:
step S121, dividing the time sequence at equal intervals by taking the data compression value as a segmentation interval to generate a plurality of sub-time sequences;
step S122, acquiring power data corresponding to the sub-time sequence, and calculating the power data to obtain a voltage fluctuation value;
step S123, connecting a left endpoint value and a right endpoint value of the sub-time sequence, and generating a segmented time sequence of the sub-time sequence;
and step S124, fitting the voltage fluctuation value with the segmentation time sequence to generate a segmentation sequence.
It should be noted that the present invention aims to determine and screen out abnormal data in electric energy metering data, wherein the most critical is that the voltage data used for determination is not stable data, but has a certain volatility, the electric energy metering data is processed only from the time dimension, the sequence trend feature is lost, and the fluctuation characteristic of the voltage curve cannot be effectively fitted. Therefore, in the invention, the time characteristic of the sub-time sequence and the fluctuation characteristic of the power data are simultaneously considered, the two dimensions of the sub-time sequence and the voltage fluctuation value are fitted, and the obtained segmented sequence has the time sequence and the voltage fluctuation of the power data.
In this embodiment, the voltage fluctuation value is a slope of a voltage curve in the power data, and the segment sequence can be generated by fitting the slope of the voltage curve with a slope of a segment time sequence generated by connecting a left endpoint value and a right endpoint value of the sub time sequence. The fitting process can be understood as adjusting the segment time sequence by the slope of the voltage curve to make it more consistent with the voltage fluctuation.
Wherein in the sequence of segments, the slope of each segment indicates the degree of change over the time period and the length indicates the duration.
S2, selecting a subsequence of the time sequence data, calculating an information gain value of the subsequence, classifying the time sequence data through the information gain value, and generating an electric energy metering state diagram;
in an alternative embodiment, selecting a sub-sequence of the time series data, and calculating the information gain value of the sub-sequence includes:
s21, dividing the time sequence data into a plurality of subsequences by taking the sequence feature points as dividing points;
step S22, two subsequences are taken from any of the subsequences, euclidean distance of power data of the two subsequences is calculated, and information gain values of the two subsequences are calculated according to the Euclidean distance;
and step S23, repeating the step S22 until the information gain values of any two subsequences in the plurality of subsequences are calculated, and finally generating an information gain set.
It should be noted that, the sequence feature point is the best matching point in the time sequence data, the time sequence data can be divided into a plurality of sub-sequences which are convenient for analyzing the features of the power data by taking the sequence feature point as a dividing point. The purpose of calculating the euclidean distance of the power data of the two sub-sequences is to calculate the similarity of the voltage curves between the two sub-sequences. The information gain value indicates a classification characteristic of the power data, and the larger the information gain value is, the greater the possibility that the two belong to the same type of power data is, so in the invention, whether the two sub-sequences belong to the same type of power data can be determined by calculating the information gain value of the sub-sequences according to the Euclidean distance.
In an alternative embodiment, taking two sub-sequences from any of the plurality of sub-sequences, calculating euclidean distances of power data of the two sub-sequences, and calculating information gain values of the two sub-sequences according to the euclidean distances includes:
wherein D is the euclidean distance of the power data of the two subsequences; l (L) 1 ,l 2 The sequence lengths of the two subsequences are respectively; t is t i ，t′ i Time points of the two subsequences respectively; v i ，v′ i Respectively two subsequences t i ，t′ i Corresponding power data; im (Im)Information gain values for two sub-sequences; s, S' are two subsequences respectively; s is S i ，S′ i Sequence fragments of two subsequences, respectively; p is p i ，p i The information gain probabilities corresponding to the sequence segments are respectively given.
In an alternative embodiment, the process of classifying the time series data by the information gain value includes:
step S24, sorting the information gain values from big to small;
s25, setting an information gain threshold, and dividing the sorted information gain sets by the information gain threshold to obtain a plurality of classification sets;
and S26, carrying out aggregation treatment on the same classification set to generate an electric energy metering plate, and splicing a plurality of electric energy metering plates to generate an electric energy metering state diagram.
And S3, constructing an abnormality judgment model, and judging the electric energy metering state diagram through the abnormality judgment model to obtain an electric energy metering abnormal result.
In an alternative embodiment, constructing the anomaly discrimination model includes:
s31, acquiring historical electric energy metering abnormal data, and analyzing current and voltage in the historical electric energy metering abnormal data;
and step S32, training and verifying the analysis result as a sample set to generate metering abnormal characteristics.
In this embodiment, the analysis of the current and the voltage in the historical electric energy metering abnormal data includes a phase failure abnormal judgment for the voltage of the private transformer client and a current loss abnormal judgment for the private transformer client.
Further, the judging of the phase failure abnormality of the voltage of the special transformer client comprises the following steps:
(1) The voltage of any one of the three phases of three-wire AC phases is smaller than K1, while the current of the same phase is smaller than K2, the voltage of the other phase is not smaller than K1
The three-phase three-wire B-phase voltage does not participate in judgment.
(2) The voltage of any one phase of ABC in the three-phase four-wire is smaller than K1, the current of the same phase is smaller than K2, the rated (basic) current, and the voltage of other two phases is not smaller than K1.
(3) 3 points need to be monitored during the day.
Generally: 3 points are monitored within a day
Important: any 30 points are accumulated for 3 consecutive days to generate abnormality
Serious: at least 60 points are monitored in one day, any 30 points are monitored, and the generation abnormality threshold value is adjustable
(4) The nominal voltage is the nominal voltage of the metering point parameter ammeter; the rated (base) current is taken to be 1.5A.
Further, the judging of the special transformer client current loss abnormality comprises the following steps:
(1) One phase of the three-phase three-wire is higher than 10% of rated current, the absolute value of the two-phase current is more than 10% different, and the difference ratio is divided into three grades of general, important and serious according to 10% -20%, 20% -50% and more than 50%.
(2) Any phase current of the three-phase four-wire ABC is higher than 10% rated current, the absolute value difference of two phases current is more than 10%, and the difference ratio is divided into three grades of general, important and serious according to 10% -20%, 20% -50% and more than 50%.
(3) At least 3 consecutive points are monitored a day to generate an anomaly.
In an alternative embodiment, discriminating the electric energy metering state diagram by the abnormality discrimination model includes:
step S33, any one electric energy metering plate is taken from the electric energy metering state diagram, and electric energy data of the electric energy metering plate are extracted;
and step S34, calculating the similarity between the electric energy data and the metering abnormal characteristics, judging that the electric energy metering state is abnormal if the similarity is larger than a similarity threshold, and recording an electric energy metering abnormal result in a state sequence.
Example 2
Fig. 2 is a schematic structural diagram of an electrical energy metering abnormality determining system according to an embodiment of the present invention, where, as shown in fig. 2, the electrical energy metering abnormality determining system includes:
the electric energy metering data processing module is used for acquiring electric energy metering data, and carrying out sectional processing on the electric energy metering data based on time sequence to obtain time sequence data of electric energy metering;
the electric energy metering state module is used for selecting a subsequence of the time sequence data, calculating an information gain value of the subsequence, classifying the time sequence data through the information gain value and generating an electric energy metering state diagram;
and the abnormality judgment module is used for constructing an abnormality judgment model, judging the electric energy metering state diagram through the abnormality judgment model and obtaining an electric energy metering abnormal result.
Example 3
Fig. 3 is a schematic structural diagram of an electronic device according to embodiment 3 of the present invention, and as shown in fig. 3, the electronic device includes a processor 21, a memory 22, an input device 23 and an output device 24; the number of processors 21 in the computer device may be one or more, one processor 21 being taken as an example in fig. 3; the processor 21, the memory 22, the input means 23 and the output means 24 in the electronic device may be connected by a bus or by other means, in fig. 3 by way of example.
The memory 22 serves as a computer-readable storage medium for storing software programs, computer-executable programs, and modules. The processor 21 executes various functional applications of the electronic device and data processing by executing software programs, instructions and modules stored in the memory 22, that is, implements a power metering abnormality determination method of embodiment 1.
The memory 22 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, at least one application program required for functions; the storage data area may store data created according to the use of the terminal, etc. In addition, the memory 22 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some examples, memory 22 may further include memory remotely located relative to processor 21, which may be connected to the electronic device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 23 may be used to receive an id and a password entered by a user, etc. The output device 24 is used for outputting the distribution network page.
Example 4
Embodiment 4 of the present invention also provides a computer-readable storage medium, which when executed by a computer processor, is configured to implement a power metering anomaly discrimination method as provided in embodiment 1.
The storage medium containing the computer executable instructions provided in the embodiments of the present invention is not limited to the method operations provided in embodiment 1, and may also perform the related operations in the method for determining an abnormality of electric energy measurement provided in any embodiment of the present invention.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (10)
1. The method for judging the abnormality of electric energy measurement is characterized by comprising the following steps:
step S1, acquiring electric energy metering data, and carrying out sectional processing on the electric energy metering data based on time sequence to obtain time sequence data of electric energy metering;
s2, selecting a subsequence of the time sequence data, calculating an information gain value of the subsequence, classifying the time sequence data through the information gain value, and generating an electric energy metering state diagram;
and S3, constructing an abnormality judgment model, and judging the electric energy metering state diagram through the abnormality judgment model to obtain an electric energy metering abnormal result.
2. The method for determining abnormality of electric energy measurement according to claim 1, wherein the step of performing segment processing on the electric energy measurement data based on time series, obtaining time series data of electric energy measurement includes:
step S11, the electric energy metering data comprise one-to-one corresponding time sequence, state sequence and power data, and a data compression value is obtained through calculation according to the power data;
s12, processing the electric energy metering data by taking the data compression value as a segmentation interval to obtain a segmentation sequence;
s13, calculating the similarity of the time sequence and the segmented sequence by adopting a DTW distance function, and taking the point with the similarity greater than or equal to a similarity threshold value in the segmented sequence as a sequence characteristic point;
and S14, integrating the sequence feature points with the state sequence corresponding to the sequence feature points and the power data to generate time sequence data.
3. The method for determining an abnormality of electric energy measurement according to claim 2, wherein processing the electric energy measurement data at the data compression value as a segment interval to obtain a segment sequence includes:
step S121, dividing the time sequence at equal intervals by taking the data compression value as a segmentation interval to generate a plurality of sub-time sequences;
step S122, acquiring power data corresponding to the sub-time sequence, and calculating the power data to obtain a voltage fluctuation value;
step S123, connecting a left endpoint value and a right endpoint value of the sub-time sequence, and generating a segmented time sequence of the sub-time sequence;
and step S124, fitting the voltage fluctuation value with the segmentation time sequence to generate a segmentation sequence.
4. The method of claim 2, wherein selecting a sub-sequence of the time series data, and calculating the information gain value of the sub-sequence comprises:
s21, dividing the time sequence data into a plurality of subsequences by taking the sequence feature points as dividing points;
step S22, two subsequences are taken from any of the subsequences, euclidean distance of power data of the two subsequences is calculated, and information gain values of the two subsequences are calculated according to the Euclidean distance;
and step S23, repeating the step S22 until the information gain values of any two subsequences in the plurality of subsequences are calculated, and finally generating an information gain set.
5. The method according to claim 4, wherein taking two sub-sequences from any of the plurality of sub-sequences, calculating euclidean distances of power data of the two sub-sequences, and calculating information gain values of the two sub-sequences according to the euclidean distances comprises:
wherein D is the euclidean distance of the power data of the two subsequences; l (L) 1 ,l 2 The sequence lengths of the two subsequences are respectively; t is t i ，t i ' time points of the two sub-sequences, respectively; v i ，v i ' two subsequences t respectively i ，t i ' corresponding power data; im is the information gain value of the two subsequences; s, S' are two subsequences respectively; s is S i ，S i ' respectivelySequence fragments of two subsequences; p is p i ，p i The information gain probabilities corresponding to the sequence segments are respectively given.
6. The method according to claim 4, wherein the step of classifying the time series data by the information gain value comprises:
step S24, sorting the information gain values from big to small;
s25, setting an information gain threshold, and dividing the sorted information gain sets by the information gain threshold to obtain a plurality of classification sets;
and S26, carrying out aggregation treatment on the same classification set to generate an electric energy metering plate, and splicing a plurality of electric energy metering plates to generate an electric energy metering state diagram.
7. The method according to claim 1, wherein an abnormality determination model is constructed, and the abnormality determination model is used for determining the electric energy measurement state diagram:
s31, acquiring historical electric energy metering abnormal data, and analyzing current and voltage in the historical electric energy metering abnormal data;
step S32, training and verifying the analysis result as a sample set to generate metering abnormal characteristics;
step S33, any one electric energy metering plate is taken from the electric energy metering state diagram, and electric energy data of the electric energy metering plate are extracted;
and step S34, calculating the similarity between the electric energy data and the metering abnormal characteristics, judging that the electric energy metering state is abnormal if the similarity is larger than a similarity threshold, and recording an electric energy metering abnormal result in a state sequence.
8. An electric energy metering abnormality discriminating system, characterized by comprising:
the electric energy metering data processing module is used for acquiring electric energy metering data, and carrying out sectional processing on the electric energy metering data based on time sequence to obtain time sequence data of electric energy metering;
the electric energy metering state module is used for selecting a subsequence of the time sequence data, calculating an information gain value of the subsequence, classifying the time sequence data through the information gain value and generating an electric energy metering state diagram;
and the abnormality judgment module is used for constructing an abnormality judgment model, judging the electric energy metering state diagram through the abnormality judgment model and obtaining an electric energy metering abnormal result.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing a method of discriminating an abnormality of electric energy metering according to claims 1 to 7 when executing the program.
10. A computer-readable storage medium having stored thereon a computer program, wherein the program when executed by a processor implements a power metering abnormality discrimination method according to claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311526900.5A CN117493857A (en) | 2023-11-15 | 2023-11-15 | Electric energy metering abnormality judging method, system, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311526900.5A CN117493857A (en) | 2023-11-15 | 2023-11-15 | Electric energy metering abnormality judging method, system, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117493857A true CN117493857A (en) | 2024-02-02 |
Family
ID=89679828
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311526900.5A Pending CN117493857A (en) | 2023-11-15 | 2023-11-15 | Electric energy metering abnormality judging method, system, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117493857A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019184131A1 (en) * | 2018-03-29 | 2019-10-03 | 清华大学 | Entropy method and density clustering method integrated power stealing detection method and apparatus |
| CN111814897A (en) * | 2020-07-20 | 2020-10-23 | 辽宁大学 | Time series data classification method based on multi-level shape |
| US20230169152A1 (en) * | 2021-11-30 | 2023-06-01 | International Business Machines Corporation | Finding outliers in similar time series samples |
| CN116861354A (en) * | 2023-07-17 | 2023-10-10 | 国家电网有限公司华北分部 | Abnormality identification and mode distinguishing method and system for monitoring data of power transformer |
| CN116956189A (en) * | 2023-07-07 | 2023-10-27 | 无锡学院 | Current abnormality detection system, method, electronic equipment and medium |
-
2023
- 2023-11-15 CN CN202311526900.5A patent/CN117493857A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019184131A1 (en) * | 2018-03-29 | 2019-10-03 | 清华大学 | Entropy method and density clustering method integrated power stealing detection method and apparatus |
| CN111814897A (en) * | 2020-07-20 | 2020-10-23 | 辽宁大学 | Time series data classification method based on multi-level shape |
| US20230169152A1 (en) * | 2021-11-30 | 2023-06-01 | International Business Machines Corporation | Finding outliers in similar time series samples |
| CN116956189A (en) * | 2023-07-07 | 2023-10-27 | 无锡学院 | Current abnormality detection system, method, electronic equipment and medium |
| CN116861354A (en) * | 2023-07-17 | 2023-10-10 | 国家电网有限公司华北分部 | Abnormality identification and mode distinguishing method and system for monitoring data of power transformer |
Non-Patent Citations (1)
| Title |
|---|
| 裴湉;齐冬莲;: "基于时间序列提取和维诺图的电力数据异常检测方法", 电力建设, no. 05, 1 May 2017 (2017-05-01), pages 109 - 114 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2528033A1 (en) | Virtual sub-metering using combined classifiers | |
| CN107422266B (en) | Fault diagnosis method and device for high-capacity battery energy storage system | |
| CN116502112B (en) | New energy power supply test data management method and system | |
| CN113011481B (en) | Electric energy meter function abnormality assessment method and system based on decision tree algorithm | |
| Ma et al. | Topology identification of distribution networks using a split-EM based data-driven approach | |
| CN111626360B (en) | Method, apparatus, device and storage medium for detecting boiler fault type | |
| CN116774077A (en) | Method, device, equipment and storage medium for detecting health of energy storage power station battery | |
| CN117849700B (en) | Modular electric energy metering system capable of controlling measurement | |
| CN108414944A (en) | Decay detection method and device | |
| Frank et al. | Extracting operating modes from building electrical load data | |
| Carotenuto et al. | Online recording a PV module fingerprint | |
| CN111894814A (en) | Fault processing system and method for power generation system | |
| CN111506636A (en) | System and method for analyzing residential electricity consumption behavior based on autoregressive and neighbor algorithm | |
| CN117493857A (en) | Electric energy metering abnormality judging method, system, equipment and medium | |
| CN116910655A (en) | Intelligent ammeter fault prediction method based on device measurement data | |
| CN116757870A (en) | Intelligent energy monitoring data processing method and system for energy Internet of things | |
| CN115343579B (en) | Power grid fault analysis method and device and electronic equipment | |
| CN111880020A (en) | Fault recording data generation method and device for power distribution and utilization system of power consumer | |
| CN116520068A (en) | Diagnostic method, device, equipment and storage medium for electric power data | |
| CN116243199A (en) | Method and device for detecting abnormal battery cell and computer storage medium | |
| CN113269478B (en) | Concentrator abnormal data reminding method and system based on multiple models | |
| CN115456097A (en) | Power utilization detection method and detection terminal suitable for high-power-supply low-count special transformer users | |
| CN114037010A (en) | Method and device for identifying abnormal electric quantity data | |
| CN109615558B (en) | User electricity habit analysis method based on electricity parameter big data statistics | |
| CN112305489A (en) | Method, device and equipment for detecting abnormal voltage fluctuation and storage medium |
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 |