CN117131448A - Big data-based electricity stealing user intelligent identification system and method - Google Patents
Big data-based electricity stealing user intelligent identification system and method Download PDFInfo
- Publication number
- CN117131448A CN117131448A CN202311081013.1A CN202311081013A CN117131448A CN 117131448 A CN117131448 A CN 117131448A CN 202311081013 A CN202311081013 A CN 202311081013A CN 117131448 A CN117131448 A CN 117131448A
- Authority
- CN
- China
- Prior art keywords
- electricity
- user
- stealing
- information
- data
- 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.)
- Granted
Links
- 230000005611 electricity Effects 0.000 title claims abstract description 866
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000007726 management method Methods 0.000 claims abstract description 46
- 238000012545 processing Methods 0.000 claims abstract description 37
- 238000013500 data storage Methods 0.000 claims abstract description 18
- 230000008859 change Effects 0.000 claims description 62
- 238000000605 extraction Methods 0.000 claims description 16
- 238000012937 correction Methods 0.000 claims description 11
- 238000012795 verification Methods 0.000 claims description 10
- 230000006399 behavior Effects 0.000 claims description 9
- 230000002159 abnormal effect Effects 0.000 claims description 8
- 238000012790 confirmation Methods 0.000 claims description 7
- 230000005540 biological transmission Effects 0.000 claims description 6
- 238000012986 modification Methods 0.000 claims description 6
- 230000004048 modification Effects 0.000 claims description 6
- 230000001360 synchronised effect Effects 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 230000007717 exclusion Effects 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000005612 types of electricity Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 7
- 238000004088 simulation Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 206010000369 Accident Diseases 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- 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
-
- 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
- G06F18/217—Validation; Performance evaluation; Active pattern learning 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Economics (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)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an intelligent identification system and method for electricity stealing users based on big data, which belong to the technical field of power grid safety and comprise the following steps: the system comprises an information acquisition module, a data processing module, an electricity stealing identification module, an intelligent control module and a data storage module. The invention solves the problems that the prior art can not intelligently identify and control electricity stealing users, resulting in poor management effect of the electricity stealing users and can not quickly find electricity stealing.
Description
Technical Field
The invention relates to the field of electric charge metering in the power grid safety technology, in particular to an intelligent identification system and method for electricity stealing users based on big data.
Background
The demand of people for electric power is increased day by day along with the progress of times and science and technology, and the electric power production is also continuously developed along with the demand of markets for electric power; meanwhile, the electricity larceny of illegal users is a non-negligible problem, and huge economic losses are caused to the electricity production departments every year, and more importantly, electricity larceny users often steal electricity by damaging electric facilities, in this case, the damaged electric facilities directly cause the economic losses of the electricity production departments, and electric shock accidents, electric fire accidents and the like are likely to occur due to the problems of exposed electric wires and the like, so that casualties, other serious disaster accidents and the like are likely to be caused.
The Chinese patent with publication number of CN115510781A discloses a verification method of an anti-electricity-theft early warning model based on an anti-electricity-theft simulation experiment platform, a public transformer area or a line is selected, electricity-theft and metering abnormal transformation is conducted on an application electricity user on the anti-electricity-theft simulation experiment platform, electricity consumption data of the public transformer area or the line after transformation is obtained through simulation, the original electricity consumption data is replaced by the electricity consumption data obtained through simulation, a plurality of historical electricity-theft users and normal electricity consumption users are called from different areas, all the electricity consumption data and event data and corresponding line loss data of the electricity-theft users in an electricity-theft time period are extracted, correlation analysis and combination are conducted on the extracted data, and the anti-electricity-theft early warning model is verified according to the combined verification data and the replaced electricity consumption data; the anti-electricity-stealing early warning model can be verified in aspects of full level checking, accurate level checking, targeted users, detection timeliness and the like, so that popularization and universality evaluation can be realized. However, the above patent has the following drawbacks in practical use:
The prior art can not intelligently identify and control the electricity stealing users, so that the management effect of the electricity stealing users is poor and the electricity stealing can not be quickly found.
Disclosure of Invention
The invention aims to provide an intelligent recognition system and method for electricity stealing users based on big data, which can intelligently recognize and control the electricity stealing users, can improve the management effect of the electricity stealing users and solve the problems in the background technology.
In order to achieve the above purpose, the present invention provides the following technical solutions:
big data-based electricity stealing user intelligent identification system comprises:
the information acquisition module is connected with the data processing module and is used for acquiring the user electricity consumption information in real time and sending the user electricity consumption information to the data processing module, wherein the user electricity consumption information comprises, but is not limited to, user electricity consumption current information, user electricity consumption voltage information, user electricity consumption power information and user electricity consumption potential information;
the data processing module is connected with the electricity stealing identification module and is used for preprocessing the received electricity consumption information of the user, acquiring the electricity consumption information of the user acquired in real time, carrying out data retrieval, grouping and feature extraction on the electricity consumption information of the user, and determining the sign data and the historical data of the electricity consumption of the user based on big data;
The electricity stealing identification module is connected with the intelligent management and control module and is used for carrying out electricity stealing identification on the electricity consumption meter data of the user, acquiring the electricity consumption meter data of the user based on the big data, indexing the stored electricity consumption meter data of the user based on the electricity consumption meter data of the user, analyzing the electricity consumption meter data of the user based on the electricity consumption meter data of the user and historical data, carrying out electricity stealing identification on the electricity consumption meter data of the user, and determining the intelligent electricity stealing user identification result based on the big data;
the intelligent management and control module is used for intelligently managing and controlling the intelligently identified electricity stealing users, acquiring intelligent identification results of the electricity stealing users based on big data, and sending early warning information to the electricity utilization manager at the first time based on the intelligent identification results of the electricity stealing users to prompt the electricity utilization manager to check on site to judge whether the electricity stealing phenomenon actually exists;
the data storage module is used for storing the user electricity utilization information and the user electricity utilization standard data acquired in real time and providing reference guiding basis for intelligent identification of electricity stealing users.
Preferably, the information acquisition module includes:
the current sensor is used for collecting current information of electricity consumption of a user in real time;
the voltage sensor is used for collecting voltage information of power consumption of a user in real time;
The power sensor is used for collecting power information of electricity consumption of a user in real time;
and the GPS locator is used for collecting the position information of the electricity consumption of the user in real time.
Preferably, the data processing module includes:
the data retrieval unit is used for retrieving the user electricity consumption information acquired in real time, acquiring the user electricity consumption information acquired in real time, retrieving the user electricity consumption information acquired in real time one by one based on a sequential retrieval method, filtering out the user electricity consumption information which is useless for intelligent identification of electricity stealing users, and determining the user electricity consumption information which is useful for intelligent identification of electricity stealing users;
the data grouping unit is used for grouping the retrieved user electricity consumption information to obtain user electricity consumption information which is useful for intelligent identification of electricity stealing users, grouping the user electricity consumption information based on a mutual exclusion principle and determining user electricity consumption information groups with different categories, wherein the user electricity consumption information groups store the user electricity consumption information with the same attribute;
the characteristic extraction unit is used for carrying out characteristic extraction on the grouped user electricity information to obtain user electricity information groups of different categories, carrying out characteristic extraction on the user electricity information in the user electricity information groups, and determining the user electricity information sign data and the historical data based on big data.
