CN104504525A - Method for realizing power-grid equipment failure prewarning through big data mining technology - Google Patents

Method for realizing power-grid equipment failure prewarning through big data mining technology Download PDF

Info

Publication number
CN104504525A
CN104504525A CN201410829285.XA CN201410829285A CN104504525A CN 104504525 A CN104504525 A CN 104504525A CN 201410829285 A CN201410829285 A CN 201410829285A CN 104504525 A CN104504525 A CN 104504525A
Authority
CN
China
Prior art keywords
equipment
data
record
defect
fault
Prior art date
Application number
CN201410829285.XA
Other languages
Chinese (zh)
Inventor
方泉
潘留兴
卜晓
Original Assignee
国家电网公司
江苏省电力公司
江苏电力信息技术有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 国家电网公司, 江苏省电力公司, 江苏电力信息技术有限公司 filed Critical 国家电网公司
Priority to CN201410829285.XA priority Critical patent/CN104504525A/en
Publication of CN104504525A publication Critical patent/CN104504525A/en

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/06Resources, workflows, human or project management, e.g. organising, planning, scheduling or allocating time, human or machine resources; Enterprise planning; Organisational models
    • G06Q10/063Operations research or analysis
    • G06Q10/0635Risk analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/06Resources, workflows, human or project management, e.g. organising, planning, scheduling or allocating time, human or machine resources; Enterprise planning; Organisational models
    • G06Q10/063Operations research or analysis
    • G06Q10/0639Performance analysis
    • G06Q10/06395Quality analysis or management
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06Electricity, gas or water supply
    • Y04S10/60

Abstract

The invention discloses a method for realizing power-grid equipment failure prewarning through big data mining technology. The method includes the following steps: acquiring main factors causing a power-grid equipment failure through historical failure record and defect data analysis; performing correlation analysis on safety accident factors; building a risk evaluation model through correlation among historical experience, basic data and factors; performing model selection on application scenes of power-grid safety accidents, and performing data preparation, data screening and data mining according to the scenes; graphically displaying data after being analyzed through a decision making platform, and verifying the data. By performing big data analysis on the historical failure record and defect record, tendency that the power-grid equipment is in a failure is prejudged, and safety prewarning is sent out, so that probability that a power grid is in a safety accident is lowered, and running reliability of the power grid is guaranteed.

Description

By the method for large data mining technology implementation grid equipment fault pre-alarming

Technical field

The invention belongs to power domain, relate to a kind of method of grid equipment fault pre-alarming, specifically a kind of method by large data mining technology implementation grid equipment fault pre-alarming

Background technology

Along with the fast development in digital information epoch, quantity of information is also in explosive increase situation.In power industry, the growth of data volume also presents similar situation, power industry large scale business enterprise's informatization in recent years, along with the all-round construction of intelligent power network of future generation, the data of the links such as generating, transmission of electricity, power transformation, scheduling, distribution, electricity consumption rapidly increase and reach a certain scale, but the lean of power industry develops the growth of the data volume that can not only rely on, how from the data of magnanimity, to identify available data, assess potential power grid security accident potential, become key one step of electric power trade information.Therefore, integrate the critical datas such as the electrical network production run of current scatter in each system, adopt the correlation techniques such as data mining analysis, the rule that mining data is hidden behind and incidence relation, for power network development provides prediction and decision support.

Summary of the invention

The object of this invention is to provide a kind of method by large data mining technology implementation grid equipment fault pre-alarming, the method is by carrying out data mining to the malfunction history data in current PMS (safe production management system), thus analyze the trend that grid equipment breaks down, and analysis result is carried out visual representing by combined with intelligent decision-making platform, achieve the early warning of power grid security accident, improve mains supply safe reliability.

Object of the present invention is achieved through the following technical solutions:

By a method for large data mining technology implementation grid equipment fault pre-alarming, it is characterized in that the method comprises the following steps:

1) by historical failure record and defect data analysis, the principal element causing grid equipment is obtained;

2) correlation analysis is carried out to security incident factor;

3) by building risk evaluation model to incidence relation between historical experience, basic data and factor;

4) carry out the application scenarios type selecting of power grid security accident, and carry out data encasement, data screening, data mining according to scene;

5) by decision-making platform, graphical representation is carried out to the data after analysis, and data are verified.

In the present invention, historical failure record comprises power transformation failure logging in safe production management system, distribution fault repairing record, and power transformation failure logging comprises trip time, protection act, reclosing situation, processes and pass through and analysis, liability cause, technical reason analysis; Distribution fault repairing record comprises regionalism, fault-time, protection act situation, failure modes, failure process, fault analysis; Defective data comprises power transformation defect record, transmission of electricity defect record and distribution defect record, and power transformation defect record comprises device type, electric pressure, defect content, defect property, technical reason, liability cause, discovery time; Transmission of electricity defect record comprises discovery time, classification of defects, defect content, defect content remarks; Distribution defect record comprises discovery date, device class, defect rank, defect content, defect content remarks, defect cause; What wherein caused by physical environment accounts for 33.65%; What caused by ageing equipment accounts for 22.48%; What caused by outside destroy accounts for 21.68%; What caused by user's reason accounts for 17.88%; By operation maintenance bad cause account for 2.15%; What caused by equipment quality accounts for 1.98%; What caused by other reasons accounts for 0.18%.

Bayesian algorithm is adopted: Bayes's classification is the general name of oneclass classification algorithm, and this kind of algorithm all based on Bayes' theorem, therefore is referred to as Bayes's classification when 1, building risk evaluation model and data mining; The application scenarios carrying out the excavation of grid equipment fault in the present system of Naive Bayes Classification is as follows:

31) category set C={y is established 0=0, y 1=1}, wherein C represents category set, and 0 expression is not broken down, and 1 expression is broken down;

32) I={x is established 1, x 2... .x m, 1≤i≤m, wherein I cries item set to be sorted, wherein each element X irepresent an item to be sorted;

33) X={a is established 1, a 2a n, 1≤j≤n is an item to be sorted, a jfor a characteristic attribute of X.X can be understood as the record (ID comprising following field in fault mining model, SB_ID, DYDJ, DW_ID, BDS_XL_ID, SJLX, SYHJ, JLZT, TYRQ, TZSJ, YEAR, DUR_DAY) wherein, ID is the logic ID of equipment, SB_ID is the physical I D of equipment, DYDJ is the electric pressure of equipment, DW_ID is the unit ID of equipment, higher level's (electric substation or circuit) ID of BDS_XL_ID indication equipment, SJLX is the type of equipment, SYHJ is the environment for use of equipment, JLZT is the state of equipment, TYRQ is putting into operation the date of equipment, statistics month when TZSJ is unit trip, YEAR is the time of equipment, DUR_DAY is the interval month of unit trip time and the time of putting into operation.

Each characteristic attribute a iall classify, such as this attribute of electric pressure, DYDJ<=20000 is masked as 1, i.e. a j=1, DYDJ>20000 is masked as 2, i.e. a j=2.

34) according to information above, under calculating the prerequisite that a certain bar record occurred, the probability of device fails.According to Bayes's classification, the computing formula of the probability of device fails is p (y i| x)=p (x|y i) p (y i)/p (x)

Calculate 34) in each conditional probability, specific as follows:

341) P (x)=1/ sample size, i.e. 1/m; P (y 0)=p (y 1)=1/2.

342) statistics obtains estimating in the conditional probability of each characteristic attribute lower of all categories; Namely

In training sample, in trouble-proof sample, attribute is respectively a 1, a 2a nprobability:

P(a 1|y 0),P(a 2|y 0),…,P(a n|y 0)

Wherein, P (a 1| y 0)=p (a 1=1|y 0) * p (a 1=2|y 0) ... * p (a 1=m|y 0),

For characteristic attribute electric pressure:

P (a 1=1|y 0sample size/trouble-proof training sample quantity of electric pressure≤20000 in)=trouble-proof training sample;

P (a 1=2|y 0sample size/trouble-proof training sample quantity of electric pressure >20000 in)=trouble-proof training sample

In training sample, in the sample broken down, attribute is respectively a 1, a 2a nprobability:

P(a 1|y 1),P(a 2|y 1),…,P(a n|y 1)

Wherein, P (a 1| y 1)=p (a 1=1|y 1) * p (a 1=2|y 1) ... * p (a 1=m|y 1),

For characteristic attribute electric pressure:

P (a 1=1|y 1the training sample quantity of the sample size/break down of electric pressure≤20000 in the training sample of)=break down;

P (a 1=2|y 1the training sample quantity of the sample size/break down of electric pressure >20000 in the training sample of)=break down

343) because each characteristic attribute is conditional sampling, then following derivation is had according to Bayes' theorem:

in native system fault mining model, two results can be obtained: under the prerequisite of certain record existence (be equivalent to x), its probability broken down, and trouble-proof probability.

The method is by carrying out large data analysis to historical failure record and defect record, thus analyze the trend that grid equipment breaks down, and analysis result is carried out visual representing by combined with intelligent decision-making platform, achieve the early warning of power grid security accident, thus reduce the probability of electrical network generation power grid security accident, guarantee operation of power networks reliability.

Accompanying drawing explanation

Fig. 1 is the process flow diagram of Naive Bayes Classification.

Embodiment

A method for grid equipment fault pre-alarming is realized by several technology of large data mining, specific as follows:

1) analyzed by the historical failure data of Jiangsu electric power and cause the principal element of power grid security accident and the incidence relation between them.

2) by building risk evaluation model to incidence relation between historical experience, basic data and factor;

3) carry out the application scenarios type selecting of power grid security accident, and carry out data encasement, data screening, data mining according to scene.

4) by decision-making platform, graphical representation is carried out to the data after analysis, and data are verified.

2, carry out data mining and model construction by Naive Bayes Classification Algorithm to electrical network historical Device fault data, Bayes's classification is the general name of oneclass classification algorithm, and this kind of algorithm all based on Bayes' theorem, therefore is referred to as Bayes's classification; The application scenarios carrying out the excavation of grid equipment fault in the present system of Naive Bayes Classification is as follows:

31) category set C={y is established 0=0, y 1=1}, wherein C represents category set, and 0 expression is not broken down, and 1 expression is broken down;

32) I={x is established 1, x 2... .x m, 1≤i≤m, wherein I cries item set to be sorted, wherein each element X irepresent an item to be sorted;

33) X={a is established 1, a 2a n, 1≤j≤n is an item to be sorted, a jfor a characteristic attribute of X.X can be understood as the record (ID comprising following field in fault mining model, SB_ID, DYDJ, DW_ID, BDS_XL_ID, SJLX, SYHJ, JLZT, TYRQ, TZSJ, YEAR, DUR_DAY) wherein, ID is the logic ID of equipment, SB_ID is the physical I D of equipment, DYDJ is the electric pressure of equipment, DW_ID is the unit ID of equipment, higher level's (electric substation or circuit) ID of BDS_XL_ID indication equipment, SJLX is the type of equipment, SYHJ is the environment for use of equipment, JLZT is the state of equipment, TYRQ is putting into operation the date of equipment, statistics month when TZSJ is unit trip, YEAR is the time of equipment, DUR_DAY is the interval month of unit trip time and the time of putting into operation.

Each characteristic attribute a iall classify, such as this attribute of electric pressure, DYDJ<=20000 is masked as 1, i.e. a j=1, DYDJ>20000 is masked as 2, i.e. a j=2.

34) according to information above, under calculating the prerequisite that a certain bar record occurred, the probability of device fails.According to Bayes's classification, the computing formula of the probability of device fails is p (y i| x)=p (x|y i) p (y i)/p (x)

Calculate 34) in each conditional probability, specific as follows:

341) P (x)=1/ sample size, i.e. 1/m; P (y 0)=p (y 1)=1/2.

342) statistics obtains estimating in the conditional probability of each characteristic attribute lower of all categories; Namely

In training sample, in trouble-proof sample, attribute is respectively a 1, a 2a nprobability:

P(a 1|y 0),P(a 2|y 0),…,P(a n|y 0)

Wherein, P (a 1| y 0)=p (a 1=1|y 0) * p (a 1=2|y 0) ... * p (a 1=m|y 0),

For characteristic attribute electric pressure:

P (a 1=1|y 0sample size/trouble-proof training sample quantity of electric pressure≤20000 in)=trouble-proof training sample;

P (a 1=2|y 0sample size/trouble-proof training sample quantity of electric pressure >20000 in)=trouble-proof training sample

In training sample, in the sample broken down, attribute is respectively a 1, a 2a nprobability:

P(a 1|y 1),P(a 2|y 1),…,P(a n|y 1)

Wherein, P (a 1| y 1)=p (a 1=1|y 1) * p (a 1=2|y 1) ... * p (a 1=m|y 1),

For characteristic attribute electric pressure:

P (a 1=1|y 1the training sample quantity of the sample size/break down of electric pressure≤20000 in the training sample of)=break down;

P (a 1=2|y 1the training sample quantity of the sample size/break down of electric pressure >20000 in the training sample of)=break down

343) because each characteristic attribute is conditional sampling, then following derivation is had according to Bayes' theorem:

in native system fault mining model, two results can be obtained: under the prerequisite of certain record existence (be equivalent to x), its probability broken down, and trouble-proof probability.

Claims (3)

1., by a method for large data mining technology implementation grid equipment fault pre-alarming, it is characterized in that the method comprises the following steps:
1) by historical failure record and defect data analysis, the principal element causing grid equipment is obtained;
2) correlation analysis is carried out to security incident factor;
3) by building risk evaluation model to incidence relation between historical experience, basic data and factor;
4) carry out the application scenarios type selecting of power grid security accident, and carry out data encasement, data screening, data mining according to scene;
5) by decision-making platform, graphical representation is carried out to the data after analysis, and data are verified.
2. the method by large data mining technology implementation grid equipment fault pre-alarming according to claim 1, it is characterized in that: step 1) in, historical failure record comprises power transformation failure logging in safe production management system, distribution fault repairing record, and power transformation failure logging comprises trip time, protection act, reclosing situation, processes and pass through and analysis, liability cause, technical reason analysis; Distribution fault repairing record comprises regionalism, fault-time, protection act situation, failure modes, failure process, fault analysis; Defective data comprises power transformation defect record, transmission of electricity defect record and distribution defect record, and power transformation defect record comprises device type, electric pressure, defect content, defect property, technical reason, liability cause, discovery time; Transmission of electricity defect record comprises discovery time, classification of defects, defect content, defect content remarks; Distribution defect record comprises discovery date, device class, defect rank, defect content, defect content remarks, defect cause; What wherein caused by physical environment accounts for 33.65%; What caused by ageing equipment accounts for 22.48%; What caused by outside destroy accounts for 21.68%; What caused by user's reason accounts for 17.88%; By operation maintenance bad cause account for 2.15%; What caused by equipment quality accounts for 1.98%; What caused by other reasons accounts for 0.18%.
3. according to claim 1 by the method for large data mining technology implementation grid equipment fault pre-alarming, it is characterized in that: step 3) and step 4) in, bayesian algorithm is adopted: Bayes's classification is the general name of oneclass classification algorithm when building risk evaluation model and data mining, this kind of algorithm all based on Bayes' theorem, therefore is referred to as Bayes's classification; The application scenarios carrying out the excavation of grid equipment fault in the present system of Naive Bayes Classification is as follows:
31) category set C={y is established 0=0, y 1=1}, wherein C represents category set, and 0 expression is not broken down, and 1 expression is broken down;
32) I={x is established 1, x 2... .x m, 1≤i≤m, wherein I cries item set to be sorted, wherein each element X irepresent an item to be sorted;
33) X={a is established 1, a 2a n, 1≤j≤n is an item to be sorted, a jfor a characteristic attribute of X.X can be understood as the record (ID comprising following field in fault mining model, SB_ID, DYDJ, DW_ID, BDS_XL_ID, SJLX, SYHJ, JLZT, TYRQ, TZSJ, YEAR, DUR_DAY) wherein, ID is the logic ID of equipment, SB_ID is the physical I D of equipment, DYDJ is the electric pressure of equipment, DW_ID is the unit ID of equipment, higher level's (electric substation or circuit) ID of BDS_XL_ID indication equipment, SJLX is the type of equipment, SYHJ is the environment for use of equipment, JLZT is the state of equipment, TYRQ is putting into operation the date of equipment, statistics month when TZSJ is unit trip, YEAR is the time of equipment, DUR_DAY is the interval month of unit trip time and the time of putting into operation.
Each characteristic attribute a iall classify, such as this attribute of electric pressure, DYDJ<=20000 is masked as 1, i.e. a j=1, DYDJ>20000 is masked as 2, i.e. a j=2.
34) according to information above, under calculating the prerequisite that a certain bar record occurred, the probability of device fails.According to Bayes's classification, the computing formula of the probability of device fails is p (y i| x)=p (x|y i) p (y i)/p (x)
Calculate 34) in each conditional probability, specific as follows:
341) P (x)=1/ sample size, i.e. 1/m; P (y 0)=p (y 1)=1/2.
342) statistics obtains estimating in the conditional probability of each characteristic attribute lower of all categories; Namely
In training sample, in trouble-proof sample, attribute is respectively a 1, a 2a nprobability:
P(a 1|y 0),P(a 2|1 0),…,P(a n|y 0)
Wherein, P (a 1| y 0)=p (a 1=1|y 0) * p (a 1=2|y 0) ... * p (a 1=m|y 0),
For characteristic attribute electric pressure:
P (a 1=1|y 0sample size/trouble-proof training sample quantity of electric pressure≤20000 in)=trouble-proof training sample;
P (a 1=2|y 0electric pressure in)=trouble-proof training sample
Sample size/trouble-proof training sample quantity of >20000
In training sample, in the sample broken down, attribute is respectively a 1, a 2a nprobability:
P(a 1|y 1),P(a 2|y 1),…,P(a n|y 1)
Wherein, P (a 1| y 1=p (a 1=1|y 1) * p (a 1=2|y 1) ... * p (a 1=m|y 1),
For characteristic attribute electric pressure:
P (a 1=1|y 1in the training sample of)=break down electric pressure≤20000 sample size/
The training sample quantity broken down;
P (a 1=2|y 1electric pressure in the training sample of)=break down
The training sample quantity of the sample size of >20000/break down
343) because each characteristic attribute is conditional sampling, then following derivation is had according to Bayes' theorem:
in native system fault mining model, two results can be obtained: under the prerequisite of certain record existence, be equivalent to x, its probability broken down, and trouble-proof probability.
CN201410829285.XA 2014-12-26 2014-12-26 Method for realizing power-grid equipment failure prewarning through big data mining technology CN104504525A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201410829285.XA CN104504525A (en) 2014-12-26 2014-12-26 Method for realizing power-grid equipment failure prewarning through big data mining technology

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201410829285.XA CN104504525A (en) 2014-12-26 2014-12-26 Method for realizing power-grid equipment failure prewarning through big data mining technology

Publications (1)

Publication Number Publication Date
CN104504525A true CN104504525A (en) 2015-04-08

Family

ID=52945920

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201410829285.XA CN104504525A (en) 2014-12-26 2014-12-26 Method for realizing power-grid equipment failure prewarning through big data mining technology

Country Status (1)

Country Link
CN (1) CN104504525A (en)

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105320126A (en) * 2015-10-21 2016-02-10 中国南方电网有限责任公司 Secondary equipment hidden danger excavation method based on big data technology
CN105322519A (en) * 2015-11-02 2016-02-10 湖南大学 Big data fusion analysis and running state monitoring method for intelligent power distribution network
CN105354614A (en) * 2015-10-21 2016-02-24 国家电网公司 Big data based power grid information operation and maintenance active early-warning method
CN105868373A (en) * 2016-03-31 2016-08-17 国网江西省电力公司信息通信分公司 Method and device for processing key data of power service information system
CN105913126A (en) * 2016-03-25 2016-08-31 北京用尚科技股份有限公司 Transformer station intelligent alarm model method for big data and cloud environment
CN106093703A (en) * 2016-06-07 2016-11-09 湖南大学 The identification of a kind of intelligent distribution network fault and localization method
CN106373032A (en) * 2016-09-09 2017-02-01 国网江苏省电力公司电力科学研究院 Distribution network high-fault region identification method
CN106649479A (en) * 2016-09-29 2017-05-10 国网山东省电力公司电力科学研究院 Probability graph-based transformer state association rule mining method
CN106843101A (en) * 2016-12-13 2017-06-13 国网北京市电力公司 Data analysis processing method and device
CN106897743A (en) * 2017-02-22 2017-06-27 广州市勤思网络科技有限公司 The anti-cheating big data detection method of movable attendance checking based on Bayesian model
CN107230015A (en) * 2017-05-25 2017-10-03 天津大学 A kind of power distribution network toughness appraisal procedure based on system information entropy
CN107807309A (en) * 2017-10-27 2018-03-16 广东电网有限责任公司中山供电局 A kind of transmission line malfunction method for early warning and system based on big data
CN108287327A (en) * 2017-12-13 2018-07-17 广西电网有限责任公司电力科学研究院 Metering automation terminal fault diagnostic method based on Bayes's classification

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103426123A (en) * 2013-07-24 2013-12-04 国家电网公司 Power grid fault risk evaluation method based on rough set theory
CN103871004A (en) * 2014-03-31 2014-06-18 国家电网公司 Power distribution network failure cause analyzing method based on expert system and D-S evidence theory

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103426123A (en) * 2013-07-24 2013-12-04 国家电网公司 Power grid fault risk evaluation method based on rough set theory
CN103871004A (en) * 2014-03-31 2014-06-18 国家电网公司 Power distribution network failure cause analyzing method based on expert system and D-S evidence theory

Cited By (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105320126A (en) * 2015-10-21 2016-02-10 中国南方电网有限责任公司 Secondary equipment hidden danger excavation method based on big data technology
CN105354614A (en) * 2015-10-21 2016-02-24 国家电网公司 Big data based power grid information operation and maintenance active early-warning method
CN105320126B (en) * 2015-10-21 2018-05-01 中国南方电网有限责任公司 A kind of secondary device hidden danger method for digging based on big data technology
CN105354614B (en) * 2015-10-21 2019-03-26 国家电网公司 A kind of electric network information O&M active forewarning method based on big data
CN105322519A (en) * 2015-11-02 2016-02-10 湖南大学 Big data fusion analysis and running state monitoring method for intelligent power distribution network
CN105322519B (en) * 2015-11-02 2018-02-13 湖南大学 A kind of intelligent distribution network big data convergence analysis and method for monitoring operation states
CN105913126A (en) * 2016-03-25 2016-08-31 北京用尚科技股份有限公司 Transformer station intelligent alarm model method for big data and cloud environment
CN105868373B (en) * 2016-03-31 2019-12-27 国网江西省电力有限公司信息通信分公司 Method and device for processing key data of power business information system
CN105868373A (en) * 2016-03-31 2016-08-17 国网江西省电力公司信息通信分公司 Method and device for processing key data of power service information system
CN106093703A (en) * 2016-06-07 2016-11-09 湖南大学 The identification of a kind of intelligent distribution network fault and localization method
CN106373032B (en) * 2016-09-09 2019-07-19 国网江苏省电力公司电力科学研究院 The high-incidence region discrimination method of Distribution Network Failure based on big data
CN106373032A (en) * 2016-09-09 2017-02-01 国网江苏省电力公司电力科学研究院 Distribution network high-fault region identification method
CN106649479A (en) * 2016-09-29 2017-05-10 国网山东省电力公司电力科学研究院 Probability graph-based transformer state association rule mining method
CN106843101A (en) * 2016-12-13 2017-06-13 国网北京市电力公司 Data analysis processing method and device
CN106897743B (en) * 2017-02-22 2020-05-05 广州市勤思网络科技有限公司 Mobile attendance anti-cheating big data detection method based on Bayesian model
CN106897743A (en) * 2017-02-22 2017-06-27 广州市勤思网络科技有限公司 The anti-cheating big data detection method of movable attendance checking based on Bayesian model
CN107230015A (en) * 2017-05-25 2017-10-03 天津大学 A kind of power distribution network toughness appraisal procedure based on system information entropy
CN107230015B (en) * 2017-05-25 2020-08-21 天津大学 Power distribution network toughness evaluation method based on system information entropy
CN107807309A (en) * 2017-10-27 2018-03-16 广东电网有限责任公司中山供电局 A kind of transmission line malfunction method for early warning and system based on big data
CN108287327A (en) * 2017-12-13 2018-07-17 广西电网有限责任公司电力科学研究院 Metering automation terminal fault diagnostic method based on Bayes's classification

Similar Documents

Publication Publication Date Title
Panteli et al. Power system resilience to extreme weather: fragility modeling, probabilistic impact assessment, and adaptation measures
Zhang et al. Big data analytics in smart grids: a review
Comes et al. Measuring disaster resilience: The impact of hurricane sandy on critical infrastructure systems.
US9158035B2 (en) System and method of automated acquisition, correlation and display of power distribution grid operational parameters and weather events
Kjølle et al. Risk analysis of critical infrastructures emphasizing electricity supply and interdependencies
AU2013257529B2 (en) Monitoring system
Shafiee A fuzzy analytic network process model to mitigate the risks associated with offshore wind farms
US20130232094A1 (en) Machine learning for power grid
Jia et al. Risk-based power system security analysis considering cascading outages
CN102236841B (en) Method for handling accidents of electric power system
US8126804B2 (en) Decision support systems and methods for complex networks
Guikema Natural disaster risk analysis for critical infrastructure systems: An approach based on statistical learning theory
Castillo Risk analysis and management in power outage and restoration: A literature survey
US20130207801A1 (en) Approach for prioritizing network alerts
CN103197177B (en) A kind of transformer fault diagnosis analytical approach based on Bayesian network
Zhou et al. Modeling weather-related failures of overhead distribution lines
Power et al. Emergency situation awareness: Twitter case studies
ES2545481T3 (en) System and method for the predictive maintenance of a battery pack by means of temporary signal processing
CN103793853B (en) Condition of Overhead Transmission Lines Based appraisal procedure based on two-way Bayesian network
CN103279831B (en) For the management system implementation method of evaluation software test mass and development ability
Mensah et al. Efficient resilience assessment framework for electric power systems affected by hurricane events
CN102779230B (en) State analysis and maintenance decision judging method of power transformer system
Kosek Contextual anomaly detection for cyber-physical security in smart grids based on an artificial neural network model
Wang et al. Copula‐based model for wind turbine power curve outlier rejection
CN105092999B (en) Positioned using the power quality events of multiple instructions

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
WD01 Invention patent application deemed withdrawn after publication
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20150408