CN114240102A - Line loss abnormal data identification method and device, electronic equipment and storage medium - Google Patents
Line loss abnormal data identification method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114240102A CN114240102A CN202111469780.0A CN202111469780A CN114240102A CN 114240102 A CN114240102 A CN 114240102A CN 202111469780 A CN202111469780 A CN 202111469780A CN 114240102 A CN114240102 A CN 114240102A
- Authority
- CN
- China
- Prior art keywords
- entropy
- data
- consumption data
- power consumption
- electricity consumption
- 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
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 73
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000003860 storage Methods 0.000 title claims abstract description 12
- 230000005611 electricity Effects 0.000 claims abstract description 89
- 230000011218 segmentation Effects 0.000 claims abstract description 56
- 230000008859 change Effects 0.000 claims description 21
- 238000007781 pre-processing Methods 0.000 claims description 9
- 230000005856 abnormality Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 10
- 238000007689 inspection Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 8
- 230000006399 behavior Effects 0.000 description 7
- 238000004590 computer program Methods 0.000 description 7
- 238000001514 detection method Methods 0.000 description 6
- 238000009826 distribution Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000002547 anomalous effect Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000010420 art technique Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- 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
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a line loss abnormal data identification method and device, electronic equipment and a storage medium, and aims to solve the technical problems that an existing line loss abnormal data identification method is easy to misreport and low in positioning accuracy. The invention comprises the following steps: acquiring power consumption data of a user; segmenting the electricity consumption data according to a preset time interval to obtain a plurality of segmentation sequences; calculating the entropy value of each power consumption data in the segmented sequence to obtain an entropy set curve of the segmented sequence; determining a normal entropy interval from the entropy set curve; and determining the electricity consumption data corresponding to the entropy value which is not in the normal entropy value interval as abnormal data.
Description
Technical Field
The present invention relates to the field of data identification technologies, and in particular, to a line loss abnormal data identification method and apparatus, an electronic device, and a storage medium.
Background
The electric energy loss is one of the important indexes of the economic benefit of power grid enterprises. The accurate identification of the line loss abnormity can effectively guide the power grid enterprise to develop energy-saving loss planning in a targeted manner on the one hand, and can provide a reference direction for the power grid enterprise to develop power utilization inspection, attack default power stealing behaviors and recover legal rights and interests of a company on the other hand. However, the service object groups of the power grid enterprises are large and complex, and the limited customer service human resources bring constraints and limitations to the comprehensive spread of on-site electricity inspection. How to scientifically, objectively, timely and accurately identify the line loss abnormal situation is a major technical challenge that all power grid enterprises are always exploring and advancing at present.
According to the traditional inspection, detailed electricity data of customers are not mastered, and power grid enterprises mainly guide to develop plan arrangement of inspection work in two modes, namely, customer visit and field inspection plans are arranged according to customer service work development experience by combining monthly electricity consumption of the customers under the conditions that the electricity consumption of the customers is increased suddenly or the highest load exceeds the loading capacity; and secondly, combining the monthly line loss of the distribution room and the load characteristics of the access customers, selecting the industry customers with higher electricity stealing possibility for the high-loss distribution room higher than the set threshold value according to the experience developed by customer service work, and arranging the customer visit and field inspection plan. The method selects monthly abnormal electricity customers and monthly high-loss transformer area to carry out on-site electricity inspection, can centralize limited resources on determined customers and transformer areas, is a traditional practical line loss abnormity identification method through practical inspection, but has the limitation derived from subjective assumption defined by the traditional practical experience.
With the deep advance of electric power intelligent construction, digital power grid enterprises gradually construct self large electric energy databases and explore ways of large electric energy data change. The line loss is used as important business data in power grid enterprise data, and continuous acquisition and intelligent analysis of the line loss data are the important direction for the high electric energy data value. At present, the data-based line loss anomaly detection mainly includes anomaly detection based on an artificial neural network, anomaly detection based on clustering, and anomaly detection based on unsupervised learning. Common prior art techniques include: detecting abnormal values based on the BP neural network, namely determining abnormality when the deviation exceeds a threshold value by comparing the predicted value of the BP neural network with line loss data; based on abnormal detection of DBSCAN clustering, namely clustering is carried out to obtain clustering clusters, and outliers are determined to be abnormal; and (3) based on abnormal value detection of the isolated forest, namely constructing a data structure of the isolated forest, rapidly judging the difference degree between the sample point and the surrounding sample points through a binary tree structure, and determining abnormality by combining abnormal value scoring.
The traditional method is too dependent on historical experience and individual ability of an inspection team, and most of the prior art designs and selects characteristic index items according to daily load curves, sudden drop of power consumption and historical inspection information and then identifies power consumption abnormity by matching with adaptive improvement of an algorithm. Although the number of service customers of the power grid enterprise is large, the types of industries are complicated, and the power utilization behavior patterns of the customers are varied, the power supply service tends to become refined and customized day by day along with the increasing electric power demand of people for pursuing good life. Nowadays, the time interval of the load curve is fixed, the generalized data identification cannot well aim at the electricity utilization behavior characteristics of the client, and the normal electricity utilization behavior characteristics of the client assumed by the selected characteristic index item are not strictly met. Moreover, the actual electricity utilization condition of the client does not strictly follow the standard load curve of the client in each time dimension, and false alarm is easily caused. Meanwhile, the problems of incomplete identification, complex identification process and the like exist in the electric energy.
Disclosure of Invention
The invention provides a line loss abnormal data identification method and device, electronic equipment and a storage medium, and aims to solve the technical problems that an existing line loss abnormal data identification method is easy to misreport and low in positioning accuracy.
The invention provides a line loss abnormal data identification method, which comprises the following steps:
acquiring power consumption data of a user;
segmenting the electricity consumption data according to a preset time interval to obtain a plurality of segmentation sequences;
calculating the entropy value of each power consumption data in the segmented sequence to obtain an entropy set curve of the segmented sequence;
determining a normal entropy interval from the entropy set curve;
and determining the electricity consumption data corresponding to the entropy value which is not in the normal entropy value interval as abnormal data.
Optionally, before the step of segmenting the electricity consumption data according to a preset time interval to obtain a plurality of segmentation sequences, the method further includes:
preprocessing the electricity consumption data to obtain preprocessed data;
the step of segmenting the electricity consumption data according to a preset time interval to obtain a plurality of segmentation sequences comprises the following steps:
and segmenting the preprocessed data according to a preset time interval to obtain a plurality of segmentation sequences.
Optionally, the step of calculating entropy values of the power consumption data in the segment sequence to obtain an entropy set curve of the segment sequence includes:
sequencing the electricity consumption data in the segmentation sequence to obtain a descending electricity consumption sequence;
sequentially calculating the entropy value of each power consumption data in the segmentation sequence according to the descending order of the electric quantity;
and generating an entropy set curve of the segmented sequence by adopting the entropy values of the electricity consumption data.
Optionally, the step of sequentially calculating an entropy value of each power consumption data in the segmentation sequence according to the descending order of the power consumption includes:
according to the electricity quantity descending order, sequentially taking the electricity consumption data except the first electricity consumption data as node data, and taking the node data and the electricity consumption data before the node data as sample data;
calculating sample mean values of power consumption time points corresponding to all power consumption data in the sample data;
calculating a second-order center distance and a fourth-order center distance according to the sample mean value and the power utilization time point;
and calculating the entropy value of the node data by adopting the second-order center distance and the fourth-order center distance.
Optionally, the step of determining a normal entropy interval from the entropy set curve includes:
acquiring an entropy value corresponding to the point with the maximum slope change in the entropy set curve and an entropy value corresponding to the point with the second maximum slope change in the entropy set curve as an over-limit value;
determining an interval between the two said over-limits as a normal entropy interval.
Optionally, the overrun value comprises an upper limit value and a lower limit value; the step of determining the electricity consumption data corresponding to the entropy value which is not in the normal entropy value interval as abnormal data comprises the following steps:
determining the power consumption data corresponding to the entropy value smaller than the lower limit value as lower abnormal data;
and determining the electricity consumption data corresponding to the entropy value larger than the upper limit value as upper abnormal data.
The invention also provides a line loss abnormal data identification device, which comprises:
the acquisition module is used for acquiring the electricity consumption data of the user;
the segmentation module is used for segmenting the electricity consumption data according to a preset time interval to obtain a plurality of segmentation sequences;
the calculation module is used for calculating the entropy value of each power consumption data in the segmentation sequence to obtain an entropy set curve of the segmentation sequence;
a normal entropy interval determination module, configured to determine a normal entropy interval from the entropy set curve;
and the abnormal data determining module is used for determining the electricity consumption data corresponding to the entropy value which is not in the normal entropy value interval as abnormal data.
Optionally, the method further comprises:
the preprocessing module is used for preprocessing the power consumption data to obtain preprocessed data;
the segmentation module comprises:
and the segmentation submodule is used for segmenting the preprocessed data according to a preset time interval to obtain a plurality of segmentation sequences.
The invention also provides an electronic device comprising a processor and a memory:
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to execute the line loss abnormal data identification method according to instructions in the program code.
The present invention also provides a computer-readable storage medium for storing a program code for executing the line loss abnormal data identification method as described in any one of the above.
According to the technical scheme, the invention has the following advantages: the invention discloses a line loss abnormal data identification method, and particularly discloses: acquiring power consumption data of a user; segmenting the electricity consumption data according to a preset time interval to obtain a plurality of segmentation sequences; calculating the entropy value of each power consumption data in the segmented sequence to obtain an entropy set curve of the segmented sequence; determining a normal entropy value interval from an entropy set curve; and determining the electricity consumption data corresponding to the entropy value which is not in the normal entropy value interval as abnormal data. Because the electricity utilization habits of the users in different time periods are different, the method divides the electricity consumption data of the users into a plurality of segmentation sequences according to the time intervals so as to avoid the influence of large difference of electricity utilization behaviors in different time periods on the recognition result. And then, respectively calculating the entropy value of each power consumption data in each segmented sequence, so as to identify abnormal data through the change condition of the entropy value, wherein the entropy value can reflect the sudden change of the power consumption to a certain extent, and therefore, the abnormal data can be effectively identified through the change condition of the entropy value.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without inventive exercise.
Fig. 1 is a flowchart illustrating steps of a line loss abnormal data identification method according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating steps of a method for identifying line loss abnormal data according to another embodiment of the present invention;
fig. 3 is a block diagram of a line loss abnormal data identification apparatus according to an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a line loss abnormal data identification method, a line loss abnormal data identification device, electronic equipment and a storage medium, and aims to solve the technical problems that an existing line loss abnormal data identification method is easy to misreport and low in positioning accuracy.
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the embodiments described below are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, fig. 1 is a flowchart illustrating steps of a method for identifying line loss abnormal data according to an embodiment of the present invention.
The invention provides a line loss abnormal data identification method, which specifically comprises the following steps:
in practical application, under the influence of line loss, the power consumption data of a user has three situations, including too low power consumption, normal power consumption and too high power consumption, wherein the too low power consumption and the too high power consumption refer to the power consumption data with the power consumption lower than or higher than the upper limit threshold value under the standard load curve. The standard load curve refers to a power consumption load curve in a standard time unit under the condition that no line loss occurs, and the standard time unit can be a natural day, a natural month and the like. The method may be determined according to actual analysis requirements, and the present invention is not limited to this.
In the embodiment of the invention, the power consumption data of the user in a certain time period can be acquired to perform line loss analysis, such as the power consumption data in a week and a month.
102, segmenting electricity consumption data according to a preset time interval to obtain a plurality of segmentation sequences;
after the power consumption data of the user is obtained, the selected time period can be segmented according to the set time interval to obtain a plurality of segmentation sequences, wherein each segmentation sequence comprises the power consumption data corresponding to the plurality of time sampling points.
In one example, assuming that the set of power usage data is E, which is divided into M segments, there is E ═ { E (1), E (2),.., E (M-1), E (M) }.
103, calculating entropy values of all power consumption data in the segmented sequence to obtain an entropy set curve of the segmented sequence;
after the time division of the power consumption data is completed to obtain a plurality of segmentation sequences, the entropy value of each power consumption data in each segmentation sequence can be calculated, so that the entropy set curve of the segmentation sequences is obtained.
In one example, entropy values for the individual power usage data in the segmented sequence may be calculated by a cloud model.
The cloud model is a specific implementation method of the cloud and is also a basis for operation, reasoning, control and the like based on the cloud. It can represent a process from qualitative to quantitative representation (forward cloud generator) and also from quantitative to qualitative representation (reverse cloud generator). Cloud model passing expectation ExEntropy EnAnd entropy HeThe 3 digital features describe the randomness and ambiguity of the concept. Wherein E isxRepresenting a desire for cloud droplet distribution; enThe uncertainty of a qualitative concept is measured, the dispersion degree and the value range of cloud droplets are reflected in a domain space, and the stability of segmented sequence data can be evaluated; heThe uncertainty of the entropy is measured.
104, determining a normal entropy value interval from the entropy set curve;
and 105, determining the power consumption data corresponding to the entropy value which is not in the normal entropy value interval as abnormal data.
Each point on the entropy set represents the entropy value of different power consumption data, and a point with a sudden change can be determined according to the change situation of the entropy values on the curve. Entropy values outside the normal entropy interval correspond to either too low power usage or too high power usage, and are all anomalous data.
In the embodiment of the invention, because the electricity utilization habits of users in different time periods are different, the electricity utilization data of the users are divided into a plurality of segmentation sequences according to the time intervals, so that the influence of large difference of electricity utilization behaviors in different time periods on the recognition result is avoided. And then, respectively calculating the entropy value of each power consumption data in each segmented sequence, so as to identify abnormal data through the change condition of the entropy value, wherein the entropy value can reflect the sudden change of the power consumption to a certain extent, and therefore, the abnormal data can be effectively identified through the change condition of the entropy value.
Referring to fig. 2, fig. 2 is a flowchart illustrating a method for identifying line loss abnormal data according to another embodiment of the present invention. The method specifically comprises the following steps:
step 201 is the same as step 101, and reference may be specifically made to the description of step 101, which is not described herein again.
after the power consumption data are obtained, the power consumption data can be preprocessed, abnormal data caused by faults of links such as measurement, collection or transmission are eliminated, and preprocessed data are obtained.
after the power consumption data of the user is obtained, the selected time period can be segmented according to the set time interval to obtain a plurality of segmentation sequences, wherein each segmentation sequence comprises the power consumption data corresponding to the plurality of time sampling points.
after the time division of the power consumption data is completed to obtain a plurality of segmentation sequences, the entropy value of each power consumption data in each segmentation sequence can be calculated, so that the entropy set curve of the segmentation sequences is obtained.
In one example, calculating entropy values of the respective power consumption data in the segment sequence to obtain an entropy set curve of the segment sequence may include the following sub-steps:
s41, sorting the electricity consumption data in the segmentation sequence to obtain a descending electricity consumption sequence;
s42, sequentially calculating the entropy value of each power consumption data in the segmentation sequence according to the descending order of the electric quantity;
and S43, generating an entropy set curve of the segmentation sequence by adopting the entropy values of the electricity consumption data.
In the present embodiment, let e (i) { (x)1,y1)，(x2,y2)，...，(xn,yn) There are n data pairs of electricity consumption time and electricity consumption, i belongs to [1, M ]](ii) a E (i) can be sorted from large to small according to the electricity consumption data to obtain the descending order of the electricity quantity; and sequentially calculating the entropy value of each power consumption data in the segmentation sequence according to the power consumption descending order of the power consumption data, thereby obtaining the entropy value of each power consumption data which is in one-to-one correspondence with the power consumption descending order of the power consumption data.
In one example, the step of sequentially calculating the entropy value of each power consumption data in the segmentation sequence in the descending order of the power consumption may include:
s421, sequentially taking the electricity consumption data except the first electricity consumption data as node data according to the descending order of the electricity quantity, and taking the node data and the electricity consumption data before the node data as sample data;
s422, calculating sample mean values of power consumption time points corresponding to all power consumption data in the sample data;
s423, calculating a second-order center distance and a fourth-order center distance according to the sample mean value and the power utilization time point;
and S424, calculating the entropy value of the node data by adopting the second-order center distance and the fourth-order center distance.
In the embodiment of the invention, the j (j e (2, n)) th power consumption data can be used as node data, and the previous j power consumption data in E (i) are sequentially input into a reverse cloud generator to calculate the entropy value of the j power consumption data, so that n-1 entropy values are obtained. It is noted that, in order to keep the entropy consistent with the amount of power consumption data, the entropy of the power consumption data of the first coordinate point may be defined as 0.
The inverse cloud generator mainly finds the distribution characteristics of a certain number of data samples and converts the characteristics into a qualitative concept represented by numerical characteristics. The method mainly comprises the following steps:
1) calculating a sample mean value E of power consumption time points corresponding to all power consumption data in sample datax：
2) Calculating the second-order center distance C of the sample data2：
3) Calculating the fourth-order center distance C of the sample data4：
4) Calculating entropy E of sample data by using second-order center distance and fourth-order center distance of sample datan：
Wherein x isi(i ═ 1, 2.., N) is the sample point.
in step 206, the interval between the two over-limits is determined as the normal entropy interval.
In the embodiment of the present invention, two points of significant slope change on the entropy-based curve, for example, entropy values corresponding to the first and second large slope changes, may be used as the super-limit values, and the two super-limit values may be used as the critical points of the normal entropy interval, so as to obtain the normal entropy interval. And the electricity consumption data with the entropy value within the normal entropy value interval is the normal electricity consumption data.
And step 207, determining the electricity consumption data corresponding to the entropy value which is not in the normal entropy value interval as abnormal data.
In this embodiment of the present invention, the overrun value may include an upper limit value and a lower limit value, and the step of determining the power consumption data corresponding to the entropy value that is not in the normal entropy value interval as abnormal data may include:
determining the power consumption data corresponding to the entropy value smaller than the lower limit value as lower abnormal data; and determining the electricity consumption data corresponding to the entropy value larger than the upper limit value as upper abnormal data.
Specifically, the entropy values of the points in the entropy set curve may be compared with an upper limit value and a lower limit value, the electricity consumption time point and the electricity consumption data corresponding to the entropy value smaller than the lower limit value are determined as lower abnormal data, and the electricity consumption time point and the electricity consumption data corresponding to the entropy value larger than the upper limit value are determined as upper abnormal data, so as to distinguish data with too low electricity consumption and data with too high electricity consumption.
In the embodiment of the invention, because the electricity utilization habits of users in different time periods are different, the electricity utilization data of the users are divided into a plurality of segmentation sequences according to the time intervals, so that the influence of large difference of electricity utilization behaviors in different time periods on the recognition result is avoided. And then, respectively calculating the entropy value of each power consumption data in each segmented sequence, so as to identify abnormal data through the change condition of the entropy value, wherein the entropy value can reflect the sudden change of the power consumption to a certain extent, and therefore, the abnormal data can be effectively identified through the change condition of the entropy value.
Referring to fig. 3, fig. 3 is a block diagram illustrating a structure of a line loss abnormal data identification apparatus according to an embodiment of the present invention.
The embodiment of the invention provides a line loss abnormal data identification device, which comprises:
an obtaining module 301, configured to obtain power consumption data of a user;
the segmentation module 302 is configured to segment the power consumption data according to a preset time interval to obtain a plurality of segmentation sequences;
the calculating module 303 is configured to calculate an entropy value of each power consumption data in the segment sequence to obtain an entropy set curve of the segment sequence;
a normal entropy interval determination module 304, configured to determine a normal entropy interval from the entropy set curve;
and the abnormal data determining module 305 is configured to determine, as abnormal data, power consumption data corresponding to an entropy value that is not in the normal entropy value interval.
In the embodiment of the present invention, the method further includes:
the preprocessing module is used for preprocessing the electricity consumption data to obtain preprocessed data;
a segmentation module 302 comprising:
and the segmentation submodule is used for segmenting the preprocessed data according to a preset time interval to obtain a plurality of segmentation sequences.
In this embodiment of the present invention, the calculating module 303 includes:
the sequencing submodule is used for sequencing the electricity consumption data in the segmentation sequence to obtain a descending order of the electricity consumption;
the entropy calculation submodule is used for sequentially calculating the entropy of each power consumption data in the segmentation sequence according to the descending order of the electric quantity;
and the entropy set curve generation submodule is used for generating an entropy set curve of the segmented sequence by adopting the entropy values of the power consumption data.
In an embodiment of the present invention, the entropy calculation sub-module includes:
the sample data generating unit is used for sequentially taking the electricity consumption data except the first electricity consumption data as node data according to the descending order of the electricity quantity, and taking the node data and the electricity consumption data before the node data as sample data;
the sample mean value calculating unit is used for calculating the sample mean values of the electricity utilization time points corresponding to all the electricity consumption data in the sample data;
the center distance calculating unit is used for calculating a second-order center distance and a fourth-order center distance according to the sample mean value and the power utilization time point;
and the entropy value calculating unit is used for calculating the entropy value of the node data by adopting the second-order center distance and the fourth-order center distance.
In this embodiment of the present invention, the normal entropy interval determining module 304 includes:
the over-limit value obtaining submodule is used for obtaining an entropy value corresponding to the point with the maximum slope change in the entropy set curve and an entropy value corresponding to the point with the second maximum slope change in the entropy set curve as an over-limit value;
and the normal entropy interval determining submodule is used for determining an interval between the two over-limit values as a normal entropy interval.
In the embodiment of the invention, the overrun value comprises an upper limit value and a lower limit value; an anomalous data determination module 305 comprising:
the lower abnormal data determining submodule is used for determining the power consumption data corresponding to the entropy value smaller than the lower limit value as lower abnormal data;
and the upper abnormal data determining submodule is used for determining the power consumption data corresponding to the entropy value larger than the upper limit value as the upper abnormal data.
An embodiment of the present invention further provides an electronic device, where the device includes a processor and a memory:
the memory is used for storing the program codes and transmitting the program codes to the processor;
the processor is used for executing the line loss abnormal data identification method according to the embodiment of the invention according to the instructions in the program codes.
The embodiment of the invention also provides a computer-readable storage medium, which is used for storing the program code, and the program code is used for executing the line loss abnormal data identification method in the embodiment of the invention.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention 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.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. 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 terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, 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 terminal 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 terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the embodiments of the invention.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal 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 terminal. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or terminal that comprises the element.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A line loss abnormal data identification method is characterized by comprising the following steps:
acquiring power consumption data of a user;
segmenting the electricity consumption data according to a preset time interval to obtain a plurality of segmentation sequences;
calculating the entropy value of each power consumption data in the segmented sequence to obtain an entropy set curve of the segmented sequence;
determining a normal entropy interval from the entropy set curve;
and determining the electricity consumption data corresponding to the entropy value which is not in the normal entropy value interval as abnormal data.
2. The method for identifying abnormal line loss data according to claim 1, wherein before the step of segmenting the electricity consumption data according to the preset time interval to obtain a plurality of segmentation sequences, the method further comprises:
preprocessing the electricity consumption data to obtain preprocessed data;
the step of segmenting the electricity consumption data according to a preset time interval to obtain a plurality of segmentation sequences comprises the following steps:
and segmenting the preprocessed data according to a preset time interval to obtain a plurality of segmentation sequences.
3. The method for identifying line loss abnormal data according to claim 1, wherein the step of calculating the entropy of each power consumption data in the segment sequence to obtain the entropy set curve of the segment sequence comprises:
sequencing the electricity consumption data in the segmentation sequence to obtain a descending electricity consumption sequence;
sequentially calculating the entropy value of each power consumption data in the segmentation sequence according to the descending order of the electric quantity;
and generating an entropy set curve of the segmented sequence by adopting the entropy values of the electricity consumption data.
4. The line loss abnormal data identification method according to claim 3, wherein the step of sequentially calculating the entropy of each power consumption data in the segment sequence according to the power quantity descending order comprises:
according to the electricity quantity descending order, sequentially taking the electricity consumption data except the first electricity consumption data as node data, and taking the node data and the electricity consumption data before the node data as sample data;
calculating sample mean values of power consumption time points corresponding to all power consumption data in the sample data;
calculating a second-order center distance and a fourth-order center distance according to the sample mean value and the power utilization time point;
and calculating the entropy value of the node data by adopting the second-order center distance and the fourth-order center distance.
5. The method for identifying line loss abnormal data according to claim 1, wherein the step of determining a normal entropy interval from the entropy set curve comprises:
acquiring an entropy value corresponding to the point with the maximum slope change in the entropy set curve and an entropy value corresponding to the point with the second maximum slope change in the entropy set curve as an over-limit value;
determining an interval between the two said over-limits as a normal entropy interval.
6. The line loss abnormality data identification method according to claim 5, wherein the excess limit value includes an upper limit value and a lower limit value; the step of determining the electricity consumption data corresponding to the entropy value which is not in the normal entropy value interval as abnormal data comprises the following steps:
determining the power consumption data corresponding to the entropy value smaller than the lower limit value as lower abnormal data;
and determining the electricity consumption data corresponding to the entropy value larger than the upper limit value as upper abnormal data.
7. A line loss abnormal data identification device is characterized by comprising:
the acquisition module is used for acquiring the electricity consumption data of the user;
the segmentation module is used for segmenting the electricity consumption data according to a preset time interval to obtain a plurality of segmentation sequences;
the calculation module is used for calculating the entropy value of each power consumption data in the segmentation sequence to obtain an entropy set curve of the segmentation sequence;
a normal entropy interval determination module, configured to determine a normal entropy interval from the entropy set curve;
and the abnormal data determining module is used for determining the electricity consumption data corresponding to the entropy value which is not in the normal entropy value interval as abnormal data.
8. The apparatus for identifying line loss abnormality data according to claim 7, further comprising:
the preprocessing module is used for preprocessing the power consumption data to obtain preprocessed data;
the segmentation module comprises:
and the segmentation submodule is used for segmenting the preprocessed data according to a preset time interval to obtain a plurality of segmentation sequences.
9. An electronic device, comprising a processor and a memory:
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to execute the line loss abnormal data identification method according to any one of claims 1 to 6 according to instructions in the program code.
10. A computer-readable storage medium for storing a program code for executing the line loss abnormality data identification method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111469780.0A CN114240102A (en) | 2021-12-03 | 2021-12-03 | Line loss abnormal data identification method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111469780.0A CN114240102A (en) | 2021-12-03 | 2021-12-03 | Line loss abnormal data identification method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114240102A true CN114240102A (en) | 2022-03-25 |
Family
ID=80753015
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111469780.0A Pending CN114240102A (en) | 2021-12-03 | 2021-12-03 | Line loss abnormal data identification method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114240102A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117708749A (en) * | 2024-02-05 | 2024-03-15 | 江苏省电力试验研究院有限公司 | Multi-model fusion type power distribution network time-sharing segmentation line loss fine diagnosis method and system |
-
2021
- 2021-12-03 CN CN202111469780.0A patent/CN114240102A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117708749A (en) * | 2024-02-05 | 2024-03-15 | 江苏省电力试验研究院有限公司 | Multi-model fusion type power distribution network time-sharing segmentation line loss fine diagnosis method and system |
| CN117708749B (en) * | 2024-02-05 | 2024-04-19 | 江苏省电力试验研究院有限公司 | Multi-model fusion type power distribution network time-sharing segmentation line loss fine diagnosis method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106909487B (en) | Early warning method and device applied to information system | |
| Llanos et al. | Load estimation for microgrid planning based on a self-organizing map methodology | |
| Rajagopal et al. | [Retracted] Human Resource Demand Prediction and Configuration Model Based on Grey Wolf Optimization and Recurrent Neural Network | |
| Chitra et al. | Customer retention in banking sector using predictive data mining technique | |
| Nwulu et al. | Modelling and predicting electricity consumption using artificial neural networks | |
| Justo et al. | Behavioral similarity of residential customers using a neural network based on adaptive resonance theory | |
| CN104598449A (en) | Preference-based clustering | |
| CN111126629B (en) | Model generation method, brush list identification method, system, equipment and medium | |
| Kim et al. | Short-term electric load forecasting using data mining technique | |
| CN114240102A (en) | Line loss abnormal data identification method and device, electronic equipment and storage medium | |
| CN109583712B (en) | Data index analysis method and device and storage medium | |
| Gökçe et al. | Performance comparison of simple regression, random forest and XGBoost algorithms for forecasting electricity demand | |
| CN115982646B (en) | Management method and system for multisource test data based on cloud platform | |
| CN109840536A (en) | A kind of power grid power supply reliability horizontal clustering method and system | |
| Tang et al. | Leveraging socioeconomic information and deep learning for residential load pattern prediction | |
| Kojury-Naftchali et al. | AMI Data Analytics: customer charactrization by relief algorithm and supplementary tools | |
| Popeangă | Data mining smart energy time series | |
| Poudel et al. | Artificial intelligence for energy fraud detection: a review | |
| Akbaş et al. | Predicting newspaper sales by using data mining techniques | |
| Zekić-Sušac | Machine learning in energy consumption management | |
| Wang et al. | Power load forecasting using data mining and knowledge discovery technology | |
| Toussaint et al. | Identifying optimal clustering structures for residential energy consumption patterns using competency questions | |
| CN113744081B (en) | Analysis method for electricity stealing behavior | |
| Alqasim | Using Regression Analysis for Predicting Energy Consumption in Dubai Police | |
| Silva et al. | Understanding the Relationship Between Population Density and Low Voltage Faults Causes in Electricity Distribution Network |
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 |