Preferably, the electricity theft identification module includes:
the engine index unit is used for indexing the user electricity utilization standard data by the engine, acquiring the user electricity utilization sign data based on the big data, and searching the stored user electricity utilization standard data which is matched with the user electricity utilization sign data by the engine based on the user electricity utilization sign data;
and the electricity stealing identification unit is used for carrying out electricity stealing identification on the user electricity utilization sign data, acquiring the user electricity utilization standard data, analyzing the user electricity utilization standard data and the historical data, carrying out electricity stealing identification on the user electricity utilization sign data, and determining an intelligent electricity stealing user identification result based on big data.
Preferably, the intelligent management and control module includes:
the intelligent control unit is used for intelligently controlling the electricity stealing users and determining early warning information based on the intelligent recognition results of the electricity stealing users;
and the data transmission unit is used for sending early warning information based on the intelligent identification result of the electricity stealing user to the power supply management party, determining the specific user position, facilitating the power supply management party to carry out field check and further carrying out confirmation.
Preferably, the intelligent management and control unit includes:
The risk prediction subunit is used for acquiring electricity stealing information of the current electricity stealing user within a preset period, respectively acquiring actual acquired electricity quantity and standard electricity quantity of the current electricity stealing user every time according to user electricity utilization sign data and user electricity utilization standard data corresponding to the current electricity stealing user every time in the electricity stealing data, and calculating the current electricity stealing severity index of the current electricity stealing user based on the following formula:
wherein, gamma is the current severity index of the current electricity stealing user; n is the total electricity stealing times of the current electricity stealing user in a preset period; n represents the electricity stealing identification times of the system within a preset period; q (Q) i Representing standard electricity consumption corresponding to the ith electricity stealing of the current electricity stealing user within a preset period; q i Representing the actual acquired electric quantity corresponding to the ith electricity stealing of the current electricity stealing user in a preset period;the method comprises the steps of (1) obtaining the electricity stealing frequency of a current electricity stealing user within a preset period; q (Q) j Representing the actual power consumption corresponding to the j-th power stealing identification of the current power stealing user within a preset period; omega 1 For the first electricity stealing serious weight value omega 2 Is the second electricity stealing serious weight value omega 1 +ω 2 ＝1；/>Representing the electricity stealing rate of the current electricity stealing user in a preset period;
when the electricity stealing severity index is larger than a preset threshold value, judging that the current electricity stealing user is an electricity stealing high risk user;
When the electricity stealing severity index is smaller than or equal to a preset threshold value, judging that the current electricity stealing user is a common electricity stealing user;
the early warning auxiliary subunit is used for acquiring historical electricity stealing electricity charge compensation data of all electricity stealing users, comparing the current risk prediction result and the current actual electricity stealing amount of the current electricity stealing users in the corresponding historical electricity stealing charge compensation data, and determining the electricity stealing recommended compensation times of the current electricity stealing users;
according to the recommended compensation multiple and the actual electricity larceny quantity of the current electricity larceny user, calculating the electricity fee compensation amount corresponding to the current electricity larceny of the current electricity larceny user by adopting the following formula:
wherein θ represents the amount of electric charge compensation corresponding to the current electricity larceny of the current electricity larceny user; beta represents the recommended power-stealing compensation times of the current power-stealing users; x is x 1 The standard electricity fee unit price of the first gear electricity utilization of the current electricity stealing user location is represented; x is x 2 The standard electricity fee unit price of the second gear electricity utilization of the current electricity stealing user location is represented; x is x 3 The standard electricity fee unit price of the third gear electricity utilization of the current electricity stealing user location is represented; a represents the actual collected electric quantity corresponding to the current electricity stealing of the current electricity stealing user; b represents the standard electricity consumption corresponding to the current electricity stealing of the current electricity stealing user; B-A represents the actual electricity stealing amount of the current electricity stealing user; t is t 1 Representing a first elevator degree threshold; t is t 2 Representing a second elevator degree threshold;
the intelligent early warning subunit is used for generating early warning information of corresponding grade based on the electric charge compensation amount of the current electricity stealing user and the current risk prediction result of the current electricity stealing user;
when the current electricity stealing user is an electricity stealing high risk user, generating first-level early warning information; and when the current electricity stealing user is a common electricity stealing user, generating secondary early warning information.
Preferably, the data storage module includes:
the information storage unit is used for storing the user power consumption information acquired in real time, and storing the user power consumption information into the information storage unit after the user power consumption information is acquired in real time;
and the data storage unit is used for storing user electricity utilization standard data and providing reference guiding basis for intelligent identification of electricity stealing users.
Preferably, the data storage module further comprises: the data updating unit is used for carrying out self-learning processing based on the newly obtained user electricity information and updating the user electricity standard data according to the self-learning processing result, and comprises the following steps:
the tag adding subunit is used for adding the electricity stealing tag to the new electricity consumption information of the user based on the intelligent identification result of the electricity stealing user of the user after acquiring the new electricity consumption information of the user, wherein the electricity stealing tag comprises two types of electricity stealing and non-electricity stealing;
The confirmation updating subunit is used for acquiring electricity stealing authentication information after the storage time of the new user electricity utilization information reaches the preset time, updating the electricity stealing label of the new user electricity utilization information based on the electricity stealing authentication information, and acquiring a final electricity stealing result;
the information acquisition subunit is used for acquiring the user power consumption information corresponding to modification of the stealing tag as target information while acquiring a final electricity stealing result, and acquiring all the historical user power consumption information of the target user corresponding to the target information based on the user tag corresponding to the target information;
the synchronous learning subunit is used for screening all the historical user electricity information based on the date label of the new user electricity information, acquiring and comparing the contemporaneous historical user electricity information of the new user electricity information, and acquiring contemporaneous electricity change indexes;
classifying historical user electricity consumption information according to quarters to obtain a plurality of information sets, and respectively carrying out subset segmentation on quarters data in the information sets based on electricity consumption year information to obtain a plurality of information subsets;
comparing all information subsets in the same information set according to the year sequence, and determining the electricity utilization change index of each quarter of the user and the target quarter corresponding to the new electricity utilization of the user;
Obtaining a change index difference based on a power utilization change index corresponding to a target quarter and a contemporaneous power utilization change index, and correcting original user power utilization standard data corresponding to a target user based on the power utilization change index of each quarter when the change index difference is smaller than or equal to a preset value to obtain new user power utilization standard data which is automatically switched according to power utilization time;
when the variation index difference is larger than a preset value, obtaining a prediction error rate based on the variation index difference and the power utilization variation index corresponding to the target quarter, and comparing the power utilization variation indexes of different quarters to obtain a variation error;
obtaining corresponding error correction factors of each quarter based on the change errors and the prediction errors, correcting the electricity utilization change indexes of each quarter based on the error correction factors, respectively obtaining final electricity utilization change indexes corresponding to each quarter, correcting original user electricity utilization standard data corresponding to a target user based on the final electricity utilization change indexes of each quarter, and obtaining new user electricity utilization standard data which is automatically switched according to electricity utilization time;
and the standard updating subunit is used for updating the original user electricity standard data based on the new user electricity standard data of the target user.
According to another aspect of the invention, an intelligent identification method of electricity larceny users based on big data is provided, and the intelligent identification system based on the big data is realized, and comprises the following steps:
s1: the information acquisition module is used for acquiring the user electricity information in real time, the user electricity information acquired in real time is sent to the data processing module, and after the data processing module receives the user electricity information, the data processing module performs data retrieval, grouping and feature extraction on the user electricity information to determine the user electricity information sign data and the historical data based on big data;
s2: the electricity stealing identification module is used for carrying out electricity stealing identification on the user electricity utilization sign data, indexing stored user electricity utilization standard data based on the user electricity utilization sign data, analyzing the stored user electricity utilization standard data based on the user electricity utilization standard data and historical data, carrying out electricity stealing identification on the user electricity utilization sign data, and determining an intelligent electricity stealing user identification result based on big data;
s3: and the intelligent management and control module is used for intelligently managing and controlling the intelligently identified electricity stealing users, determining early warning information based on the intelligent identification result of the electricity stealing users, and sending the early warning information based on the intelligent identification result of the electricity stealing users to guide the electricity stealing users to legally use the electric power.
Preferably, in the step S2, the electricity stealing identification module is used to identify the electricity consumption meter data of the user, and the following operations are performed:
acquiring user electricity utilization sign data based on big data;
based on the user electricity utilization characteristic data, the engine searches out stored user electricity utilization standard data which is matched with the user electricity utilization characteristic data;
aiming at the situation that the user electricity utilization sign data is in the range of the user electricity utilization standard data, the intelligent identification result of the electricity stealing user based on big data is that the electricity utilization of the electricity utilization user is normal, and no electricity stealing behavior exists;
aiming at the situation that the user electricity utilization sign data is not in the range of the user electricity utilization standard data, the intelligent identification result of the electricity stealing user based on big data is that the electricity utilization of the electricity utilization user is abnormal, and electricity stealing behavior exists;
aiming at the condition that the electricity utilization of the electricity utilization user is abnormal and the electricity stealing behavior exists, the early warning information based on the intelligent identification result of the electricity utilization user is determined, and the early warning information based on the intelligent identification result of the electricity utilization user is sent to the power supply management party to guide the management personnel to timely conduct on-site verification.
Compared with the prior art, the invention has the beneficial effects that:
according to the intelligent identification system and method for the electricity stealing users based on the big data, the electricity utilization information of the users is collected in real time, the data retrieval, grouping and feature extraction are carried out on the electricity utilization information of the users collected in real time, the electricity utilization sign data of the users based on the big data are determined, the stored electricity utilization standard data of the users are indexed based on the electricity utilization sign data of the users, the electricity stealing identification is carried out on the electricity utilization sign data of the users based on the electricity utilization standard data of the users, the intelligent identification result of the electricity stealing users based on the big data is determined, the early warning information based on the intelligent identification result of the electricity stealing users is determined, and the early warning information based on the intelligent identification result of the electricity stealing users is sent to an electricity stealing management party to guide management personnel to carry out on-site verification in time.
Drawings
FIG. 1 is a block diagram of a big data based electricity theft user intelligent identification system of the present invention;
FIG. 2 is a flow chart of the intelligent identification method of the electricity larceny user based on big data of the invention;
FIG. 3 is an algorithm flow chart of the big data based electricity stealing user intelligent identification method of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In order to solve the problems that the prior art cannot intelligently identify and control the electricity stealing users, which results in poor management effect and cannot quickly find out electricity stealing, referring to fig. 1-3, the embodiment provides the following technical scheme:
the intelligent electricity larceny user identification system based on big data comprises an information acquisition module, a data processing module, an electricity larceny identification module, an intelligent management and control module and a data storage module;
It should be noted that, through the network transmission connection among the information acquisition module, the data processing module, the electricity stealing identification module, the intelligent management and control module and the data storage module, the electricity stealing user can be intelligently identified and managed and controlled, and the management effect of the electricity stealing user can be improved.
The information acquisition module is connected with the data processing module;
the information acquisition module can acquire user power consumption information in real time and send the user power consumption information acquired in real time to the data processing module;
the user power consumption information comprises, but is not limited to, user power consumption current information, user power consumption voltage information, user power consumption information and user power consumption potential information;
the information acquisition module comprises a current sensor, a voltage sensor, a power sensor and a GPS (global positioning system) locator;
the current sensor can collect current information of user electricity in real time;
the current sensor can sense the information of the current used by the user, and can convert the sensed current information into an electric signal meeting certain standard or other information output in a required form according to a certain rule so as to meet the requirements of information transmission, processing, storage, display, recording, control and the like.
The voltage sensor can acquire voltage information of electricity consumption of a user in real time;
it should be noted that, the voltage sensor is a sensor capable of sensing the measured voltage and converting the measured voltage into a usable output signal, and in various automatic detection and control systems, it is often necessary to track and collect ac and dc voltage signals that change at high speed, and perform spectrum analysis on relatively complex voltage waveforms.
The power sensor can collect power information of user electricity in real time;
the power sensor adopts a special power conversion circuit to convert an alternating current power signal into a standard direct current voltage signal in linear relation with the alternating current power signal, and then the standard direct current voltage signal is amplified linearly by active filtering to output a constant current or constant voltage analog quantity, so that the transmitter has the characteristics of high precision, stable operation and the like, outputs the constant current or constant signal, and can output the power signal in pulse at the same time, and the electric value can be obtained only by counting the pulse.
The GPS locator can collect the position information of the electricity consumption of the user in real time.
It should be noted that the GPS locator is a high-precision radio navigation positioning system based on artificial earth satellites, which can provide accurate geographic position, vehicle speed and accurate time information in any place around the globe and in the near-earth space.
The data processing module is connected with the electricity stealing identification module;
the data processing module can preprocess the received user power consumption information;
it should be noted that the data processing module includes a data retrieving unit, a data grouping unit and a feature extracting unit;
the data retrieval unit can retrieve user power consumption information acquired in real time;
specifically, acquiring user electricity information acquired in real time, searching the user electricity information acquired in real time one by one based on a sequential searching method, filtering out useless user electricity information for intelligent identification of electricity stealing users, and determining useful user electricity information for intelligent identification of the electricity stealing users;
it should be noted that, the user electricity information collected in real time includes missing user electricity information, and the missing user electricity information is useless for intelligent identification of electricity stealing users, so that the missing user electricity information needs to be filtered first, and the burden of intelligent identification of electricity stealing users can be reduced.
The data grouping unit can group the retrieved user power consumption information;
specifically, user electricity information which is useful for intelligent identification of electricity stealing users is obtained, the user electricity information is grouped based on a mutual exclusion principle, and user electricity information groups with different categories are determined, wherein the user electricity information groups store the user electricity information with the same attribute;
The retrieved user electricity information contains different categories, so that the retrieved user electricity information is subjected to grouping processing, and the retrieved user electricity information can be stored in a grouping manner.
The feature extraction unit can perform feature extraction on the grouped user power consumption information;
specifically, user electricity consumption information groups of different categories are obtained, feature extraction is performed on the user electricity consumption information in the user electricity consumption information groups, and user electricity consumption sign data based on big data is determined.
The electricity stealing identification module is connected with the intelligent control module;
specifically, the electricity stealing identification module can be used for carrying out electricity stealing identification on the user electricity utilization meter data;
it should be noted that, the electricity stealing identification module includes an engine index unit and an electricity stealing identification unit;
the engine index unit can index the user electricity standard data by an engine;
specifically, acquiring user electricity utilization standard data based on big data, and based on the user electricity utilization standard data, searching out stored user electricity utilization standard data matched with the user electricity utilization standard data by an engine;
the electricity stealing identification unit can be used for carrying out electricity stealing identification on the user electricity utilization sign data;
Specifically, user electricity utilization standard data are obtained, electricity stealing identification is carried out on the user electricity utilization sign data based on the user electricity utilization standard data, and an intelligent electricity stealing user identification result based on big data is determined.
The intelligent control module can intelligently control the intelligently identified electricity stealing users;
it should be noted that the intelligent control module includes an intelligent control unit and a data transmission unit;
the intelligent management and control unit can carry out intelligent management and control on the electricity stealing users, and based on the intelligent identification result of the electricity stealing users, early warning information based on the intelligent identification result of the electricity stealing users is determined;
the data transmission unit can send early warning information based on intelligent identification results of electricity stealing users to the power supply management party, and determine the specific user position, so that the power supply management party can conveniently check the site and further confirm the site.
The method includes the steps that user electricity consumption information is collected in real time, the user electricity consumption information collected in real time is processed, user electricity consumption representation data and historical data are determined, analysis is conducted on the basis of user electricity consumption standard data and the historical data, if abnormal fluctuation, mutation, more or less than or equal to obvious problems occur in the user electricity consumption representation data, electricity stealing identification is conducted on the user electricity consumption representation data, intelligent electricity stealing user identification results based on big data and early warning information based on the intelligent electricity stealing user identification results are determined, early warning information based on the intelligent electricity stealing user identification results is sent to a power supply management party, a manager is reminded to conduct on-site verification judgment, meanwhile, part of early warning information sent by electricity stealing users can be used for guiding the electricity stealing users to legally use electric power, intelligent electricity stealing user identification, management and control can be conducted on the electricity stealing users, and management effects of the electricity stealing users can be improved.
It should be noted that, the intelligent management and control unit includes: the risk prediction subunit, the early warning auxiliary subunit and the intelligent early warning subunit;
the risk prediction subunit is configured to obtain electricity stealing information of a current electricity stealing user within a preset period, respectively obtain actual collected electricity quantity and standard electricity quantity of the current electricity stealing user each time according to user electricity consumption sign data and user electricity consumption standard data corresponding to each time of electricity stealing of the current electricity stealing user in the electricity stealing data, and calculate a current electricity stealing severity index of the current electricity stealing user based on the following formula:
wherein, gamma is the current severity index of the current electricity stealing user; n is the total electricity stealing times of the current electricity stealing user in a preset period; n represents the electricity stealing identification times of the system within a preset period; q (Q) i Representing standard electricity consumption corresponding to the ith electricity stealing of the current electricity stealing user within a preset period; q i Representing the actual acquired electric quantity corresponding to the ith electricity stealing of the current electricity stealing user in a preset period;the method comprises the steps of (1) obtaining the electricity stealing frequency of a current electricity stealing user within a preset period; q (Q) j Representing the actual electricity consumption corresponding to the jth electricity stealing identification of the current electricity stealing user within a preset period, and when the electricity stealing identification result is electricity stealing, obtaining the actual electricity consumption corresponding to the electricity stealing identification of the electricity stealing user as the standard electricity consumption corresponding to the electricity stealing identification result An amount of; omega 1 The first electricity stealing serious weight value is (0.2,0.7), omega 2 The serious weight value of the second electricity stealing is (0.3,0.8), omega 1 +ω 2 ＝1；/>Representing the electricity stealing rate of the current electricity stealing user in a preset period;
when the electricity stealing severity index is larger than a preset threshold value, judging that the current electricity stealing user is an electricity stealing high risk user;
when the electricity stealing severity index is smaller than or equal to a preset threshold value, judging that the current electricity stealing user is a common electricity stealing user;
the early warning auxiliary subunit is used for acquiring historical electricity stealing electricity charge compensation data of all electricity stealing users, comparing the current risk prediction result and the current actual electricity stealing amount of the current electricity stealing users in the corresponding historical electricity stealing charge compensation data, and determining the electricity stealing recommended compensation times of the current electricity stealing users;
according to the recommended compensation multiple and the actual electricity larceny quantity of the current electricity larceny user, calculating the electricity fee compensation amount corresponding to the current electricity larceny of the current electricity larceny user by adopting the following formula:
wherein θ represents the amount of electric charge compensation corresponding to the current electricity larceny of the current electricity larceny user; beta represents the recommended power-stealing compensation times of the current power-stealing users; x is x 1 The standard electricity fee unit price of the first gear electricity utilization of the current electricity stealing user location is represented; x is x 2 The standard electricity fee unit price of the second gear electricity utilization of the current electricity stealing user location is represented; x is x 3 The standard electricity fee unit price of the third gear electricity utilization of the current electricity stealing user location is represented; a represents the actual collected electric quantity corresponding to the current electricity stealing of the current electricity stealing user; b represents the standard electricity consumption corresponding to the current electricity stealing of the current electricity stealing user; B-A represents the actual electricity stealing amount of the current electricity stealing user; t is t 1 Representing a first elevator degree threshold; t is t 2 Representing a second useAn elevator degree threshold;
the intelligent early warning subunit is used for generating early warning information of corresponding grade based on the electric charge compensation amount of the current electricity stealing user and the current risk prediction result of the current electricity stealing user;
when the current electricity stealing user is an electricity stealing high risk user, generating first-level early warning information; and when the current electricity stealing user is a common electricity stealing user, generating secondary early warning information.
In this embodiment, the electricity stealing information refers to all the user electricity consumption information corresponding to the current electricity stealing user in a preset period (for example, 6 months, 12 months, etc.).
The actual collected electric quantity is the electric quantity collected when the electricity stealing identification is carried out each time.
The standard electricity consumption refers to a standard value for judging whether the current electricity stealing user steals electricity or not.
The current risk prediction result comprises a high-risk user and a common electricity stealing user
The technical scheme has the working principle and beneficial effects that: according to the invention, the risk prediction subunit calculates the current electricity stealing severity index of the current electricity stealing user based on the corresponding electricity stealing frequency and the electricity stealing rate of the current electricity stealing user within the preset period and the corresponding electricity stealing severity weight value, judges the current risk of the current electricity stealing user according to the electricity stealing severity index, obtains the current risk prediction result, provides a grade basis for the generation of early warning information, compares the current electricity stealing user risk prediction result and the current actual electricity stealing amount in the corresponding historical electricity stealing fee compensation data through the early warning auxiliary subunit, determines the current electricity stealing recommended compensation multiple of the current electricity stealing user, calculates the current electricity fee compensation amount corresponding to the current electricity stealing of the current electricity stealing user, reduces the management pressure and the work load of power grid management personnel, rapidly and positively determines the compensation multiple, completes the electricity fee compensation calculation of the electricity stealing user, and effectively improves the electricity stealing event processing efficiency; and the intelligent early warning subunit generates early warning information of a corresponding grade based on the electric charge compensation amount of the current electricity stealing user and the current risk prediction result of the current electricity stealing user, so that the severity of the current electricity stealing event can be quickly determined by power grid management personnel.
It should be noted that, using the electricity stealing identification module to identify electricity stealing of the user meter data includes:
acquiring user electricity utilization sign data based on big data;
based on the user electricity utilization characteristic data, the engine searches out stored user electricity utilization standard data which is matched with the user electricity utilization characteristic data;
aiming at the situation that the user electricity utilization sign data is in the range of the user electricity utilization standard data, the intelligent identification result of the electricity stealing user based on big data is that the electricity utilization of the electricity utilization user is normal, and no electricity stealing behavior exists;
aiming at the situation that the user electricity utilization sign data is not in the range of the user electricity utilization standard data, the intelligent identification result of the electricity stealing user based on big data is that the electricity utilization of the electricity utilization user is abnormal, and electricity stealing behavior exists;
aiming at the condition that the electricity utilization of the electricity utilization user is abnormal and the electricity stealing behavior exists, the early warning information based on the intelligent identification result of the electricity utilization user is determined, and the early warning information based on the intelligent identification result of the electricity utilization user is sent to the power supply management party to guide the management personnel to timely conduct on-site verification.
The data storage module can store user electricity information and user electricity standard data acquired in real time, and provides reference guiding basis for intelligent identification of electricity stealing users.
It should be noted that, the intelligent recognition system of the electricity stealing user based on big data is adopted to intelligently recognize the electricity stealing user, wherein the intelligent recognition condition of the electricity stealing user based on big data is shown in table 1:
table 1: big data-based intelligent identification condition of electricity stealing user
It should be noted that the data storage module includes an information storage unit and a data storage unit;
specifically, the information storage unit can store the user electricity information acquired in real time, and after the user electricity information is acquired in real time, the user electricity information is stored in the information storage unit;
specifically, the data storage unit can store user electricity standard data, and provides reference guiding basis for intelligent identification of electricity stealing users.
It should be noted that the data storage module further includes: the data updating unit is used for carrying out self-learning processing based on the newly obtained user electricity information and updating the user electricity standard data according to the self-learning processing result, and comprises a label adding subunit, a confirmation updating subunit, an information obtaining subunit, a synchronous learning subunit and a standard updating subunit;
the tag adding subunit is used for adding the electricity stealing tag to the new electricity consumption information of the user based on the intelligent identification result of the electricity stealing user of the user after acquiring the new electricity consumption information of the user, wherein the electricity stealing tag comprises two types of electricity stealing and non-electricity stealing;
The verification updating subunit is used for acquiring electricity stealing authentication information after the storage time of the new user electricity information reaches the preset time, updating the electricity stealing label of the new user electricity information based on the electricity stealing authentication information, and acquiring a final electricity stealing result;
the information acquisition subunit is used for acquiring the user power consumption information corresponding to modification of the stealing tag as target information while acquiring a final electricity stealing result, and acquiring all historical user power consumption information of the target user corresponding to the target information based on the user tag corresponding to the target information;
the synchronous learning subunit is used for screening all historical user electricity consumption information based on date labels of the new user electricity consumption information, acquiring and comparing the contemporaneous historical user electricity consumption information of the new user electricity consumption information, and acquiring contemporaneous electricity consumption change indexes;
classifying historical user electricity consumption information according to quarters to obtain a plurality of information sets, and respectively carrying out subset segmentation on quarters data in the information sets based on electricity consumption year information to obtain a plurality of information subsets;
comparing all information subsets in the same information set according to the year sequence, and determining the electricity utilization change index of each quarter of the user and the target quarter corresponding to the new electricity utilization of the user;
Obtaining a change index difference based on a power utilization change index corresponding to a target quarter and a contemporaneous power utilization change index, and correcting original user power utilization standard data corresponding to a target user based on the power utilization change index of each quarter when the change index difference is smaller than or equal to a preset value to obtain new user power utilization standard data which is automatically switched according to power utilization time;
when the variation index difference is larger than a preset value, obtaining a prediction error rate based on the variation index difference and the power utilization variation index corresponding to the target quarter, and comparing the power utilization variation indexes of different quarters to obtain a variation error;
obtaining corresponding error correction factors of each quarter based on the change errors and the prediction errors, correcting the electricity utilization change indexes of each quarter based on the error correction factors, respectively obtaining final electricity utilization change indexes corresponding to each quarter, correcting original user electricity utilization standard data corresponding to a target user based on the final electricity utilization change indexes of each quarter, and obtaining new user electricity utilization standard data which is automatically switched according to electricity utilization time;
and the standard updating subunit is used for updating the original user electricity standard data based on the new user electricity standard data of the target user.
In this embodiment, the electricity stealing tag refers to adding a tag to new user electricity consumption information according to an intelligent identification result of the electricity stealing user while the new user electricity consumption information is stored based on the data storage unit.
The electricity larceny authentication information refers to electricity larceny final confirmation information corresponding to new user electricity consumption information, and electricity larceny declaration time is reserved for the user to avoid misjudgment.
The final electricity larceny result is the electricity larceny result which is finally determined after the preset time, and the electricity larceny result comprises two kinds of electricity larceny and non-electricity larceny, wherein the final electricity larceny result cannot be changed.
The modification of the stolen tag refers to the modification of the stolen tag caused by the fact that the fraudulent use of electricity is declared and successful or the fraudulent use of electricity result is changed due to the recognition error found by a power manager when the storage time of the new user electricity information reaches a preset time (for example, 5 working days).
The target information refers to new user electricity information of which the stolen tag is modified at preset time.
The user tag is a tag which is carried on the user electricity information and indicates the identity of the user; the date label is a label which is carried on the user electricity information and indicates the electricity utilization time and the data acquisition time corresponding to the user electricity utilization information.
The target user refers to a user corresponding to new user electricity consumption information of which the stealing tag is modified in preset time.
The contemporaneous historical user electricity consumption information refers to historical user electricity consumption information which is the same as the electricity consumption use date corresponding to the new user electricity consumption information.
The data storage unit stores user electricity consumption for at least three years.
The contemporaneous electricity utilization change index is used for representing the increase or decrease condition of the electricity utilization data of the new user electricity utilization information compared with the electricity utilization data corresponding to the contemporaneous historical user electricity utilization information.
The information collection refers to classifying all historical user electricity consumption information corresponding to the target user, and the historical user electricity consumption information in the same quarter forms a collection.
The electricity usage year information refers to the electricity usage year corresponding to each historical user electricity usage.
The information subset is a plurality of subsets obtained by dividing the same information according to the year of electricity consumption.
The electricity utilization change index is used for representing the situation that the electricity utilization data corresponding to the historical user electricity utilization of the same quarter of different years is increased or decreased compared with the electricity utilization data corresponding to each quarter of the current year.
The target quarter refers to the quarter corresponding to the electricity utilization time corresponding to the new user electricity utilization.
The change index difference refers to the absolute value of the difference between the power utilization change index corresponding to the target quarter and the contemporaneous power utilization change index.
The error rate is predicted to be the ratio of the variation index difference to the power utilization variation index corresponding to the target quarter; the variation error refers to the ratio of the phase difference of the electricity variation index of different quarters compared with the average value thereof.
The error correction factor refers to the product of the variation error and the prediction error.
The final electricity change index is an electricity change index corrected based on the error correction factor.
The technical scheme has the working principle and beneficial effects that: according to the invention, the tag adding subunit is used for adding the electricity stealing tag to the new user electricity consumption information, so that the data can be conveniently searched, and a manager can find the electricity stealing data corresponding to the user in a short time according to the tag; acquiring electricity stealing authentication information after the storage time of new user electricity information reaches a preset time through a confirmation updating subunit, then carrying out tag updating to obtain a final electricity stealing result, reserving electricity stealing declaration time for a user, avoiding error punishment caused by electricity stealing misjudgment, and then determining target information modified by a stealing tag and all historical user electricity information of the corresponding target user through an information acquisition subunit to provide data support for self-learning processing; the method comprises the steps of screening out and comparing contemporaneous historical user electricity information of new user electricity information based on date labels of the new user electricity information through a synchronous learning subunit, obtaining contemporaneous electricity change indexes of the new user electricity information, obtaining information sets corresponding to different quarters and corresponding information subsets of the information sets according to the electricity year information and the quarters, classifying the electricity information according to the quarters, conveniently obtaining different user electricity standard data according to the quarters, then confirming consistency of electricity change conditions according to the electricity change indexes corresponding to the target quarters and contemporaneous electricity change indexes of the new user electricity information, and indicating that the electricity change corresponding to the user electricity information of the target user is changed and changed in climate and caused by household appliances when difference value change index difference of the electricity change indexes is smaller than or equal to a preset value, and finishing correction of original user electricity standard data according to the electricity change index of each quarter; when the difference value change index difference of the two values is larger than a preset value, the change of the user electricity consumption of the target user is related to climate change and increase and decrease of household appliances, and other interference factors are included, then, a predicted error rate is obtained based on the change index difference and the electricity consumption change index corresponding to the target quarter, and the change error is obtained by comparing the electricity consumption change indexes of different quarters; based on the change errors and the prediction errors, obtaining corresponding error correction factors of each quarter, correcting electricity utilization change indexes of each quarter based on the error correction factors, respectively obtaining final electricity utilization change indexes corresponding to each quarter, correcting original user electricity utilization standard data corresponding to a target user according to the final electricity utilization change indexes, obtaining new user electricity utilization standard data which are automatically switched according to electricity utilization time, adding other interference factors to effectively improve the accuracy of the new user electricity utilization standard data, carrying out self-learning processing after the new user electricity utilization standard data are based on the newly obtained user electricity utilization information through a data updating unit, updating the user electricity utilization standard data according to self-learning processing results, overcoming the problem that misjudgment is caused by mismatching of the user electricity utilization standard data and actual conditions due to change of consumption caused by climate change and the like, continuously updating the user electricity utilization standard data according to updating of user electricity utilization information, effectively improving the accuracy of intelligent identification of a power stealing user in intelligent management and control, and reducing the probability of misjudgment of electricity stealing.
In order to better show the intelligent identification flow of the electricity larceny user based on big data, the embodiment now provides the intelligent identification method of the electricity larceny user based on big data, and the intelligent identification system of the electricity larceny user based on big data is realized, and the method comprises the following steps:
s1: the information acquisition module is used for acquiring the user electricity information in real time, the user electricity information acquired in real time is sent to the data processing module, and after the data processing module receives the user electricity information, the data processing module performs data retrieval, grouping and feature extraction on the user electricity information to determine the user electricity information sign data and the historical data based on big data;
s2: the electricity stealing identification module is used for carrying out electricity stealing identification on the user electricity utilization sign data, indexing stored user electricity utilization standard data based on the user electricity utilization sign data, analyzing the stored user electricity utilization standard data based on the user electricity utilization standard data and historical data, carrying out electricity stealing identification on the user electricity utilization sign data, and determining an intelligent electricity stealing user identification result based on big data;
s3: and the intelligent management and control module is used for intelligently managing and controlling the intelligently identified electricity stealing users, determining early warning information based on the intelligent identification result of the electricity stealing users, and sending the early warning information based on the intelligent identification result of the electricity stealing users to guide the electricity stealing users to legally use the electric power.
In summary, the intelligent identification system and method for the electricity stealing users based on big data acquire the electricity consumption information of the users in real time, perform data retrieval, grouping and feature extraction on the electricity consumption information of the users acquired in real time, determine the electricity consumption sign data of the users based on the big data, index the stored electricity consumption standard data of the users based on the electricity consumption sign data of the users, perform electricity stealing identification on the electricity consumption sign data of the users based on the electricity consumption standard data of the users, determine the intelligent identification result of the electricity stealing users based on the big data, determine the early warning information based on the intelligent identification result of the electricity stealing users, send the early warning information based on the intelligent identification result of the electricity stealing users to a power stealing management party, guide the management personnel to perform on-site verification in time, automatically perform electricity quantity supplement calculation according to the verification result, and perform intelligent identification and management control on the electricity stealing users at the same time, and improve the management effect of the electricity stealing users.
It is noted that relational terms such as first and second, and the like are 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. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. Big data-based electricity stealing user intelligent identification system is characterized by comprising:
the information acquisition module is connected with the data processing module and is used for acquiring the user electricity consumption information in real time and sending the user electricity consumption information to the data processing module, wherein the user electricity consumption information comprises, but is not limited to, user electricity consumption current information, user electricity consumption voltage information, user electricity consumption power information and user electricity consumption potential information;
the data processing module is connected with the electricity stealing identification module and is used for preprocessing the received electricity consumption information of the user, acquiring the electricity consumption information of the user acquired in real time, carrying out data retrieval, grouping and feature extraction on the electricity consumption information of the user, and determining the sign data and the historical data of the electricity consumption of the user based on big data;
the electricity stealing identification module is connected with the intelligent management and control module and is used for carrying out electricity stealing identification on the electricity consumption meter data of the user, acquiring the electricity consumption meter data of the user based on the big data, indexing the stored electricity consumption meter data of the user based on the electricity consumption meter data of the user, analyzing the electricity consumption meter data of the user based on the electricity consumption meter data of the user and historical data, carrying out electricity stealing identification on the electricity consumption meter data of the user, and determining the intelligent electricity stealing user identification result based on the big data;
The intelligent management and control module is used for intelligently managing and controlling the intelligently identified electricity stealing users, acquiring intelligent identification results of the electricity stealing users based on big data, and sending early warning information to the electricity utilization manager at the first time based on the intelligent identification results of the electricity stealing users to prompt the electricity utilization manager to check on site to judge whether the electricity stealing phenomenon actually exists;
the data storage module is used for storing the user electricity utilization information and the user electricity utilization standard data acquired in real time and providing reference guiding basis for intelligent identification of electricity stealing users.
2. The big data based electricity theft user intelligent identification system of claim 1, wherein the information collection module comprises:
the current sensor is used for collecting current information of electricity consumption of a user in real time;
the voltage sensor is used for collecting voltage information of power consumption of a user in real time;
the power sensor is used for collecting power information of electricity consumption of a user in real time;
and the GPS locator is used for collecting the position information of the electricity consumption of the user in real time.
3. The big data based electricity theft user intelligent identification system of claim 2, wherein the data processing module comprises:
the data retrieval unit is used for retrieving the user electricity consumption information acquired in real time, acquiring the user electricity consumption information acquired in real time, retrieving the user electricity consumption information acquired in real time one by one based on a sequential retrieval method, filtering out the user electricity consumption information which is useless for intelligent identification of electricity stealing users, and determining the user electricity consumption information which is useful for intelligent identification of electricity stealing users;
The data grouping unit is used for grouping the retrieved user electricity consumption information to obtain user electricity consumption information which is useful for intelligent identification of electricity stealing users, grouping the user electricity consumption information based on a mutual exclusion principle and determining user electricity consumption information groups with different categories, wherein the user electricity consumption information groups store the user electricity consumption information with the same attribute;
the characteristic extraction unit is used for carrying out characteristic extraction on the grouped user electricity information to obtain user electricity information groups of different categories, carrying out characteristic extraction on the user electricity information in the user electricity information groups, and determining the user electricity information sign data and the historical data based on big data.
4. The big data based electricity theft user intelligent identification system of claim 3, wherein the electricity theft identification module comprises:
the engine index unit is used for indexing the user electricity utilization standard data by the engine, acquiring the user electricity utilization sign data based on the big data, and searching the stored user electricity utilization standard data which is matched with the user electricity utilization sign data by the engine based on the user electricity utilization sign data;
and the electricity stealing identification unit is used for carrying out electricity stealing identification on the user electricity utilization sign data, acquiring the user electricity utilization standard data, analyzing the user electricity utilization standard data and the historical data, carrying out electricity stealing identification on the user electricity utilization sign data, and determining an intelligent electricity stealing user identification result based on big data.
5. The big data based electricity theft user intelligent identification system of claim 4, wherein the intelligent management and control module comprises:
the intelligent control unit is used for intelligently controlling the electricity stealing users and determining early warning information based on the intelligent recognition results of the electricity stealing users;
and the data transmission unit is used for sending early warning information based on the intelligent identification result of the electricity stealing user to the power supply management party, determining the specific user position, facilitating the power supply management party to carry out field check and further carrying out confirmation.
6. The big data based electricity theft user intelligent identification system of claim 4, wherein the intelligent management and control unit comprises:
the risk prediction subunit is used for acquiring electricity stealing information of the current electricity stealing user within a preset period, respectively acquiring actual acquired electricity quantity and standard electricity quantity of the current electricity stealing user every time according to user electricity utilization sign data and user electricity utilization standard data corresponding to the current electricity stealing user every time in the electricity stealing data, and calculating the current electricity stealing severity index of the current electricity stealing user based on the following formula:
wherein, gamma is the current severity index of the current electricity stealing user; n is the total electricity stealing times of the current electricity stealing user in a preset period; n represents the electricity stealing identification times of the system within a preset period; q (Q) i Representing standard electricity consumption corresponding to the ith electricity stealing of the current electricity stealing user within a preset period; q i Representing the actual acquired electric quantity corresponding to the ith electricity stealing of the current electricity stealing user in a preset period;the method comprises the steps of (1) obtaining the electricity stealing frequency of a current electricity stealing user within a preset period; q (Q) j Representing the actual power consumption corresponding to the j-th power stealing identification of the current power stealing user within a preset period; omega 1 For the first electricity stealing serious weight value omega 2 Is the second electricity stealing serious weight value omega 1 +ω 2 ＝1；/>Representing the electricity stealing rate of the current electricity stealing user in a preset period;
when the electricity stealing severity index is larger than a preset threshold value, judging that the current electricity stealing user is an electricity stealing high risk user;
when the electricity stealing severity index is smaller than or equal to a preset threshold value, judging that the current electricity stealing user is a common electricity stealing user;
the early warning auxiliary subunit is used for acquiring historical electricity stealing electricity charge compensation data of all electricity stealing users, comparing the current risk prediction result and the current actual electricity stealing amount of the current electricity stealing users in the corresponding historical electricity stealing charge compensation data, and determining the electricity stealing recommended compensation times of the current electricity stealing users;
according to the recommended compensation multiple and the actual electricity larceny quantity of the current electricity larceny user, calculating the electricity fee compensation amount corresponding to the current electricity larceny of the current electricity larceny user by adopting the following formula:
Wherein θ represents the amount of electric charge compensation corresponding to the current electricity larceny of the current electricity larceny user; beta represents the recommended power-stealing compensation times of the current power-stealing users; x is x 1 The standard electricity fee unit price of the first gear electricity utilization of the current electricity stealing user location is represented; x is x 2 The standard electricity fee unit price of the second gear electricity utilization of the current electricity stealing user location is represented; x is x 3 The standard electricity fee unit price of the third gear electricity utilization of the current electricity stealing user location is represented; a represents the actual collected electric quantity corresponding to the current electricity stealing of the current electricity stealing user; b represents the standard electricity consumption corresponding to the current electricity stealing of the current electricity stealing user; B-A represents the actual electricity stealing amount of the current electricity stealing user; t is t 1 Representing a first elevator degree threshold; t is t 2 Representing a second elevator degree threshold;
the intelligent early warning subunit is used for generating early warning information of corresponding grade based on the electric charge compensation amount of the current electricity stealing user and the current risk prediction result of the current electricity stealing user;
when the current electricity stealing user is an electricity stealing high risk user, generating first-level early warning information; and when the current electricity stealing user is a common electricity stealing user, generating secondary early warning information.
7. The big data based electricity theft user intelligent identification system of claim 5, wherein the data storage module comprises:
The information storage unit is used for storing the user power consumption information acquired in real time, and storing the user power consumption information into the information storage unit after the user power consumption information is acquired in real time;
and the data storage unit is used for storing user electricity utilization standard data and providing reference guiding basis for intelligent identification of electricity stealing users.
8. The big data based electricity theft user intelligent identification system of claim 7, wherein the data storage module further comprises: the data updating unit is used for carrying out self-learning processing based on the newly obtained user electricity information and updating the user electricity standard data according to the self-learning processing result, and comprises the following steps:
the tag adding subunit is used for adding the electricity stealing tag to the new electricity consumption information of the user based on the intelligent identification result of the electricity stealing user of the user after acquiring the new electricity consumption information of the user, wherein the electricity stealing tag comprises two types of electricity stealing and non-electricity stealing;
the confirmation updating subunit is used for acquiring electricity stealing authentication information after the storage time of the new user electricity utilization information reaches the preset time, updating the electricity stealing label of the new user electricity utilization information based on the electricity stealing authentication information, and acquiring a final electricity stealing result;
The information acquisition subunit is used for acquiring the user power consumption information corresponding to modification of the stealing tag as target information while acquiring a final electricity stealing result, and acquiring all the historical user power consumption information of the target user corresponding to the target information based on the user tag corresponding to the target information;
the synchronous learning subunit is used for screening all the historical user electricity information based on the date label of the new user electricity information, acquiring and comparing the contemporaneous historical user electricity information of the new user electricity information, and acquiring contemporaneous electricity change indexes;
classifying historical user electricity consumption information according to quarters to obtain a plurality of information sets, and respectively carrying out subset segmentation on quarters data in the information sets based on electricity consumption year information to obtain a plurality of information subsets;
comparing all information subsets in the same information set according to the year sequence, and determining the electricity utilization change index of each quarter of the user and the target quarter corresponding to the new electricity utilization of the user;
obtaining a change index difference based on a power utilization change index corresponding to a target quarter and a contemporaneous power utilization change index, and correcting original user power utilization standard data corresponding to a target user based on the power utilization change index of each quarter when the change index difference is smaller than or equal to a preset value to obtain new user power utilization standard data which is automatically switched according to power utilization time;
When the variation index difference is larger than a preset value, obtaining a prediction error rate based on the variation index difference and the power utilization variation index corresponding to the target quarter, and comparing the power utilization variation indexes of different quarters to obtain a variation error;
obtaining corresponding error correction factors of each quarter based on the change errors and the prediction errors, correcting the electricity utilization change indexes of each quarter based on the error correction factors, respectively obtaining final electricity utilization change indexes corresponding to each quarter, correcting original user electricity utilization standard data corresponding to a target user based on the final electricity utilization change indexes of each quarter, and obtaining new user electricity utilization standard data which is automatically switched according to electricity utilization time;
and the standard updating subunit is used for updating the original user electricity standard data based on the new user electricity standard data of the target user.
9. The intelligent identification method of the electricity larceny user based on big data is realized based on the intelligent identification system of the electricity larceny user based on big data as claimed in claim 6, and is characterized by comprising the following steps:
s1: the information acquisition module is used for acquiring the user electricity information in real time, the user electricity information acquired in real time is sent to the data processing module, and after the data processing module receives the user electricity information, the data processing module performs data retrieval, grouping and feature extraction on the user electricity information to determine the user electricity information sign data and the historical data based on big data;
S2: the electricity stealing identification module is used for carrying out electricity stealing identification on the user electricity utilization sign data, indexing stored user electricity utilization standard data based on the user electricity utilization sign data, analyzing the stored user electricity utilization standard data based on the user electricity utilization standard data and historical data, carrying out electricity stealing identification on the user electricity utilization sign data, and determining an intelligent electricity stealing user identification result based on big data;
s3: and the intelligent management and control module is used for intelligently managing and controlling the intelligently identified electricity stealing users, determining early warning information based on the intelligent identification result of the electricity stealing users, and sending the early warning information based on the intelligent identification result of the electricity stealing users to guide the electricity stealing users to legally use the electric power.
10. The intelligent power stealing user identification method based on big data according to claim 9, wherein in S2, the power stealing identification module is used for performing power stealing identification on the user electricity meter data, and the following operations are performed:
acquiring user electricity utilization sign data based on big data;
based on the user electricity utilization characteristic data, the engine searches out stored user electricity utilization standard data which is matched with the user electricity utilization characteristic data;
Aiming at the situation that the user electricity utilization sign data is in the range of the user electricity utilization standard data, the intelligent identification result of the electricity stealing user based on big data is that the electricity utilization of the electricity utilization user is normal, and no electricity stealing behavior exists;
aiming at the situation that the user electricity utilization sign data is not in the range of the user electricity utilization standard data, the intelligent identification result of the electricity stealing user based on big data is that the electricity utilization of the electricity utilization user is abnormal, and electricity stealing behavior exists;
aiming at the condition that the electricity utilization of the electricity utilization user is abnormal and the electricity stealing behavior exists, the early warning information based on the intelligent identification result of the electricity utilization user is determined, and the early warning information based on the intelligent identification result of the electricity utilization user is sent to the power supply management party to guide the management personnel to timely conduct on-site verification.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311081013.1A CN117131448B (en) | 2023-08-25 | 2023-08-25 | Big data-based electricity stealing user intelligent identification system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311081013.1A CN117131448B (en) | 2023-08-25 | 2023-08-25 | Big data-based electricity stealing user intelligent identification system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117131448A true CN117131448A (en) | 2023-11-28 |
| CN117131448B CN117131448B (en) | 2024-04-16 |
Family
ID=88855880
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311081013.1A Active CN117131448B (en) | 2023-08-25 | 2023-08-25 | Big data-based electricity stealing user intelligent identification system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117131448B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118508614A (en) * | 2024-07-17 | 2024-08-16 | 北京博纳电气股份有限公司 | Intelligent acquisition terminal system and method for electricity larceny prevention |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103954816A (en) * | 2014-04-30 | 2014-07-30 | 国网上海市电力公司 | Inelegant remote anti-electricity-stealing inspection method |
| US20150316620A1 (en) * | 2012-07-31 | 2015-11-05 | British Columbia Hydro And Power Authority | Method for identifying a system anomaly in a power distribution system |
| CN105932773A (en) * | 2016-05-06 | 2016-09-07 | 深圳市同昌汇能科技发展有限公司 | Intelligent charging electricity larceny prevention system |
| CN106203832A (en) * | 2016-07-12 | 2016-12-07 | 亿米特（上海）信息科技有限公司 | Intelligent electricity anti-theft analyzes system and the method for analysis |
| CN107742127A (en) * | 2017-10-19 | 2018-02-27 | 国网辽宁省电力有限公司 | A kind of improved anti-electricity-theft intelligent early-warning system and method |
| CN110264015A (en) * | 2019-06-28 | 2019-09-20 | 国网河南省电力公司电力科学研究院 | It opposes electricity-stealing and checks monitoring method and platform |
| CN111798107A (en) * | 2020-06-18 | 2020-10-20 | 国网河北省电力有限公司石家庄市栾城区供电分公司 | Novel electricity stealing prevention system and method applying AI intelligent diagnosis and analysis |
-
2023
- 2023-08-25 CN CN202311081013.1A patent/CN117131448B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150316620A1 (en) * | 2012-07-31 | 2015-11-05 | British Columbia Hydro And Power Authority | Method for identifying a system anomaly in a power distribution system |
| CN103954816A (en) * | 2014-04-30 | 2014-07-30 | 国网上海市电力公司 | Inelegant remote anti-electricity-stealing inspection method |
| CN105932773A (en) * | 2016-05-06 | 2016-09-07 | 深圳市同昌汇能科技发展有限公司 | Intelligent charging electricity larceny prevention system |
| CN106203832A (en) * | 2016-07-12 | 2016-12-07 | 亿米特（上海）信息科技有限公司 | Intelligent electricity anti-theft analyzes system and the method for analysis |
| CN107742127A (en) * | 2017-10-19 | 2018-02-27 | 国网辽宁省电力有限公司 | A kind of improved anti-electricity-theft intelligent early-warning system and method |
| CN110264015A (en) * | 2019-06-28 | 2019-09-20 | 国网河南省电力公司电力科学研究院 | It opposes electricity-stealing and checks monitoring method and platform |
| CN111798107A (en) * | 2020-06-18 | 2020-10-20 | 国网河北省电力有限公司石家庄市栾城区供电分公司 | Novel electricity stealing prevention system and method applying AI intelligent diagnosis and analysis |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118508614A (en) * | 2024-07-17 | 2024-08-16 | 北京博纳电气股份有限公司 | Intelligent acquisition terminal system and method for electricity larceny prevention |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117131448B (en) | 2024-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11043808B2 (en) | Method for identifying pattern of load cycle | |
| CN110097297B (en) | Multi-dimensional electricity stealing situation intelligent sensing method, system, equipment and medium | |
| CN117131448B (en) | Big data-based electricity stealing user intelligent identification system and method | |
| CN108106663B (en) | Online visual bridge monitoring platform for creating and managing | |
| Michalak | GIS in land use change analysis: integration of remotely sensed data into GIS | |
| CN112035544B (en) | Power distribution network data anomaly monitoring and diagnosis method | |
| CN111723339B (en) | Transformer area low-voltage hanging identification method based on trend similarity and distance measurement | |
| US20210349135A1 (en) | Techniques For Analysis Of Data From Smart Meters | |
| CN112508105A (en) | Method for detecting and retrieving faults of oil extraction machine | |
| CN109145001A (en) | Real-time data-coding method based on KKS coding rule | |
| CN112258337B (en) | Self-complement correction base station energy consumption model prediction method | |
| CN112418687B (en) | User electricity utilization abnormity identification method and device based on electricity utilization characteristics and storage medium | |
| CN107958395A (en) | A kind of recognition methods of electric system abnormal user | |
| CN104537052B (en) | Traffic trip transfer point recognition methods based on wavelet analysis Study of modulus maximum algorithm | |
| CN111177208A (en) | Power consumption abnormity detection method based on big data analysis | |
| CN112257013A (en) | Electricity stealing user identification and positioning method based on dynamic time warping algorithm for high-loss distribution area | |
| KR101838393B1 (en) | Apparatus and method for 24 hour electrical load forecasting | |
| CN116933157A (en) | Electricity larceny detection method | |
| CN115994131A (en) | Residential community feature tag calculation method and system based on electricity utilization time sequence data | |
| CN107808308A (en) | A kind of yield management method of intellectualized detection dull and rush season | |
| KR20160074325A (en) | Electricity Demand Index (EDI) Forecasting System with respect to Weather Condition Change | |
| CN113642933A (en) | Power distribution station low-voltage diagnosis method and device | |
| CN116488335A (en) | Dynamic monitoring and allocation method, system and equipment for electric power consumption of urban scale | |
| CN115456442A (en) | Emergency connection bus parking point site selection method based on GIS and fuzzy comprehensive evaluation | |
| CN113806899B (en) | Power distribution network topological relation identification method and device and mobile terminal |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |