CN107945053A - A kind of multiple source power distribution network data convergence analysis platform and its control method - Google Patents
A kind of multiple source power distribution network data convergence analysis platform and its control method Download PDFInfo
- Publication number
- CN107945053A CN107945053A CN201711469327.3A CN201711469327A CN107945053A CN 107945053 A CN107945053 A CN 107945053A CN 201711469327 A CN201711469327 A CN 201711469327A CN 107945053 A CN107945053 A CN 107945053A
- Authority
- CN
- China
- Prior art keywords
- data
- distribution network
- platform
- source heterogeneous
- server end
- 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.)
- Withdrawn
Links
- 238000009826 distribution Methods 0.000 title claims abstract description 134
- 238000004458 analytical method Methods 0.000 title claims abstract description 35
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000001514 detection method Methods 0.000 claims abstract description 35
- 230000010354 integration Effects 0.000 claims abstract description 32
- 230000005540 biological transmission Effects 0.000 claims abstract description 9
- 230000004927 fusion Effects 0.000 claims abstract description 7
- 230000008569 process Effects 0.000 claims abstract description 6
- 238000004891 communication Methods 0.000 claims description 19
- 238000000605 extraction Methods 0.000 claims description 18
- 238000007726 management method Methods 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 238000010801 machine learning Methods 0.000 claims description 6
- 230000006855 networking Effects 0.000 claims description 6
- 230000003287 optical effect Effects 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 5
- 235000015849 Apium graveolens Dulce Group Nutrition 0.000 claims description 4
- 235000010591 Appio Nutrition 0.000 claims description 4
- 238000012098 association analyses Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 230000002068 genetic effect Effects 0.000 claims description 3
- 230000007935 neutral effect Effects 0.000 claims description 3
- 238000003909 pattern recognition Methods 0.000 claims description 3
- 230000002123 temporal effect Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000000547 structure data Methods 0.000 claims 2
- 244000101724 Apium graveolens Dulce Group Species 0.000 claims 1
- 238000012544 monitoring process Methods 0.000 abstract description 5
- 238000007405 data analysis Methods 0.000 abstract description 3
- 240000007087 Apium graveolens Species 0.000 description 3
- 230000005611 electricity Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000009432 framing Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000033772 system development Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
-
- 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
- G06F16/26—Visual data mining; Browsing structured data
-
- 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)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention discloses a kind of multiple source power distribution network data convergence analysis platform and its control method, analysis platform includes Real-time Electrical Distribution Network Data detection platform, power distribution network data integration platform, server end and control platform;The Real-time Electrical Distribution Network Data detection platform is used to detect in real time and gathers power generating network and the multi-source heterogeneous data of power transmission network, and by multi-source heterogeneous data sending to the power distribution network data integration platform and server end;The power distribution network data integration platform be used to extract multi-source heterogeneous data, pre-process, integrate and fusion treatment after send to the server end;The server end is used to multi-source heterogeneous data are stored, analyzed, counted and managed;The control platform is controlled the server end and shows corresponding multi-source heterogeneous data.The present invention can preferably distinguish power distribution network overall operation state, exception or failure, and carry out effective monitoring by big data analysis.
Description
Technical field
The present invention relates to distribution network system technical field, more particularly to a kind of multiple source power distribution network data convergence analysis platform and
Its control method.
Background technology
Distribution system is to connect electricity generation system, transmission system and the intermediate link of user, for a long time China's distribution system
Development lag far behind transmission system, common problem is:Ageing equipment, accident rate are high, load is heavy, Network Loss Rate is high,
Radius of electricity supply length, poor reliability, power quality are horizontal low and operation the degree of automation is low etc., and how power distribution network responds actively event
Barrier event, not only needs have science accurately to assess self-operating state, also to be made in time for continually changing operating mode
Necessary adjustment, this just needs to be grasped accurate, reliable, comprehensive, the timely status information of the local distribution of covering, it is carried out
The analysis of specialty judges, to effectively being assessed with Running State.Power distribution network mainly includes the asset management system, metering at present
Automated system, dispatch automated system, electrical power distribution automatization system, voltage power-less monitoring system running, using in platform not
Dispatch automated system data, fault message, defect information, equipment operating data and the device status data of disconnected renewal, which are carried out, matches somebody with somebody
Operation of power networks is analyzed.Effective information is excavated from the substantial amounts of historical data of power distribution network, carries out the special project point of distribution Running State
Analysis, reference frame is provided for the following decision-making in the power failure of distribution synthesis, emergency first-aid repair, distribution construction, rack transformation.
In terms of foundation and visual presentation for the distributed data base of the multi-source heterogeneous data of power distribution network, the country is existing not
Few research, but it is main or for some specific business expansion.Existing power supply bureau of the country completes dispatches essence in electricity consumption
Benefitization manages the exploitation of application aspect, implements distribution scheduling intensive management, realizes Distribution Network Equipment account and production procedure system
System property management, dynamically stop telegram in reply management and failure rapid rush-repair management, but be mostly for the specific service management of some power supply enterprise,
The contents such as workflow, information issue are developed;Existing power distribution network operating index also focus mostly in examination power quality it is horizontal,
Operation grade etc., it can not reflect power distribution network overall operation state, exception or failure well, cause operational monitoring horizontal
Deficiency.At present there has been no ripe, practical power distribution network data integration monitoring platform, excavate magnanimity distribution data and carry out power distribution network point
Analysis evaluation, it is especially desirable to which particular association analysis is carried out in key index-equipment fault to distribution.To multisystem multi-dimensional data
Carry out going deep into mining analysis, effective integration data message, is the side such as Distribution Network Equipment O&M, distribution emergency first-aid repair, distribution construction
Face provides policy-making opinion with suggesting.
It has recorded the data of different dimensions, including meteorology, family meter terminal relation, family table code in collection power distribution network operational process
The data of number, Current Voltage, power, power off time, warning message, rate of qualified voltage, line loss statistics etc..Each dimension data
It is acquired respectively by different system, equipment, so data are in state scattered, that recording mode is inconsistent.If necessary to right
Distribution network data is analyzed the data just needed in view of each system, and conventional analysis mode is by different systems
Data carry out Macro or mass analysis, wherein, some information and precision can be lost during data summarization, and if to collect
Data afterwards carry out data analysis, and as a result unsatisfactory and accuracy is low.
The content of the invention
In order to overcome shortcoming and deficiency existing in the prior art, the present invention provides a kind of multiple source power distribution network data convergence analysis
Platform and its control method, carry out excavation effective information from the substantial amounts of historical data of power distribution network, carry out distribution Running State
Special analysis, by big data analysis, can preferably distinguish power distribution network overall operation state, exception or failure, and carry out
Effective monitoring, solves that power distribution network can not be analyzed in the case of data volume is big using conventional method or analysis efficiency is low
The problem of.
In order to solve the above technical problems, the present invention provides following technical solution:A kind of multiple source power distribution network data convergence analysis
Platform, including Real-time Electrical Distribution Network Data detection platform, power distribution network data integration platform, server end and control platform, it is described
It is connected with each other between Real-time Electrical Distribution Network Data detection platform, power distribution network data integration platform and server end, the server
End connects the control platform;The Real-time Electrical Distribution Network Data detection platform is used to detect in real time and gather power generating network and power transmission network
Multi-source heterogeneous data, and by multi-source heterogeneous data sending to the power distribution network data integration platform and server end;It is described
Power distribution network data integration platform be used for multi-source heterogeneous data are extracted, are pre-processed, are integrated and fusion treatment after send to
The server end;The server end is used to multi-source heterogeneous data are stored, analyzed, counted and managed;The control
Platform processed is controlled the server end and shows corresponding multi-source heterogeneous data.
Further, the Real-time Electrical Distribution Network Data detection platform connects the distribution netting index by power communication optical networking
According to integrated platform and server end;The Real-time Electrical Distribution Network Data detection platform includes data detecting unit, data acquisition unit
And the first power communication interface unit, the data detecting unit are used to detect Real-time Electrical Distribution Network Data detection platform in real time,
The data acquisition unit is used to gather the multi-source heterogeneous data that the data detecting unit detects, first power communication
Interface unit is used to go out multi-source heterogeneous data sending.
Further, the power distribution network data integration platform connects the power distribution network by power communication optical networking and counts in real time
According to detection platform and server end;The power distribution network data integration platform include extraction unit, pretreatment unit, integrated unit,
Integrated unit and the second power communication interface unit, the extraction unit is used to extract multi-source heterogeneous data characteristics, described pre-
Processing unit is used to be pre-processed the multi-source heterogeneous data after extraction feature, and the integrated unit is used to integrate multi-source heterogeneous
Multi-source heterogeneous data fusion is sent to server by data, the integrated unit by the second power communication interface unit after reunification
End.
Further, the server end connects the control platform by network switch;The server end includes
Interface server, application server and relationship server, structure between interface server, application server and relationship server
Build LAN to be attached, LAN connects the control platform by network switch;The interface server is used to connect
The Real-time Electrical Distribution Network Data detection platform and power distribution network data integration platform, the application server are used to analyzing and counting more
Source isomeric data, the relationship server are used to storing, process and managing multi-source heterogeneous data.
Further, the control platform includes control main frame and display, and the control main frame is used for the service
Device end is controlled;The display is used to show corresponding multi-source heterogeneous data, including parallel coordinates, distribution map and scatterplot
Figure.
Another object of the present invention is to provide a kind of control method of multiple source power distribution network data convergence analysis platform, including following
Step:
S1, Real-time Electrical Distribution Network Data detection platform detect and gather power generating network and the multi-source heterogeneous data of power transmission network in real time,
And by multi-source heterogeneous data sending to power distribution network data integration platform and server end, server end carries out storing multi-source heterogeneous number
According to;
The multi-source heterogeneous data received are carried out feature extraction by S2, power distribution network data integration platform, are then believed by feature
Breath is classified, polymerize and is integrated to multi-source heterogeneous data, produces characteristic vector, and the characteristic vector is carried out in temporal sequence
It is fused to feature vector set;By the multi-source heterogeneous data sending in feature vector set to server end;
S3, server end constantly receive multi-source heterogeneous data and are stored and computing;Server end is according to multi-source heterogeneous
Data, deeply excavate the historical information of the multi-source heterogeneous data of distribution network operation;
S4, the historical information to multi-source heterogeneous data carry out machine learning, obtain experience storehouse;
S5, establish accident analysis and the special business of management:Real-time Electrical Distribution Network Data detection platform is detected and gathered new more
Source isomeric data, the experience storehouse of contrast step S4, draws distribution network construction and O&M strategy optimum data.
Further, the multi-source heterogeneous data in the step S1 include weather information, family meter terminal relation, family table code
Number, Current Voltage value, performance number, power off time, warning message, rate of qualified voltage and line loss statistics.
Further, in the step S2, the power distribution network data integration platform by the multi-source heterogeneous data received into
Row feature extraction, feature extraction are specifically included using method:
(1) Filter filtration methods:Score the feature of multi-source heterogeneous data, set according to diversity or correlation
The number of threshold value or threshold value to be selected, selects feature;
(2) Wrapper packs:Sets target function, selects some features of multi-source heterogeneous data every time, or excludes
Some features of multi-source heterogeneous data;
(3) Embedded embedding inlay techniques:First it is trained using the algorithm and model of machine learning, obtains multi-source heterogeneous data
Each feature weight coefficient, feature is selected according to coefficient from big to small.
Further, in the step S3, server end using non-relational database to multi-source heterogeneous data storage and
Computing;
The server end deeply excavates power distribution network history run information, and the method for use includes:Utilize association analysis, number
According to combinational reasoning, pattern-recognition, neutral net or genetic algorithm.
Further, in the step S3, server end constantly receives multi-source heterogeneous data and is stored and computing,
In server end, it is not enough in single server performance come in the case of doing mass data computing, server end operation redis+
Celery distributed computing frameworks, joint multiple servers carry out parallel computation.
After adopting the above technical scheme, the present invention at least has the advantages that:
(1) present invention is possibly realized the quasi real time Cooperative Analysis of each system data of power distribution network, power distribution network multi-source data
Automatic convergence analysis is possibly realized;
(2) non-relational database has been used to be stored to multi-source heterogeneous data and computing in the method for the present invention, rather than
Relational database has performance higher, autgmentability more preferable, the advantages that being adapted to handle mass data;And the prior art uses
Relevant database have the scalability it is poor, be not suitable for mass data application scenarios the shortcomings of;
(3) server end has used the Mechanism of Task Allocation of redis+celery in the method for the present invention, wherein,
Redis is suitable for doing cache, can support the concurrency of higher, and when task amount is big, effect becomes apparent from when slaves is more, favorably
In the extension of application, and dispose relatively easy.
Brief description of the drawings
Fig. 1 is a kind of structural framing figure of multiple source power distribution network data convergence analysis platform of the present invention;
Fig. 2 is a kind of control method block diagram of multiple source power distribution network data convergence analysis platform of the present invention.
Embodiment
It should be noted that in the case where there is no conflict, the feature in embodiment and embodiment in the application can phase
Mutually combine, the application is described in further detail with specific embodiment below in conjunction with the accompanying drawings.
Embodiment
As shown in Figure 1, the present invention provides a kind of multiple source power distribution network data convergence analysis platform, power distribution network is mainly included
Real time data detection platform, power distribution network data integration platform, server end and control platform, wherein, Real-time Electrical Distribution Network Data
It is connected with each other between detection platform, power distribution network data integration platform and server end, server end connection control platform.It is preferred that
Ground, Real-time Electrical Distribution Network Data detection platform of the invention are mutually interconnected with power distribution network data integration platform by power communication optical networking
Connect, and Real-time Electrical Distribution Network Data detection platform and power distribution network data integration platform pass through power communication optical networking Connection Service device
End;Alternatively, it can pass through between Real-time Electrical Distribution Network Data detection platform, power distribution network data integration platform and server end three
Either WiFi network or other wireless networks are attached mobile network.In addition, server end is connected by network switch
Control platform.
Wherein, above-mentioned Real-time Electrical Distribution Network Data detection platform be used for detect in real time and gather power generating network and power transmission network it is more
Source isomeric data, and by multi-source heterogeneous data sending to the power distribution network data integration platform and server end;Distribution netting index
Be used to extracting multi-source heterogeneous data according to integrated platform, pre-process, integrating and fusion treatment after send to the service
Device end;Server end is used to multi-source heterogeneous data are stored, analyzed, counted and managed;Control platform is to server end
It is controlled and shows corresponding multi-source heterogeneous data.
The Real-time Electrical Distribution Network Data detection platform of the present invention is led to including data detecting unit, data acquisition unit and electric power
Believe interface unit, data detecting unit is used to detect Real-time Electrical Distribution Network Data detection platform in real time, and data acquisition unit is used to adopt
The multi-source heterogeneous data that collection data detecting unit detects, power communication interface unit are used to multi-source heterogeneous data sending
Go.
The present invention power distribution network data integration platform include extraction unit, pretreatment unit, integrated unit, integrated unit with
And power communication interface unit, power communication interface unit of the power communication interface unit with Real-time Electrical Distribution Network Data detection platform
Unanimously;Extraction unit is used to extract multi-source heterogeneous data characteristics, and pretreatment unit is used for the multi-source heterogeneous number after extraction feature
According to being pre-processed, integrated unit is used to integrate multi-source heterogeneous data, and integrated unit leads to multi-source heterogeneous data fusion after reunification
Cross power communication interface unit and be sent to server end.
As shown in Figure 1, server end includes interface server, application server and relationship server, interface server,
Build LAN between application server and relationship server to be attached, LAN is flat by network switch connection control
Platform;Interface server is used to connect Real-time Electrical Distribution Network Data detection platform and power distribution network data integration platform, and application server is used
In analyzing and counting multi-source heterogeneous data, relationship server is used to storing, process and managing multi-source heterogeneous data.
The control platform of the present invention includes control main frame and display, and control main frame is used to control the server end
System;Display is used to show corresponding multi-source heterogeneous data, including parallel coordinates, distribution map and scatter diagram.
As shown in Fig. 2, for a kind of above-mentioned multiple source power distribution network data convergence analysis platform, its specific control method is:
S1, Real-time Electrical Distribution Network Data detection platform detect and gather power generating network and the multi-source heterogeneous data of power transmission network in real time,
And by multi-source heterogeneous data sending to power distribution network data integration platform and server end, server end carries out storing multi-source heterogeneous number
According to.
The multi-source heterogeneous data received are carried out feature extraction by S2, power distribution network data integration platform, are then believed by feature
Breath is classified, polymerize and is integrated to multi-source heterogeneous data, produces characteristic vector, and the characteristic vector is carried out in temporal sequence
It is fused to feature vector set;By the multi-source heterogeneous data sending in feature vector set to server end;
Usually, the multi-source heterogeneous data received are carried out feature extraction, feature by the power distribution network data integration platform
Extraction is specifically included using method:
(1) Filter filtration methods:Score the feature of multi-source heterogeneous data, set according to diversity or correlation
The number of threshold value or threshold value to be selected, selects feature;
(2) Wrapper packs:Sets target function, selects some features of multi-source heterogeneous data every time, or excludes
Some features of multi-source heterogeneous data;
(3) Embedded embedding inlay techniques:First it is trained using the algorithm and model of machine learning, obtains multi-source heterogeneous data
Each feature weight coefficient, feature is selected according to coefficient from big to small.
S3, server end constantly receive multi-source heterogeneous data and are stored and computing;Server end is according to multi-source heterogeneous
Data, deeply excavate the historical information of the multi-source heterogeneous data of distribution network operation;
Preferably, server end stores multi-source heterogeneous data using non-relational database and computing;
Preferably, the server end deeply excavates power distribution network history run information, and the method for use includes:Utilize association
Analysis, data combinational reasoning, pattern-recognition, neutral net or genetic algorithm;
Preferably, server end constantly receives multi-source heterogeneous data and is stored and computing, in server end, in list
Platform server performance is not enough to come in the case of doing mass data computing, server end operation redis+celery Distributed Calculation frames
Frame, joint multiple servers carry out parallel computation.
S4, server end carry out machine learning to the historical information of multi-source heterogeneous data, obtain experience storehouse.
S5, server end establish accident analysis and the special business of management:Real-time Electrical Distribution Network Data detection platform is detected and adopted
The new multi-source heterogeneous data of collection, the experience storehouse of contrast step S4, draw distribution network construction and O&M strategy optimum data.
Although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
Understand, can carry out a variety of equivalent changes to these embodiments without departing from the principles and spirit of the present invention
Change, change, replacing and modification, the scope of the present invention are limited by appended claims and its equivalency range.
Claims (10)
1. a kind of multiple source power distribution network data convergence analysis platform, it is characterised in that including Real-time Electrical Distribution Network Data detection platform, match somebody with somebody
Electric network data integrated platform, server end and control platform, the Real-time Electrical Distribution Network Data detection platform, power distribution network data set
It is connected with each other between platform and server end, the server end connects the control platform;The power distribution network counts in real time
It is used to detect in real time according to detection platform and gathers power generating network and the multi-source heterogeneous data of power transmission network, and by multi-source heterogeneous data sending
To the power distribution network data integration platform and server end;The power distribution network data integration platform is used for multi-source heterogeneous data
Extracted, pre-processed, being integrated and fusion treatment after send to the server end;The server end is used for different to multi-source
Structure data are stored, are analyzed, counted and managed;The control platform is controlled the server end and shows corresponding
Multi-source heterogeneous data.
2. a kind of multiple source power distribution network data convergence analysis platform as claimed in claim 1, it is characterised in that the power distribution network is real
When Data Detection platform pass through power communication optical networking and connect the power distribution network data integration platform and server end;The distribution
Net real time data detection platform includes data detecting unit, data acquisition unit and the first power communication interface unit, described
Data detecting unit is used to detect Real-time Electrical Distribution Network Data detection platform in real time, and the data acquisition unit is used to gather the number
The multi-source heterogeneous data detected according to detection unit, the first power communication interface unit are used for multi-source heterogeneous data sending
Go out.
A kind of 3. multiple source power distribution network data convergence analysis platform as claimed in claim 1, it is characterised in that the distribution netting index
The Real-time Electrical Distribution Network Data detection platform and server end are connected by power communication optical networking according to integrated platform;The distribution
Network data integrated platform includes extraction unit, pretreatment unit, integrated unit, integrated unit and the second power communication interface list
Member, the extraction unit are used to extract multi-source heterogeneous data characteristics, and the pretreatment unit is used for the multi-source after extraction feature
Isomeric data is pre-processed, and the integrated unit is used to integrate multi-source heterogeneous data, and the integrated unit is by multi-source heterogeneous number
Server end is sent to by the second power communication interface unit after reunification according to fusion.
A kind of 4. multiple source power distribution network data convergence analysis platform as claimed in claim 1, it is characterised in that the server end
The control platform is connected by network switch;The server end includes interface server, application server and relation
Server, builds LAN and is attached, LAN passes through net between interface server, application server and relationship server
Network exchanger connects the control platform;The interface server is used to connect the Real-time Electrical Distribution Network Data detection platform and match somebody with somebody
Electric network data integrated platform, the application server are used to analyzing and counting multi-source heterogeneous data, and the relationship server is used for
Store, process and manage multi-source heterogeneous data.
A kind of 5. multiple source power distribution network data convergence analysis platform as claimed in claim 1, it is characterised in that the control platform
Including control main frame and display, the control main frame is used to be controlled the server end;The display is used to show
Show corresponding multi-source heterogeneous data, including parallel coordinates, distribution map and scatter diagram.
6. a kind of control method of multiple source power distribution network data convergence analysis platform as any one of claim 1-5, its
It is characterized in that, comprises the following steps:
S1, Real-time Electrical Distribution Network Data detection platform detect and gather power generating network and the multi-source heterogeneous data of power transmission network in real time, and will
To power distribution network data integration platform and server end, server end carries out storing multi-source heterogeneous data multi-source heterogeneous data sending;
The multi-source heterogeneous data received are carried out feature extraction by S2, power distribution network data integration platform, then by characteristic information pair
Multi-source heterogeneous data are classified, polymerize and are integrated, and produce characteristic vector, the characteristic vector is merged in temporal sequence
To feature vector set;By the multi-source heterogeneous data sending in feature vector set to server end;
S3, server end constantly receive multi-source heterogeneous data and are stored and computing;Server end according to multi-source heterogeneous data,
Deeply excavate the historical information of the multi-source heterogeneous data of distribution network operation;
S4, the historical information to multi-source heterogeneous data carry out machine learning, obtain experience storehouse;
S5, establish accident analysis and the special business of management:Real-time Electrical Distribution Network Data detection platform detects and to gather new multi-source different
Structure data, the experience storehouse of contrast step S4, draw distribution network construction and O&M strategy optimum data.
7. a kind of control method of multiple source power distribution network data convergence analysis platform as claimed in claim 5, it is characterised in that described
Multi-source heterogeneous data in step S1 include weather information, family meter terminal relation, family table yardage, Current Voltage value, performance number, stop
Electric time, warning message, rate of qualified voltage and line loss statistics.
8. a kind of control method of multiple source power distribution network data convergence analysis platform as claimed in claim 5, it is characterised in that described
In step S2, the multi-source heterogeneous data received are carried out feature extraction, feature extraction tool by the power distribution network data integration platform
Body is included using method:
(1) Filter filtration methods:Score according to diversity or correlation the feature of multi-source heterogeneous data, given threshold
Or the number of threshold value to be selected, select feature;
(2) Wrapper packs:Sets target function, selects some features of multi-source heterogeneous data every time, or excludes multi-source
Some features of isomeric data;
(3) Embedded embedding inlay techniques:First it is trained using the algorithm and model of machine learning, obtains each of multi-source heterogeneous data
The weight coefficient of a feature, feature is selected according to coefficient from big to small.
9. a kind of control method of multiple source power distribution network data convergence analysis platform as claimed in claim 5, it is characterised in that described
In step S3, multi-source heterogeneous data are stored using non-relational database for server end and computing;
The server end deeply excavates power distribution network history run information, and the method for use includes:Utilize association analysis, data group
Close reasoning, pattern-recognition, neutral net or genetic algorithm.
A kind of 10. control method of multiple source power distribution network data convergence analysis platform as described in claim 5 or 9, it is characterised in that
In the step S3, server end constantly receives multi-source heterogeneous data and is stored and computing, in server end, in separate unit
Server performance is not enough to come in the case of doing mass data computing, server end operation redis+celery Distributed Calculation frames
Frame, joint multiple servers carry out parallel computation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711469327.3A CN107945053A (en) | 2017-12-29 | 2017-12-29 | A kind of multiple source power distribution network data convergence analysis platform and its control method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711469327.3A CN107945053A (en) | 2017-12-29 | 2017-12-29 | A kind of multiple source power distribution network data convergence analysis platform and its control method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107945053A true CN107945053A (en) | 2018-04-20 |
Family
ID=61936843
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711469327.3A Withdrawn CN107945053A (en) | 2017-12-29 | 2017-12-29 | A kind of multiple source power distribution network data convergence analysis platform and its control method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107945053A (en) |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109086573A (en) * | 2018-07-30 | 2018-12-25 | 东北师范大学 | Multi-source biology big data convergence platform |
CN109241169A (en) * | 2018-11-16 | 2019-01-18 | 广西电网有限责任公司电力科学研究院 | The multi-source heterogeneous data fusion geo-database integration method of power distribution network operation information |
CN109299151A (en) * | 2018-10-26 | 2019-02-01 | 国网安徽省电力有限公司繁昌县供电公司 | A kind of photoelectricity big data distribution operation management system |
CN109406943A (en) * | 2018-11-16 | 2019-03-01 | 国网江苏省电力有限公司盐城供电分公司 | A kind of active distribution network monitoring method based on big data |
CN109471884A (en) * | 2018-09-12 | 2019-03-15 | 国网浙江省电力有限公司嘉兴供电公司 | The relevant multi-source heterogeneous data processing method of distributed new |
CN109688597A (en) * | 2018-12-18 | 2019-04-26 | 北京邮电大学 | A kind of mist Radio Access Network network-building method and device based on artificial intelligence |
CN109919315A (en) * | 2019-03-13 | 2019-06-21 | 科大讯飞股份有限公司 | A kind of forward inference method, apparatus, equipment and the storage medium of neural network |
CN110210559A (en) * | 2019-05-31 | 2019-09-06 | 北京小米移动软件有限公司 | Object screening technique and device, storage medium |
CN110543508A (en) * | 2019-08-30 | 2019-12-06 | 海南电网有限责任公司 | multi-source big data fusion access method for power distribution communication network |
CN111598409A (en) * | 2020-04-24 | 2020-08-28 | 广西电网有限责任公司电力科学研究院 | Distribution network operating efficiency monitoring and analysis system |
CN111597415A (en) * | 2020-05-13 | 2020-08-28 | 云南电网有限责任公司电力科学研究院 | Neural network-based power distribution network account data communication method and device |
CN112015813A (en) * | 2020-08-26 | 2020-12-01 | 南方电网数字电网研究院有限公司 | Data sharing method, system and device of power distribution network and computer equipment |
CN112463910A (en) * | 2020-12-17 | 2021-03-09 | 福州物联网开放实验室有限公司 | Internet of things multidimensional data fusion system and method |
CN113036917A (en) * | 2021-03-08 | 2021-06-25 | 国网浙江省电力有限公司金华供电公司 | Power distribution network monitoring information monitoring system and method based on machine learning |
CN113837604A (en) * | 2021-09-23 | 2021-12-24 | 万申科技股份有限公司 | Multi-source heterogeneous data fusion and multi-dimensional data correlation analysis system |
CN114142611A (en) * | 2021-11-30 | 2022-03-04 | 贵州电网有限责任公司 | Power distribution network intelligent measurement and control universal terminal based on open architecture and measurement and control method |
CN115952770A (en) * | 2023-03-15 | 2023-04-11 | 广州汇通国信科技有限公司 | Data standardization processing method and device, electronic equipment and storage medium |
-
2017
- 2017-12-29 CN CN201711469327.3A patent/CN107945053A/en not_active Withdrawn
Cited By (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109086573B (en) * | 2018-07-30 | 2021-08-24 | 东北师范大学 | Multi-source biological big data fusion system |
CN109086573A (en) * | 2018-07-30 | 2018-12-25 | 东北师范大学 | Multi-source biology big data convergence platform |
CN109471884A (en) * | 2018-09-12 | 2019-03-15 | 国网浙江省电力有限公司嘉兴供电公司 | The relevant multi-source heterogeneous data processing method of distributed new |
CN109299151A (en) * | 2018-10-26 | 2019-02-01 | 国网安徽省电力有限公司繁昌县供电公司 | A kind of photoelectricity big data distribution operation management system |
CN109241169A (en) * | 2018-11-16 | 2019-01-18 | 广西电网有限责任公司电力科学研究院 | The multi-source heterogeneous data fusion geo-database integration method of power distribution network operation information |
CN109406943A (en) * | 2018-11-16 | 2019-03-01 | 国网江苏省电力有限公司盐城供电分公司 | A kind of active distribution network monitoring method based on big data |
CN109688597A (en) * | 2018-12-18 | 2019-04-26 | 北京邮电大学 | A kind of mist Radio Access Network network-building method and device based on artificial intelligence |
CN109919315B (en) * | 2019-03-13 | 2021-10-01 | 科大讯飞股份有限公司 | Forward reasoning method, device, equipment and storage medium of neural network |
CN109919315A (en) * | 2019-03-13 | 2019-06-21 | 科大讯飞股份有限公司 | A kind of forward inference method, apparatus, equipment and the storage medium of neural network |
CN110210559B (en) * | 2019-05-31 | 2021-10-08 | 北京小米移动软件有限公司 | Object screening method and device and storage medium |
CN110210559A (en) * | 2019-05-31 | 2019-09-06 | 北京小米移动软件有限公司 | Object screening technique and device, storage medium |
CN110543508A (en) * | 2019-08-30 | 2019-12-06 | 海南电网有限责任公司 | multi-source big data fusion access method for power distribution communication network |
CN111598409A (en) * | 2020-04-24 | 2020-08-28 | 广西电网有限责任公司电力科学研究院 | Distribution network operating efficiency monitoring and analysis system |
CN111597415A (en) * | 2020-05-13 | 2020-08-28 | 云南电网有限责任公司电力科学研究院 | Neural network-based power distribution network account data communication method and device |
CN111597415B (en) * | 2020-05-13 | 2023-05-26 | 云南电网有限责任公司电力科学研究院 | Neural network-based distribution network account data penetration method and device |
CN112015813A (en) * | 2020-08-26 | 2020-12-01 | 南方电网数字电网研究院有限公司 | Data sharing method, system and device of power distribution network and computer equipment |
CN112015813B (en) * | 2020-08-26 | 2024-03-26 | 南方电网数字电网研究院有限公司 | Data sharing method, system and device for power distribution network and computer equipment |
CN112463910A (en) * | 2020-12-17 | 2021-03-09 | 福州物联网开放实验室有限公司 | Internet of things multidimensional data fusion system and method |
CN113036917A (en) * | 2021-03-08 | 2021-06-25 | 国网浙江省电力有限公司金华供电公司 | Power distribution network monitoring information monitoring system and method based on machine learning |
CN113837604A (en) * | 2021-09-23 | 2021-12-24 | 万申科技股份有限公司 | Multi-source heterogeneous data fusion and multi-dimensional data correlation analysis system |
CN114142611A (en) * | 2021-11-30 | 2022-03-04 | 贵州电网有限责任公司 | Power distribution network intelligent measurement and control universal terminal based on open architecture and measurement and control method |
CN115952770A (en) * | 2023-03-15 | 2023-04-11 | 广州汇通国信科技有限公司 | Data standardization processing method and device, electronic equipment and storage medium |
CN115952770B (en) * | 2023-03-15 | 2023-07-25 | 广州汇通国信科技有限公司 | Data standardization processing method and device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107945053A (en) | A kind of multiple source power distribution network data convergence analysis platform and its control method | |
CN110333402B (en) | User voltage abnormity sensing method and system based on edge calculation | |
CN110996259B (en) | Intelligent garbage monitoring and clearing method and device based on edge calculation | |
CN102932195B (en) | A kind of business diagnosis method for supervising of protocal analysis Network Based and system | |
CN105574593B (en) | Track state static detection and control system and method based on cloud computing and big data | |
CN104376365A (en) | Method for constructing information system running rule libraries on basis of association rule mining | |
CN210166487U (en) | Power supply station area power failure fault warning device based on edge calculation | |
CN105069025A (en) | Intelligent aggregation visualization and management control system for big data | |
CN104966330A (en) | Remote machine room intelligent inspection system based on cloud computer | |
CN107341609B (en) | Energy efficiency management system and method based on cloud platform | |
CN107300375A (en) | A kind of high-speed railway subgrade Monitoring method of the subsidence and system | |
CN105187554A (en) | Method and system for monitoring server performance | |
CN108696369A (en) | A kind of warning information processing equipment and method | |
CN106610616A (en) | Automatic performance tuning method and automatic performance tuning device based on big data analysis | |
CN103106629B (en) | Stand district's passenger flow density acquisition system | |
CN106168766A (en) | The energy monitor management system of a kind of Smart Home and carbon assets management method | |
CN115908046A (en) | Visual power distribution system based on airport terminal building BIM | |
CN103234520A (en) | Controller area network (CAN) bus-based settlement deformation monitoring system | |
CN110673559A (en) | Robot scheduling management system | |
CN110430261A (en) | Detecting devices fault handling method and device | |
CN106529842A (en) | Control operation quantitative evaluation system and method for power grid | |
CN104038736B (en) | Video data dynamic transmission method | |
CN106649034B (en) | Visual intelligent operation and maintenance method and platform | |
CN106645938A (en) | Electric energy management system and method for urban rail transit | |
CN111460027A (en) | Intelligent dynamic monitoring method and system suitable for energy Internet |
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 | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20180420 |