CN112257937A - Power distribution network fault prediction system and method based on big data technology - Google Patents
Power distribution network fault prediction system and method based on big data technology Download PDFInfo
- Publication number
- CN112257937A CN112257937A CN202011169983.3A CN202011169983A CN112257937A CN 112257937 A CN112257937 A CN 112257937A CN 202011169983 A CN202011169983 A CN 202011169983A CN 112257937 A CN112257937 A CN 112257937A
- Authority
- CN
- China
- Prior art keywords
- data
- fault
- module
- distribution network
- analysis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Abstract
A power distribution network fault prediction system and method based on big data technology, realize the automatic access of the massive data that the operation management of the power distribution network produces through the data analysis domain of the big data platform, realize the fusion, unity of each professional data of scheduling, operation inspection, marketing, support the basis of the fault diagnosis of the power distribution network for the big data technology, can realize the time distribution and space distribution prediction to the electric load as analyzing the sample with the big electric power data that the volume is bigger, the type is more, offer the basis for planning design, electric network operation scheduling, promote the accuracy and validity of the decision; the power failure loss of the distribution network can be calculated more accurately through the fault diagnosis system, the potential increase is achieved through a big data technology, the real-time running information and the equipment maintenance information of the distribution network are comprehensively analyzed, and the power failure influence is reduced.
Description
Technical Field
The invention relates to the technical field of power distribution network fault diagnosis, in particular to a power distribution network fault prediction system and method based on a big data technology.
Background
With the continuous improvement of social science and technology, the development of big data technology is mature day by day and is widely applied to various industry fields, and on the other hand, with the massive popularization and use of new energy, the number of power grid users is increased day by day, and the power grid structure is more complicated. In order to scientifically plan the power grid layout, improve the reliability, economy and foresight of a power distribution network and enhance the planning and management level of the power distribution network, more and more power enterprises introduce big data to analyze the load characteristics of the power grid, various data of power grid operation management are accurately calculated by constructing a load model, and the operation mode of the power distribution network is reasonably and scientifically arranged.
Disclosure of Invention
The invention aims to solve the problems in the prior art, and provides a power distribution network fault prediction system and method based on a big data technology, so that the technical expansion of the big data technology in the field of smart power grids is realized, the service application scenes of user power consumption behavior analysis, power saving, power consumption prediction, grid structure optimization, off-peak scheduling and the like are met, the intelligent level and the comprehensive benefit of the power grids are improved, and the requirements of deep construction of the smart power grids on fusion and mining of multi-source data are met.
The invention adopts the technical scheme for solving the technical problems that: a power distribution network fault prediction system based on big data technology comprises a data source platform, a big data platform data analysis domain and a service application platform, wherein the data source platform power grid enterprise internal data and external environment information data are sent to the big data platform data analysis domain, and the big data platform data analysis domain accesses, stores, calculates and analyzes the power grid enterprise internal data and external environment information data and uploads the data to the service application platform for application;
the data source platform comprises a data processing domain module and an external data module; the data processing domain module is used for calling production management, power grid operation, service marketing and power utilization acquisition data in the power grid, and the external data module is used for calling external geographic information, meteorological information and social and economic data;
the big data platform data analysis domain comprises a data access layer, a data storage layer, a data calculation layer and a unified analysis service layer;
further perfecting, the data access layer comprises a real-time data acquisition access module, an external data access module and a data extraction cleaning module;
the real-time data acquisition access module is used for accessing data of the data processing domain module and acquiring power grid operation data in real time; a high-speed carrier chip is arranged in the real-time data acquisition access module, and the topological data of the power distribution network is acquired in real time through a high-speed carrier;
the external data acquisition access module is used for accessing the external data module and acquiring external data;
the data cleaning module is used for cleaning and converting the accessed internal data and the accessed external data, and respectively writing the data into a data warehouse and a storage area in the data storage layer;
further perfecting, the data storage layer comprises an enterprise data warehouse, a real-time data storage area and a hot data storage area; the enterprise data warehouse comprises an OOS buffer area, an OOS unified view area, a data warehouse and a data mart; the real-time data storage area is used for storing the power grid operation data of the real-time data acquisition access module;
the hot spot data storage area is used for storing hot spot data of the external data acquisition access module;
further perfecting, the data computation layer comprises an offline computation engine module and a real-time computation module, data intensive computation is carried out on the power grid operation data and the hot data by adopting a distributed parallel computation technology, and normal state monitoring subject result data are output to a data mart for integration processing;
the unified analysis service layer comprises a data mining module and an analysis display module; the data mining module is used for mining the result data of the normal state monitoring subject in the data mart and then uploading the monitoring data to the service application platform; the analysis and presentation module performs theme scene application configuration work of a business application platform on the monitoring data by utilizing a Tableau analysis component, and automatically generates and presents a monitoring data report;
the service application platform comprises a monitoring and early warning module, a diagnosis and treatment module, a quality evaluation module, an image research module, a power failure optimization module and a load prediction module.
A power distribution network fault prediction method based on big data technology comprises the following steps:
step 01, extracting power grid internal data and external data in a data source platform into a big data platform data analysis domain for processing to form big data platform data, and performing data preprocessing on the big data platform data, wherein the data preprocessing comprises power distribution network fault influence factor analysis, data mining extraction and sample screening;
step 011, analyzing the power distribution network fault influence factors by adopting a clustering analysis method and a fault classification method to realize power fault positioning; various abnormal states affecting the power quality are diagnosed accurately in time, abnormal points are found out and prevented or eliminated, and therefore expansion of faults is avoided; the automation level of real-time fault detection of the power distribution network power transmission and distribution line is effectively improved; and the method provides guarantee for removing line faults.
Step 012, data mining and extraction, namely generating curve clusters with similar changes for data in clustering analysis by a statistical description method; carrying out dimensionless processing on the curve cluster data, and extracting outliers of the curve cluster as data samples;
step 013, performing sample screening on the data samples based on a particle swarm optimization algorithm, and selecting extreme value samples;
step 02, selecting characteristic variables of the sample data; the feature variable selection comprises primary feature vector screening and optimal feature vector screening;
021, primarily screening the feature vectors, and screening all related variables in the extreme value sample to form a primary feature vector set;
022, screening the optimal feature vectors, and screening the primary feature vector set again through a feature selection algorithm to form an optimal feature variable set;
step 03, performing fault prediction diagnosis on the power distribution network; the fault prediction diagnosis comprises the steps of fault grade division, SVM fault prediction model establishment and prediction result output;
step 031, according to the analysis result of the distribution network fault influence factor in step 011, the distribution network is subjected to fault grade division, and a corresponding prevention scheme is generated for the reference of operators;
step 032, inputting the optimal feature vector of the optimal feature variable set in step 022 into a support vector machine for training; optimizing parameters of the support vector machine through a particle swarm optimization algorithm, and establishing an SVM fault prediction model; weak links in the power distribution network frame structure are comprehensively analyzed, a refined power distribution network frame and a reactive power source adjusting scheme are formulated, the electric energy quality is improved, and the requirement of high electric energy quality of the power distribution network in operation is met.
And 033, outputting a prediction result report of the SVM fault prediction model, timely and accurately diagnosing various abnormal states affecting the power quality, finding abnormal points, and monitoring and early warning through a service application platform.
For further improvement, the fault classification method in the step 011 adopts a Bayesian classification method and a neural network method to realize the identification and diagnosis of the faults of the distribution transformer of the distribution network; the Bayesian classification method classifies transformer faults into internal or external grounding and short-circuit fault types, and the neural network method identifies fault types including high-temperature, low-energy and high-energy states.
Further perfecting, the cluster analysis method in step 011 adopts a partition clustering method, a hierarchical clustering method and a grid clustering method to extract user load curves of different areas and different types in the operation management data and the load monitoring data of the power distribution network, so as to realize fault transient characteristic extraction, and carries out cluster analysis on an original data matrix, so that measuring points are divided into fault classes and non-fault classes, and fault positions are positioned through the topological structure of the actual power grid.
Further perfecting, the statistical description method comprises discrete variable statistics and continuous variable statistics.
Further perfecting, the data analysis domain processing in step 01 comprises the following steps: 1) data access, namely accessing various data from a data source platform for use in the processes of calculation and analysis, wherein the accessed data types comprise: structuring data and collecting measurement data; 2) data storage, namely storing real-time acquired data and hot spot data by adopting a distributed structured database; 3) data calculation, namely performing distributed calculation on the real-time acquired data and the hot spot data through a real-time calculation engine module and a data offline calculation engine module to generate normal state monitoring subject result data; 4) and displaying the application, integrating the processed normal state monitoring subject result data, performing subject scene application configuration work by using a Tableau analysis component, and automatically generating a tool output monitoring report through the monitoring report.
Further elaborated, the feature selection algorithm in step 022 employs a Relief feature selection algorithm.
Further perfecting, the fault grade division in the step 031 is divided according to the severity of the fault, including equipment importance grade classification, importance evaluation, fault grade evaluation and equipment modification record.
The invention has the beneficial effects that: the power distribution network fault diagnosis system disclosed by the invention realizes automatic access of mass data generated by power distribution network operation management through the data analysis domain of the big data platform, realizes fusion and unification of professional data of scheduling, operation and inspection and marketing, provides a foundation for big data technology to support power distribution network fault diagnosis, and the real-time data acquisition access module of the data analysis domain acquires internal data of a power distribution network by applying new technologies such as high-speed carrier waves and the like, and extracts external environment information through the external data module, so that the authenticity, reliability and timeliness of the big data of the power distribution network are greatly improved; storing real-time acquired data and hot spot data in a data storage layer by adopting a distributed structured database; in a data calculation layer, distributed calculation is carried out on real-time collected data and hot spot data through a real-time calculation engine module and a data offline calculation engine module, time distribution and space distribution prediction of power loads can be realized by taking power big data with larger volume and more types as analysis samples, a basis is provided for planning design and power grid operation scheduling, and the accuracy and the effectiveness of decision making are improved; the power failure loss of the distribution network can be calculated more accurately through the fault diagnosis system, the potential increase is achieved through a big data technology, the real-time running information and the equipment maintenance information of the distribution network are comprehensively analyzed, and the power failure influence is reduced.
Drawings
FIG. 1 is a schematic diagram of a prediction system of a big data platform data analysis domain according to the present invention;
FIG. 2 is a schematic diagram of a prediction method according to the present invention;
Detailed Description
The invention will be further described with reference to the accompanying drawings in which:
with reference to the accompanying drawings: the power distribution network fault prediction system based on the big data technology comprises a data source platform, a big data platform data analysis domain and a business application platform, wherein the data source platform power grid enterprise internal data and external environment information data are sent to the big data platform data analysis domain, and the big data platform data analysis domain accesses, stores, calculates and analyzes the power grid enterprise internal data and external environment information data and uploads the data to the business application platform for application;
the data source platform comprises a data processing domain module and an external data module; the data processing domain module is used for calling production management, power grid operation, service marketing and power utilization acquisition data in the power grid, and the external data module is used for calling external geographic information, meteorological information and social and economic data;
the big data platform data analysis domain comprises a data access layer, a data storage layer, a data calculation layer and a unified analysis service layer;
the data access layer comprises a real-time data acquisition access module, an external data access module and a data extraction cleaning module;
the real-time data acquisition access module is used for accessing data of the data processing domain module and acquiring power grid operation data in real time;
the external data acquisition access module is used for accessing the external data module and acquiring external data;
the data cleaning module is used for cleaning and converting the accessed internal data and the accessed external data, and respectively writing the data into a data warehouse and a storage area in the data storage layer;
the data storage layer comprises an enterprise data warehouse, a real-time data storage area and a hot spot data storage area; the enterprise data warehouse comprises an OOS buffer area, an OOS unified view area, a data warehouse and a data mart; the real-time data storage area is used for storing the power grid operation data of the real-time data acquisition access module;
the hot spot data storage area is used for storing hot spot data of the external data acquisition access module;
the data computation layer comprises an offline computation engine module and a real-time computation module, and is used for performing data-intensive computation on the power grid operation data and the hot data by adopting a distributed parallel computation technology and outputting the data of the normal monitoring subject result to a data mart for integration processing;
the unified analysis service layer comprises a data mining module and an analysis display module; the data mining module is used for mining the result data of the normal state monitoring subject in the data mart and then uploading the monitoring data to the service application platform; the analysis and presentation module performs theme scene application configuration work of a business application platform on the monitoring data by utilizing a Tableau analysis component, and automatically generates and presents a monitoring data report;
the service application platform comprises a monitoring and early warning module, a diagnosis and treatment module, a quality evaluation module, an image research module, a power failure optimization module and a load prediction module.
A power distribution network fault prediction method based on big data technology comprises the following steps:
step 01, extracting power grid internal data and external data in a data source platform into a big data platform data analysis domain for processing to form big data platform data, and performing data preprocessing on the big data platform data, wherein the data preprocessing comprises power distribution network fault influence factor analysis, data mining extraction and sample screening; the processing of the big data platform data analysis domain comprises the following steps: 1) data access, namely accessing various data from a data source platform for use in the processes of calculation and analysis, wherein the accessed data types comprise: structuring data and collecting measurement data; 2) data storage, namely storing real-time acquired data and hot spot data by adopting a distributed structured database; 3) data calculation, namely performing distributed calculation on the real-time acquired data and the hot spot data through a real-time calculation engine module and a data offline calculation engine module to generate normal state monitoring subject result data; 4) and displaying the application, integrating the processed normal state monitoring subject result data, performing subject scene application configuration work by using a Tableau analysis component, and automatically generating a tool output monitoring report through the monitoring report.
Step 011, analyzing the power distribution network fault influence factors by adopting a clustering analysis method and a fault classification method to realize power fault positioning; the fault classification method adopts a Bayesian classification method and a neural network method to realize the identification and diagnosis of the faults of the distribution transformer of the power distribution network; the Bayesian classification method classifies transformer faults into internal or external grounding and short-circuit fault types, and the neural network method identifies fault types including high-temperature, low-energy and high-energy states. The clustering analysis method adopts a partition clustering method, a hierarchical clustering method and a grid clustering method to extract user load curves of different areas and different types in the operation management data and the load monitoring data of the power distribution network, realizes fault transient characteristic extraction, performs clustering analysis on an original data matrix, divides measuring points into fault types and non-fault types, and positions fault positions through the topological structure of an actual power grid.
Step 012, data mining and extraction, namely generating curve clusters with similar changes for data in clustering analysis by a statistical description method; carrying out dimensionless processing on the curve cluster data, and extracting outliers of the curve cluster as data samples; the statistical description method comprises discrete variable statistics and continuous variable statistics.
Step 013, performing sample screening on the data samples based on a particle swarm optimization algorithm, and selecting extreme value samples;
step 02, selecting characteristic variables of the sample data; the feature variable selection comprises primary feature vector screening and optimal feature vector screening;
021, primarily screening the feature vectors, and screening all related variables in the extreme value sample to form a primary feature vector set;
022, screening the optimal feature vectors, and screening the primary feature vector set again through a feature selection algorithm to form an optimal feature variable set; the feature selection algorithm adopts a Relief feature selection algorithm.
Step 03, performing fault prediction diagnosis on the power distribution network; the fault prediction diagnosis comprises the steps of fault grade division, SVM fault prediction model establishment and prediction result output;
step 031, according to the analysis result of the distribution network fault influence factor in step 011, the distribution network is subjected to fault grade division, and a corresponding prevention scheme is generated for the reference of operators; and the fault grade division is carried out according to the severity of the fault, and comprises equipment importance grade classification, importance evaluation, fault grade evaluation and equipment modification record.
Step 032, inputting the optimal feature vector of the optimal feature variable set in step 022 into a support vector machine for training; optimizing parameters of the support vector machine through a particle swarm optimization algorithm, and establishing an SVM fault prediction model;
and 033, outputting a prediction result report of the SVM fault prediction model, timely and accurately diagnosing various abnormal states affecting the power quality, finding abnormal points, and monitoring and early warning through a service application platform.
While the invention has been shown and described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the scope of the appended claims.
Claims (10)
1. A power distribution network fault prediction system based on big data technology is characterized by comprising a data source platform, a big data platform data analysis domain and a service application platform, wherein the data source platform comprises a data processing domain module and an external data module; the data processing domain module is used for calling production management, power grid operation, service marketing and power utilization acquisition data in the power grid, and the external data module is used for calling external geographic information, meteorological information and social and economic data; the data source platform power grid enterprise internal data and external environment information data are sent to a big data platform data analysis domain, and the big data platform data analysis domain comprises a data access layer, a data storage layer, a data calculation layer and a unified analysis service layer; the big data platform data analysis domain accesses, stores, calculates and analyzes the internal data and the external environment information data of the power grid enterprise and uploads the data to the service application platform for application; the service application platform comprises a monitoring and early warning module, a diagnosis and treatment module, a quality evaluation module, an image research module, a power failure optimization module and a load prediction module.
2. The system for predicting the fault of the power distribution network based on the big data technology as claimed in claim 1, wherein: the data access layer comprises a real-time data acquisition access module, an external data access module and a data extraction cleaning module; the real-time data acquisition access module is used for accessing data of the data processing domain module and acquiring power grid operation data in real time; the external data acquisition access module is used for accessing the external data module and acquiring external data; and the data cleaning module is used for cleaning and converting the accessed internal data and the accessed external data and respectively writing the data into a data warehouse and a storage area in the data storage layer.
3. The system for predicting the fault of the power distribution network based on the big data technology as claimed in claim 2, wherein: the data storage layer comprises an enterprise data warehouse, a real-time data storage area and a hot spot data storage area; the enterprise data warehouse comprises an OOS buffer area, an OOS unified view area, a data warehouse and a data mart; the real-time data storage area is used for storing the power grid operation data of the real-time data acquisition access module; the hot spot data storage area is used for storing hot spot data of the external data acquisition access module.
4. The system for power distribution network fault prediction based on big data technology as claimed in claim 3, wherein: the data computation layer comprises an offline computation engine module and a real-time computation module, data intensive computation is carried out on the power grid operation data and the hot data by adopting a distributed parallel computation technology, and the data of the normal state monitoring subject result is output to a data mart for integration processing. The unified analysis service layer comprises a data mining module and an analysis display module; the data mining module is used for mining the result data of the normal state monitoring subject in the data mart and then uploading the monitoring data to the service application platform; the analysis display module performs theme scene application configuration work of a business application platform on the monitoring data by utilizing a Tableau analysis component, and automatically generates and displays a monitoring data report.
5. A power distribution network fault prediction method based on big data technology is characterized by comprising the following steps:
step 01, extracting power grid internal data and external data in a data source platform into a big data platform data analysis domain for processing to form big data platform data, and performing data preprocessing on the big data platform data, wherein the data preprocessing comprises power distribution network fault influence factor analysis, data mining extraction and sample screening;
step 011, analyzing the power distribution network fault influence factors by adopting a clustering analysis method and a fault classification method to realize power fault positioning;
step 012, data mining and extraction, namely generating curve clusters with similar changes for data in clustering analysis by a statistical description method; carrying out dimensionless processing on the curve cluster data, and extracting outliers of the curve cluster as data samples;
step 013, performing sample screening on the data samples based on a particle swarm optimization algorithm, and selecting extreme value samples;
step 02, selecting characteristic variables of the sample data; the feature variable selection comprises primary feature vector screening and optimal feature vector screening;
021, primarily screening the feature vectors, and screening all related variables in the extreme value sample to form a primary feature vector set;
022, screening the optimal feature vectors, and screening the primary feature vector set again through a feature selection algorithm to form an optimal feature variable set;
step 03, performing fault prediction diagnosis on the power distribution network; the fault prediction diagnosis comprises the steps of fault grade division, SVM fault prediction model establishment and prediction result output;
step 031, according to the analysis result of the distribution network fault influence factor in step 011, the distribution network is subjected to fault grade division, and a corresponding prevention scheme is generated for the reference of operators;
step 032, inputting the optimal feature vector of the optimal feature variable set in step 022 into a support vector machine for training; optimizing parameters of the support vector machine through a particle swarm optimization algorithm, and establishing an SVM fault prediction model;
and 033, outputting a prediction result report of the SVM fault prediction model, timely and accurately diagnosing various abnormal states affecting the power quality, finding abnormal points, and monitoring and early warning through a service application platform.
6. The power distribution network fault prediction method based on the big data technology as claimed in claim 5, wherein: the fault classification method in the step 011 adopts a Bayesian classification method and a neural network method to realize the identification and diagnosis of the faults of the distribution transformer of the distribution network; the Bayes classification method classifies the transformer faults into internal or external grounding and short-circuit fault types, and the neural network method identifies fault types including high-temperature, low-energy and high-energy states; the clustering analysis method in the step 011 adopts a partition clustering method, a hierarchical clustering method and a grid clustering method to extract user load curves of different areas and different types in the operation management data and the load monitoring data of the power distribution network, realizes fault transient characteristic extraction, carries out clustering analysis on an original data matrix, thereby dividing measuring points into a fault class and a non-fault class, and positioning fault positions through the topological structure of an actual power grid.
7. The power distribution network fault prediction method based on big data technology as claimed in claim 6, wherein: the statistical description method comprises discrete variable statistics and continuous variable statistics.
8. The method for predicting the fault of the power distribution network based on the big data technology as claimed in claim 7, wherein the method comprises the following steps: the data analysis domain processing in step 01 comprises the following steps: 1) data access, namely accessing various data from a data source platform for use in the processes of calculation and analysis, wherein the accessed data types comprise: structuring data and collecting measurement data; 2) data storage, namely storing real-time acquired data and hot spot data by adopting a distributed structured database; 3) data calculation, namely performing distributed calculation on the real-time acquired data and the hot spot data through a real-time calculation engine module and a data offline calculation engine module to generate normal state monitoring subject result data; 4) and displaying the application, integrating the processed normal state monitoring subject result data, performing subject scene application configuration work by using a Tableau analysis component, and automatically generating a tool output monitoring report through the monitoring report.
9. The method for predicting the fault of the power distribution network based on the big data technology as claimed in claim 8, wherein: the feature selection algorithm in step 022 employs a Relief feature selection algorithm.
10. The method for predicting the fault of the power distribution network based on the big data technology as claimed in claim 9, wherein: the fault grade classification in step 031 is performed according to the severity of the fault, and includes equipment importance grade classification, importance evaluation, fault grade evaluation, and equipment modification record.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011169983.3A CN112257937B (en) | 2020-10-28 | 2020-10-28 | Power distribution network fault prediction system and method based on big data technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011169983.3A CN112257937B (en) | 2020-10-28 | 2020-10-28 | Power distribution network fault prediction system and method based on big data technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112257937A true CN112257937A (en) | 2021-01-22 |
| CN112257937B CN112257937B (en) | 2023-06-16 |
Family
ID=74262580
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011169983.3A Active CN112257937B (en) | 2020-10-28 | 2020-10-28 | Power distribution network fault prediction system and method based on big data technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112257937B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113537590A (en) * | 2021-07-14 | 2021-10-22 | 深圳供电局有限公司 | Data anomaly prediction method and system |
| CN117347791A (en) * | 2023-11-01 | 2024-01-05 | 国网河南省电力公司濮阳供电公司 | Power grid fault online identification system and method based on big data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2752674A1 (en) * | 2013-01-03 | 2014-07-09 | ABB Technology AG | A detection method of a ground fault in an electric power distribution network |
| CN105160593A (en) * | 2015-08-18 | 2015-12-16 | 国家电网公司 | Power transmission and transformation equipment multidimensional heterogeneous data fusion method and system facing big data |
| CN106651188A (en) * | 2016-12-27 | 2017-05-10 | 贵州电网有限责任公司贵阳供电局 | Electric transmission and transformation device multi-source state assessment data processing method and application thereof |
| CN108564254A (en) * | 2018-03-15 | 2018-09-21 | 国网四川省电力公司绵阳供电公司 | Controller switching equipment status visualization platform based on big data |
| CN111429034A (en) * | 2020-04-21 | 2020-07-17 | 国网信通亿力科技有限责任公司 | Method for predicting power distribution network fault |
-
2020
- 2020-10-28 CN CN202011169983.3A patent/CN112257937B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2752674A1 (en) * | 2013-01-03 | 2014-07-09 | ABB Technology AG | A detection method of a ground fault in an electric power distribution network |
| CN105160593A (en) * | 2015-08-18 | 2015-12-16 | 国家电网公司 | Power transmission and transformation equipment multidimensional heterogeneous data fusion method and system facing big data |
| CN106651188A (en) * | 2016-12-27 | 2017-05-10 | 贵州电网有限责任公司贵阳供电局 | Electric transmission and transformation device multi-source state assessment data processing method and application thereof |
| CN108564254A (en) * | 2018-03-15 | 2018-09-21 | 国网四川省电力公司绵阳供电公司 | Controller switching equipment status visualization platform based on big data |
| CN111429034A (en) * | 2020-04-21 | 2020-07-17 | 国网信通亿力科技有限责任公司 | Method for predicting power distribution network fault |
Non-Patent Citations (2)
| Title |
|---|
| 梁朔等: "基于统一数据模型的广西配用电大数据分析平台的设计与实现", 《广西电力》 * |
| 陶飞达等: "配电网故障智能诊断技术综述", 《机电工程技术》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113537590A (en) * | 2021-07-14 | 2021-10-22 | 深圳供电局有限公司 | Data anomaly prediction method and system |
| CN117347791A (en) * | 2023-11-01 | 2024-01-05 | 国网河南省电力公司濮阳供电公司 | Power grid fault online identification system and method based on big data |
| CN117347791B (en) * | 2023-11-01 | 2024-05-03 | 国网河南省电力公司濮阳供电公司 | Power grid fault online identification system and method based on big data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112257937B (en) | 2023-06-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111259947A (en) | Power system fault early warning method and system based on multi-mode learning | |
| CN108564254A (en) | Controller switching equipment status visualization platform based on big data | |
| CN112348339A (en) | Power distribution network planning method based on big data analysis | |
| CN107977737A (en) | Distribution transformer load Forecasting Methodology based on mxnet frame depth neutral nets | |
| CN113064866B (en) | Power business data integration system | |
| CN110703057A (en) | Power equipment partial discharge diagnosis method based on data enhancement and neural network | |
| CN112257937B (en) | Power distribution network fault prediction system and method based on big data technology | |
| CN113420162B (en) | Equipment operation chain state monitoring method based on knowledge graph | |
| CN106383916A (en) | Data processing method based on predictive maintenance of industrial equipment | |
| CN103617447A (en) | Evaluation system and method for intelligent substation | |
| CN111524026A (en) | Power resource allocation method and device | |
| CN107368932A (en) | A kind of load Analysis forecasting system suitable for power network development specialty | |
| CN115908046A (en) | Visual power distribution system based on airport terminal building BIM | |
| CN115965136A (en) | Carbon emission comprehensive prediction system based on electric power big data | |
| CN106649765A (en) | Smart power grid panoramic data analysis method based on big data technology | |
| CN115186935B (en) | Electromechanical device nonlinear fault prediction method and system | |
| CN116308883A (en) | Regional power grid data overall management system based on big data | |
| Bashkari et al. | Distribution power system outage diagnosis based on root cause analysis | |
| Hu et al. | Big data management and application research in power load forecasting and power transmission and transformation equipment evaluation | |
| Tang et al. | Research on Anomaly Detection of Smart Meter Based on Big Data Mining | |
| Hao et al. | Detection of Outlier of Electric Power Data Based on Improved Fast Density Peak Clustering | |
| Liangzhi et al. | Research on fault prediction and diagnosis of power equipment based on big data | |
| Abusida et al. | A New Approach to Load Shedding Prediction in GECOL Using Deep Learning Neural Network | |
| Cao | Big Data Technology Application in Mechanical Intelligent Fault Diagnosis | |
| Xiaodong et al. | Artificial Intelligence in power multimodal data analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |