CN105354614B - A kind of electric network information O&M active forewarning method based on big data - Google Patents
A kind of electric network information O&M active forewarning method based on big data Download PDFInfo
- Publication number
- CN105354614B CN105354614B CN201510695185.7A CN201510695185A CN105354614B CN 105354614 B CN105354614 B CN 105354614B CN 201510695185 A CN201510695185 A CN 201510695185A CN 105354614 B CN105354614 B CN 105354614B
- Authority
- CN
- China
- Prior art keywords
- early warning
- threshold value
- information
- grid nodes
- information resources
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000011156 evaluation Methods 0.000 claims abstract description 35
- 238000012423 maintenance Methods 0.000 claims abstract description 26
- 238000005065 mining Methods 0.000 claims abstract description 10
- 238000012544 monitoring process Methods 0.000 claims description 15
- 238000013178 mathematical model Methods 0.000 claims description 12
- 230000004913 activation Effects 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000013138 pruning Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 11
- 238000007619 statistical method Methods 0.000 abstract description 4
- 230000008569 process Effects 0.000 abstract description 3
- 238000011161 development Methods 0.000 description 5
- 230000007774 longterm Effects 0.000 description 5
- 238000012098 association analyses Methods 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 238000004140 cleaning Methods 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000000611 regression analysis Methods 0.000 description 2
- 239000000523 sample Substances 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 230000000505 pernicious effect Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000001373 regressive effect Effects 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Abstract
The invention belongs to information technology fields, it discloses a kind of electric network information O&M active forewarning method system based on big data to include status early warning, threshold value early warning, become early warning, trending early warning, evaluation early warning fastly and be associated with early warning, realizes effective combination of information O&M active forewarning method Yu information operation and maintenance system;Realize big data technology in the popularization and application in electric network information O&M field, based on big data technology, efficient statistical analysis, mining analysis and the real-time stream process of information operation/maintenance data, effective mining data value are realized, it realizes active forewarning, promotes the efficiency of information O&M.
Description
Technical field
The invention belongs to information technology fields, are related to a kind of method for early warning of electric network information O&M, and in particular to Yi Zhongji
In the electric network information O&M active forewarning method of big data.
Background technique
In recent years, with the fast development of informatization, grid company information system quantity is continuously increased, to daily fortune
Dimension proposes higher standard and demand.The passive O&M mould for being alerted and being repaired after the failure occurs is mainly taken at present
Formula, this mode cause operation maintenance personnel that daily most of the time and energy are all spent " passive fire fighting " simple and duplicate in processing
In problem, not only gets half the result with twice the effort but also often will appear pernicious chain reaction.Lack before the failure occurs to information operation and maintenance system
The ability to give warning in advance lacks the ability that O&M hidden danger is positioned and analyzed, and needs to realize the master aimed at prevention
Dynamic O&M mode.
Find that memory leak issue, archive log are asked by the statistical conditions analysis to test unit's information O&M failure
Most information O&M failures such as topic and database connectivity problem can obtain relevant information before generation, pass through risk assessment
Early warning can be carried out to information operation and maintenance system, prevent failure.In addition, with the development of information O&M business, mass data
It is continuously generated and accumulates, but at present information operation/maintenance data value is not able to achieve to only some most basic analysis means.It realizes
Information O&M active forewarning based on big data can carry out effective analysis mining to information operation/maintenance data, it occurs in failure
Preceding realization fault location, accident analysis and fault pre-alarming promote company's information O&M efficiency, promote corporate business development.
There is also following insufficient in terms of information O&M active forewarning at present:
One, the information operation and maintenance system of current company realizes post-event alarm, and tentatively realizes Real-time Alarm, but unreal
Existing active forewarning, lacks the ability for just carrying out early warning to it when hidden danger and exception occurs in information operation and maintenance system, and shortage solves hidden
The ability of trouble lacks matched management system;
Two, fail to establish information O&M active forewarning method system, lack information O&M active forewarning theories integration and
Realization rate;
Three, fail effectively to manage information operation/maintenance data using big data technology, fail to establish scientific and reasonable fortune
Row data analyze system and business item analyzes system, need to promote means of numerical analysis, realize operation/maintenance data value.
Summary of the invention
Goal of the invention: the purpose of the present invention is to solve information O&M network system is pre- without active in the prior art above
Alert deficiency provides a kind of electric network information O&M active forewarning method based on big data, thus for the safety fortune of network system
Row provides a strong guarantee.
Technical solution: the electric network information O&M active forewarning method of the present invention based on big data, the purpose is to this
What sample was realized,
A kind of electric network information O&M active forewarning method based on big data, which comprises the steps of:
M01: status early warning, by being detected and being obtained as a result, information is provided to the information resources between grid nodes
Source state is divided into normal condition, lost contact state and unstable state three classes;
If information resources are in lost contact state, alerted;If information resources play pendulum, need
Carry out status early warning;
M02: threshold value early warning is compared by the numerical value of the information resources to grid nodes with preset threshold value,
If exceeding threshold value, early warning or alarm are carried out;
M03: become early warning, including lateral early warning and longitudinal early warning fastly;
Lateral early warning be any grid nodes information resources numerical value with and the node side by side similar node numerical value
It is compared, then carries out early warning beyond certain threshold value, establish the mathematical model that two grid nodes information resources numerical value compare:
In formula, SkIndicate the load of kth platform equipment, SiIndicate the load of i-th equipment, n is total number of devices, n be greater than
1 natural number, α is fast variable threshold value, by user configuration;
Longitudinal early warning is that the numerical value of the information resources of any grid nodes is compared with the historical data of the node itself,
Early warning is then carried out beyond certain threshold value, data cleansing, limitation are carried out by the history data to the nodal information resource
The reasonable range of operation of the node, establishes the mathematical model of the range of operation:
In formula, TmaxAnd TminThe respectively upper threshold value and lower threshold value of the grid nodes, RmaxAnd RminRespectively pass through data
The history data maximum value and minimum value of cleaning, A are the average value of historical data, and L represents the reasonable fortune of the grid nodes
Line range;
M04: trending early warning continuously monitors the information resources of grid nodes, by the threshold value of warning of grid nodes,
Difference, the target rate of growth this four Index Establishment mathematical models between early warning activation threshold value, index current value and threshold value of warning,
Judge that current electric grid node operating status, the mathematical model are as follows:
In formula, V is the current value of the grid nodes, V0For the grid nodes one acquire time difference t before numerical value,
α, β are correction value, and Z is trending early warning threshold value, wherein α, β and Z are by user configuration, TwFor threshold value of warning, N is early warning triggering
Threshold value;
M05: evaluation early warning carries out real-time monitoring to the information resources of grid nodes, and establishes grid nodes scoring
Mathematical model:
In formula, S0For the initial score that can be customized by users setting, m, n, p are respectively the alarm in O&M monitoring cycle
Event level quantity, early warning event level quantity, maintenance event level quantity, α and f be respectively events at different levels weight and time
Number, S are final evaluation score, are customized by the user setting threshold value, realize evaluation early warning;
M06: association early warning carries out data correlation rule mining algorithms to the data of each grid nodes, with Apriori algorithm
Based on, Boolean matrix is constructed, and pass through branch's screening and optimizing, the binomial most to occupancy computing resource in Apriori algorithm
Frequent Set calculating task carries out beta pruning to improve efficiency of algorithm, analyzes the relevance between grid nodes by data, and carry out
Monitoring.
A kind of electric network information O&M active forewarning method based on big data as described above, which is characterized in that at least wrap
Include any two in step M01~M06.
The utility model has the advantages that the beneficial effects of the present invention are:
One, information O&M active forewarning method system: the information O&M active forewarning side of the method for the present invention design is devised
Law system includes status early warning, threshold value early warning, becomes early warning, trending early warning, evaluation early warning fastly and be associated with the big method of early warning six.Wherein
Fast change early warning includes lateral early warning and longitudinal early warning.
Two, effective combination of information O&M active forewarning method Yu information operation and maintenance system is realized: information operation and maintenance system
Warning level is respectively as follows: index grade, page-level, infrastructure grade and information system grade from low to high.The active of index levels is pre-
It is alert to be based on status early warning, threshold value early warning, become early warning, trending early warning, evaluation early warning fastly and be associated with early warning;The active of page level is pre-
It is alert to be based on status early warning, threshold value early warning, evaluation early warning;The active forewarning of infrastructure rank is based on status early warning, evaluation early warning
Be associated with early warning;The active forewarning of information system rank be based on evaluation early warning be associated with early warning.
Three, it realizes big data technology in the popularization and application in national grid information O&M field: being based on big data technology, realize
Efficient statistical analysis, mining analysis and the real-time stream process of information operation/maintenance data, effective mining data value, are realized actively pre-
It is alert, promote the efficiency of information O&M.
The present invention innovate by big data technology be applied to information O&M active forewarning in, devise including status early warning,
Threshold value early warning becomes early warning, trending early warning, evaluation early warning and the information O&M active forewarning method body for being associated with the big method of early warning six fastly
System realizes that active forewarning and failure are high by acquiring to effective monitoring of information operation and maintenance system and data before the failure occurs
Effect solves, and promotes the efficiency of information O&M, reduces O&M cost, promotes O&M business development.
Detailed description of the invention
Fig. 1 is a kind of electric network information O&M active forewarning method system architecture diagram based on big data of the present invention.
Specific embodiment
In order to deepen the understanding of the present invention, below in conjunction with embodiment and attached drawing, the invention will be further described, should
The examples are only for explaining the invention, is not intended to limit the scope of the present invention..
A kind of electric network information O&M active forewarning method based on big data, as shown in Figure 1, including status early warning, threshold value
Early warning becomes early warning, trending early warning, evaluation early warning fastly and is associated with six class submethod of early warning, is illustrated individually below:
M01: status early warning
Status early warning is by hardware or the whether reachable state to judge information resources of service, by its state
Early warning is realized in monitoring.
It realizes status early warning, first has to judge whether information resources are reachable, by the information resources between grid nodes
It is detected and is obtained as a result, system detection in every five minutes at present once, determines whether information resources respond.If receiving letter
Cease the reply data of resource, then it is assumed that its is reachable, otherwise, if waiting time-out to be answered, determines that its is unreachable.
Determine information resources whether up under the premise of, its state is divided into three kinds: normal condition, lost contact state and not
Stable state.Normal condition indicates that information resources are every time reachable, and lost contact state indicates that information resources are unreachable twice in succession, no
Stable state indicates that information resources are often unreachable, but lost contact standard is not achieved.Current unstable state judgment principle is:
Because every five minutes detect once information resources, can be detected within a working day 288 times, if in this 288 times at least
Have 3 times it is unreachable and discontinuous, then it is assumed that it plays pendulum.If information resources are in lost contact state, need to it
It is alerted;If information resources play pendulum, need to carry out status early warning to it.
M02: threshold value early warning
By the way that information resources are arranged with the threshold value of Risk-warning, the currently monitored data are compared with threshold value of warning, such as
Fruit monitoring data are not within the scope of corresponding threshold value of warning, then it is assumed that monitoring object meets early-warning conditions, generates early warning event.It passes
The information resources threshold value of system be by unified standard or operation maintenance personnel manual setting by rule of thumb, this normally result in threshold value with
Actual conditions are not inconsistent, and cause to miss early warning on a large scale, cause not early warning in the case where generation problem.The method of the present invention is abundant
Information resources range of operation is obtained by effective analysis to historical data using big data technology, and based on the analysis results certainly
Adapt to setting threshold value.Meanwhile system provides interface and carries out manual modification to information resources threshold value for operation maintenance personnel, makes up system
It is insufficient.
M03: become early warning fastly
Information resources monitoring data needs are compared with homogeneous data, if variation is excessively violent, difference is greater than certain ratio
Example, then it is assumed that monitored resource is likely to be in large variation, needs to generate early warning event.It is fast become early warning include lateral early warning and
Longitudinal early warning two ways.
Lateral early warning indicate the numerical value of the information resources of any grid nodes with and the node similar node arranged side by side number
Value is compared, and mainly for load balancing cluster, if the load of certain equipment is far longer than other equipment in cluster, is recognized
To need to carry out Risk-warning to it.The mathematical model of lateral early warning is as follows:
In formula, SkIndicate the load of kth platform equipment, SiIndicate the load of i-th equipment, n is total number of devices, n be greater than
1 natural number, α is fast variable threshold value, by user configuration.The algorithm is by calculating certain apparatus of load and entire cluster load mean value
Difference judge whether the equipment needs to carry out early warning.
Longitudinal early warning indicates that the historical data of the numerical value and the node itself of the information resources of any grid nodes is compared
Compared with the early warning of formation is mainly based upon big data statistical analysis technique, carries out mining analysis to historical data, and analysis is tied
Fruit is applied to information O&M active forewarning model.Longitudinal early warning carries out early warning from two dimensions of working time and non-working time
Design.Wherein the working time is traditionally arranged to be 8:30~17:00 of Mon-Fri, and other times are non-working time, work
Making time and non-working time can be configured by user.
Longitudinal early warning carries out data cleansing by history data to index, and abnormality value removing is fallen, then to going through
History data are for statistical analysis, determine its maximum value, minimum value and average value, then determine the reasonable range of operation of index.It is vertical
It is as follows to early warning mathematical model:
In formula, TmaxAnd TminThe respectively upper threshold value and lower threshold value of the grid nodes, RmaxAnd RminRespectively pass through data
The history data maximum value and minimum value of cleaning, A are the average value of historical data, and L represents the reasonable fortune of the grid nodes
Line range.
M04: trending early warning
Trending early warning judges whether resource can reach early warning triggering by the trend analysis to information resources monitoring data
Condition.Trending early warning is divided into short-term trend early warning and long-term trend early warning.
Short-term trend early warning passes through the threshold value of warning of grid nodes, early warning activation threshold value, index current value and threshold value of warning
Between difference, this four indexs of the target rate of growth realize the Risk-warnings of short-term information resources.Short-term trend early warning number
It is as follows to learn model:
In formula, V is the current value of the grid nodes, V0For the grid nodes one acquire time difference t before numerical value,
α, β are correction value, and Z is trending early warning threshold value, wherein by user configuration, Tw is threshold value of warning by α, β and Z, and N is early warning triggering
Threshold value.When index value is lower than early warning activation threshold value, early warning not will do it;Index value meets or exceeds early warning activation threshold value
When, by short-term trend warning algorithm, the short term risk early warning of information resources may be implemented.
The long-run development trend of resource is predicted in long-term trend early warning by the regression analysis in data mining, thus
Realize information resources Risk-warning.In the case where clear trend prediction objectives, using daily index average value as going through
A basic value in history data tentatively establishes long-term trend regression forecasting mould by the regression analysis to metric history data
Type.The forecast analysis of information resources long-term trend is carried out using long-term trend regressive prediction model, and in actual moving process,
Using real-time running data to model carry out verification and it is perfect.
M05: evaluation early warning
Based on the evaluation of index, the evaluation of optimized integration facility.Based on the evaluation of infrastructure, information is analyzed
System topological framework realizes the architecture evaluation of information system;Whether there is response with active probe index, including information system
And based on response time index, Information System Reliability evaluation is realized;On the basis of information system maintenance situation, letter is realized
Breath system maintenance evaluation.With the architecture evaluation, Information System Reliability evaluation and information system maintenance evaluation of information system
Based on, Risk of Information System evaluation is realized, to realize the Risk-warning of information system.
Real-time monitoring is carried out to the information resources of grid nodes, and establishes the mathematical model of grid nodes scoring:
In formula, S0For the initial score that can be customized by users setting, m, n, p are respectively the alarm in O&M monitoring cycle
Event level quantity, early warning event level quantity, maintenance event level quantity, α and f be respectively events at different levels weight and time
Number, S are final evaluation score, are customized by the user setting threshold value, realize evaluation early warning.
M06: association early warning
Association analysis is also known as association mining, is exactly to run in the magnanimity of information system and its infrastructure and using data
In, search frequent mode, association, correlation or the causal structure being present between project set or object set.Association is abundant
Using big data association analysis means, analysis is associated to all kinds of indexs of information system and its infrastructure, is excavated related
Mode realizes resource early warning.
According to information O&M active forewarning demand, with data correlation rule mining algorithms --- the Apriori that industry is general
Based on algorithm, and the advanced idea of many related scholars is combined to carry out two o'clock improvement to algorithm: first is by constructing cloth
That matrix, simplifies the calculating to support, reduces the number of reading database;Second is by branch's screening and optimizing plan
Slightly, the binomial Frequent Set calculating task most to occupancy computing resource in Apriori algorithm has carried out effective beta pruning.By above
Two o'clock is improved, and efficiency of algorithm is greatly improved, and is realized and is excavated to the efficient analysis of information resources correlation rule, to realize information fortune
It ties up active forewarning and big data theoretical basis is provided.
Association early warning makes full use of big data acquisition technique, big data memory technology and distributed computing and data mining
Technology runs the magnanimity of information system and its infrastructure and is acquired using data, divides historical failure information
Class is excavated and association analysis, to obtain information O&M active forewarning model.
Based on system to the monitoring of information resources and the operation monitoring of system acquisition and service application data, believed using six kinds
Breath O&M active forewarning method is analyzed in real time data and early warning, with regard to carrying out active forewarning and solving to ask before failure occurs
Topic, Optimal Maintenance strategy promote O&M efficiency.
As shown in table 1, the warning level of information operation and maintenance system is divided into index grade, page-level, infrastructure grade and information system
Irrespective of size (arranges) from low to high.Infrastructure includes database, middleware, host equipment, the network equipment, safety equipment and storage
Equipment.The active forewarning of page level refers to that information system main page is monitored and is acquired, and judges whether it has sound
It answers, judges whether its response time is more than baseline time, and realize the active of information system main page by reliability evaluation
Early warning.
The active forewarning of index levels be based on status early warning, threshold value early warning, fastly become early warning, trending early warning, evaluation early warning and
It is associated with early warning;The active forewarning of page level is based on status early warning, threshold value early warning, evaluation early warning;The active of infrastructure rank
Early warning is based on status early warning, evaluation early warning and is associated with early warning;The active forewarning of information system rank is based on evaluation early warning and association
Early warning.
Information operation and maintenance system | Active forewarning method |
Index | Status early warning, threshold value early warning become early warning, trending early warning, evaluation early warning, association early warning fastly |
The page | Status early warning, threshold value early warning, evaluation early warning |
Infrastructure | Status early warning, evaluation early warning, association early warning |
Information system | Evaluate early warning, association early warning |
Table 1
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Within mind and principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (2)
1. a kind of electric network information O&M active forewarning method based on big data, which comprises the steps of:
M01: status early warning, by being detected and being obtained to the information resources between grid nodes as a result, by information resources shape
State is divided into normal condition, lost contact state and unstable state three classes;
If information resources are in lost contact state, alerted;If information resources play pendulum, need to carry out
Status early warning;
M02: threshold value early warning is compared by the numerical value of the information resources to grid nodes with preset threshold value, if super
Threshold value out then carries out early warning or alarm;
M03: become early warning, including lateral early warning and longitudinal early warning fastly;
Lateral early warning be the information resources of any grid nodes numerical value with and the arranged side by side similar node of the node numerical value progress
Compare, then carry out early warning beyond certain threshold value, establishes the mathematical model that two grid nodes information resources numerical value compare:
In formula, SkIndicate the load of kth platform equipment, SiIndicate the load of i-th equipment, n is total number of devices, and n is greater than 1
Natural number, λ is fast variable threshold value, by user configuration;Longitudinal early warning is the numerical value and the node of the information resources of any grid nodes
The historical data of itself is compared, and then carries out early warning beyond certain threshold value, passes through the history number to the nodal information resource
According to data cleansing is carried out, the reasonable range of operation of the node is limited, the mathematical model of the range of operation is established:
In formula, TmaxAnd TminThe respectively numerical value upper threshold value and lower threshold value of the information resources of grid nodes, RmaxAnd RminRespectively
Historical data maximum value and minimum value by data cleansing, A are the average value of historical data, and L represents the conjunction of the grid nodes
Manage range of operation;
M04: trending early warning continuously monitors the information resources of grid nodes, passes through the threshold value of warning of grid nodes, early warning
Difference, the target rate of growth this four Index Establishment mathematical models between activation threshold value, index current value and threshold value of warning, judgement
Current electric grid node operating status, the mathematical model are as follows:
In formula, V is the current value of the grid nodes, V0For numerical value of the grid nodes before one acquires time difference t, α, β are
Correction value, Z are trending early warning threshold value, wherein by user configuration, Tw is threshold value of warning by ε, β and Z, and N is early warning activation threshold value;
M05: evaluation early warning carries out real-time monitoring to the information resources of grid nodes, and establishes the mathematics of grid nodes scoring
Model:
In formula, S0For the initial score that can be customized by users setting, m, d, p are respectively the alarm event in O&M monitoring cycle
Number of levels, early warning event level quantity, maintenance event level quantity, α and f are respectively the weight and number of events at different levels, and S is
Final evaluation score, is customized by the user the threshold value of the numerical value of the information resources of setting grid nodes, realizes evaluation early warning;
M06: association early warning carries out data correlation rule mining algorithms to the data of each grid nodes, using Apriori algorithm as base
Plinth constructs Boolean matrix, and by branch's screening and optimizing, to occupying in Apriori algorithm, the most binomial of computing resource is frequent
Collect calculating task and carry out beta pruning to improve efficiency of algorithm, analyzes the relevance between grid nodes by data, and be monitored.
2. a kind of electric network information O&M active forewarning method based on big data according to claim 1, which is characterized in that
Including at least any two in step M01~M06.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510695185.7A CN105354614B (en) | 2015-10-21 | 2015-10-21 | A kind of electric network information O&M active forewarning method based on big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510695185.7A CN105354614B (en) | 2015-10-21 | 2015-10-21 | A kind of electric network information O&M active forewarning method based on big data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105354614A CN105354614A (en) | 2016-02-24 |
CN105354614B true CN105354614B (en) | 2019-03-26 |
Family
ID=55330581
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510695185.7A Active CN105354614B (en) | 2015-10-21 | 2015-10-21 | A kind of electric network information O&M active forewarning method based on big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105354614B (en) |
Families Citing this family (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106444694A (en) * | 2016-05-30 | 2017-02-22 | 重庆大学 | System abnormal condition pre-warning technology under big data |
CN107066369A (en) * | 2017-04-25 | 2017-08-18 | 上海德衡数据科技有限公司 | A kind of O&M pre-alarm and prevention system prototype based on polycaryon processor |
CN107066368A (en) * | 2017-04-25 | 2017-08-18 | 上海德衡数据科技有限公司 | A kind of O&M pre-alarm and prevention system based on multi-sensor information fusion |
CN107918803B (en) * | 2017-10-24 | 2021-07-23 | 深圳供电局有限公司 | Equipment annual operation and maintenance plan checking method |
CN109085463B (en) * | 2018-08-24 | 2020-09-08 | 广西电网有限责任公司贵港供电局 | Intelligent power grid fault positioning method and device |
CN109443396B (en) * | 2018-09-18 | 2022-03-04 | 中国电力科学研究院有限公司 | Method and system for judging overlarge energy supply intensity difference |
CN110186507A (en) * | 2019-05-08 | 2019-08-30 | 浙江大学 | A kind of Multifunctional intelligent safe monitoring system |
CN110298452B (en) * | 2019-05-14 | 2022-07-22 | 国网浙江省电力有限公司嘉兴供电公司 | Power grid active operation and maintenance early warning method based on big data |
CN110596486B (en) * | 2019-08-26 | 2022-02-18 | 国创移动能源创新中心(江苏)有限公司 | Intelligent early warning operation and maintenance method and system for charging pile |
CN110851670A (en) * | 2019-10-25 | 2020-02-28 | 袁茂银 | Underground cable fault repairing method and device |
CN110647093B (en) * | 2019-11-13 | 2021-01-08 | 上海迈内能源科技有限公司 | Intelligent monitoring system and monitoring method for power system based on big data analysis |
CN112199348A (en) * | 2020-08-21 | 2021-01-08 | 李苗 | Fire fighting monitoring method and device based on big data, computer equipment and storage medium |
CN112580961B (en) * | 2020-12-15 | 2022-09-09 | 国网电力科学研究院有限公司 | Power grid information system based operation risk early warning method and device |
CN112737109B (en) * | 2020-12-18 | 2022-05-31 | 北京国电通网络技术有限公司 | Real-time safety early warning system of smart power grids |
CN114157017A (en) * | 2021-10-18 | 2022-03-08 | 国网安徽省电力有限公司马鞍山供电公司 | Power grid information operation and maintenance active early warning method based on big data |
CN114999095B (en) * | 2022-05-23 | 2023-11-14 | 山东建筑大学 | Building electrical fire monitoring method and system based on time and space fusion |
CN116186017B (en) * | 2023-04-25 | 2023-07-28 | 蓝色火焰科技成都有限公司 | Big data collaborative supervision method and platform |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2003195922A (en) * | 2001-12-25 | 2003-07-11 | Mitsubishi Electric Corp | Standard information data managing method and system |
CN103473626A (en) * | 2013-08-20 | 2013-12-25 | 国家电网公司 | Security protection method based on integrated dispatching data network operation and maintenance system |
CN204119396U (en) * | 2014-10-28 | 2015-01-21 | 天津豪世达科技有限公司 | The large online data monitor and early warning system of a kind of power transmission network |
CN104504525A (en) * | 2014-12-26 | 2015-04-08 | 国家电网公司 | Method for realizing power-grid equipment failure prewarning through big data mining technology |
CN104950187A (en) * | 2014-11-27 | 2015-09-30 | 国网山东省电力公司应急管理中心 | Power-grid-GIS-based lightning analysis and early warning method and system thereof |
-
2015
- 2015-10-21 CN CN201510695185.7A patent/CN105354614B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2003195922A (en) * | 2001-12-25 | 2003-07-11 | Mitsubishi Electric Corp | Standard information data managing method and system |
CN103473626A (en) * | 2013-08-20 | 2013-12-25 | 国家电网公司 | Security protection method based on integrated dispatching data network operation and maintenance system |
CN204119396U (en) * | 2014-10-28 | 2015-01-21 | 天津豪世达科技有限公司 | The large online data monitor and early warning system of a kind of power transmission network |
CN104950187A (en) * | 2014-11-27 | 2015-09-30 | 国网山东省电力公司应急管理中心 | Power-grid-GIS-based lightning analysis and early warning method and system thereof |
CN104504525A (en) * | 2014-12-26 | 2015-04-08 | 国家电网公司 | Method for realizing power-grid equipment failure prewarning through big data mining technology |
Non-Patent Citations (2)
Title |
---|
基于状态监测的预警管理系统研究与应用;张栋梁等;《电子设计工程》;20110630;第1节 |
综述变电设备状态检修中试验数据的处理方法;李正超;《电力建设》;20120228;第1节 |
Also Published As
Publication number | Publication date |
---|---|
CN105354614A (en) | 2016-02-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105354614B (en) | A kind of electric network information O&M active forewarning method based on big data | |
CN106209432B (en) | Network equipment inferior health method for early warning and device based on dynamic threshold | |
CN106054104B (en) | A kind of intelligent electric meter failure real-time predicting method based on decision tree | |
CN106204330A (en) | A kind of power distribution network intelligent diagnosis system | |
CN103337043B (en) | The method for early warning of electric power communication device running status and system | |
CN102055187B (en) | Large-scale interconnected power grid spinning reserve risk assessment method based on state space division method | |
CN106933693A (en) | A kind of data-base cluster node failure self-repairing method and system | |
CN109240126A (en) | A kind of distributed application services monitoring system and method with simulated operation function | |
CN109884473A (en) | A kind of electric power overhaul system and method | |
CN113708493A (en) | Cloud edge cooperation-based power distribution terminal operation and maintenance method and device and computer equipment | |
CN115063058B (en) | Comprehensive energy situation perception system based on model driving and data driving | |
CN113191687B (en) | Elastic power distribution network panoramic information visualization method and system | |
CN106570567A (en) | Main network maintenance multi-constraint multi-target evaluation expert system and optimization method | |
CN107656156A (en) | A kind of equipment fault diagnosis and running status appraisal procedure and system based on cloud platform | |
CN115062901A (en) | Assessment method for electric power informatization comprehensive performance | |
CN106649034B (en) | Visual intelligent operation and maintenance method and platform | |
CN117391675A (en) | Data center infrastructure operation and maintenance management method | |
CN107862459A (en) | Metering equipment state evaluation method and system based on big data | |
CN108037387A (en) | The equipment fault analysis method and device collected based on cluster | |
CN107482767A (en) | A kind of distributed measure line loss and the apparatus and method for for monitoring power network | |
CN116345687A (en) | User behavior safety early warning system of power monitoring system | |
CN109472449A (en) | Urban Rail Transit Signal equipment health status evaluation method based on group decision | |
CN115936663A (en) | Maintenance method and device for power system | |
CN115514099A (en) | Electric power utilization safety inspection system and method | |
CN105809257B (en) | Trigger type state maintenance method based on power communication network |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |