CN111080476A - User electricity stealing behavior analysis and early warning method based on data center - Google Patents
User electricity stealing behavior analysis and early warning method based on data center Download PDFInfo
- Publication number
- CN111080476A CN111080476A CN201911240302.5A CN201911240302A CN111080476A CN 111080476 A CN111080476 A CN 111080476A CN 201911240302 A CN201911240302 A CN 201911240302A CN 111080476 A CN111080476 A CN 111080476A
- Authority
- CN
- China
- Prior art keywords
- user
- electricity
- data
- behavior
- abnormal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000005611 electricity Effects 0.000 title claims abstract description 72
- 238000004458 analytical method Methods 0.000 title claims abstract description 27
- 238000000034 method Methods 0.000 title claims abstract description 23
- 230000006399 behavior Effects 0.000 claims abstract description 72
- 230000002159 abnormal effect Effects 0.000 claims abstract description 30
- 238000013145 classification model Methods 0.000 claims description 8
- 238000007418 data mining Methods 0.000 claims description 7
- 238000005516 engineering process Methods 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 4
- 230000005856 abnormality Effects 0.000 claims description 3
- 238000007726 management method Methods 0.000 claims description 3
- 238000000611 regression analysis Methods 0.000 claims description 3
- 238000003066 decision tree Methods 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 claims description 2
- 230000010354 integration Effects 0.000 claims 1
- 238000004141 dimensional analysis Methods 0.000 abstract description 2
- 230000002265 prevention Effects 0.000 abstract description 2
- 230000009897 systematic effect Effects 0.000 abstract description 2
- 238000013024 troubleshooting Methods 0.000 abstract description 2
- 238000012545 processing Methods 0.000 description 3
- 238000007621 cluster analysis Methods 0.000 description 2
- 238000010835 comparative analysis Methods 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- General Engineering & Computer Science (AREA)
- Primary Health Care (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a user electricity stealing behavior analysis and early warning method based on a data center, which is used for fusing data of multi-source data by adopting the data center, establishing a multi-layer dynamic index system for sensing abnormal electricity using behaviors, identifying the success rate of abnormal user behavior identification to reach a satisfactory index through a specific clustering algorithm, establishing a customer electricity stealing early warning analysis model, carrying out multi-dimensional analysis on all electricity customers, accurately identifying the electricity stealing users, establishing a systematic and normalized electricity stealing analysis, early warning, troubleshooting and closed-loop service flow, and improving the work success rate of electricity stealing prevention.
Description
Technical Field
The invention relates to the field of power grid data analysis, in particular to a user electricity stealing behavior analysis and early warning method based on a data center.
Background
With the construction and development of the smart power grid, numerous data acquisition devices are installed and deployed in six links of power generation, power transmission, power transformation, power distribution, power utilization and scheduling of the power grid, and a corresponding information management system is constructed in a matched manner. These systems generate and manage a vast amount of structurally complex, interrelated data. The massive data of the multiple data sources provides good conditions for data mining, relevant work of big data application is developed around each link of the smart power grid, work such as data processing performance improvement, data value mining, data conversion into assets and the like is urgently carried out, and the actual problem of power grid solution is the mission of electric big data.
At present, the electricity stealing behavior of the power users becomes an important factor influencing the benefits of the power company and causing artificial power accidents. By analyzing and mining the information reflected by the power consumer power load curve, the power consumption behavior of the user can be better mastered. However, in the power system, data structures of various data sources are different, and it becomes a challenge how to combine a plurality of heterogeneous data to provide a power-stealing early-warning system for power consumers.
Disclosure of Invention
The purpose of the invention is as follows: the invention aims to provide a user electricity stealing behavior analysis and early warning method based on a data center station, which aims to meet the requirements of gathering multi-source data, analyzing the user electricity using behavior by adopting a clustering analysis method and prejudging the electricity stealing requirements of users.
The technical scheme is as follows: the invention relates to a user electricity stealing behavior analysis and early warning method based on a data center, which comprises the following steps:
step 1, acquiring and converging multi-source power user electricity utilization data from a system by adopting a data center method;
step 2, establishing a user electricity consumption behavior analysis model by using the user electricity consumption data, wherein the user electricity consumption behavior analysis model is used for analyzing and judging the user electricity consumption behavior;
and 3, classifying and judging the user electricity utilization behaviors by the user electricity utilization behavior analysis model, screening abnormal users and actively pushing out early warning information.
By adopting the technical scheme, the data of each data source is collected and gathered by adopting a data center method, and the data is analyzed and distinguished according to the user electricity consumption behavior analysis model:
and (4) classifying the abnormal electricity utilization behaviors of the users. Depending on the collected typical electricity stealing cases, according to different electricity stealing types, multi-dimensional characteristics describing the abnormal degree of the customer are analyzed and obtained, such as: whether current three-phase imbalance occurs or not and whether voltage breaking is equal or not. Meanwhile, a data mining regression analysis technology is adopted, and potential characteristics in the customer electricity consumption behavior information data are mined through analyzing relevant characteristics of a large amount of data, so that a customer electricity consumption behavior abnormity classification model is established.
And judging the abnormal electricity utilization behavior of the user. The method comprises the steps of adopting a data mining clustering analysis technology, dividing customers into different types according to regions and electricity utilization categories, generating typical electricity utilization behavior curves of various types of customers by using historical electricity utilization information data through the clustering analysis technology, and judging whether electricity utilization behaviors are abnormal or not through comparing and analyzing the electricity utilization behavior curves of the customers in new data and the typical electricity utilization behavior curves.
And screening out abnormal users and actively pushing out the early warning information.
Has the advantages that: aiming at multi-source data, a data center is adopted for data fusion, a multi-layer dynamic index system for sensing abnormal power consumption behaviors is established, a satisfactory index is achieved for the success rate of abnormal user behavior identification through a specific clustering algorithm, a customer power stealing early warning analysis model is established, multi-dimensional analysis is carried out on all power consumption customers, the meaning power stealing users are accurately identified, systematic and normalized power stealing analysis, early warning, troubleshooting and closed-loop service flows are established, and the work success rate of power stealing prevention is improved.
Drawings
FIG. 1 is a user load curve classification step;
FIG. 2 is a flow of modeling to determine electricity stealing behavior;
fig. 3 is a process of judging electricity stealing.
Detailed Description
As shown in fig. 1, firstly, a data center station is adopted to extract daily load curve data required by analyzing the power consumption behavior of a user from a multi-data source SG186 marketing service application system, a power user information acquisition system, a D5000 scheduling support system, a PMS production management system and a marketing and distribution integrated system, and the data is subjected to standardized processing. And processing the extracted data by adopting a K-proximity clustering algorithm according to multiple dimensions such as whether current three-phase imbalance occurs and whether voltage phase failure occurs according to the opinion of a service expert to obtain user power utilization behavior classification, and screening the user classification with abnormal power utilization behavior from the classification according to historical records.
And then establishing a user electricity utilization behavior analysis model, wherein the user electricity utilization behavior analysis model comprises a user electricity utilization behavior abnormity classification model and a user electricity utilization behavior abnormity discrimination model.
As shown in fig. 2, a classification model for abnormal electricity consumption behaviors of users is established by using classification results, abnormal electricity consumption users are screened out according to the classification results shown in fig. 1, and electricity consumption behavior characteristics of the users, such as current abnormality, voltage abnormality and the like, are extracted. And the user electricity consumption behavior abnormity classification model classifies the user electricity consumption behavior abnormity. Depending on the collected typical electricity stealing cases, according to different electricity stealing types, multi-dimensional characteristics describing the abnormal degree of the customer are analyzed and obtained, such as: whether current three-phase imbalance occurs or not and whether voltage breaking is equal or not. Meanwhile, a data mining regression analysis technology is adopted, and potential characteristics in the customer electricity consumption behavior information data are mined through analyzing relevant characteristics of a large amount of data.
And (3) establishing a user electricity consumption behavior abnormity discrimination model based on the existing data and vector machine regression (PSO-SVR), and training and improving the model through a large amount of data.
Fig. 3 shows a flow of judging whether a user power consumption behavior is abnormal, in which a data mining cluster analysis technique is adopted to classify customers into different types according to regions and power consumption categories, historical power consumption information data is used to generate typical power consumption behavior curves of various types of customers through the cluster analysis technique, whether the power consumption behavior is abnormal or not is judged through comparative analysis of the power consumption behavior curves of the customers in new data and the typical power consumption behavior curves, and suspected power consumption users are screened out.
And (3) synthesizing suspected electricity stealing users screened by the classification model for the abnormal electricity utilization behavior of the users and the discrimination model for the abnormal electricity utilization behavior of the users, and rapidly and dynamically discriminating whether electricity stealing behavior occurs or not by analyzing the probability that each item of data accords with the typical abnormal characteristic through the association rule between the data characteristic and the electricity stealing behavior identification, the comparative analysis between the new data and the typical abnormal curve and the decision tree algorithm.
Claims (7)
1. A user electricity stealing behavior analysis and early warning method based on a data center station is characterized by comprising the following steps:
step 1, acquiring and converging multi-source power user electricity utilization data from a system by adopting a data center method;
step 2, establishing a user electricity consumption behavior analysis model by using the user electricity consumption data, wherein the user electricity consumption behavior analysis model is used for analyzing and judging the user electricity consumption behavior;
and 3, classifying and judging the user electricity utilization behaviors by the user electricity utilization behavior analysis model, screening abnormal user electricity utilization behaviors and actively pushing out early warning information.
2. The method for analyzing and early warning the electricity stealing behavior of the user based on the data center platform as claimed in claim 1, wherein in the step 1, a user historical load curve is extracted from the obtained multi-source electricity consumption data of the power users, the load curve is processed by a clustering method, and an obtained clustering center is a daily load characteristic curve of the user.
3. The method according to claim 1, wherein in step 1, the systems include, but are not limited to, SG186 marketing service application system, power consumer information collection system, D5000 scheduling support system, PMS production management system, and marketing and distribution integration system.
4. The method for analyzing and warning the electricity stealing behavior of the user based on the data center as claimed in claim 2 or 3, wherein in the step 2, the analysis model of the electricity consumption behavior of the user comprises a classification model of the abnormal electricity consumption behavior of the user and a discrimination model of the abnormal electricity consumption behavior of the user.
5. The method as claimed in claim 4, wherein in step 3, the classification model for abnormal power consumption behavior of the user can analyze and obtain multidimensional characteristics describing the abnormal degree of the user according to different power consumption types, the multidimensional characteristics include but are not limited to whether three-phase imbalance of current occurs or not and whether phase loss of voltage occurs or not, the model further adopts a data mining regression analysis technology, and analyzes related characteristics through a large amount of data, so as to mine potential characteristics in the information data of the power consumption behavior of the user, and screen out suspected power consumption users.
6. The method as claimed in claim 4, wherein in step 3, the power consumption behavior abnormality distinguishing model of the user adopts a data mining clustering analysis technique to classify the customers into different categories according to areas and power consumption categories, typical power consumption behavior curves of various types of customers are generated by using historical power consumption information data through the clustering analysis technique, whether the power consumption behavior is abnormal or not is judged by comparing and analyzing the power consumption behavior curves of the customers in the new data with the typical power consumption behavior curves, and suspected power consumption users are screened out.
7. The method as claimed in claim 6, wherein in step 3, the classification model of abnormal user electricity consumption behavior and the discrimination model of abnormal user electricity consumption behavior are integrated to select suspected electricity-stealing users, and the probability that each item of data meets the typical abnormal characteristic is analyzed through the association rule between the data characteristic and the electricity-stealing behavior identifier, the comparison analysis between the new data and the typical abnormal curve, and the decision tree algorithm, so as to rapidly and dynamically identify whether the electricity-stealing behavior occurs, and actively push out the information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911240302.5A CN111080476A (en) | 2019-12-06 | 2019-12-06 | User electricity stealing behavior analysis and early warning method based on data center |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911240302.5A CN111080476A (en) | 2019-12-06 | 2019-12-06 | User electricity stealing behavior analysis and early warning method based on data center |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111080476A true CN111080476A (en) | 2020-04-28 |
Family
ID=70313135
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911240302.5A Pending CN111080476A (en) | 2019-12-06 | 2019-12-06 | User electricity stealing behavior analysis and early warning method based on data center |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111080476A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111652761A (en) * | 2020-07-28 | 2020-09-11 | 国网江西省电力有限公司供电服务管理中心 | Multi-source feature fusion electricity stealing behavior detection method based on evidence theory |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106156269A (en) * | 2016-06-01 | 2016-11-23 | 国网河北省电力公司电力科学研究院 | One is opposed electricity-stealing precise positioning on-line monitoring method |
| CN107145966A (en) * | 2017-04-12 | 2017-09-08 | 山大地纬软件股份有限公司 | Logic-based returns the analysis and early warning method of opposing electricity-stealing of probability analysis Optimized model |
| CN109146705A (en) * | 2018-07-02 | 2019-01-04 | 昆明理工大学 | A kind of method of electricity consumption characteristic index dimensionality reduction and the progress stealing detection of extreme learning machine algorithm |
| CN110097297A (en) * | 2019-05-21 | 2019-08-06 | 国网湖南省电力有限公司 | A kind of various dimensions stealing situation Intellisense method, system, equipment and medium |
-
2019
- 2019-12-06 CN CN201911240302.5A patent/CN111080476A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106156269A (en) * | 2016-06-01 | 2016-11-23 | 国网河北省电力公司电力科学研究院 | One is opposed electricity-stealing precise positioning on-line monitoring method |
| CN107145966A (en) * | 2017-04-12 | 2017-09-08 | 山大地纬软件股份有限公司 | Logic-based returns the analysis and early warning method of opposing electricity-stealing of probability analysis Optimized model |
| CN109146705A (en) * | 2018-07-02 | 2019-01-04 | 昆明理工大学 | A kind of method of electricity consumption characteristic index dimensionality reduction and the progress stealing detection of extreme learning machine algorithm |
| CN110097297A (en) * | 2019-05-21 | 2019-08-06 | 国网湖南省电力有限公司 | A kind of various dimensions stealing situation Intellisense method, system, equipment and medium |
Non-Patent Citations (1)
| Title |
|---|
| 王申华 等: "基于泛在电力物联网多源信息的电网动态风险评估系统" * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111652761A (en) * | 2020-07-28 | 2020-09-11 | 国网江西省电力有限公司供电服务管理中心 | Multi-source feature fusion electricity stealing behavior detection method based on evidence theory |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110232499A (en) | A kind of power distribution network information physical side method for prewarning risk and system | |
| CN104679828A (en) | Rules-based intelligent system for grid fault diagnosis | |
| CN110388315B (en) | Oil transfer pump fault identification method, device and system based on multi-source information fusion | |
| CN104616092A (en) | Distributed log analysis based distributed mode handling method | |
| CN114048870A (en) | Power system abnormity monitoring method based on log characteristic intelligent mining | |
| Yacout | Fault detection and diagnosis for condition based maintenance using the logical analysis of data | |
| CN114596061B (en) | Project data management method and system based on big data | |
| CN112785108A (en) | Power grid operation data correlation analysis method and system based on regulation cloud | |
| CN115099335A (en) | Abnormal identification and feature screening method and system for multi-source heterogeneous data | |
| CN110633729A (en) | Driving risk hierarchical clustering method for intelligent networking vehicle group test | |
| Cuzzocrea et al. | An information-theoretic approach for setting the optimal number of decision trees in random forests | |
| CN103493075A (en) | Outlier detecting apparatus, outlier detecting method, and vehicle trouble diagnosis system | |
| CN107104951A (en) | The detection method and device of Attack Source | |
| CN115358155A (en) | Power big data abnormity early warning method, device, equipment and readable storage medium | |
| CN114689965A (en) | Power equipment online monitoring method and system based on embedded intelligent sensor | |
| CN117391458B (en) | Safety production risk detection and early warning method and system based on data analysis | |
| CN116541782A (en) | Power marketing data anomaly identification method | |
| CN116011825A (en) | Multi-dimensional evaluation method for operation risk of distribution cable line | |
| CN117666367A (en) | Remote control method and system for underground coal mine machinery | |
| CN111080476A (en) | User electricity stealing behavior analysis and early warning method based on data center | |
| US20170236071A1 (en) | Alarm management system | |
| CN114118222A (en) | Coal mill state early warning system and fault identification and diagnosis method | |
| CN112363891B (en) | Method for obtaining abnormal reasons based on fine-grained events and KPIs (Key Performance indicators) analysis | |
| CN113780354A (en) | Telemetry data anomaly identification method and device for dispatching automation master station system | |
| CN117390546A (en) | Multimode database fusion calculation model for instant anti-electricity-theft detection |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200428 |
|
| RJ01 | Rejection of invention patent application after publication |