CN112256693A - Method for predicting line fault power failure and customer complaints - Google Patents
Method for predicting line fault power failure and customer complaints Download PDFInfo
- Publication number
- CN112256693A CN112256693A CN202010945310.6A CN202010945310A CN112256693A CN 112256693 A CN112256693 A CN 112256693A CN 202010945310 A CN202010945310 A CN 202010945310A CN 112256693 A CN112256693 A CN 112256693A
- Authority
- CN
- China
- Prior art keywords
- data
- model
- power failure
- training
- fault
- 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
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000012549 training Methods 0.000 claims abstract description 34
- 238000012545 processing Methods 0.000 claims abstract description 8
- 238000011144 upstream manufacturing Methods 0.000 claims abstract description 4
- 238000011156 evaluation Methods 0.000 claims description 20
- 238000003066 decision tree Methods 0.000 claims description 15
- 238000004140 cleaning Methods 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000012821 model calculation Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 230000008439 repair process Effects 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 10
- 238000005516 engineering process Methods 0.000 abstract description 6
- 238000007405 data analysis Methods 0.000 abstract description 4
- 238000010276 construction Methods 0.000 abstract description 3
- 230000006872 improvement Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 6
- 238000001556 precipitation Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2282—Tablespace storage structures; Management thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/248—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- 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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Primary Health Care (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Water Supply & Treatment (AREA)
- Artificial Intelligence (AREA)
- Human Resources & Organizations (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Quality & Reliability (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method for predicting line fault power failure and customer complaints, which comprises the following steps: acquiring original data; step two, processing related to fault power failure and customer complaints; step three, training a fault power failure model; step four, predicting a fault power failure model; step five, training a complaint model of the user; step six, forecasting a user complaint model; in the first step, the data acquisition module is actively connected with an upstream system to acquire an original data chart, and original data results are stored in a database, wherein the original data are used for subsequent data processing; according to the invention, by adopting a big data analysis technology, analysis and improvement are carried out from the aspects of system function, architecture realization and the like, a construction scheme of the power grid risk automatic early warning system based on the big data analysis technology is provided, and data sharing is effectively realized through interconnection and intercommunication with all relevant information systems of operation, distribution and dispatching, so that the accuracy and timeliness of power grid automatic early warning are favorably improved.
Description
Technical Field
The invention relates to the technical field of automatic early warning system maintenance, in particular to a method for predicting line fault power failure and user complaints.
Background
In recent years, with the rapid development of Chinese economy and technology, the total electricity consumption of society rises year by year, the demand for electric energy is continuously increased, and the construction scale of a power grid is increased for the situation. However, as the scale of the power grid is continuously increased, the operation mechanism becomes complex, and with the development of the modern power electronic industry, the large increase of the large-capacity nonlinear power load and the influence of the long-term overload operation of the power system on the power system are increasingly concerned by people. For a long time, due to serious shortage of Chinese power, a power system is always in a serious overload running state, and various unpredictable hidden dangers exist. In recent years, major power failure accidents in the United states, Europe and Russia have made a knock on a police clock for the research of electric power systems in China. In order to discover potential safety hazards of a power grid in time and improve the operation level of the power grid. The research and development of a power grid safety early warning system become a mainstream trend; however, the existing automatic early warning system of the power grid has the problems of incomplete analysis, unscientific method, limited application range and the like, so that a method for predicting line fault power failure and customer complaints is necessary.
Disclosure of Invention
The invention aims to provide a method for predicting line fault power failure and customer complaints, so as to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: a method for predicting line fault power failure and customer complaints, comprising the steps of: acquiring original data; step two, processing related to fault power failure and customer complaints; step three, training a fault power failure model; step four, predicting a fault power failure model; step five, training a complaint model of the user; step six, forecasting a user complaint model;
in the first step, the data acquisition module is actively connected with an upstream system to acquire an original data chart, and original data results are stored in a database, wherein the original data are used for subsequent data processing;
in the second step, the acquired antenna table, the power failure related information table and the distribution transformer related table are respectively processed, a plurality of null values and abnormal data exist in the data in the process, a set of cleaning rules is established for ensuring the prediction accuracy, and the cleaning rules take the fault power failure information table as an example: counting the missing condition and the percentage of each feature in the table, if the missing percentage is 60-100% and comprises 60% and 100%, because the provided useful information is little, directly deleting the feature in the condition; if the missing proportion is 0-60%, including 0, not including 60%, filling missing values in a front-back mean value or middle value mode for continuous features according to actual data distribution conditions, filling missing values in a mode of mode for class features, and performing other information table cleaning rules in the same way, wherein in addition, source data are distributed in different tables, and data are required to be integrated and feature-constructed to generate a prediction training table;
in the third step, the data of the distribution transformer fault training table in the second step are used for model training in three algorithms of XGBOST, decision tree and GBDT, and the three distribution transformer fault models are locally stored after being trained;
in the fourth step, starting three models of XGBOST, decision tree and GBDT which are locally stored in the third step, using a fault power failure to-be-predicted table to predict the models, writing a data chart obtained by model calculation into an evaluation table appointed in a database, writing a real value and a model predicted value into a prediction result table in the database, and performing interface display of the evaluation table and the result table through a BI tool;
in the fifth step, on the day of failure and power failure of the first prediction distribution transformer, corresponding data of the user complaint prediction training table obtained in the second step of correlation screening are used as training data of the user complaint, an XGBOST model, a decision tree model and a GBDT model are adopted for training, and the three user complaint models are locally stored after being trained;
in the sixth step, the XGBOST model, the decision tree model and the GBDT model which are locally stored in the fifth step are started, the fault power failure prediction table is used for model prediction, the data chart obtained by model calculation is written into the specified evaluation table in the database, the real value and the model prediction value are written into the prediction result table in the database, and interface display of the evaluation table and the result table is carried out through a BI tool.
According to the technical scheme, in the first step, the original data chart comprises a distribution transformer detail chart, a power failure information equipment chart, an emergency repair order, a public transformer load event detail chart, a marketing user information chart, a marketing distribution transformer chart, a line load chart and historical meteorological data.
According to the technical scheme, in the second step, the prediction training table comprises a distribution transformer fault training table, a fault power failure to-be-predicted table, a user complaint prediction training table and a to-be-predicted table.
According to the technical scheme, in the fourth step, the data chart comprises accuracy, precision, recall, F1 evaluation indexes, a confusion matrix and the like.
According to the technical scheme, in the sixth step, the data chart comprises accuracy, precision, recall, F1 evaluation indexes, a confusion matrix and the like.
Compared with the prior art, the invention has the following beneficial effects: according to the method for predicting line fault power failure and user complaints, a big data analysis technology is adopted, analysis and improvement are carried out from the aspects of system functions, architecture realization and the like, and a construction scheme of the power grid risk automatic early warning system based on the big data analysis technology is provided.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flow chart of a method of the present invention;
FIG. 2 is a graph illustrating an analysis of the number of failed outages in an embodiment of the present invention;
FIG. 3 is a diagram of month failure number analysis in an embodiment of the present invention;
FIG. 4 is a graph of the number of line faults in an embodiment of the invention;
FIG. 5 is a distribution diagram of distribution variables and failure times according to an embodiment of the present invention;
FIG. 6 is a fault rate distribution diagram for a line and distribution transformer in an embodiment of the present invention;
FIG. 7 is a graph of importance of features of a decision tree model in an embodiment of the invention;
FIG. 8 is a graph of the significance of features of an Xgboost model in an embodiment of the invention;
FIG. 9 is a frequency statistics chart of complaint types in an embodiment of the invention;
fig. 10 is a diagram for predicting whether or not each user on the line will complain and the probability of complaining on the "day" on which the distribution transformer is predicted to have failed and power failure the next day, based on data such as basic information of the distribution transformer, weather, measurement, and historical failure.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-10, the present invention provides a technical solution: a method for predicting line fault power failure and customer complaints, comprising the steps of: acquiring original data; step two, processing related to fault power failure and customer complaints; step three, training a fault power failure model; step four, predicting a fault power failure model; step five, training a complaint model of the user; step six, forecasting a user complaint model;
in the first step, the data acquisition module is actively connected with an upstream system to acquire an original data chart and store an original data result in a database, the original data chart comprises a distribution transformer detail table, a power failure information equipment table, an emergency repair order, a public transformation load event detail table, a marketing user information table, a marketing distribution transformer table, a line load table and historical meteorological data, and the original data are used for subsequent data processing;
in the second step, the acquired antenna table, the power failure related information table and the distribution transformer related table are respectively processed, a plurality of null values and abnormal data exist in the data in the process, a set of cleaning rules is established for ensuring the prediction accuracy, and the cleaning rules take the fault power failure information table as an example: counting the missing condition and the percentage of each feature in the table, if the missing percentage is 60-100% and comprises 60% and 100%, because the provided useful information is little, directly deleting the feature in the condition; if the missing proportion is 0-60%, including 0, not including 60%, filling missing values in a front-back mean value or middle value mode for continuous features according to actual data distribution conditions, filling missing values in a mode of mode for class features, and similarly for other information table cleaning rules, in addition, source data are distributed in different tables, data are required to be integrated and feature-constructed, and a prediction training table is generated and comprises a distribution transformer fault training table, a fault power failure to-be-predicted table, a user complaint prediction training table and a table to be predicted;
in the third step, the data of the distribution transformer fault training table in the second step are used for model training in three algorithms of XGBOST, decision tree and GBDT, and the three distribution transformer fault models are locally stored after being trained;
in the fourth step, starting three models of XGBOST, decision tree and GBDT which are locally stored in the third step, performing model prediction by using a fault and power failure prediction table, writing a data chart obtained by model calculation into an evaluation table appointed in a database, writing a real value and a model prediction value into a prediction result table in the database, performing interface display of the evaluation table and the result table through a BI tool, wherein the data chart comprises accuracy, precision, recall rate, F1 evaluation indexes, a confusion matrix and the like;
in the fifth step, on the day of failure and power failure of the first prediction distribution transformer, corresponding data of the user complaint prediction training table obtained in the second step of correlation screening are used as training data of the user complaint, an XGBOST model, a decision tree model and a GBDT model are adopted for training, and the three user complaint models are locally stored after being trained;
in the sixth step, the XGBOST model, the decision tree model and the GBDT model which are locally stored in the fifth step are started, the fault power failure prediction table is used for model prediction, the data diagram obtained by model calculation is written into the specified evaluation table in the database, the data diagram comprises accuracy, precision, recall rate, F1 evaluation indexes, confusion matrix and the like, the real value and the model prediction value are written into the prediction result table in the database, and interface display of the evaluation table and the result table is performed through a BI tool.
The method is used for testing the original data required to be used in 2018 and 2019, the used original data and the used test data are uniformly sorted, and the obtained failure times, the line number and the ratio table are as follows:
the obtained failure times, distribution variables and the proportion table are as follows:
the resulting model widths are tabulated below:
the obtained fault power failure analysis table is as follows:
the weather analysis table obtained one day before the predicted day is as follows:
| number of samples | Minimum precipitation | Maximum precipitation | Minimum wind speed | Maximum wind speed | Minimum humidity | Maximum humidity | |
| Is normal | 9063037 | 0.00 | 5.97 | 0.00 | 82.80 | 16.76 | 96.43 |
| Fault power failure | 38558 | 0.00 | 8.60 | 0.00 | 86.14 | 17.58 | 96.76 |
The weather analysis table on the predicted day is as follows:
| number of samples | Minimum precipitation | Maximum precipitation | Minimum wind speed | Maximum wind speed | Minimum humidity | Maximum humidity | |
| Is normal | 9063037 | 0 | 5.96 | 0.01 | 82.73 | 16.89 | 96.38 |
| Fault power failure | 38558 | 0 | 11.71 | 0.01 | 96.25 | 16.64 | 96.93 |
The resulting decision tree model evaluation table is as follows:
the obtained complaint times, the user number and the proportion table are as follows:
| number of complaints | Number of users | In proportion to complaint users |
| 1 | 152959 | 95.22％ |
| 2 | 6857 | 4.27％ |
| 3 | 669 | 0.42％ |
| 4 | 98 | 0.06％ |
| 5 | 37 | 0.02％ |
| 6 | 6 | 0.00％ |
| 7 | 4 | 0.00％ |
| 8 | 4 | 0.00％ |
| Total up to | 160634 |
The analysis table of the complaints and the historical complaints is as follows:
the analysis table for the association of the complaints and the faults is as follows:
the resulting decision tree model evaluation table is as follows:
based on the above, the method has the advantages that the original data are collected and recorded, and are analyzed, so that interconnection and intercommunication of all related information systems of operation, distribution and dispatching are facilitated, data sharing is effectively realized, a real and comprehensive basis is provided for automatic early warning of a power grid, and the accuracy and timeliness of the automatic early warning of the power grid are improved.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or 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.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (5)
1. A method for predicting line fault power failure and customer complaints, comprising the steps of: acquiring original data; step two, processing related to fault power failure and customer complaints; step three, training a fault power failure model; step four, predicting a fault power failure model; step five, training a complaint model of the user; step six, forecasting a user complaint model; the method is characterized in that:
in the first step, the data acquisition module is actively connected with an upstream system to acquire an original data chart, and original data results are stored in a database, wherein the original data are used for subsequent data processing;
in the second step, the acquired antenna table, the power failure related information table and the distribution transformer related table are respectively processed, a plurality of null values and abnormal data exist in the data in the process, a set of cleaning rules is established for ensuring the prediction accuracy, and the cleaning rules take the fault power failure information table as an example: counting the missing condition and the percentage of each feature in the table, if the missing percentage is 60-100% and comprises 60% and 100%, because the provided useful information is little, directly deleting the feature in the condition; if the missing proportion is 0-60%, including 0, not including 60%, filling missing values in a front-back mean value or middle value mode for continuous features according to actual data distribution conditions, filling missing values in a mode of mode for class features, and performing other information table cleaning rules in the same way, wherein in addition, source data are distributed in different tables, and data are required to be integrated and feature-constructed to generate a prediction training table;
in the third step, the data of the distribution transformer fault training table in the second step are used for model training in three algorithms of XGBOST, decision tree and GBDT, and the three distribution transformer fault models are locally stored after being trained;
in the fourth step, starting three models of XGBOST, decision tree and GBDT which are locally stored in the third step, using a fault power failure to-be-predicted table to predict the models, writing a data chart obtained by model calculation into an evaluation table appointed in a database, writing a real value and a model predicted value into a prediction result table in the database, and performing interface display of the evaluation table and the result table through a BI tool;
in the fifth step, on the day of failure and power failure of the first prediction distribution transformer, corresponding data of the user complaint prediction training table obtained in the second step of correlation screening are used as training data of the user complaint, an XGBOST model, a decision tree model and a GBDT model are adopted for training, and the three user complaint models are locally stored after being trained;
in the sixth step, the XGBOST model, the decision tree model and the GBDT model which are locally stored in the fifth step are started, the fault power failure prediction table is used for model prediction, the data chart obtained by model calculation is written into the specified evaluation table in the database, the real value and the model prediction value are written into the prediction result table in the database, and interface display of the evaluation table and the result table is carried out through a BI tool.
2. The method of predicting line fault blackouts and customer complaints of claim 1, wherein: in the first step, the original data chart comprises a distribution transformer detail chart, a power failure information equipment chart, an emergency repair order, a public transformer load event detail chart, a marketing user information chart, a marketing distribution transformer chart, a line load chart and historical meteorological data.
3. The method of predicting line fault blackouts and customer complaints of claim 1, wherein: in the second step, the prediction training table comprises a distribution transformer fault training table, a fault power failure to-be-predicted table, a user complaint prediction training table and a to-be-predicted table.
4. The method of predicting line fault blackouts and customer complaints of claim 1, wherein: in the fourth step, the data chart comprises accuracy, precision, recall, F1 evaluation indexes, a confusion matrix and the like.
5. The method of predicting line fault blackouts and customer complaints of claim 1, wherein: in the sixth step, the data chart comprises accuracy, precision, recall, F1 evaluation indexes, a confusion matrix and the like.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010945310.6A CN112256693A (en) | 2020-09-10 | 2020-09-10 | Method for predicting line fault power failure and customer complaints |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010945310.6A CN112256693A (en) | 2020-09-10 | 2020-09-10 | Method for predicting line fault power failure and customer complaints |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112256693A true CN112256693A (en) | 2021-01-22 |
Family
ID=74233064
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010945310.6A Pending CN112256693A (en) | 2020-09-10 | 2020-09-10 | Method for predicting line fault power failure and customer complaints |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112256693A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112862172A (en) * | 2021-01-29 | 2021-05-28 | 国网河南省电力公司漯河供电公司 | State network 95598 power failure complaint prediction method and device, computer equipment and storage medium |
-
2020
- 2020-09-10 CN CN202010945310.6A patent/CN112256693A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112862172A (en) * | 2021-01-29 | 2021-05-28 | 国网河南省电力公司漯河供电公司 | State network 95598 power failure complaint prediction method and device, computer equipment and storage medium |
| CN112862172B (en) * | 2021-01-29 | 2024-05-28 | 国网河南省电力公司漯河供电公司 | National network 95598 power outage complaint prediction method, device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110097297B (en) | Multi-dimensional electricity stealing situation intelligent sensing method, system, equipment and medium | |
| CN103617568B (en) | Setting method for abnormal data determination threshold in steady-state power quality early-warning mechanism | |
| CN111008193B (en) | Data cleaning and quality evaluation method and system | |
| CN110222991B (en) | Metering device fault diagnosis method based on RF-GBDT | |
| CN109670676A (en) | Distributing net platform region method for prewarning risk and system based on Support Vector data description | |
| CN110927654B (en) | Batch running state evaluation method for intelligent electric energy meters | |
| CN104504508A (en) | Area closed-loop data analysis method on basis of analytical hierarchy process and wavelet regression | |
| CN110503570A (en) | A kind of exception electricity consumption data detection method, system, equipment, storage medium | |
| CN109687426B (en) | Fault rate parameter modeling method, device, equipment and storage medium | |
| CN104933477A (en) | Method for optimizing maintenance strategy by using risk assessment of power transmission and transformation equipment | |
| CN113435759B (en) | Primary equipment risk intelligent assessment method based on deep learning | |
| CN115905319B (en) | Automatic identification method and system for abnormal electricity fees of massive users | |
| CN114519514A (en) | Low-voltage transformer area reasonable line loss value measuring and calculating method, system and computer equipment | |
| CN114118588A (en) | Peak-facing summer power failure prediction method based on game feature extraction under clustering undersampling | |
| Liu | FDI and employment by industry: A co-integration study | |
| CN112308425A (en) | Method for constructing distribution transformer health evaluation index system | |
| CN111552686A (en) | Power data quality assessment method and device | |
| CN111091223A (en) | Distribution transformer short-term load prediction method based on Internet of things intelligent sensing technology | |
| CN111178690A (en) | Electricity stealing risk assessment method for electricity consumers based on wind control scoring card model | |
| CN118194202A (en) | Transverse federal-based electricity stealing identification algorithm and prototype system thereof | |
| CN112256693A (en) | Method for predicting line fault power failure and customer complaints | |
| CN113642933A (en) | Power distribution station low-voltage diagnosis method and device | |
| CN114139408A (en) | Power transformer health state assessment method | |
| CN114168662A (en) | Power distribution network problem combing and analyzing method and system based on multiple data sources | |
| CN114662589A (en) | Ammeter fault research and judgment method, device, equipment and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |