CN114253953A - Power distribution network multidimensional data processing method and system based on cluster analysis - Google Patents
Power distribution network multidimensional data processing method and system based on cluster analysis Download PDFInfo
- Publication number
- CN114253953A CN114253953A CN202111369118.8A CN202111369118A CN114253953A CN 114253953 A CN114253953 A CN 114253953A CN 202111369118 A CN202111369118 A CN 202111369118A CN 114253953 A CN114253953 A CN 114253953A
- Authority
- CN
- China
- Prior art keywords
- data
- abnormal
- cluster analysis
- power distribution
- distribution network
- 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
- 238000009826 distribution Methods 0.000 title claims abstract description 31
- 238000007621 cluster analysis Methods 0.000 title claims abstract description 24
- 238000003672 processing method Methods 0.000 title claims abstract description 7
- 230000002159 abnormal effect Effects 0.000 claims abstract description 52
- 238000000034 method Methods 0.000 claims abstract description 22
- 238000001514 detection method Methods 0.000 claims abstract description 19
- 238000003860 storage Methods 0.000 claims abstract description 17
- 230000005856 abnormality Effects 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims description 15
- 238000012937 correction Methods 0.000 claims description 5
- 230000002547 anomalous effect Effects 0.000 claims description 3
- 238000013499 data model Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000013500 data storage Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 10
- 238000004590 computer program Methods 0.000 description 7
- 238000007726 management method Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000004927 fusion Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 241000533950 Leucojum Species 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000007619 statistical method Methods 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
- G06F16/21—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
- G06F16/25—Integrating or interfacing systems involving database management systems
-
- 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
- G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
-
- 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
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Quality & Reliability (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a power distribution network multidimensional data processing method based on cluster analysis, which comprises the following steps: performing standard access and storage on data of multiple data sources; carrying out anomaly detection on the stored data; determining a strong correlation attribute of the abnormal data according to the multi-dimensional characteristics of the data after the abnormality detection; according to the method, the abnormal data are corrected by adopting cluster analysis according to the strong association attribute of the abnormal data, the data quality of the power distribution network can be effectively improved, and the method has higher data storage and query efficiency.
Description
Technical Field
The invention belongs to the technical field of power grid data processing, and particularly relates to a power distribution network multidimensional data processing method based on cluster analysis.
Background
Along with the continuous development of the information-based construction of the intelligent power distribution network, the types and the quantity of data collected by the power distribution network terminals are also continuously increased. The power distribution and utilization information management system in the intelligent power distribution network comprises more than ten systems such as a power distribution automation system, a load control and management system, a marketing service management system, a power utilization information acquisition system and the like, and acquired data have obvious multi-source and heterogeneous big data characteristics. On one hand, the integration of mass multi-source data can provide a data basis for large data application such as power distribution network operation state perception, but the multi-source and heterogeneous characteristics of the data also bring challenges to data fusion and storage; on the other hand, as the intelligent acquisition equipment is wide in distribution and numerous in quantity, the operation environment of part of terminals is severe, the working condition is poor, and data loss or abnormal conditions often occur in the data acquisition and transmission process. The statistical analysis of the abnormal data is often far from the true value, which affects the accuracy of prediction precision and control decision, and the existing research methods for improving data quality are many, such as interpolation method, neural network method, etc., but all correct from the characteristic of a certain dimension of data.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a power distribution network multidimensional data processing method and system based on cluster analysis, which can correct abnormal data.
The technical problem to be solved by the invention is realized by the following technical scheme:
in a first aspect, a power distribution network multidimensional data processing method based on cluster analysis is provided, which includes:
performing standard access and storage on data of multiple data sources;
carrying out anomaly detection on the stored data;
determining a strong correlation attribute of the abnormal data according to the multi-dimensional characteristics of the data after the abnormality detection;
and correcting the abnormal data by adopting cluster analysis according to the strong association attribute of the abnormal data.
With reference to the first aspect, further, the performing canonical access and storage on the multiple data sources specifically includes: accessing multi-data source data by adopting a unified standard interface based on a national power grid public data model; and storing the data of multiple data sources in a database according to different data types and characteristics.
With reference to the first aspect, further, the performing abnormality detection on the stored data specifically includes: and detecting abnormal data by adopting a density-based clustering method DBSCAN.
With reference to the first aspect, further, the determining the strong association attribute of the abnormal data specifically includes:
determining the relevance of anomalous data using the following equation
Wherein X is an abnormal data set, Y is a historical data set of the strong correlation attribute of the abnormal data, and sigma isx、σyX, Y standard deviations, cov (X, Y) is the covariance between X, Y, respectively;
n is the number of data in the abnormal data set, xiIs the ith element in X in the set, yiIs the ith element in the set Y.
With reference to the first aspect, further, the modifying the abnormal data by cluster analysis according to the strong association attribute of the abnormal data specifically includes:
establishing a set C of strong correlation attributes;
determining the weight w of each attribute in the set C by adopting an entropy weight methodj;
For exception data xiSelecting the jth strong correlation attribute from the set C, and performing historical data y on the jth strong correlation attribute in the same time periodjClustering the set;
at yjAnd recording the point with the minimum distance with the strongly-associated attribute data in the class
In a second aspect, a power distribution network multidimensional data processing system based on cluster analysis is provided, which includes:
the preprocessing module is used for performing standard access and storage on the data of multiple data sources;
the abnormal data detection module is used for carrying out abnormal detection on the stored data;
the data correction module is used for determining the strong correlation attribute of the abnormal data according to the multi-dimensional characteristics of the data after the abnormality detection;
and correcting the abnormal data by adopting cluster analysis according to the strong association attribute of the abnormal data.
The invention has the beneficial effects that: the invention provides a data service center for multi-source data fusion and data quality improvement. The data service center performs data fusion aiming at the characteristics of wide data sources and multi-source isomerism of the power distribution network, adopts standardized access, performs database storage according to data characteristics, and performs integrated management on data from different sources; aiming at the conditions of large data collection quantity and low quality of the power distribution network, a clustering analysis method is used for extracting and abnormal detecting historical data and correcting abnormal data by combining multidimensional characteristics of the data, so that the data quality is improved; and finally, providing the correction data for big data analysis application through a data publishing module. Practical application shows that the data service center can effectively improve the data quality of the power distribution network and has higher data storage and query efficiency.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a system architecture diagram of the present invention;
fig. 3 is a schematic diagram of the circuit breaker a-phase current before and after data correction according to the present invention.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some, but not all embodiments of the present invention. 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.
For better understanding of the present invention, the related art in the technical solution of the present invention is explained below.
As shown in fig. 1 to 3, a method for processing multidimensional data of a power distribution network based on cluster analysis includes the following steps:
the method comprises the following steps of firstly, standardizing data access and integrated storage according to different data sources in a distribution network system, ensuring data uniformity, and specifically comprising the following steps:
the power distribution network operation real-time data, historical data and model data are accessed in a standard mode, stored in a sub-base mode and unified by main keys, and the method specifically comprises the following steps:
the synchronization and integration of data are based on a national power grid public data model (SG-CIM) and serve as multi-source data such as a standard docking marketing system, a power utilization information acquisition system, a production management system, a scheduling automation system and the like, and different system data are accessed into the system by adopting a uniform standard interface format. And the database storage is carried out according to different data types and characteristics, the storage efficiency is improved, and the data unification is ensured by establishing a global main key through a snowflake algorithm.
(1) Running real-time data storage
The operation real-time data source comprises relevant data of the production control system, and the data source comprises: a dispatching automation system, an electricity utilization metering system, a GIS system and the like. The data types are mainly metrology data. The data are transmitted through a data center real-time data interface, and the data center is responsible for receiving and transferring the data into a distributed redis deployment real-time library through a stream processing module.
(2) Historical profile data storage
The historical section data is from the electricity charge data of the marketing system, the user file data, the measurement historical value of the production control system and the like. And storing the time sequence library of infiluxdb through batch processing, and supporting offline analysis.
(3) Power distribution network model storage
The power distribution network model comprises a Common Information Model (CIM) generated by a power distribution automation system, network topology information, equipment ledger information and the like. And extracting the data to a data center for analysis in an ETL mode of a data warehouse.
Step two, carrying out abnormity detection on the stored data
1. DBSCAN relates to concept description
The algorithm partitions the data class clusters by analyzing how close the data points in the sample data set are. If the original data set is X ═ X1,x2…xnThen, the following definitions can be given:
(1) ε -neighborhood: refers to the data set X, with the sample point XjAll sets of points having a distance between them not greater than epsilon.
(2) Core point: if in data set X, a certain sample point XjAt least MinPts data points exist in the epsilon-neighborhood, then xjReferred to as core points.
(3) Boundary points are as follows: if the sample point xjIf there are less than MinPts data points within its ε -neighborhood, xjReferred to as boundary points.
(4) Noise points: in the data set X, points that are neither boundary points nor core points are referred to as noise points.
(5) The density is up to: if the sample point xjAt point xiAnd x is in the neighborhood ofiIs a core point, and is called xjFrom xiThe density is up to.
(6) The density can reach: for sample point xiAnd xjIf there is a set of sample sequences p1,p2,…pmSo that x isi=p1,xj=pmAnd the sample sequence pi+1Can be formed from piDensity is through, the sample point x can be calledjCan be composed of xiThe sample is reachable.
(7) Density connection: for sample point xiAnd xjIf there is a sample xkSo that xiAnd xjBy xkIf the sample can be reached, x is indicatediAnd xjAre sample-connected.
2. The method comprises the following implementation steps:
(1) the method comprises the steps of inputting an original data set, a neighborhood radius epsilon and a judgment neighborhood data quantity threshold MinPts. Randomly selecting a point p as an initial object;
(2) calculating whether the number of points in the epsilon neighborhood of the point p is more than or equal to MinPts. Judging whether the point p is a core point, if the point p is the core point, finding out all data points with the reachable density of the point p to form a new cluster, and marking the points as processed;
(3) if the number of points in the epsilon neighborhood of the point p is not less than MinPts, marking the point p as a noise point and selecting another unprocessed data point;
(4) repeating (2) and (3) until all points are processed.
Through clustering calculation, abnormal data, namely noise points, in the data set can be screened out. We can then correct and fill in the data by multi-dimensional correlation of the data.
Step three, determining the strong correlation attribute of the abnormal data according to the multi-dimensional characteristics of the data after the abnormal detection, and specifically comprising the following steps:
determining the relevance of anomalous data using the following equation
Wherein X is an abnormal historical data set, Y is a normal historical data set strongly related to abnormal data, and sigma isx、σyX, Y standard deviations, cov (X, Y) is the covariance between X, Y, respectively;
n is the number of data in the abnormal data set, xiIs the ith element in X in the set, yiIs the ith element in the set Y.
Step four, correcting the abnormal data by adopting cluster analysis according to the strong association attribute of the abnormal data, and specifically comprises the following steps:
establishing a set C of strong correlation attributes;
determining the weight w of each attribute in the set C by adopting an entropy weight methodj;
For exception data xiSelecting the jth strong correlation attribute from the set C, and performing historical data y on the jth strong correlation attribute in the same time periodjClustering the set;
at yjAnd recording the point with the minimum distance with the strongly-associated attribute data in the class
The invention also provides a power distribution network multidimensional data processing system based on cluster analysis, which comprises:
the preprocessing module is used for performing standard access and storage on the data of multiple data sources;
the abnormal data detection module is used for carrying out abnormal detection on the stored data;
the data correction module is used for determining the strong correlation attribute of the abnormal data according to the multi-dimensional characteristics of the data after the abnormality detection;
and correcting the abnormal data by adopting cluster analysis according to the strong association attribute of the abnormal data.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Claims (6)
1. A power distribution network multidimensional data processing method based on cluster analysis is characterized by comprising the following steps:
performing standard access and storage on data of multiple data sources;
carrying out anomaly detection on the stored data;
determining a strong correlation attribute of the abnormal data according to the multi-dimensional characteristics of the data after the abnormality detection;
and correcting the abnormal data by adopting cluster analysis according to the strong association attribute of the abnormal data.
2. The method for processing the multidimensional data of the power distribution network based on the cluster analysis as claimed in claim 1, wherein the performing of the canonical access and the storage of the data of multiple data sources specifically comprises: accessing multi-data source data by adopting a unified standard interface based on a national power grid public data model; and storing the data of multiple data sources in a database according to different data types and characteristics.
3. The method for processing the multidimensional data of the power distribution network based on the cluster analysis, according to claim 1, is characterized in that the abnormal detection of the stored data is specifically as follows: and detecting abnormal data by adopting a density-based clustering method DBSCAN.
4. The method for processing the multidimensional data of the power distribution network based on the cluster analysis is characterized by comprising the following steps of: the determining of the strong association attribute of the abnormal data specifically includes:
determining the relevance of anomalous data using the following equation
Wherein X is an abnormal historical data set, and Y is normal historical data strongly related to the abnormal dataSet, σx、σyX, Y standard deviations, cov (X, Y) is the covariance between X, Y, respectively;
n is the number of data in the abnormal data set, xiIs the ith element in X in the set, yiIs the ith element in the set Y.
5. The method for processing the multidimensional data of the power distribution network based on the cluster analysis as claimed in claim 4, wherein the correcting the abnormal data by the cluster analysis according to the strong association attribute of the abnormal data specifically comprises:
establishing a set C of strong correlation attributes;
determining the weight w of each attribute in the set C by adopting an entropy weight methodj;
For exception data xiSelecting the jth strong correlation attribute from the set C, and performing historical data y on the jth strong correlation attribute in the same time periodjClustering the set;
at yjAnd recording the point with the minimum distance with the strongly-associated attribute data in the class
6. A power distribution network multidimensional data processing system based on cluster analysis is characterized by comprising:
the preprocessing module is used for performing standard access and storage on the data of multiple data sources;
the abnormal data detection module is used for carrying out abnormal detection on the stored data;
the data correction module is used for determining the strong correlation attribute of the abnormal data according to the multi-dimensional characteristics of the data after the abnormality detection;
and correcting the abnormal data by adopting cluster analysis according to the strong association attribute of the abnormal data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111369118.8A CN114253953A (en) | 2021-11-18 | 2021-11-18 | Power distribution network multidimensional data processing method and system based on cluster analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111369118.8A CN114253953A (en) | 2021-11-18 | 2021-11-18 | Power distribution network multidimensional data processing method and system based on cluster analysis |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114253953A true CN114253953A (en) | 2022-03-29 |
Family
ID=80790977
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111369118.8A Pending CN114253953A (en) | 2021-11-18 | 2021-11-18 | Power distribution network multidimensional data processing method and system based on cluster analysis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114253953A (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110197113A1 (en) * | 2008-10-09 | 2011-08-11 | Nec Corporation | Abnormality detection system, abnormality detection method, and abnormality detection program storage medium |
CN105978715A (en) * | 2016-05-09 | 2016-09-28 | 国网浙江省电力公司湖州供电公司 | Data access interface uniform management method based on real time data center |
US20170192115A1 (en) * | 2015-12-30 | 2017-07-06 | Yulia BAKER | Clustering Algorithm For Geoscience Data Fusion |
US20180348998A1 (en) * | 2017-06-02 | 2018-12-06 | The Research Foundation For The State University Of New York | Data access interface |
CN109508743A (en) * | 2018-11-13 | 2019-03-22 | 大连理工大学 | A kind of restorative procedure of the building energy consumption monitoring abnormal data based on KNN innovatory algorithm |
CN112527789A (en) * | 2020-12-17 | 2021-03-19 | 北京中恒博瑞数字电力科技有限公司 | Method and device for detecting repeated data in online monitoring data of power transformation equipment |
US20210192586A1 (en) * | 2019-12-20 | 2021-06-24 | Cintra Holding US Corp. | Systems and Methods for Detecting and Responding to Anomalous Traffic Conditions |
CN113570200A (en) * | 2021-06-30 | 2021-10-29 | 国电南瑞科技股份有限公司 | Power grid operation state monitoring method and system based on multidimensional information |
-
2021
- 2021-11-18 CN CN202111369118.8A patent/CN114253953A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110197113A1 (en) * | 2008-10-09 | 2011-08-11 | Nec Corporation | Abnormality detection system, abnormality detection method, and abnormality detection program storage medium |
US20170192115A1 (en) * | 2015-12-30 | 2017-07-06 | Yulia BAKER | Clustering Algorithm For Geoscience Data Fusion |
CN105978715A (en) * | 2016-05-09 | 2016-09-28 | 国网浙江省电力公司湖州供电公司 | Data access interface uniform management method based on real time data center |
US20180348998A1 (en) * | 2017-06-02 | 2018-12-06 | The Research Foundation For The State University Of New York | Data access interface |
CN109508743A (en) * | 2018-11-13 | 2019-03-22 | 大连理工大学 | A kind of restorative procedure of the building energy consumption monitoring abnormal data based on KNN innovatory algorithm |
US20210192586A1 (en) * | 2019-12-20 | 2021-06-24 | Cintra Holding US Corp. | Systems and Methods for Detecting and Responding to Anomalous Traffic Conditions |
CN112527789A (en) * | 2020-12-17 | 2021-03-19 | 北京中恒博瑞数字电力科技有限公司 | Method and device for detecting repeated data in online monitoring data of power transformation equipment |
CN113570200A (en) * | 2021-06-30 | 2021-10-29 | 国电南瑞科技股份有限公司 | Power grid operation state monitoring method and system based on multidimensional information |
Non-Patent Citations (5)
Title |
---|
孟春雷等: "《人工智能与交通运输》", 31 May 2021, 科学技术文献出版社, pages: 163 * |
张朝阳: "《深入浅出工业机器学习算法详解与实战》", 31 January 2020, 机械工业出版社, pages: 20 - 21 * |
成清: "《基于图的社交网络异常检测》", 31 January 2021, 国防工业出版社, pages: 21 * |
谢霖铨等: "基于PCA的近邻均值填补优化算法", 软件导刊, vol. 17, no. 6, 29 May 2018 (2018-05-29), pages 76 - 76 * |
赖晓晨等: "《基于机器学习的数据缺失值填补》", 30 September 2020, 机械工业出版社, pages: 38 - 39 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106708989B (en) | Skyline query method based on space time sequence data stream application | |
CN110163429B (en) | Short-term load prediction method based on similarity day optimization screening | |
Zhao et al. | User electricity behavior analysis based on K-means plus clustering algorithm | |
CN114676883A (en) | Power grid operation management method, device and equipment based on big data and storage medium | |
CN110503256A (en) | Short-term load forecasting method and system based on big data technology | |
CN109446243B (en) | Method for detecting power generation abnormity of photovoltaic power station based on big data analysis | |
CN114861788A (en) | Load abnormity detection method and system based on DBSCAN clustering | |
CN111008726A (en) | Class image conversion method in power load prediction | |
CN117078048A (en) | Digital twinning-based intelligent city resource management method and system | |
CN112865089A (en) | Improved large-scale scene analysis method for active power distribution network | |
CN110287237B (en) | Social network structure analysis based community data mining method | |
CN111159152A (en) | Secondary operation and maintenance data fusion method based on big data processing technology | |
CN117455070A (en) | Traditional Chinese medicine production data management system based on big data | |
CN113094448A (en) | Method and device for analyzing vacant state of house and electronic equipment | |
CN114253953A (en) | Power distribution network multidimensional data processing method and system based on cluster analysis | |
Aljibawi et al. | A survey on clustering density based data stream algorithms | |
CN111476316B (en) | Method and system for clustering mean value of power load characteristic data based on cloud computing | |
CN111125082B (en) | Cement process parameter data analysis method based on association rule mining | |
CN114676586A (en) | Construction method based on multidimensional, multi-space-time digital simulation and emulation | |
CN113486063A (en) | Method and device for processing flow data in power internet of things and terminal equipment | |
CN109447490B (en) | User address-based abnormal change relation discrimination method | |
Bin et al. | An Improved Algorithm for High Speed Train's Maintenance Data Mining Based on MapReduce | |
CN111144540A (en) | Generation method of anti-electricity-stealing simulation data set | |
CN113191656B (en) | Low-voltage distribution network equipment load and topology linkage method based on data correlation analysis | |
CN116595102B (en) | Big data management method and system for improving clustering algorithm |
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 |