CN112559308B - Statistical model-based root alarm analysis method - Google Patents
Statistical model-based root alarm analysis method Download PDFInfo
- Publication number
- CN112559308B CN112559308B CN202011445891.3A CN202011445891A CN112559308B CN 112559308 B CN112559308 B CN 112559308B CN 202011445891 A CN202011445891 A CN 202011445891A CN 112559308 B CN112559308 B CN 112559308B
- Authority
- CN
- China
- Prior art keywords
- alarm
- root
- coefficient
- statistical model
- analysis method
- 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
Images
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
- G06F11/3452—Performance evaluation by statistical analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/32—Monitoring with visual or acoustical indication of the functioning of the machine
- G06F11/324—Display of status information
- G06F11/327—Alarm or error message display
-
- 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
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Human Resources & Organizations (AREA)
- Evolutionary Biology (AREA)
- Entrepreneurship & Innovation (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- Computer Hardware Design (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a statistical model-based root alarm analysis method, which comprises the following steps: collecting alarm information of different manufacturers, normalizing the alarms of the same type of different manufacturers, and setting label classification; performing multi-classification on data of alarm, physical data, link logic and time based on the classification label, calculating a distribution weight by a weight distribution algorithm according to a large amount of sample data to obtain a high-dimensional space coordinate, and generating a high-dimensional space sphere; and based on the high-dimensionality space sphere, rapidly searching an effective solution by using an approximate nearest neighbor search strategy to perform root analysis, and completing the follow-up alarm analysis. The method and the device can improve the efficiency and the accuracy of root association, avoid the condition of input error of partial resource data in manual operation, quickly position the alarm condition on the equipment after new equipment is accessed, and improve the accuracy.
Description
Technical Field
The invention relates to the technical field of transmission networks, in particular to a root alarm analysis method based on a statistical model.
Background
The operation and maintenance work in the communication network is developed towards the direction of intensive management, and operation and maintenance personnel need to monitor and analyze mass alarms of multiple networks, multiple manufacturers and multiple devices; at present, the analysis of root alarms in the industry is generally carried out by analyzing the generation and transmission mechanism of alarm signals, constructing an alarm event tree, forming and analyzing the alarm event tree based on a rule matching mode. However, alarm names of different networks, devices and even devices of different models are different, and how to put together an accurate and applicable rule is a difficult point in the field.
Disclosure of Invention
This section is for the purpose of summarizing some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. In this section, as well as in the abstract and the title of the invention of this application, simplifications or omissions may be made to avoid obscuring the purpose of the section, the abstract and the title, and such simplifications or omissions are not intended to limit the scope of the invention.
The present invention has been made in view of the above-mentioned conventional problems.
Therefore, the technical problem solved by the invention is as follows: the rule-based method is limited by the limited available scenes of the rule knowledge base and cannot process the conditions except the rules; the Bayesian network algorithm is complex, the instantaneity is poor, and the requirement of rapidly positioning faults in management cannot be met; the artificial neural network is suitable for a network with a relatively stable structure, but under the condition that the actual production network has a complex structure and changes frequently, the accuracy and the real-time performance have great influence.
In order to solve the technical problems, the invention provides the following technical scheme: collecting alarm information of different manufacturers, normalizing the alarms of the same type of the different manufacturers, and setting label classification; performing multi-classification on data of alarm, physical data, link logic and time based on the classification label, calculating a distribution weight value through an algorithm according to a large amount of sample data to obtain a high-dimensional space coordinate, and generating a high-dimensional space sphere; and based on the high-dimensionality space sphere, rapidly searching an effective solution by using an approximate nearest neighbor search strategy to perform root analysis, and completing the follow-up alarm analysis.
As a preferred scheme of the statistical model-based root alarm analysis method of the present invention, the statistical model-based root alarm analysis method comprises: the tag classification includes that the physical data includes: the method comprises the steps of setting label classification for a machine room, network elements, boards and ports; the linking logic comprises: linking, channel, service, setting label classification; the time window is defined as a life cycle.
As a preferred embodiment of the statistical model-based root alarm analysis method of the present invention, the method comprises: the weight distribution algorithm comprises the following components of score = (alarm type score coefficient) + (network element coefficient) + (board card type coefficient) + (same link alarm coefficient) + (time interval coefficient) + (manual score) - (manual/automatic score reduction)
As a preferred embodiment of the statistical model-based root alarm analysis method of the present invention, the method comprises: the approximate nearest-neighbor search strategy includes,
d(r,c)≤(1+ε)·d(r*,c),ε≥0
where c represents the query point, r represents the exact solution, ε represents the approximation error, and d represents the distance function.
As a preferred embodiment of the statistical model-based root alarm analysis method of the present invention, the method comprises: the alarm information comprises an alarm position and an alarm reason.
As a preferred embodiment of the statistical model-based root alarm analysis method of the present invention, the method comprises: the alert location may include one or more of,
/Ems＝*/Ne＝*/Shelf＝*/Board＝*/Port＝*
wherein, ems represents the network management, ne represents the network element, shelf represents the frame, board represents the Board, port represents the Port.
As a preferred embodiment of the statistical model-based root alarm analysis method of the present invention, the method comprises: the normalized alarm comprises the steps of performing normalized processing on various types of alarms of multiple manufacturers by defining standard alarm names; and when the matching degree accords with the definition, automatically transferring the standard alarm name.
As a preferred embodiment of the statistical model-based root alarm analysis method of the present invention, the method comprises: the high-dimensional space coordinate comprises an x-axis coordinate generated after the alarm is weighted according to different alarm reasons; matching resource data, and converting the machine room to which the network element belongs into y-axis coordinates by combining the network manager, the network element, the rack, the board card and the port; generating a z-axis coordinate based on the business weighting conversion of the link, the channel and the bearer where the matching port is located; the network element alarm time is a w-axis coordinate; each alarm generates a sphere of the high-dimensional coordinates (x, y, z, w) based on the above-mentioned indices.
As a preferred embodiment of the statistical model-based root alarm analysis method of the present invention, the method comprises: the matching degree model comprises a similar neighbor alarm sphere of an alarm sphere which is searched in an index constructed based on the recommendation algorithm of the similar neighbor, and the similar neighbor range is corrected through a large number of sample root alarm data; setting a time slice area to confirm the diameter length of the minimum ball; and according to the data set in the step, performing high-dimensional space minimum sphere coverage calculation on the basis of the root alarm and the minimum sphere set in the time slice area to obtain the included sub-alarms.
As a preferred embodiment of the statistical model-based root alarm analysis method of the present invention, the method comprises: the effective solution includes a model of the high-dimensional spatial minimum sphere.
The invention has the beneficial effects that: the method can improve the efficiency and the accuracy of root association, avoid the condition of input error of partial resource data in manual operation, quickly position the alarm condition on the equipment after new equipment is accessed, and improve the accuracy.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise. Wherein:
fig. 1 is a basic flow diagram of a root alarm analysis method based on a statistical model according to an embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, specific embodiments accompanied with figures are described in detail below, and it is apparent that the described embodiments are a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present invention, shall fall within the protection scope of the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those specifically described and will be readily apparent to those of ordinary skill in the art without departing from the spirit of the present invention, and therefore the present invention is not limited to the specific embodiments disclosed below.
Furthermore, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
The present invention will be described in detail with reference to the drawings, wherein the cross-sectional views illustrating the structure of the device are not enlarged partially in general scale for convenience of illustration, and the drawings are only exemplary and should not be construed as limiting the scope of the present invention. In addition, the three-dimensional dimensions of length, width and depth should be included in the actual fabrication.
Meanwhile, in the description of the present invention, it should be noted that the terms "upper, lower, inner and outer" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of describing the present invention and simplifying the description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation and operate, and thus, cannot be construed as limiting the present invention. Furthermore, the terms first, second, or third are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The terms "mounted, connected and connected" in the present invention are to be understood broadly, unless otherwise explicitly specified or limited, for example: can be fixedly connected, detachably connected or integrally connected; they may be mechanically, electrically, or directly connected, or indirectly connected through intervening media, or may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Example 1
Referring to fig. 1, an embodiment of the present invention provides a root alarm analysis method based on a statistical model, including:
s1: collecting alarm information of different manufacturers, normalizing the alarms of the same type of different manufacturers, and setting label classification;
it should be noted that the alarm information includes an alarm location and an alarm reason;
wherein, the alarm position sample comprises,
/Ems＝*/Ne＝*/Shelf＝*/Board＝*/Port＝*
intercepting relevant corresponding data for classification: ems represents network management, ne represents network elements, shelf represents racks, board represents Board, and Port represents ports.
Further, the physical data includes: the method comprises the following steps of setting label classification for a machine room, network elements, board cards and ports; the linking logic includes: linking, channel, service, setting label classification; the time window is defined as a life cycle.
Further, normalizing the alarms includes, for example,
normalizing the multi-type alarms of multiple manufacturers by defining standard alarm names; and when the matching degree meets the definition, automatically transferring the alarm name of the standard, wherein the normalized sample is shown in table 1:
table 1: and (5) normalizing the sample table.
S2: performing multi-classification on data of alarm, physical data, link logic and time based on a classification label, calculating a distribution weight by a weight distribution algorithm according to a large amount of sample data to obtain a high-dimensional space coordinate, and generating a high-dimensional space sphere;
it should be noted that, the weight assignment algorithm includes,
score = (alarm type score coefficient) + (network element coefficient) + (board card type coefficient) + (same link alarm coefficient) + (time interval coefficient) + (manual score-adding) - (manual/automatic score-reducing)
Further, the high-dimensional spatial coordinates include,
the alarm is weighted according to different alarm reasons to generate an x-axis coordinate; matching resource data, and converting the machine room to which the network element belongs into y-axis coordinates by combining the network manager, the network element, the rack, the board card and the port; generating a z-axis coordinate based on the business weighting conversion of the link, the channel and the bearer where the matching port is located; the network element alarm time is a w-axis coordinate;
each alarm generates a sphere of high dimensional coordinates (x, y, z, w) based on the above-mentioned indices.
S3: based on a high-dimensionality space sphere, an effective solution is quickly searched by using an approximate nearest neighbor search strategy to perform root analysis, and then the follow-up alarm analysis is completed.
It should be noted that, the approximate nearest neighbor search strategy includes,
d(r,c)≤(1+ε)·d(r*,c),ε≥0
where c represents the query point, r represents the exact solution, ε represents the approximation error, and d represents the distance function.
Where the effective solution includes a model of the minimum sphere in the high-dimensional space.
Further, the matching degree model used in the present embodiment includes,
searching similar neighbor alarm spheres of the alarm spheres in an index constructed based on a similar neighbor recommendation algorithm, and correcting a similar neighbor range through a large amount of sample root alarm data;
setting a time slice area to confirm the diameter length of the minimum ball;
and according to the data set in the step, performing the sub-alarm included in the high-dimensional space minimum ball covering calculation based on the root alarm and the minimum ball set in the time slice area.
Example 2
In order to verify the technical effects adopted in the method, the embodiment adopts the traditional technical scheme and the method of the invention to carry out comparison test, and compares the test results by means of scientific demonstration to verify the real effect of the method.
The traditional technical scheme is as follows: the traditional root analysis scheme uses a rule engine, and judges whether a root relation exists or not by artificially setting rule logic, and more manpower is needed to carry out manual analysis and set rule authentication; in order to verify that the method has higher efficiency and accuracy compared with the traditional method, the method and the system in the embodiment respectively compare the efficiency and the quasi-efficiency of the simulated root alarm by adopting the traditional rule engine root analysis mode.
And (3) testing environment: simulating a large number of alarms in MATLB and including root alarm conditions of the same network element and the same link characteristic, respectively carrying out root analysis by utilizing a rule engine of a traditional method through comparing a plurality of groups of test samples and obtaining test result data; by adopting the method, after the sample data is input, the alarm is subjected to root analysis through the algorithm model, and the test of the method is realized. Each method tests 6 groups of alarm data, and by obtaining the time required by analyzing the root condition of each group of alarm data and the number of root alarms, the method of manually checking the accuracy rate of the root alarms compares and calculates errors, and the results are shown in the following table:
table 1: the experimental results are shown in a comparison table.
From the above table, it can be seen that the time consumption of the rule analysis mode is less than that of the minimum ball coverage model when the alarm amount is less, and the efficiency of the minimum ball coverage model is higher when the alarm amount reaches a certain magnitude; in the experiment, the condition of the root alarm difference is checked manually, and the analysis of the serial relation of partial upstream and downstream ports of the root alarm is analyzed regularly, so that partial root alarm is not analyzed; compared with a regular analysis mode, the high-dimensional space minimum sphere coverage model algorithm reduces manual maintenance of data relationships and improves the accuracy of root alarm analysis.
It should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the claims of the present invention.
Claims (7)
1. A statistical model-based root alarm analysis method is characterized by comprising the following steps:
collecting alarm information of different manufacturers, normalizing the alarms of the same type of different manufacturers, and setting label classification;
performing multi-classification on data of alarm, physical data, link logic and time based on the label classification, calculating a distribution weight through a weight distribution algorithm according to a large amount of sample data to obtain a high-dimensional space coordinate, and generating a high-dimensional space sphere; the label classification comprises that the physical data comprises a machine room, a network element, a board card and a port, and label classification is set; the link logic comprises links, channels and services, and label classification is set; defining a time window range as a life cycle;
the weight value distribution algorithm comprises the following steps of,
score = (alarm type score coefficient) + (network element coefficient) + (board card type coefficient) + (same link alarm coefficient) + (time interval coefficient) + (manual score raising) - (manual score lowering); or the like, or, alternatively,
score = (alarm type score coefficient) + (network element coefficient) + (board card type coefficient) + (same link alarm coefficient) + (time interval coefficient) + (manual score-increase) - (automatic score-decrease);
based on the high-dimensional space sphere, an approximate nearest neighbor search strategy is utilized to quickly search an effective solution for root analysis, and root alarm analysis is completed; the approximate nearest-neighbor search strategy includes,
wherein the content of the first and second substances,
the point of the query is represented as,
the exact solution is represented by the number of points,
the error of the approximation is represented by,
representing a distance function.
2. The statistical model-based root alarm analysis method of claim 1, wherein: the alarm information comprises an alarm position and an alarm reason.
3. The statistical model-based root alarm analysis method of claim 2, wherein: the alert location may include one or more of,
/Ems=*/Ne=*/Shelf=*/Board=*/Port=*
wherein, ems represents the network management, ne represents the network element, shelf represents the frame, board represents the Board, port represents the Port, indicates the alarm information of different manufacturers.
4. The statistical model-based root alarm analysis method of any one of claims 1~3 wherein: the normalization processes alarms of the same type from different manufacturers including,
normalizing the multi-type alarms of multiple manufacturers by defining standard alarm names;
and when the matching degree accords with the definition, automatically transferring the alarm name of the standard.
5. The statistical model-based root alarm analysis method of claim 4, wherein: the high-dimensional spatial coordinates include,
the alarm is weighted according to different alarm reasons to generate an x-axis coordinate;
matching resource data, and converting the machine room to which the network element belongs, and combining the network management, the network element, the rack, the board card and the port to be weighted into y-axis coordinates;
generating a z-axis coordinate based on the business weighting conversion of the link, the channel and the bearer where the matching port is located;
the network element alarm time is a w-axis coordinate;
each alarm generates a sphere of high dimensional coordinates (x, y, z, w) based on the above coordinates.
6. The statistical model-based root alarm analysis method of claim 5, wherein: the matching degree model used for completing root alarm analysis by utilizing an approximate nearest neighbor search strategy to quickly search an effective solution based on the high-dimensional space sphere comprises,
searching similar neighbor alarm spheres of the alarm spheres in an index constructed based on the approximate nearest neighbor search strategy, and correcting the similar neighbor range through a large amount of sample root alarm data;
setting a time slice area to confirm the diameter length of the minimum ball;
and according to the set data, carrying out high-dimensional space minimum sphere coverage calculation on the basis of the root alarm and the minimum sphere set in the time slice area to obtain the included sub-alarms.
7. The statistical model-based root alarm analysis method of claim 1 or 6, wherein: the effective solution includes a model of the smallest sphere in a high dimensional space.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011445891.3A CN112559308B (en) | 2020-12-11 | 2020-12-11 | Statistical model-based root alarm analysis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011445891.3A CN112559308B (en) | 2020-12-11 | 2020-12-11 | Statistical model-based root alarm analysis method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112559308A CN112559308A (en) | 2021-03-26 |
| CN112559308B true CN112559308B (en) | 2023-02-28 |
Family
ID=75062286
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011445891.3A Active CN112559308B (en) | 2020-12-11 | 2020-12-11 | Statistical model-based root alarm analysis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112559308B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1916969A (en) * | 2006-08-07 | 2007-02-21 | 浙江大学 | Method for generating reaction accompany movement based on hybrid control |
| WO2011159255A2 (en) * | 2010-06-14 | 2011-12-22 | Blue Prism Technologies Pte Ltd | High-dimensional data analysis |
| CN102708288A (en) * | 2012-04-28 | 2012-10-03 | 东北大学 | Brain-computer interface based doctor-patient interaction method |
| CN104791233A (en) * | 2015-04-30 | 2015-07-22 | 西安交通大学 | Reciprocating compressor fault diagnosis method based on improved ball vector machine closure ball solution acquisition |
| CN105427043A (en) * | 2015-11-20 | 2016-03-23 | 江苏省电力公司扬州供电公司 | Improved nearest neighbor algorithm-based power grid alarm analysis method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080021897A1 (en) * | 2006-07-19 | 2008-01-24 | International Business Machines Corporation | Techniques for detection of multi-dimensional clusters in arbitrary subspaces of high-dimensional data |
| JP2008112412A (en) * | 2006-10-31 | 2008-05-15 | Sony Corp | Data processing device, data processing method, and program |
-
2020
- 2020-12-11 CN CN202011445891.3A patent/CN112559308B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1916969A (en) * | 2006-08-07 | 2007-02-21 | 浙江大学 | Method for generating reaction accompany movement based on hybrid control |
| WO2011159255A2 (en) * | 2010-06-14 | 2011-12-22 | Blue Prism Technologies Pte Ltd | High-dimensional data analysis |
| CN102708288A (en) * | 2012-04-28 | 2012-10-03 | 东北大学 | Brain-computer interface based doctor-patient interaction method |
| CN104791233A (en) * | 2015-04-30 | 2015-07-22 | 西安交通大学 | Reciprocating compressor fault diagnosis method based on improved ball vector machine closure ball solution acquisition |
| CN105427043A (en) * | 2015-11-20 | 2016-03-23 | 江苏省电力公司扬州供电公司 | Improved nearest neighbor algorithm-based power grid alarm analysis method |
Non-Patent Citations (2)
| Title |
|---|
| 基于数据挖掘的动环监控系统告警相关性研究;贾海涛;《中国优秀硕士学位论文全文数据库 信息科技辑》;20180615;全文 * |
| 高维空间网络告警智能关联分析方法;匡立伟等;《邮电设计技术》;20181231;第1-4节，图1-3 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112559308A (en) | 2021-03-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111505433B (en) | Low-voltage transformer area indoor variable relation error correction and phase identification method | |
| CN108196132B (en) | Method for evaluating electromagnetic compatibility in system | |
| CN113780436B (en) | Complex network key node identification method based on comprehensive degree | |
| CN110705887A (en) | Low-voltage transformer area operation state comprehensive evaluation method based on neural network model | |
| CN110895495A (en) | Human error analysis method, system, computer device and storage medium | |
| CN113466627A (en) | Power grid fault prediction method suitable for severe weather | |
| CN114676749A (en) | Power distribution network operation data abnormity judgment method based on data mining | |
| CN110544047A (en) | Bad data identification method | |
| CN113887729A (en) | Fault diagnosis method for low-voltage power line carrier communication system | |
| CN113065223A (en) | Multi-level probability correction method for digital twin model of tower mast cluster | |
| CN111709668A (en) | Power grid equipment parameter risk identification method and device based on data mining technology | |
| CN112559308B (en) | Statistical model-based root alarm analysis method | |
| CN117156484B (en) | Communication base station energy consumption analysis system and method based on 5G technology | |
| CN116956189A (en) | Current abnormality detection system, method, electronic equipment and medium | |
| CN115937079A (en) | YOLO v 3-based rapid detection method for defects of power transmission line | |
| CN116151799A (en) | BP neural network-based distribution line multi-working-condition fault rate rapid assessment method | |
| CN113449966B (en) | Gypsum board equipment inspection method and system | |
| CN115907461A (en) | Electric power engineering method based on mechanism derivation equation | |
| CN115801538A (en) | Site server application asset deep identification method, system and equipment | |
| CN113408656B (en) | Power failure level classification method suitable for being caused by meteorological change | |
| CN112732773B (en) | Method and system for checking uniqueness of relay protection defect data | |
| CN114139802A (en) | Real-time optimization scheduling method based on basin water regime change trend analysis model | |
| CN113792923A (en) | Visual scheduling window method based on power failure sensitivity prediction model | |
| CN114124721A (en) | Topology automatic identification method based on power line carrier | |
| CN113705973A (en) | Neural network learning-based power grid security risk online evaluation method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |