CN110457193A - Health portrait methods of exhibiting and its system based on power information system operation/maintenance data - Google Patents
Health portrait methods of exhibiting and its system based on power information system operation/maintenance data Download PDFInfo
- Publication number
- CN110457193A CN110457193A CN201910695457.1A CN201910695457A CN110457193A CN 110457193 A CN110457193 A CN 110457193A CN 201910695457 A CN201910695457 A CN 201910695457A CN 110457193 A CN110457193 A CN 110457193A
- Authority
- CN
- China
- Prior art keywords
- data
- label
- portrait
- maintenance
- power information
- 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
- 238000012423 maintenance Methods 0.000 title claims abstract description 59
- 230000036541 health Effects 0.000 title claims abstract description 35
- 238000000034 method Methods 0.000 title claims abstract description 34
- 230000001747 exhibiting effect Effects 0.000 title claims abstract description 15
- 238000012544 monitoring process Methods 0.000 claims abstract description 54
- 238000012545 processing Methods 0.000 claims abstract description 15
- 238000004458 analytical method Methods 0.000 claims abstract description 11
- 239000000284 extract Substances 0.000 claims abstract description 8
- 238000002372 labelling Methods 0.000 claims abstract description 8
- 238000007405 data analysis Methods 0.000 claims description 18
- 238000010606 normalization Methods 0.000 claims description 12
- 230000010354 integration Effects 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 5
- 230000003862 health status Effects 0.000 abstract description 5
- 230000035508 accumulation Effects 0.000 description 4
- 238000009825 accumulation Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000000875 corresponding effect Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000001360 synchronised effect Effects 0.000 description 3
- 230000004888 barrier function Effects 0.000 description 2
- 230000001052 transient effect Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3409—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment for performance assessment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3452—Performance evaluation by statistical analysis
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- 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
- G06Q10/20—Administration of product repair or maintenance
-
- 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)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Computer Hardware Design (AREA)
- Game Theory and Decision Science (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to health portrait methods of exhibiting and its system based on power information system operation/maintenance data, and described method includes following steps: step S1, obtaining raw power monitoring operation/maintenance data and pre-processed to obtain preprocessed data to raw power monitoring operation/maintenance data;Step S2, labeling processing is carried out to the preprocessed data, extracts the variable and attribute of the preprocessed data, and label data is obtained to its variable and attribute setting label;Step S3, the label data analyze and portrait is drawn a portrait and shown in building based on the analysis results.The present invention passes through the comprehensive behavior portrait of big data O&M, the health status and feature of analysis system, so that O&M precision be better achieved.
Description
Technical field
The present invention relates to big data processing technology fields, and in particular to a kind of strong based on power information system operation/maintenance data
Health portrait methods of exhibiting and its system.
Background technique
In recent years, as the fast development of China's economic, electric power selling market constantly expand, it have stimulated entire power industry
Rapid development.Electric power is one of most important basic energy resource industry in the national economic development.At the same time, with power industry
System reform deepens continuously, and electric power enterprise constantly promotes information-based requirement.
2008, " big data (BigData) " this concept was first appeared in " Nature " magazine.Big data refers generally to
The data acquisition system that can not be captured, managed and be handled with conventional software tool within the scope of certain time is in newly processing mould
Magnanimity, high growth rate and the diversified letter that could have stronger decision edge under formula, see clearly discovery power and process optimization ability
Cease assets.With monitoring informationization continue to develop, monitoring performance index, alarm data, failure solve data, fault message,
A large amount of daily monitoring data has been descended in the extensive use accumulation of the systems such as monitoring system, O&M process.Regular data is with regard to structure within these day
At O&M big data, these data substantially can it is objective, be truly reflected system monitoring situation.We can use these prisons
The big data of accumulation is controlled, the value for playing data in O&M and fault pre-alarming is sufficiently excavated, is supervised by big data operational system
Control portrait, the health status and feature of analysis system, so that O&M precision be better achieved.
At present in system health portrait display systems, health portrait is closely related with service application framework, not general
Portrait system, also without being suitble to the health portrait of electric power industry information system to practice.And in terms of fault-finding and intelligent early-warning,
The research by perfect monitoring and big data analysis system, in intelligent early-warning part is needed, mainly has portion in Internet enterprises
Divide and realizes, and on the information system structure of the traditional forms of enterprises, it is still in infancy.
Summary of the invention
It is an object of the invention to propose it is a kind of based on power information system operation/maintenance data health portrait methods of exhibiting and
Its system monitors big data building by the electric power O&M of power information system and draws a portrait about power information health, to analyze
The health status and feature of power information system, so that O&M precision be better achieved.
In order to achieve the above object, according to a first aspect of the present invention, the embodiment of the present invention provides a kind of based on power information system
The health portrait methods of exhibiting of operation/maintenance data, includes the following steps:
Step S1, it obtains raw power monitoring operation/maintenance data and raw power monitoring operation/maintenance data is pre-processed
Obtain preprocessed data;
Step S2, labeling processing is carried out to the preprocessed data, extracts the variable and attribute of the preprocessed data,
And label data is obtained to its variable and attribute setting label;
Step S3, the label data analyze and portrait is drawn a portrait and shown in building based on the analysis results.
Preferably, the step S1 includes:
Raw power monitoring operation/maintenance data to be presented is extracted from the monitoring operation/maintenance data library at power information center;
The Data Integration that isomery multi-data source is carried out to raw power monitoring operation/maintenance data, between different data sources
Data synchronize.
Preferably, in step s 2, each data include multiple labels, and the multiple label is retouched from different angles respectively
State data object.
Preferably, the step S3 includes:
The label data is normalized;
Data analysis is carried out according to the label data after normalized;
Portrait is constructed according to data analysis result and shows portrait.
Preferably, the described label data is normalized includes:
Label data is mapped to [0,1] section by linearized fashion, normalized function is as follows:
Wherein, Xn is the data after normalization, and X is data value, and Xmax and Xmin are respectively the original of label data
The maximum value and minimum value of initial value collection.
Preferably, the described label data is normalized includes:
Mean value and standard deviation to label data carry out data normalization processing, according to the following formula by the original of label data
Beginning data value X is normalized into Xn by Z-score;
Wherein, Xn is the new data after standardization, and X is former data value, and μ is mean value, and σ is standard deviation.
Preferably, the label data progress data according to after normalized, which are analyzed, includes:
The busy index of system is obtained to CPU usage, disk utilization rate, memory usage weighted sum;Wherein, the system
The idle condition for busy index reflection electric system of uniting;The label data includes that CPU usage, disk utilization rate, memory make
With rate;
Fault index N is calculated according to formula N=1.725+0.321t, wherein t is that mean failure rate restores duration, the event
Barrier index N is for evaluating electric system health degree.
In order to achieve the above object, according to a second aspect of the present invention, the embodiment of the present invention provides a kind of based on power information system
The health portrait display systems of operation/maintenance data, for realizing a kind of health portrait based on power information system operation/maintenance data
Methods of exhibiting, comprising:
Data acquisition unit, for obtaining raw power monitoring operation/maintenance data and monitoring operation/maintenance data to the raw power
It is pre-processed to obtain preprocessed data;
Data processing unit extracts the preprocessed data for carrying out labeling processing to the preprocessed data
Variable and attribute, and label data is obtained to its variable and attribute setting label;
Picture exhibition unit, for analyze and construct based on the analysis results drawing a portrait and showing to the label data
Portrait.
Preferably, the data acquisition unit includes the first data acquisition unit and the second data acquisition unit, institute
The first data acquisition unit is stated for extracting raw power to be presented from the monitoring operation/maintenance data library at power information center
Monitor operation/maintenance data;The second data acquisition unit is used to carry out isomery to raw power monitoring operation/maintenance data most
According to the Data Integration in source, the data different data sources are synchronized;
Wherein, each data include multiple labels, and the multiple label describes data object from different angles respectively.
Preferably, the picture exhibition unit includes data normalization subelement, data analysis subelement and portrait building
And showing subelement, the data normalization subelement is for being normalized the label data, the data point
It analyses subelement and is used to carry out data analysis according to the label data after normalized, the portrait building and displaying subelement are used
It draws a portrait in constructing portrait according to data analysis result and showing.
In embodiments of the present invention, using the monitoring operation/maintenance data at power information center, performance data is sufficiently excavated and are being transported
The monitoring operation/maintenance data of value in peacekeeping fault pre-alarming, power information center comes from multiple power information systems, passes through electric power
The monitoring O&M big data building of information centre is drawn a portrait about power information health, to analyze the healthy shape of power information system
State and feature, so that O&M precision be better achieved.
Other features and advantages of the present invention will be illustrated in the following description, also, partly becomes from specification
It obtains it is clear that being emerged from by implementing the present invention.The objectives and other advantages of the invention can by specification,
Specifically noted structure is achieved and obtained in claims and attached drawing.Certainly, implement any of the products of the present invention or
Method does not necessarily require achieving all the advantages described above at the same time.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is a kind of health portrait methods of exhibiting stream based on power information system operation/maintenance data in the embodiment of the present invention one
Cheng Tu.
Fig. 2 shows for the health portrait display systems based on power information system operation/maintenance data a kind of in the embodiment of the present invention two
It is intended to.
Specific embodiment
Various exemplary embodiments, feature and the aspect of the disclosure are described in detail below with reference to attached drawing.It is identical in attached drawing
Appended drawing reference indicate element functionally identical or similar.Although the various aspects of embodiment are shown in the attached drawings, remove
It non-specifically points out, it is not necessary to attached drawing drawn to scale.
In addition, in order to better illustrate the present invention, numerous details is given in specific embodiment below.This
Field is it will be appreciated by the skilled person that without certain details, the present invention equally be can be implemented.In some instances, for this
Means known to the technical staff of field are not described in detail, in order to highlight purport of the invention.
As shown in Figure 1, the embodiment of the present invention provides a kind of health portrait displaying based on power information system operation/maintenance data
Method includes the following steps:
Step S1, it obtains raw power monitoring operation/maintenance data and raw power monitoring operation/maintenance data is pre-processed
Obtain preprocessed data;
Step S2, labeling processing is carried out to the preprocessed data, extracts the variable and attribute of the preprocessed data,
And label data is obtained to its variable and attribute setting label;
Step S3, the label data analyze and portrait is drawn a portrait and shown in building based on the analysis results.
Specifically, according to above processing method, comprehensive all data construct picture by the way of really reflection ontology
Picture, basic building method Case-based Reasoning, class, relationship, the part such as function form.In computer science and information science field,
Ontology refers to certain genus among specific area and its Formal Representation of mutual relationship, finally to describe such one
A portrait system needs the standard knowledge system of a set of digitization, symbolism, formalization, goes to solve by machine, reasoning this set
Knowledge hierarchy formalizes it further;It, also will be according to the pass of real logic simultaneously in addition to reference label logic in building process
Connection relationship is constructed.
Wherein, the step S1 includes following sub-step:
Step S11, raw power monitoring O&M to be presented is extracted from the monitoring operation/maintenance data library at power information center
Data;
Step S12, the Data Integration that isomery multi-data source is carried out to raw power monitoring operation/maintenance data, to different numbers
It is synchronized according to the data between source.
Specifically, the daily monitoring O&M in power information center has accumulated magnanimity monitoring operation/maintenance data, supervised from the magnanimity
Data needed for system health portrait constructs are extracted in control operation/maintenance data, these data include static data and dynamic data, with
And structural data and unstructured data.
The magnanimity monitoring operation/maintenance data at power information center derives from different monitoring system, is mostly lack of standardization, imperfect, again
Multiple, abnormal " dirty data ".It for " dirty data ", should first be cleaned, complete the Data Integration of isomery multi-data source, to realize
Data between different data sources are synchronous.According to certain data standard, the database of connected reference different business systems.For not
Authority data is created, is browsed, deleted and is modified, and is formed unified database, is stored in data warehouse.For imperfect
Data, the general interpolation by the way of machine learning is automatically performed integration.For example, with the presence of database " sky " value, usually
It is replaced with " 0 " or average value.Wherein, abnormal data refers to the data more than regime values range, then for abnormal data
Otherwise processed or deletion need to be screened.
Wherein, in step s 2, each data include multiple labels, and the multiple label describes from different angles respectively
Data object.
Specifically, label refers to the highly refined characteristic symbol mark of Manual definition, it is a kind of presentation side of feature
Formula.There are two obvious characteristics for it: first is that semantization, convenient for helping the meaning it is appreciated that label;Second is that short text, is conducive to machine
Device extraction standard information.Data progress labeling is referred to, initial data is analyzed, extracts monitoring data correlated variables
Or attribute, and " label " is sticked for it.Each label describes data object from different angles, not only had any different but also was related, from
And it is whole to collectively form system monitoring portrait.
Wherein, in the present embodiment label it is inclusive can label, service label, healthy label, maintenance label, management label and
Financial label respectively corresponds different data contents.
Wherein, the step S3 includes following sub-step:
Step S31, the label data is normalized;
Step S32, data analysis is carried out according to the label data after normalized;
Step S33, it constructs portrait according to data analysis result and shows and draw a portrait.
Specifically, the data source for constructing system health portrait is in different monitoring systems including operation system
Deng data represent different feature tags, and unit, number of levels, the value range of data are all different.Some data value models
Especially big (for example file size 0-1T) is enclosed, the training time that will lead to algorithm is too long, restrains slower;The big data of value range
Contribution in pattern classification may also be bigger than normal, and the small contribution data of value range may be very small, between data can
It is more poor than property.Therefore, it is necessary to which feature tag data are normalized, the statistical distribution of unified samples is concluded, is being protected
While holding relativeness between data, it is comparable the data of no comparativity.
In one embodiment, the step S31 includes:
Label data is mapped to [0,1] section by linearized fashion, normalized function is as follows:
Wherein, Xn is the data after normalization, and X is data value, and Xmax and Xmin are respectively the original of label data
The maximum value and minimum value of initial value collection.
It can be realized the equal proportion scaling to primitive character label data;
In another embodiment, the step S31 includes:
Mean value and standard deviation to label data carry out data normalization processing, according to the following formula by the original of label data
Beginning data value X is normalized into Xn by Z-score;
Wherein, Xn is the new data after standardization, and X is former data value, and μ is mean value, and σ is standard deviation.
Specifically, the present embodiment normalized function is capable of handling the distribution of initial data, it is approximately gaussian distribution data,
Data after standardization are in normal distribution, i.e., mean value is 0, and standard deviation 1 changes the distribution of feature to a certain extent.
It should be noted that usually in classification, clustering algorithm, when needing to carry out measured similarity using distance, or
When carrying out dimensionality reduction using PCA technology, 0 mean value standardized method is performed better than;And it be not related to distance metric, covariance meter
When calculation, data attribute do not meet normal distribution, linear function method for normalizing can be used.For example, in image procossing, it will
After RGB image is converted to gray level image, its value is limited to [0,255] section.Therefore, it can be adopted according to specific data content
With different normalized modes.
Wherein, the step S32 is included at least:
The busy index of system is obtained to CPU usage, disk utilization rate, memory usage weighted sum;Wherein, the system
The idle condition for busy index reflection electric system of uniting;
Specifically, in the present embodiment according to the busy index of the system by system performance evaluation ranking score are as follows: performance is critical,
Moderate performance, performance idle and comparison are idle.
Wherein, the label data includes CPU usage, disk utilization rate, memory usage.
Fault index N is calculated according to formula N=1.725+0.321t, wherein t is that mean failure rate restores duration, the event
Barrier index is for evaluating electric system health degree.
Specifically, mean failure rate restores duration t and O&M time linear correlation in electric system, in the present embodiment
According to O&M timing definition fault index, for evaluating electric system health degree, fault index N is higher, then electric system is corresponding
The O&M time it is longer, then illustrate that electric system is more unhealthy, conversely, fault index N is lower, then the corresponding O&M of electric system
Time is shorter, then illustrates that electric system is more healthy.
Wherein, according to the electric system health degree, monitoring system is cooperated to realize intelligent early-warning, with mail, wechat, short message
Etc. modes inform the health status of operation maintenance personnel system in real time, prevent trouble before it happens.
Wherein, the step S33 is included at least:
The busy index of system and the electric system health degree generate portrait signal, and control display unit and show
The portrait signal.
To sum up, as the informationization of monitoring continues to develop, monitoring performance index, alarm data, failure solve data, failure
A large amount of daily monitoring data has been descended in the extensive use accumulation of the systems such as information, monitoring system, O&M process.These day regular data
Just constitute O&M big data, these data substantially can it is objective, be truly reflected system monitoring situation.The present embodiment method benefit
With the big data of these monitoring accumulations, the value for playing data in O&M and fault pre-alarming is sufficiently excavated, is transported by big data
Tie up comprehensive behavior portrait, the health status and feature of analysis system, so that O&M precision be better achieved.
The embodiment of the present invention two also provides a kind of health portrait display systems based on power information system operation/maintenance data, uses
The method described in realization embodiment one, the system comprises:
Data acquisition unit 1, for obtaining raw power monitoring operation/maintenance data and monitoring O&M number to the raw power
According to being pre-processed to obtain preprocessed data;
Data processing unit 2 extracts the preprocessed data for carrying out labeling processing to the preprocessed data
Variable and attribute, and label data is obtained to its variable and attribute setting label;
Picture exhibition unit 3, for analyze and construct based on the analysis results drawing a portrait and opening up to the label data
Show portrait.
Wherein, the data acquisition unit 1 includes the first data acquisition unit 11 and the second data acquisition unit 12,
The first data acquisition unit 11 is used to extract from the monitoring operation/maintenance data library at power information center to be presented original
Power monitoring operation/maintenance data;The second data acquisition unit 12 is used to carry out raw power monitoring operation/maintenance data different
The Data Integration of structure multi-data source synchronizes the data different data sources;
Wherein, each data include multiple labels, and the multiple label describes data object from different angles respectively.
Wherein, the picture exhibition unit 3 includes data normalization subelement 31, data analysis subelement 32 and portrait
Building and displaying subelement 33, the data normalization subelement 31 is for being normalized the label data, institute
It states data analysis subelement 32 and is used to carry out data analysis, the portrait building and exhibition according to the label data after normalized
Show that subelement 33 is drawn a portrait for constructing portrait according to data analysis result and showing.
It should be noted that system described in the present embodiment two is corresponding with one the method for embodiment, accordingly, with respect to embodiment two
The part that the system is not described in detail may refer to above obtain the description section of one the method for embodiment, no longer superfluous herein
It states.
It should also be understood that system described in one the method for embodiment and embodiment two can be implemented in many ways, including
As process, device or system.Method described herein partly can execute this method by being used to indicate processor
Program instruction and the instruction being recorded in non-transient computer readable storage medium and implement, non-transient computer is readable
Storage medium such as hard drive, floppy disk, optical disc (such as small-sized dish (CD) or digital universal dish (DVD)), flash memory
Deng.In some embodiments, program instruction can be stored remotely and via optics or electronic communication link and on network
It is sent.
Various embodiments of the present invention are described above, above description is exemplary, and non-exclusive, and
It is not limited to disclosed each embodiment.Without departing from the scope and spirit of illustrated each embodiment, for this skill
Many modifications and changes are obvious for the those of ordinary skill in art field.The selection of term used herein, purport
In principle, the practical application or to the technological improvement in market for best explaining each embodiment, or make the art its
Its those of ordinary skill can understand each embodiment disclosed herein.
Claims (10)
1. a kind of health portrait methods of exhibiting based on power information system operation/maintenance data, which comprises the steps of:
Step S1, it obtains raw power monitoring operation/maintenance data and raw power monitoring operation/maintenance data is pre-processed to obtain
Preprocessed data;
Step S2, labeling processing is carried out to the preprocessed data, extracts the variable and attribute of the preprocessed data, and right
Its variable and attribute setting label obtain label data;
Step S3, the label data analyze and portrait is drawn a portrait and shown in building based on the analysis results.
2. the health portrait methods of exhibiting based on power information system operation/maintenance data as described in claim 1, which is characterized in that
The step S1 includes:
Raw power monitoring operation/maintenance data to be presented is extracted from the monitoring operation/maintenance data library at power information center;
The Data Integration that isomery multi-data source is carried out to raw power monitoring operation/maintenance data, between the data different data sources
It synchronizes.
3. the health portrait methods of exhibiting based on power information system operation/maintenance data as described in claim 1, which is characterized in that
In step s 2, each data include multiple labels, and the multiple label describes data object from different angles respectively.
4. the health portrait methods of exhibiting based on power information system operation/maintenance data as described in claim 1, which is characterized in that
The step S3 includes:
The label data is normalized;
Data analysis is carried out according to the label data after normalized;
Portrait is constructed according to data analysis result and shows portrait.
5. the health portrait methods of exhibiting based on power information system operation/maintenance data as claimed in claim 4, which is characterized in that
The described label data is normalized include:
Label data is mapped to [0,1] section by linearized fashion, normalized function is as follows:
Wherein, Xn is the data after normalization, and X is data value, and Xmax and Xmin are respectively the original value of label data
The maximum value and minimum value of collection.
6. the health portrait methods of exhibiting based on power information system operation/maintenance data as claimed in claim 4, which is characterized in that
The described label data is normalized include:
Mean value and standard deviation to label data carry out data normalization processing, according to the following formula by the original number of label data
Xn is normalized by Z-score according to value X;
Wherein, Xn is the new data after standardization, and X is former data value, and μ is mean value, and σ is standard deviation.
7. the health portrait methods of exhibiting based on power information system operation/maintenance data as claimed in claim 4, which is characterized in that
The label data according to after normalized carries out data analysis
The busy index of system is obtained to CPU usage, disk utilization rate, memory usage weighted sum;Wherein, the system is numerous
The idle condition of busy index reflection electric system;The label data includes CPU usage, disk utilization rate, memory usage;
Fault index N is calculated according to formula N=1.725+0.321t, wherein t is that mean failure rate restores duration, and the failure refers to
Number N is for evaluating electric system health degree.
8. a kind of health portrait display systems based on power information system operation/maintenance data, any for realizing claim 1-7
Method described in characterized by comprising
Data acquisition unit, for obtaining raw power monitoring operation/maintenance data and being carried out to raw power monitoring operation/maintenance data
Pretreatment obtains preprocessed data;
Data processing unit extracts the variable of the preprocessed data for carrying out labeling processing to the preprocessed data
And attribute, and label data is obtained to its variable and attribute setting label;
Picture is drawn a portrait and shown to picture exhibition unit for analyze and construct based on the analysis results to the label data
Picture.
9. the health portrait display systems based on power information system operation/maintenance data as claimed in claim 8, which is characterized in that
The data acquisition unit includes the first data acquisition unit and the second data acquisition unit, first data acquisition
Unit is used to extract raw power monitoring operation/maintenance data to be presented from the monitoring operation/maintenance data library at power information center;It is described
Second data acquisition unit is used to carry out the raw power monitoring operation/maintenance data Data Integration of isomery multi-data source, right
Data between different data sources synchronize;
Wherein, each data include multiple labels, and the multiple label describes data object from different angles respectively.
10. the health portrait display systems based on power information system operation/maintenance data, feature exist as claimed in claim 8
In, the picture exhibition unit includes data normalization subelement, data analysis subelement and portrait building and shows subelement,
For the data normalization subelement for the label data to be normalized, the data analysis subelement is used for root
Data analysis is carried out according to the label data after normalized, the portrait building and displaying subelement according to data for analyzing
As a result building portrait and displaying portrait.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910695457.1A CN110457193A (en) | 2019-07-30 | 2019-07-30 | Health portrait methods of exhibiting and its system based on power information system operation/maintenance data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910695457.1A CN110457193A (en) | 2019-07-30 | 2019-07-30 | Health portrait methods of exhibiting and its system based on power information system operation/maintenance data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110457193A true CN110457193A (en) | 2019-11-15 |
Family
ID=68484033
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910695457.1A Pending CN110457193A (en) | 2019-07-30 | 2019-07-30 | Health portrait methods of exhibiting and its system based on power information system operation/maintenance data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110457193A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111259947A (en) * | 2020-01-13 | 2020-06-09 | 国网浙江省电力有限公司信息通信分公司 | Power system fault early warning method and system based on multi-mode learning |
CN111445126A (en) * | 2020-03-25 | 2020-07-24 | 国网湖南省电力有限公司 | Power distribution network equipment portrait method and system based on multidimensional data analysis application |
CN111667278A (en) * | 2020-04-27 | 2020-09-15 | 北京国网信通埃森哲信息技术有限公司 | ICT system fault analysis recommendation method and system based on user portrait |
CN112131096A (en) * | 2020-05-07 | 2020-12-25 | 北京国网信通埃森哲信息技术有限公司 | Automatic generation method and device for ICT system fault analysis and auxiliary study and judgment test cases |
CN113064936A (en) * | 2021-03-31 | 2021-07-02 | 深圳供电局有限公司 | User portrait method and system and storage medium |
CN116860562A (en) * | 2023-09-04 | 2023-10-10 | 湖南中青能科技有限公司 | Method and system for monitoring data quality of data center |
CN117596133A (en) * | 2024-01-18 | 2024-02-23 | 山东中测信息技术有限公司 | Service portrayal and anomaly monitoring system and monitoring method based on multidimensional data |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108279650A (en) * | 2018-01-19 | 2018-07-13 | 广东电网有限责任公司珠海供电局 | A kind of evaluation of power equipment state monitoring and command system |
CN109274178A (en) * | 2018-11-14 | 2019-01-25 | 国网甘肃省电力公司电力科学研究院 | A kind of automatic analysis system and method for the preposition operation information of power scheduling |
US20190108044A1 (en) * | 2017-10-09 | 2019-04-11 | Box, Inc. | Deploying data processing service plug-ins into a cloud-based collaboration platform |
CN109685344A (en) * | 2018-12-14 | 2019-04-26 | 广东电网有限责任公司 | A kind of power equipment O&M strategy determines method, apparatus and storage medium |
CN109783322A (en) * | 2018-11-22 | 2019-05-21 | 远光软件股份有限公司 | A kind of monitoring analysis system and its method of enterprise information system operating status |
CN109857831A (en) * | 2019-02-20 | 2019-06-07 | 云南电网有限责任公司信息中心 | A kind of power equipment portrait label system building method based on big data technology |
CN110059917A (en) * | 2019-01-04 | 2019-07-26 | 国网浙江省电力有限公司 | A kind of electric power acquisition exception high-efficient treatment method based on equipment portrait |
-
2019
- 2019-07-30 CN CN201910695457.1A patent/CN110457193A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20190108044A1 (en) * | 2017-10-09 | 2019-04-11 | Box, Inc. | Deploying data processing service plug-ins into a cloud-based collaboration platform |
CN108279650A (en) * | 2018-01-19 | 2018-07-13 | 广东电网有限责任公司珠海供电局 | A kind of evaluation of power equipment state monitoring and command system |
CN109274178A (en) * | 2018-11-14 | 2019-01-25 | 国网甘肃省电力公司电力科学研究院 | A kind of automatic analysis system and method for the preposition operation information of power scheduling |
CN109783322A (en) * | 2018-11-22 | 2019-05-21 | 远光软件股份有限公司 | A kind of monitoring analysis system and its method of enterprise information system operating status |
CN109685344A (en) * | 2018-12-14 | 2019-04-26 | 广东电网有限责任公司 | A kind of power equipment O&M strategy determines method, apparatus and storage medium |
CN110059917A (en) * | 2019-01-04 | 2019-07-26 | 国网浙江省电力有限公司 | A kind of electric power acquisition exception high-efficient treatment method based on equipment portrait |
CN109857831A (en) * | 2019-02-20 | 2019-06-07 | 云南电网有限责任公司信息中心 | A kind of power equipment portrait label system building method based on big data technology |
Non-Patent Citations (1)
Title |
---|
《数据库百科全书》编委会: "《数据库百科全书》", 上海交通大学出版社, pages: 616 - 618 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111259947A (en) * | 2020-01-13 | 2020-06-09 | 国网浙江省电力有限公司信息通信分公司 | Power system fault early warning method and system based on multi-mode learning |
CN111445126A (en) * | 2020-03-25 | 2020-07-24 | 国网湖南省电力有限公司 | Power distribution network equipment portrait method and system based on multidimensional data analysis application |
CN111667278A (en) * | 2020-04-27 | 2020-09-15 | 北京国网信通埃森哲信息技术有限公司 | ICT system fault analysis recommendation method and system based on user portrait |
CN112131096A (en) * | 2020-05-07 | 2020-12-25 | 北京国网信通埃森哲信息技术有限公司 | Automatic generation method and device for ICT system fault analysis and auxiliary study and judgment test cases |
CN112131096B (en) * | 2020-05-07 | 2024-05-24 | 北京国网信通埃森哲信息技术有限公司 | ICT system fault analysis and auxiliary research and judgment test case automatic generation method and device |
CN113064936A (en) * | 2021-03-31 | 2021-07-02 | 深圳供电局有限公司 | User portrait method and system and storage medium |
CN116860562A (en) * | 2023-09-04 | 2023-10-10 | 湖南中青能科技有限公司 | Method and system for monitoring data quality of data center |
CN116860562B (en) * | 2023-09-04 | 2023-11-24 | 湖南中青能科技有限公司 | Method and system for monitoring data quality of data center |
CN117596133A (en) * | 2024-01-18 | 2024-02-23 | 山东中测信息技术有限公司 | Service portrayal and anomaly monitoring system and monitoring method based on multidimensional data |
CN117596133B (en) * | 2024-01-18 | 2024-04-05 | 山东中测信息技术有限公司 | Service portrayal and anomaly monitoring system and monitoring method based on multidimensional data |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110457193A (en) | Health portrait methods of exhibiting and its system based on power information system operation/maintenance data | |
CN104598367B (en) | Data center's event of failure management specialty and method | |
US8504492B2 (en) | Identification of attributes and values using multiple classifiers | |
CN110909165A (en) | Data processing method, device, medium and electronic equipment | |
CN110008343A (en) | File classification method, device, equipment and computer readable storage medium | |
CN111708938B (en) | Method, apparatus, electronic device, and storage medium for information processing | |
CN106371975A (en) | Automatic operation and maintenance early-warning method and system | |
CN108241867B (en) | Classification method and device | |
US10783453B2 (en) | Systems and methods for automated incident response | |
US11443277B2 (en) | System and method for identifying object information in image or video data | |
CN112148881A (en) | Method and apparatus for outputting information | |
CN112559771A (en) | Intelligent capital transaction monitoring method and system based on knowledge graph | |
CN108280021A (en) | A kind of logging level analysis method based on machine learning | |
CN112884452A (en) | Intelligent operation and maintenance multi-source data acquisition visualization analysis system | |
CN110532492A (en) | A kind of forum data management classification system and method | |
CN112861895B (en) | Abnormal article detection method and device | |
CN106846170B (en) | Generator set trip monitoring method and monitoring device thereof | |
CN115660262A (en) | Intelligent engineering quality inspection method, system and medium based on database application | |
CN116468460A (en) | Consumer finance customer image recognition system and method based on artificial intelligence | |
CN110019820A (en) | Main suit and present illness history symptom Timing Coincidence Detection method in a kind of case history | |
CN109800133A (en) | A kind of method, one-stop monitoring alarm platform and the system of unified monitoring alarm | |
CN106202509A (en) | A kind of processing method of log information | |
CN109146306B (en) | Enterprise management system | |
CN111241077A (en) | Financial fraud behavior identification method based on internet data | |
CN115062725B (en) | Hotel income anomaly analysis method and system |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191115 |