CN113033598A - Electricity stealing identification method based on curve similarity and integrated learning algorithm - Google Patents
Electricity stealing identification method based on curve similarity and integrated learning algorithm Download PDFInfo
- Publication number
- CN113033598A CN113033598A CN202110076044.2A CN202110076044A CN113033598A CN 113033598 A CN113033598 A CN 113033598A CN 202110076044 A CN202110076044 A CN 202110076044A CN 113033598 A CN113033598 A CN 113033598A
- Authority
- CN
- China
- Prior art keywords
- user
- curve
- electricity stealing
- load
- 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.)
- Pending
Links
- 230000005611 electricity Effects 0.000 title claims abstract description 72
- 238000000034 method Methods 0.000 title claims abstract description 23
- 230000006399 behavior Effects 0.000 claims abstract description 19
- 230000002159 abnormal effect Effects 0.000 claims abstract description 7
- 238000012216 screening Methods 0.000 claims abstract description 4
- 238000012549 training Methods 0.000 claims description 13
- 238000012360 testing method Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000000717 retained effect Effects 0.000 claims description 3
- 238000000691 measurement method Methods 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a power stealing identification method based on curve similarity and an integrated learning algorithm, and belongs to the field of user power consumption behavior abnormity identification. The normal electricity utilization behavior of a user has certain regularity, when the electricity stealing behavior occurs, the electricity utilization trend of the user can deviate from the conventional electricity utilization rule, and the numerical value of the relevant electrical parameter index generates abnormal change. The method analyzes the historical electricity utilization data of the user, firstly, clustering load curve data to obtain a characteristic curve and dividing electricity utilization behaviors, secondly, comparing and analyzing the similarity between the load curve and the characteristic curve of the user to be tested, primarily screening suspected electricity stealing users, and finally substituting related index data into an AdaBoost integrated learning model for further electricity stealing identification. The invention can effectively narrow the identification range of the electricity stealing users and has good electricity stealing identification effect.
Description
Technical Field
The invention relates to a power stealing identification method based on curve similarity and an integrated learning algorithm, and belongs to the field of user power consumption behavior abnormity identification.
Background
Electric power plays a very important role in production and life, and with the development of society and economy, the demand of electric power is more and more, and the trend of increasing year by year is presented. The sufficient supply of electric power greatly supports the development and progress of the society, so that the production and the life are more stable, and the economy and the health are developed. However, driven by illegal benefits, the electricity stealing phenomenon becomes more obvious, electricity stealing modes and means are increasingly diversified, the traditional electricity stealing mode is developed to a high-tech electricity stealing mode, and the electricity stealing device is extremely hidden. The traditional electricity stealing means mostly depend on changing the normal wiring of the metering device or destroying the metering device to achieve the purpose of metering no electric energy or little electric energy. The high-tech electricity stealing means enables the metering device to generate negative errors through interference signals so as to achieve the purpose of abnormal word movement or damage of the electric energy meter, the interference means disappears, and the metering device can normally work and is extremely hidden. The popularization of the intelligent electric meter is accompanied with the occurrence of high-tech intelligent electricity stealing phenomenon, and non-contact electricity stealing behaviors such as strong magnetic field interference, strong radio interference or high-frequency high-voltage interference are more and more common. Generally speaking, illegal electricity stealing is to reduce the payment of electricity fee by various means (including technical means and non-technical means) so as to achieve the purpose of obtaining illegal benefits. The electricity stealing behavior seriously affects the normal operation of the electric power system, increases the potential safety hazard, causes great economic loss for power supply enterprises, and also seriously affects the normal power supply and utilization order. The system aims to further improve the safety of social electricity utilization, guarantee the normal benefits of power generation enterprises, power grid enterprises and power consumers and stop the occurrence of electricity stealing behaviors as far as possible. In the electric power data analysis, intelligent detection and intelligent identification methods such as data mining, machine learning and the like are adopted, historical data of a user are analyzed, potential electricity stealing behaviors of the user are mined, and an electricity stealing identification model or rule is constructed. Through detection and identification of the model or the rule, abnormal electricity utilization behaviors are found in time, relevant countermeasures are taken, normal benefits of power enterprises and power users are guaranteed as much as possible, and economic loss is reduced to the lowest.
Disclosure of Invention
Aiming at the problems, the invention provides a power stealing identification method based on curve similarity and an integrated learning algorithm. The historical electricity utilization data of the user are analyzed, the curve similarity analysis and the AdaBoost integrated learning algorithm are combined to identify electricity stealing behaviors, and the method has a good identification effect.
The technical scheme of the invention is as follows: a power stealing identification method based on curve similarity and an integrated learning algorithm comprises the following steps:
step1, extracting the power load data of the user;
step2, preprocessing data, filtering data records with load values of all 0 or negative values, eliminating users with abnormal data of more than 30%, filling partial missing items in the retained data by adopting a mean value substitution method, and carrying out range normalization processing on the data in order to ensure that each individual has the same importance degree in the analysis process;
step3, performing weighted average calculation on the load values at the same time point to form a typical daily load curve;
and Step4, clustering the typical daily load curve through an FCM algorithm, and obtaining a clustering center curve which is a daily load characteristic curve. Different clustering center curves represent different types of daily load characteristic curves, and the electricity utilization behaviors are divided into different categories according to the different clustering center curves;
step5, calculating the similarity between the typical daily load curve and the load characteristic curve of the user to be detected, comparing the similarity with a set similarity threshold, and if the similarity between the load curve and the characteristic curve of the user to be detected is smaller than the similarity threshold, primarily screening the user to be suspected of electricity stealing;
step6, selecting screened suspected electricity stealing users and part of normal users as a sample set, randomly selecting normal users, wherein the number of the normal users is not too much or too little relative to the suspected electricity stealing users, dividing training set samples and testing set samples randomly according to a proportion, training and testing an AdaBoost integrated learning model, extracting relevant electrical parameter index values of the sample set, performing relevant calculation and normalization processing, converting the values into electricity stealing judgment index data which can be used as input, training the AdaBoost integrated learning model by using the training set samples, and performing classification prediction on the testing set samples by using the trained AdaBoost integrated learning model;
and Step7, identifying and judging whether the electricity stealing users are electricity stealing users according to the AdaBoost ensemble learning model classification prediction results.
Specifically, Step3 includes: a typical daily load curve is constructed by using a weighted average method:
let the load curve data of the i-th day of a certain user be Di＝{di1，di2，…，dimA total of n days of data are extracted. According to the n-day electricity consumption data of the user, calculating the load weight of the ith day at the time point j
The weighted average load of the user at time point j is
The typical daily load curve of the user can be obtained by carrying out weighted average on the load values at the same time point.
Specifically, Step5 includes: and measuring the similarity between the typical daily load curve and the characteristic curve of the user to be measured by adopting the similarity based on the time sequence. The dynamic time warping distance can well reflect the overall dynamic characteristics between curves, so the DTW distance is calculated first and then converted into the similarity.
Specifically, Step6 includes: when electricity stealing behavior occurs, the relevant electrical parameter index values are abnormally changed, so the selected electricity stealing judgment index data are power factor unbalance rate, rated voltage deviation, voltage unbalance rate, current unbalance rate, phase angle unbalance rate, electric quantity unbalance rate, line loss rate, monthly electricity consumption same ratio and contract capacity ratio.
Specifically, Step6 includes: and adopting an AdaBoost integrated learning model to solve the classification problem. Logistic is adopted as a weak classifier of the AdaBoost integrated learning model. And distributing the sample set into the training set samples and the test set samples according to the proportion of 7: 3.
The invention has the beneficial effects that:
according to the method, on the basis of the characteristic characteristics, when a user has electricity stealing behavior, the electricity utilization trend of the user deviates from the conventional electricity utilization law, the index values of related electrical parameters generate abnormal changes, historical electricity utilization data of the user are analyzed, load curve data are clustered to obtain a characteristic curve and divide the electricity utilization behavior, the similarity between the load curve and the characteristic curve of the user to be tested is contrasted and analyzed, the electricity stealing suspected user is preliminarily screened, and the range of electricity stealing identification can be narrowed. The AdaBoost integrated learning model has higher precision and better stability compared with a single classification model, and relevant index data are substituted into the AdaBoost integrated learning model for further electricity stealing identification, so that the identification efficiency of electricity stealing behaviors can be improved.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
For a more detailed description of the present invention and to facilitate understanding thereof by those skilled in the art, the present invention is further described below with reference to the accompanying drawings and examples.
Example 1: a power stealing identification method based on curve similarity and an integrated learning algorithm is carried out according to the steps shown in figure 1 and the scheme in the invention content:
the electricity load data of the user is extracted, and the sampling interval is 15 minutes, so each record comprises 96 points of load data.
And (3) data preprocessing, namely filtering data records with load values of all 0 or negative values, eliminating users with abnormal data of more than 30%, filling partial missing items in the retained data by adopting a mean value substitution method, and then performing range normalization processing on the data.
And forming a typical daily load curve by performing weighted average calculation on the load values at the same time point.
And clustering the typical daily load curve through an FCM algorithm to obtain a clustering center curve, namely a daily load characteristic curve. Different clustering center curves represent different types of daily load characteristic curves, and the electricity utilization behaviors are divided into different categories according to the different clustering center curves.
The DTW distance between the typical daily load curve and the load characteristic curve of the user to be detected is calculated and then converted into the similarity.
And setting a similarity threshold, and if the similarity between the typical daily load curve and the load characteristic curve of the user to be detected is smaller than the set similarity threshold, preliminarily screening the user to be detected as a suspected electricity stealing user.
And taking the screened electricity stealing suspected users and part of normal users as a sample set, and dividing a training set sample and a test set sample according to a ratio of 7: 3.
And extracting the relevant electrical parameter index values of the sample set, performing relevant calculation and normalization processing, and converting the values into electricity stealing judgment index data which can be used as input.
And training the AdaBoost integrated learning model by using the training set samples, and then performing classification prediction on the test set samples by using the trained AdaBoost integrated learning model.
And identifying and judging whether the user is a power stealing user or not according to the classification prediction result of the AdaBoost integrated learning model.
Claims (5)
1. A power stealing identification method based on curve similarity and an integrated learning algorithm is characterized by comprising the following steps:
step1, extracting the power load data of the user;
step2, preprocessing data, filtering data records with load values of all 0 or negative values, eliminating users with abnormal data of more than 30%, filling partial missing items in the retained data by adopting a mean value replacement method, and then performing range normalization processing on the data;
step3, performing weighted average calculation on the load values at the same time point to form a typical daily load curve;
step4, clustering the typical daily load curve through an FCM algorithm to obtain a clustering center curve which is a daily load characteristic curve; different clustering center curves represent different types of daily load characteristic curves, and the electricity utilization behaviors are divided into different categories according to the different clustering center curves;
step5, calculating the similarity between the typical daily load curve and the load characteristic curve of the user to be detected, comparing the similarity with a set similarity threshold, and if the similarity between the load curve and the characteristic curve of the user to be detected is smaller than the similarity threshold, primarily screening the user to be suspected of electricity stealing;
step6, taking the screened suspected electricity stealing users and part of normal users as sample sets, dividing training set samples and test set samples according to proportion, training and testing an AdaBoost integrated learning model, extracting relevant electrical parameter index values of the sample sets, performing relevant calculation and normalization processing, converting the values into electricity stealing judgment index data which can be used as input, training the AdaBoost integrated learning model by using the training set samples, and performing classification prediction on the test set samples by using the trained AdaBoost integrated learning model;
and Step7, identifying and judging whether the electricity stealing users are electricity stealing users according to the AdaBoost ensemble learning model classification prediction results.
2. The method for identifying electricity stealing according to claim 1, wherein the Step3 includes:
the load curve is a curve reflecting the load change rule of a user in a period of time, the power load curve of a certain day cannot comprehensively reflect the daily power behavior of the user, and a typical daily load curve is constructed by adopting a weighted average method:
let the load curve data of the i-th day of a certain user be Di＝{di1，di2，…，dimExtracting data for a total of n days; according to the n-day electricity consumption data of the user, calculating the load weight of the ith day at the time point j
The weighted average load of the user at time point j is
The typical daily load curve of the user can be obtained by carrying out weighted average on the load values at the same time point.
3. The method for identifying electricity stealing according to claim 1, wherein the Step5 includes:
the load curve is formed by a series of load values related to a time sequence, and a similarity measurement method between a typical daily load curve and a characteristic curve of a user to be measured is measured by adopting similarity based on the time sequence on the basis of the characteristics of load curve data; the dynamic time warping distance can well reflect the overall dynamic characteristics between curves, so the DTW distance is calculated first and then converted into the similarity.
4. The method for identifying electricity stealing according to claim 1, wherein the Step6 includes:
the electricity stealing judgment index data comprise a power factor unbalance rate, a rated voltage deviation degree, a voltage unbalance rate, a current unbalance rate, a phase angle unbalance rate, an electric quantity unbalance rate, a line loss rate, a monthly electricity consumption same proportion and a contract capacity ratio.
5. The method for identifying electricity stealing according to claim 1, wherein the Step6 includes:
AdaBoost can be used for solving the classification problem and the regression problem; further detecting users with suspicion of electricity stealing to obtain classification prediction results of electricity stealing users and non-electricity stealing users, so that an AdaBoost integrated learning model is adopted to solve the classification problem; adopting Logistic as a weak classifier of an AdaBoost integrated learning model;
the sample set was as follows 7: and 3, distributing the ratio into the training set samples and the test set samples.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110076044.2A CN113033598A (en) | 2021-01-20 | 2021-01-20 | Electricity stealing identification method based on curve similarity and integrated learning algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110076044.2A CN113033598A (en) | 2021-01-20 | 2021-01-20 | Electricity stealing identification method based on curve similarity and integrated learning algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113033598A true CN113033598A (en) | 2021-06-25 |
Family
ID=76459616
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110076044.2A Pending CN113033598A (en) | 2021-01-20 | 2021-01-20 | Electricity stealing identification method based on curve similarity and integrated learning algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113033598A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113705710A (en) * | 2021-09-02 | 2021-11-26 | 国网安徽省电力有限公司营销服务中心 | Method and device for identifying default electricity consumption of electric vehicle charging facility |
| CN113743501A (en) * | 2021-09-03 | 2021-12-03 | 国网江苏省电力有限公司常州供电分公司 | Electricity stealing identification method of communication base station, computer equipment and storage medium |
| CN113762373A (en) * | 2021-08-30 | 2021-12-07 | 广东电网有限责任公司 | Load characteristic abnormity identification method and device, electronic equipment and medium |
| CN113792477A (en) * | 2021-08-18 | 2021-12-14 | 珠海派诺科技股份有限公司 | Power utilization abnormity identification method, system and device and fire early warning system |
| CN113869601A (en) * | 2021-10-18 | 2021-12-31 | 深圳供电局有限公司 | Power consumer load prediction method, device and equipment |
| CN113884734A (en) * | 2021-10-27 | 2022-01-04 | 广东电网有限责任公司 | Non-invasive electricity utilization abnormity diagnosis method and device |
| CN114217160A (en) * | 2022-02-18 | 2022-03-22 | 青岛鼎信通讯股份有限公司 | Method for installing and positioning load monitoring unit of medium-voltage distribution line |
| CN114330583A (en) * | 2021-12-31 | 2022-04-12 | 四川大学 | Abnormal electricity utilization identification method and abnormal electricity utilization identification system |
| CN116027254A (en) * | 2023-03-22 | 2023-04-28 | 国网江苏省电力有限公司常州供电分公司 | Method for analyzing unbalanced current stealing of three-phase electric energy meter |
| CN116345481A (en) * | 2023-03-17 | 2023-06-27 | 江苏华信新能源管理有限公司 | Power factor optimization method, device, equipment and storage medium |
| CN116862116A (en) * | 2023-09-05 | 2023-10-10 | 国网天津市电力公司营销服务中心 | Intelligent early warning method and system for preventing electricity larceny, electronic equipment and storage medium |
| CN117932445A (en) * | 2024-03-25 | 2024-04-26 | 西安航科创星电子科技有限公司 | High-stability HTCC alumina ceramic preparation parameter anomaly identification method |
-
2021
- 2021-01-20 CN CN202110076044.2A patent/CN113033598A/en active Pending
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113792477A (en) * | 2021-08-18 | 2021-12-14 | 珠海派诺科技股份有限公司 | Power utilization abnormity identification method, system and device and fire early warning system |
| CN113792477B (en) * | 2021-08-18 | 2024-06-07 | 珠海派诺科技股份有限公司 | Electricity utilization abnormality identification method, system, device and fire disaster early warning system |
| CN113762373A (en) * | 2021-08-30 | 2021-12-07 | 广东电网有限责任公司 | Load characteristic abnormity identification method and device, electronic equipment and medium |
| CN113705710A (en) * | 2021-09-02 | 2021-11-26 | 国网安徽省电力有限公司营销服务中心 | Method and device for identifying default electricity consumption of electric vehicle charging facility |
| CN113743501A (en) * | 2021-09-03 | 2021-12-03 | 国网江苏省电力有限公司常州供电分公司 | Electricity stealing identification method of communication base station, computer equipment and storage medium |
| CN113869601A (en) * | 2021-10-18 | 2021-12-31 | 深圳供电局有限公司 | Power consumer load prediction method, device and equipment |
| CN113884734B (en) * | 2021-10-27 | 2024-04-19 | 广东电网有限责任公司 | Non-invasive electricity consumption abnormality diagnosis method and device |
| CN113884734A (en) * | 2021-10-27 | 2022-01-04 | 广东电网有限责任公司 | Non-invasive electricity utilization abnormity diagnosis method and device |
| CN114330583A (en) * | 2021-12-31 | 2022-04-12 | 四川大学 | Abnormal electricity utilization identification method and abnormal electricity utilization identification system |
| CN114217160A (en) * | 2022-02-18 | 2022-03-22 | 青岛鼎信通讯股份有限公司 | Method for installing and positioning load monitoring unit of medium-voltage distribution line |
| CN116345481A (en) * | 2023-03-17 | 2023-06-27 | 江苏华信新能源管理有限公司 | Power factor optimization method, device, equipment and storage medium |
| CN116027254A (en) * | 2023-03-22 | 2023-04-28 | 国网江苏省电力有限公司常州供电分公司 | Method for analyzing unbalanced current stealing of three-phase electric energy meter |
| CN116027254B (en) * | 2023-03-22 | 2023-06-13 | 国网江苏省电力有限公司常州供电分公司 | Method for analyzing unbalanced current stealing of three-phase electric energy meter |
| CN116862116A (en) * | 2023-09-05 | 2023-10-10 | 国网天津市电力公司营销服务中心 | Intelligent early warning method and system for preventing electricity larceny, electronic equipment and storage medium |
| CN117932445A (en) * | 2024-03-25 | 2024-04-26 | 西安航科创星电子科技有限公司 | High-stability HTCC alumina ceramic preparation parameter anomaly identification method |
| CN117932445B (en) * | 2024-03-25 | 2024-05-31 | 西安航科创星电子科技有限公司 | High-stability HTCC alumina ceramic preparation parameter anomaly identification method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113033598A (en) | Electricity stealing identification method based on curve similarity and integrated learning algorithm | |
| CN110223196B (en) | Anti-electricity-stealing analysis method based on typical industry feature library and anti-electricity-stealing sample library | |
| CN110097297B (en) | Multi-dimensional electricity stealing situation intelligent sensing method, system, equipment and medium | |
| CN109146705B (en) | Method for detecting electricity stealing by using electricity characteristic index dimension reduction and extreme learning machine algorithm | |
| CN107609783B (en) | Method and system for evaluating comprehensive performance of intelligent electric energy meter based on data mining | |
| CN103678766B (en) | A kind of abnormal Electricity customers detection method based on PSO algorithm | |
| CN106093707B (en) | The data processing method of intelligent electricity anti-theft analysis system | |
| CN103103570B (en) | Based on the aluminium cell condition diagnostic method of pivot similarity measure | |
| CN111340065B (en) | User load electricity stealing model mining system and method based on complex user behavior analysis | |
| CN110738232A (en) | grid voltage out-of-limit cause diagnosis method based on data mining technology | |
| CN110059845A (en) | Metering device clocking error trend forecasting method based on timing evolved genes model | |
| Long et al. | A data-driven combined algorithm for abnormal power loss detection in the distribution network | |
| CN112132210A (en) | Electricity stealing probability early warning analysis method based on customer electricity consumption behavior | |
| CN112101471A (en) | Electricity stealing probability early warning analysis method | |
| CN115760400A (en) | Mining behavior detection method based on electric power data and storage medium | |
| CN116796271A (en) | Resident energy abnormality identification method | |
| CN118194202A (en) | Transverse federal-based electricity stealing identification algorithm and prototype system thereof | |
| Pan et al. | Kernel-based non-parametric clustering for load profiling of big smart meter data | |
| CN114240041A (en) | Lean line loss analysis method and system for distribution network distribution area | |
| CN107274025B (en) | System and method for realizing intelligent identification and management of power consumption mode | |
| CN112528762A (en) | Harmonic source identification method based on data correlation analysis | |
| CN111932078A (en) | Risk user identification method based on measurement data multi-situation evaluation | |
| CN116384622A (en) | Carbon emission monitoring method and device based on electric power big data | |
| CN113256092B (en) | Evaluation method of portable electric quantity metering device based on improved optimization membership function | |
| Peiyi et al. | Analysis and research on enterprise resumption of work and production based on K-means clustering |
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 |