CN113191074B - Machine room power supply parameter detection method for data center - Google Patents
Machine room power supply parameter detection method for data center Download PDFInfo
- Publication number
- CN113191074B CN113191074B CN202110396105.3A CN202110396105A CN113191074B CN 113191074 B CN113191074 B CN 113191074B CN 202110396105 A CN202110396105 A CN 202110396105A CN 113191074 B CN113191074 B CN 113191074B
- Authority
- CN
- China
- Prior art keywords
- power supply
- machine room
- parameters
- preset
- target power
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 50
- 230000002159 abnormal effect Effects 0.000 claims abstract description 37
- 238000010586 diagram Methods 0.000 claims abstract description 33
- 238000012423 maintenance Methods 0.000 claims abstract description 21
- 239000013598 vector Substances 0.000 claims description 42
- 238000011156 evaluation Methods 0.000 claims description 39
- 230000011218 segmentation Effects 0.000 claims description 20
- 238000010248 power generation Methods 0.000 claims description 18
- 238000000034 method Methods 0.000 claims description 17
- 238000004458 analytical method Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 10
- 238000012935 Averaging Methods 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 238000013135 deep learning Methods 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 5
- 230000032683 aging Effects 0.000 claims description 4
- 238000010937 topological data analysis Methods 0.000 claims description 4
- AFSYRVDDZGJTIL-UHFFFAOYSA-N oxydibutanol Chemical compound CC(O)CCOCCC(C)O AFSYRVDDZGJTIL-UHFFFAOYSA-N 0.000 claims 2
- 230000002035 prolonged effect Effects 0.000 claims 1
- 230000009286 beneficial effect Effects 0.000 abstract description 12
- 230000005251 gamma ray Effects 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000006403 short-term memory Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/06—Power analysis or power optimisation
-
- 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- General Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Tourism & Hospitality (AREA)
- Software Systems (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Biophysics (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Mathematical Physics (AREA)
- Game Theory and Decision Science (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a machine room power supply parameter detection method for a data center, which comprises the following steps: acquiring machine room power supply topological relation data, and generating a machine room power supply topological relation diagram according to the machine room power supply topological relation data; acquiring target power supply equipment in the machine room power supply topological relation diagram, and configuring a power supply parameter detection node for the target power supply equipment; and receiving the power supply parameters of the corresponding target power supply equipment sent by the power supply parameter detection node, comparing the power supply parameters with standard power supply parameters corresponding to the target power supply equipment, and marking the target power supply equipment in the machine room power supply topological relation diagram and carrying out first alarm prompt when the power supply parameters of the target power supply equipment are determined to be abnormal parameters according to the comparison result. The beneficial effects are that: the accuracy of the detection result is guaranteed by comparing the power supply parameters, the timeliness of maintenance is guaranteed by marking the fault power supply equipment, and the property loss of a user is reduced.
Description
Technical Field
The invention relates to the technical field of machine room monitoring, in particular to a machine room power supply parameter detection method for a data center.
Background
Along with the rapid development of the information technology, along with the gradual development of smart cities, a large number of central machine rooms are required to be established to ensure the information construction requirement, equipment in the machine rooms becomes necessary support for the information construction, and if the machine room equipment is unstable in operation and even frequently breaks down, larger direct and indirect economic losses are caused to ensure the stable operation of the machine room equipment, so that the equipment becomes an important point of the information construction.
The operation of the equipment in the machine room is guaranteed to be stable, the working state of the power supply equipment is important, in the prior art, the power supply parameters are not intelligently analyzed and managed, when the power supply parameters are abnormal, the alarm can not be timely given, the position information of the power supply equipment with faults can not be known, and huge economic loss is caused.
Disclosure of Invention
The present invention aims to solve, at least to some extent, one of the technical problems in the above-described technology. Therefore, a first object of the present invention is to provide a method for detecting power supply parameters of a machine room for a data center, which ensures accuracy of detection results by comparing the power supply parameters, ensures timeliness of maintenance by marking fault power supply equipment, and reduces property loss of users.
To achieve the above objective, an embodiment of the present invention provides a method for detecting a power supply parameter of a machine room for a data center, including:
acquiring machine room power supply topological relation data, and generating a machine room power supply topological relation diagram according to the machine room power supply topological relation data;
acquiring target power supply equipment in the machine room power supply topological relation diagram, and configuring a power supply parameter detection node for the target power supply equipment; wherein, a target power supply device is configured with a power supply parameter detection node;
and receiving the power supply parameters of the corresponding target power supply equipment sent by the power supply parameter detection node, comparing the power supply parameters with the standard power supply parameters corresponding to the target power supply equipment respectively to obtain a comparison result, marking the target power supply equipment in the machine room power supply topological relation diagram and carrying out a first alarm prompt when the power supply parameters of the target power supply equipment are determined to be abnormal parameters according to the comparison result, and simultaneously storing the power supply parameters of the corresponding target power supply equipment sent by the power supply parameter detection node into a magnetic disk.
Further, the obtaining the machine room power supply topology relation data and generating the machine room power supply topology relation graph according to the machine room power supply topology relation data includes:
The machine room power supply topological relation data comprise first operation data of a machine room power grid and a machine room GIS map;
processing the first operation data based on a data checking algorithm to obtain second operation data, and performing topology analysis on the second operation data based on a network topology analysis algorithm to obtain a topology analysis result;
and generating a machine room power supply topological relation diagram according to the machine room GIS map and the topological analysis result.
Further, the configuring a power supply parameter detection node for the target power supply device includes:
and acquiring the position information of the target power supply equipment in the machine room power supply topological relation diagram, and configuring a power supply parameter detection node for the target power supply equipment according to the position information.
Further, the comparing the power supply parameters with standard power supply parameters corresponding to the target power supply equipment respectively to obtain a comparison result includes:
acquiring the equipment type of the target power supply equipment;
inquiring a preset equipment type-standard power supply parameter table according to the equipment type to obtain corresponding standard power supply parameters;
and comparing the power supply parameters with standard power supply parameters to obtain a comparison result.
Further, the power supply parameters comprise a first power generation amount, a first active power, a first power factor and a first apparent power;
The standard power supply parameters comprise a second power generation amount, a second active power, a second power factor and a second apparent power.
Further, the determining that the power supply parameter is an abnormal parameter according to the comparison result includes:
calculating a first difference absolute value of the first power generation amount and the second power generation amount, judging whether the first difference absolute value is in a preset first difference range, and determining the power supply parameter as an abnormal parameter when the first difference absolute value is not in the preset first difference range;
or (b)
Calculating a second difference absolute value of the first active power and the second active power, judging whether the second difference absolute value is within a preset second difference range, and determining the power supply parameter as an abnormal parameter when the second difference absolute value is not within the preset second difference range;
or (b)
Calculating a third difference absolute value of the first power factor and the second power factor, judging whether the third difference absolute value is in a preset second difference range, and determining the power supply parameter as an abnormal parameter when the third difference absolute value is not in the preset third difference range;
or (b)
And calculating a fourth difference absolute value of the first apparent power and the second apparent power, judging whether the fourth difference absolute value is in a preset fourth difference range, and determining the power supply parameter as an abnormal parameter when the fourth difference absolute value is not in the preset fourth difference range.
Further, the machine room power supply parameter detection method for the data center further comprises the following steps:
extracting historical power supply parameters which are abnormal parameters from the magnetic disk, extracting characteristic information of the historical power supply parameters, clustering the characteristic information of the historical power supply parameters as input of a self-organizing map neural network to obtain a plurality of historical power supply parameter sets, and obtaining a first fault type of the corresponding historical power supply parameter sets according to the characteristic information;
generating a first fault text according to the first fault type, performing word segmentation processing on the first fault text to obtain a plurality of first words, performing vectorization processing on the plurality of first words to obtain a plurality of first word segmentation vectors, summing the plurality of first word segmentation vectors, and taking an average value to obtain a first fault vector;
establishing a fault recognition model based on a deep learning LSTM network, training a plurality of historical power supply parameter sets by using the LSTM model, calculating through forward propagation, outputting a second fault type by using a last layer of network, generating a second fault text according to the second fault type, performing word segmentation on the second fault text to obtain a plurality of second words, performing vectorization on the plurality of second words to obtain a plurality of second word vectors, summing the plurality of second word vectors, averaging to obtain a second fault vector, calculating error values of the first fault vector and the second fault vector according to a preset loss function, judging whether the error value is smaller than a preset error value, and finishing training when the error value is determined to be smaller than the preset error value to obtain a trained fault recognition model;
Inputting the power supply parameters with the comparison result being the abnormal parameters into a trained fault identification model, and outputting a third fault type;
and inquiring a preset fault type-solution table according to the third fault type, acquiring a corresponding solution and sending the solution to a maintenance personnel terminal.
Further, the machine room power supply parameter detection method for the data center further comprises the following steps:
acquiring target power supply equipment information;
calculating a residual service life evaluation value of the target power supply equipment according to the target power supply equipment information, judging whether the residual service life evaluation value is smaller than a preset residual service life evaluation value, and marking the target power supply equipment in the machine room power supply topological relation diagram and carrying out a second alarm prompt when the residual service life evaluation value is smaller than the preset residual service life evaluation value.
Further, the calculating the remaining service life evaluation value of the target power supply device according to the target power supply device information includes:
calculating a health coefficient K of the target power supply equipment, as shown in a formula (1):
zeta is the coefficient of performance of the target power supply equipment; lambda is the objectThe fatigue coefficient of the standard equipment; n is the historical maintenance times of the target power supply equipment; m is M i The damage degree of the target power supply equipment is the damage degree of the ith maintenance; χ is the aging coefficient of the target power supply device; t is the power supply time length of the target power supply equipment; d is the factory life of the target power supply equipment;
calculating a residual service life evaluation value S of the target power supply equipment according to a health coefficient K of the target power supply equipment, wherein the residual service life evaluation value S is shown in a formula (2):
wherein α is a stability factor of the target power supply device; gamma ray 1 An attenuation coefficient for the performance of the target power supply equipment affected by the external environment; gamma ray 2 An attenuation coefficient for the target power supply device performance that is internally affected; z is the natural attenuation coefficient of the performance of the target power supply equipment.
Further, before storing the power supply parameters of the corresponding target power supply device sent by the power supply parameter detection node to the disk, the method further includes:
acquiring working information of the magnetic disk;
calculating the fault rate of the disk according to the working information, judging whether the fault rate is larger than a preset fault rate, and storing the power supply parameters of the corresponding target power supply equipment sent by the power supply parameter detection node into a standby disk when the fault rate is determined to be larger than the preset fault rate;
The calculating the failure rate of the disk according to the working information comprises the following steps:
calculating the actual consumed energy E of the magnetic disk in the preset time T 1 As shown in formula (3):
E 1 ＝(P×T+E 2 ×n 1 +E 3 ×n 2 )×3.14d×ρ×ω (3)
wherein P is the operating power of the magnetic disk; e (E) 2 The energy required for the disk start; n is n 1 The number of times of starting the magnetic disk in a preset time T is set; e (E) 3 Energy required for stopping the magnetic disk; n is n 2 The number of times of stopping the magnetic disk in a preset time T is set; d is the diameter of the innermost ring of the magnetic disk; ρ is the bit density of the disk; omega is the average rotating speed of the magnetic disk in a preset time T;
according to the actual consumed energy E of the magnetic disk in the preset time T 1 Calculating the failure rate beta of the magnetic disk, as shown in a formula (4):
wherein τ is the reliability coefficient of the magnetic disk; e is a natural constant; r is the effective utilization rate of disk space; c (C) 1 The data quantity of the stored power supply parameters for the magnetic disk; c (C) 2 Is the total capacity of the disk; e (E) 4 And presetting consumed energy for the magnetic disk in preset time T.
The invention has the beneficial effects that: the accuracy of the detection result is guaranteed by comparing the power supply parameters, the fault power supply equipment is marked in the acquired machine room power supply topological relation diagram, the position information of the fault power supply equipment can be accurately and intuitively seen, the timeliness of maintenance by maintenance personnel is guaranteed, and the property loss of a user is reduced.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a flowchart of a method for detecting machine room power supply parameters for a data center according to an embodiment of the present invention;
FIG. 2 is a flowchart of generating a topology relationship diagram for machine room power supply according to an embodiment of the present invention;
fig. 3 is a flowchart of a comparison result of a power supply parameter and a standard power supply parameter according to an embodiment of the invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
The following describes a machine room power supply parameter detection method for a data center according to an embodiment of the present invention with reference to fig. 1 to 3.
As shown in fig. 1, a method for detecting a machine room power supply parameter for a data center includes:
s1, acquiring machine room power supply topology relation data, and generating a machine room power supply topology relation diagram according to the machine room power supply topology relation data;
s2, acquiring target power supply equipment in the machine room power supply topological relation diagram, and configuring a power supply parameter detection node for the target power supply equipment; wherein, a target power supply device is configured with a power supply parameter detection node;
And S3, receiving the power supply parameters of the corresponding target power supply equipment sent by the power supply parameter detection node, comparing the power supply parameters with the standard power supply parameters corresponding to the target power supply equipment respectively to obtain a comparison result, marking the target power supply equipment in the machine room power supply topological relation diagram and carrying out a first alarm prompt when the power supply parameters of the target power supply equipment are determined to be abnormal parameters according to the comparison result, and storing the power supply parameters of the corresponding target power supply equipment sent by the power supply parameter detection node into a magnetic disk.
The working principle of the scheme is as follows: acquiring machine room power supply topological relation data, and generating a machine room power supply topological relation diagram according to the machine room power supply topological relation data; acquiring target power supply equipment in the machine room power supply topological relation diagram, and configuring a power supply parameter detection node for the target power supply equipment; wherein, a target power supply device is configured with a power supply parameter detection node; and receiving the power supply parameters of the corresponding target power supply equipment sent by the power supply parameter detection node, comparing the power supply parameters with the standard power supply parameters corresponding to the target power supply equipment respectively to obtain a comparison result, marking the target power supply equipment in the machine room power supply topological relation diagram and carrying out a first alarm prompt when the power supply parameters of the target power supply equipment are determined to be abnormal parameters according to the comparison result, and simultaneously storing the power supply parameters of the corresponding target power supply equipment sent by the power supply parameter detection node into a magnetic disk.
The beneficial effect of above-mentioned scheme: and when the power supply parameter is an abnormal parameter, the target power supply equipment is marked in the machine room power supply topological relation diagram and carries out a first alarm prompt, so that maintenance personnel are reminded of timely maintenance, the timeliness of the maintenance is ensured, important property loss caused by untimely maintenance is avoided, the experience of a user is improved, and the practicability of the method is improved.
As shown in fig. 2, according to some embodiments of the present invention, the obtaining the machine room power supply topology relationship data, generating a machine room power supply topology relationship graph according to the machine room power supply topology relationship data includes:
s201, the machine room power supply topological relation data comprise first operation data of a machine room power grid and a machine room GIS map;
s202, processing the first operation data based on a data checking algorithm to obtain second operation data, and performing topology analysis on the second operation data based on a network topology analysis algorithm to obtain a topology analysis result;
And S203, generating a machine room power supply topological relation diagram according to the machine room GIS map and the topological analysis result.
The working principle of the scheme is as follows: the machine room power supply topological relation data comprise first operation data of a machine room power grid and a machine room GIS map; processing the first operation data based on a data checking algorithm to obtain second operation data, and performing topology analysis on the second operation data based on a network topology analysis algorithm to obtain a topology analysis result; and generating a machine room power supply topological relation diagram according to the machine room GIS map and the topological analysis result. GIS, fully: geographic Information Science abbreviations for geographical information science. The system is a technical system for collecting, storing, managing, operating, analyzing, displaying and describing the related geographic distribution data in the whole or partial earth surface (including atmosphere) space under the support of a computer hard and software system.
The beneficial effect of above-mentioned scheme: the power grid operation data is analyzed through a network topology analysis algorithm, and then a power grid power supply path diagram is drawn on a GIS map according to the analysis result of the network topology, so that a user power supply path diagram which is relatively visual is drawn on the map by calling GIS service under a micro service architecture in an enterprise, and the operation is convenient and simple.
According to some embodiments of the invention, the configuring a power supply parameter detection node for the target power supply device includes:
and acquiring the position information of the target power supply equipment in the machine room power supply topological relation diagram, and configuring a power supply parameter detection node for the target power supply equipment according to the position information.
The working principle of the scheme is as follows: and acquiring the position information of the target power supply equipment in the machine room power supply topological relation diagram, and configuring a power supply parameter detection node for the target power supply equipment according to the position information.
The beneficial effect of above-mentioned scheme: and establishing a one-to-one correspondence between the target power supply equipment and the power supply parameter detection node according to the position information, and ensuring the accuracy of a final detection result.
As shown in fig. 3, according to some embodiments of the present invention, the comparing the power supply parameters with standard power supply parameters corresponding to a target power supply device, respectively, to obtain a comparison result includes:
s301, acquiring the equipment type of the target power supply equipment;
s302, inquiring a preset equipment type-standard power supply parameter table according to the equipment type to obtain corresponding standard power supply parameters;
s303, comparing the power supply parameters with standard power supply parameters to obtain a comparison result.
The working principle of the scheme is as follows: acquiring the equipment type of the target power supply equipment; inquiring a preset equipment type-standard power supply parameter table according to the equipment type to obtain corresponding standard power supply parameters; and comparing the power supply parameters with standard power supply parameters to obtain a comparison result.
The beneficial effect of above-mentioned scheme: and acquiring corresponding standard power supply parameters according to the equipment type of the target power supply equipment, and ensuring the accuracy of a final detection result.
According to some embodiments of the invention, the power supply parameter includes a first power generation amount, a first active power, a first power factor, a first apparent power;
the standard power supply parameters comprise a second power generation amount, a second active power, a second power factor and a second apparent power.
The working principle of the scheme is as follows: the power supply parameters comprise a first power generation amount, a first active power, a first power factor and a first apparent power; the standard power supply parameters comprise a second power generation amount, a second active power, a second power factor and a second apparent power.
According to some embodiments of the invention, the determining that the power supply parameter is an abnormal parameter according to the comparison result includes:
calculating a first difference absolute value of the first power generation amount and the second power generation amount, judging whether the first difference absolute value is in a preset first difference range, and determining the power supply parameter as an abnormal parameter when the first difference absolute value is not in the preset first difference range;
Or (b)
Calculating a second difference absolute value of the first active power and the second active power, judging whether the second difference absolute value is within a preset second difference range, and determining the power supply parameter as an abnormal parameter when the second difference absolute value is not within the preset second difference range;
or (b)
Calculating a third difference absolute value of the first power factor and the second power factor, judging whether the third difference absolute value is in a preset second difference range, and determining the power supply parameter as an abnormal parameter when the third difference absolute value is not in the preset third difference range;
or (b)
And calculating a fourth difference absolute value of the first apparent power and the second apparent power, judging whether the fourth difference absolute value is in a preset fourth difference range, and determining the power supply parameter as an abnormal parameter when the fourth difference absolute value is not in the preset fourth difference range.
The working principle of the scheme is as follows: calculating a first difference absolute value of the first power generation amount and the second power generation amount, judging whether the first difference absolute value is in a preset first difference range, and determining the power supply parameter as an abnormal parameter when the first difference absolute value is not in the preset first difference range; calculating a second difference absolute value of the first active power and the second active power, judging whether the second difference absolute value is within a preset second difference range, and determining the power supply parameter as an abnormal parameter when the second difference absolute value is not within the preset second difference range; calculating a third difference absolute value of the first power factor and the second power factor, judging whether the third difference absolute value is in a preset second difference range, and determining the power supply parameter as an abnormal parameter when the third difference absolute value is not in the preset third difference range; and calculating a fourth difference absolute value of the first apparent power and the second apparent power, judging whether the fourth difference absolute value is in a preset fourth difference range, and determining the power supply parameter as an abnormal parameter when the fourth difference absolute value is not in the preset fourth difference range.
The beneficial effect of above-mentioned scheme: by calculating the first power generation amount, the first active power, the first power factor, the first apparent power, the second power generation amount, the second active power, the second power factor and the second apparent power, abnormal parameters in the power supply parameters are accurately screened out, the accuracy of the power supply parameter detection result is improved, and the practicability of the method is improved.
According to some embodiments of the present invention, a method for detecting a machine room power supply parameter for a data center further includes:
extracting historical power supply parameters which are abnormal parameters from the magnetic disk, extracting characteristic information of the historical power supply parameters, clustering the characteristic information of the historical power supply parameters as input of a self-organizing map neural network to obtain a plurality of historical power supply parameter sets, and obtaining a first fault type of the corresponding historical power supply parameter sets according to the characteristic information;
generating a first fault text according to the first fault type, performing word segmentation processing on the first fault text to obtain a plurality of first words, performing vectorization processing on the plurality of first words to obtain a plurality of first word segmentation vectors, summing the plurality of first word segmentation vectors, and taking an average value to obtain a first fault vector;
Establishing a fault recognition model based on a deep learning LSTM network, training a plurality of historical power supply parameter sets by using the LSTM model, calculating through forward propagation, outputting a second fault type by using a last layer of network, generating a second fault text according to the second fault type, performing word segmentation on the second fault text to obtain a plurality of second words, performing vectorization on the plurality of second words to obtain a plurality of second word vectors, summing the plurality of second word vectors, averaging to obtain a second fault vector, calculating error values of the first fault vector and the second fault vector according to a preset loss function, judging whether the error value is smaller than a preset error value, and finishing training when the error value is determined to be smaller than the preset error value to obtain a trained fault recognition model;
inputting the power supply parameters with the comparison result being the abnormal parameters into a trained fault identification model, and outputting a third fault type;
and inquiring a preset fault type-solution table according to the third fault type, acquiring a corresponding solution and sending the solution to a maintenance personnel terminal.
The working principle of the scheme is as follows: extracting historical power supply parameters which are abnormal parameters from the magnetic disk, extracting characteristic information of the historical power supply parameters, clustering the characteristic information of the historical power supply parameters as input of a self-organizing map neural network to obtain a plurality of historical power supply parameter sets, and obtaining a first fault type of the corresponding historical power supply parameter sets according to the characteristic information; generating a first fault text according to the first fault type, performing word segmentation processing on the first fault text to obtain a plurality of first words, performing vectorization processing on the plurality of first words to obtain a plurality of first word segmentation vectors, summing the plurality of first word segmentation vectors, and taking an average value to obtain a first fault vector; establishing a fault recognition model based on a deep learning LSTM network, training a plurality of historical power supply parameter sets by using the LSTM model, calculating through forward propagation, outputting a second fault type by using a last layer of network, generating a second fault text according to the second fault type, performing word segmentation on the second fault text to obtain a plurality of second words, performing vectorization on the plurality of second words to obtain a plurality of second word vectors, summing the plurality of second word vectors, averaging to obtain a second fault vector, calculating error values of the first fault vector and the second fault vector according to a preset loss function, judging whether the error value is smaller than a preset error value, and finishing training when the error value is determined to be smaller than the preset error value to obtain a trained fault recognition model; inputting the power supply parameters with the comparison result being the abnormal parameters into a trained fault identification model, and outputting a third fault type; and inquiring a preset fault type-solution table according to the third fault type, acquiring a corresponding solution and sending the solution to a maintenance personnel terminal.
The beneficial effect of above-mentioned scheme: the prior art does not have intelligent analysis management on power supply parameters, when the power supply parameters are abnormal, the power supply parameters cannot be timely alarmed, and the position information of the power supply equipment with faults cannot be known, so that huge economic loss is often caused. Generating a first fault text according to the first fault type, performing word segmentation processing on the first fault text to obtain a plurality of first words, performing vectorization processing on the plurality of first words to obtain a plurality of first word segmentation vectors, summing the plurality of first word segmentation vectors, and taking an average value to obtain a first fault vector; establishing a fault recognition model based on a deep learning LSTM network, training a plurality of historical power supply parameter sets by using the LSTM model, calculating through forward propagation, outputting a second fault type by using a last layer of network, generating a second fault text according to the second fault type, performing word segmentation on the second fault text to obtain a plurality of second words, performing vectorization on the plurality of second words to obtain a plurality of second word vectors, summing the plurality of second word vectors, averaging to obtain a second fault vector, calculating error values of the first fault vector and the second fault vector according to a preset loss function, judging whether the error value is smaller than a preset error value, and finishing training when the error value is determined to be smaller than the preset error value to obtain a trained fault recognition model; the LSTM (Long Short-Term Memory) is a Long-Term and Short-Term Memory network, is a time recurrent neural network, is suitable for processing and predicting important events with relatively Long intervals and delays in a time sequence, calculates error values through a first fault vector obtained by a first fault type and a second fault vector obtained by a second fault type, iteratively updates the LSTM model according to the error values until the error values are smaller than preset error values, so that a finally established model is more reliable, errors are smaller, the accuracy of a final output result is ensured, and power supply parameters with comparison results being abnormal parameters are input into a trained fault identification model to output a third fault type; the third fault type is the last fault type, a preset fault type-solution table is queried according to the third fault type, a corresponding solution is obtained and sent to a maintenance personnel terminal, and timeliness of maintenance are guaranteed.
According to some embodiments of the present invention, a method for detecting a machine room power supply parameter for a data center further includes:
acquiring target power supply equipment information;
calculating a residual service life evaluation value of the target power supply equipment according to the target power supply equipment information, judging whether the residual service life evaluation value is smaller than a preset residual service life evaluation value, and marking the target power supply equipment in the machine room power supply topological relation diagram and carrying out a second alarm prompt when the residual service life evaluation value is smaller than the preset residual service life evaluation value.
The working principle of the scheme is as follows: acquiring target power supply equipment information; calculating a residual service life evaluation value of the target power supply equipment according to the target power supply equipment information, judging whether the residual service life evaluation value is smaller than a preset residual service life evaluation value, and marking the target power supply equipment in the machine room power supply topological relation diagram and carrying out a second alarm prompt when the residual service life evaluation value is smaller than the preset residual service life evaluation value.
The beneficial effect of above-mentioned scheme: calculating a residual service life evaluation value of the target power supply equipment according to the target power supply equipment information, judging whether the residual service life evaluation value is smaller than a preset residual service life evaluation value, marking the target power supply equipment in the machine room power supply topological relation diagram and carrying out a second alarm prompt when the residual service life evaluation value is smaller than the preset residual service life evaluation value, reminding workers of timely replacing the target power supply equipment, and guaranteeing the stability of machine room power supply.
According to some embodiments of the invention, the calculating the remaining service life evaluation value of the target power supply device according to the target power supply device information includes:
calculating a health coefficient K of the target power supply equipment, as shown in a formula (1):
zeta is the coefficient of performance of the target power supply equipment; λ is a fatigue coefficient of the target device; n is the historical maintenance times of the target power supply equipment; m is M i The damage degree of the target power supply equipment is the damage degree of the ith maintenance; χ is the aging coefficient of the target power supply device; t is the power supply time length of the target power supply equipment; d is the factory life of the target power supply equipment;
calculating a residual service life evaluation value S of the target power supply equipment according to a health coefficient K of the target power supply equipment, wherein the residual service life evaluation value S is shown in a formula (2):
wherein α is a stability factor of the target power supply device; gamma ray 1 An attenuation coefficient for the performance of the target power supply equipment affected by the external environment; gamma ray 2 An attenuation coefficient for the target power supply device performance that is internally affected; z is the natural attenuation coefficient of the performance of the target power supply equipment.
The beneficial effect of above-mentioned scheme: the attenuation coefficient of the performance of the target power supply equipment is influenced by the external environment, wherein the external environment is factors such as dirt, temperature and the like; the performance of the target power supply equipment is affected by the attenuation coefficient of the internal environment, wherein the internal environment is short circuit, open circuit and other factors.
The beneficial effect of above-mentioned scheme: when the residual service life evaluation value of the target power supply equipment is calculated, factors such as the stability factor of the target power supply equipment, the attenuation coefficient of the performance of the target power supply equipment affected by the external environment, the attenuation coefficient of the performance of the target power supply equipment affected by the internal environment, the aging coefficient of the target power supply equipment, the power supply duration of the target power supply equipment, the natural attenuation coefficient of the performance of the target power supply equipment, the historical maintenance times of the target power supply equipment and the like are considered, so that the calculated residual service life evaluation value is more accurate, the accuracy of judging the residual service life evaluation value and the preset residual service life evaluation value is improved, and when the residual service life evaluation value is smaller than the preset residual service life evaluation value, the target power supply equipment is marked in the machine room power supply topological relation graph and a second alarm prompt is carried out, workers are reminded of timely replacing the target power supply equipment, and the stability of power supply of a machine room is ensured.
According to some embodiments of the invention, before storing the power supply parameters of the corresponding target power supply device sent by the power supply parameter detection node to the disk, the method further includes:
Acquiring working information of the magnetic disk;
calculating the fault rate of the disk according to the working information, judging whether the fault rate is larger than a preset fault rate, and storing the power supply parameters of the corresponding target power supply equipment sent by the power supply parameter detection node into a standby disk when the fault rate is determined to be larger than the preset fault rate;
the calculating the failure rate of the disk according to the working information comprises the following steps:
calculating the actual consumed energy E of the magnetic disk in the preset time T 1 As shown in formula (3):
E 1 ＝(P×T+E 2 ×n 1 +E 3 ×n 2 )×3.14d×ρ×ω (3)
wherein P is the operating power of the magnetic disk; e (E) 2 The energy required for the disk start; n is n 1 The number of times of starting the magnetic disk in a preset time T is set; e (E) 3 Energy required for stopping the magnetic disk; n is n 2 The number of times of stopping the magnetic disk in a preset time T is set; d is the diameter of the innermost ring of the magnetic disk; ρ is the bit density of the disk; omega is the average rotating speed of the magnetic disk in a preset time T;
according to the actual consumed energy E of the magnetic disk in the preset time T 1 Calculating the failure rate beta of the magnetic diskAs shown in formula (4):
wherein τ is the reliability coefficient of the magnetic disk; e is a natural constant; r is the effective utilization rate of disk space; c (C) 1 The data quantity of the stored power supply parameters for the magnetic disk; c (C) 2 Is the total capacity of the disk; e (E) 4 And presetting consumed energy for the magnetic disk in preset time T.
The working principle of the scheme is as follows: acquiring working information of the magnetic disk; and calculating the fault rate of the magnetic disk according to the working information, judging whether the fault rate is larger than a preset fault rate, and storing the power supply parameters of the corresponding target power supply equipment sent by the power supply parameter detection node into a standby magnetic disk when the fault rate is determined to be larger than the preset fault rate.
The beneficial effect of above-mentioned scheme: the method comprises the steps that when the fault rate of the magnetic disk is calculated, the data quantity of the stored power supply parameters of the magnetic disk, the total capacity of the magnetic disk, the energy consumed by the magnetic disk in the preset time T, the operation power of the magnetic disk and other factors are considered, so that the calculated fault rate is more accurate, and when the fault rate is smaller than the preset fault rate, the power supply parameters of the corresponding target power supply equipment sent by the power supply parameter detection node are stored in the standby magnetic disk, so that the power supply parameters are not lost, and the experience of a user is improved.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (8)
1. The machine room power supply parameter detection method for the data center is characterized by comprising the following steps of:
acquiring machine room power supply topological relation data, and generating a machine room power supply topological relation diagram according to the machine room power supply topological relation data;
acquiring target power supply equipment in the machine room power supply topological relation diagram, and configuring a power supply parameter detection node for the target power supply equipment; wherein, a target power supply device is configured with a power supply parameter detection node;
the power supply parameters of the corresponding target power supply equipment sent by the power supply parameter detection node are received, the power supply parameters are respectively compared with standard power supply parameters corresponding to the target power supply equipment to obtain a comparison result, when the power supply parameters of the target power supply equipment are determined to be abnormal parameters according to the comparison result, the target power supply equipment is marked in the machine room power supply topology relation diagram, a first alarm prompt is carried out, and meanwhile the power supply parameters of the corresponding target power supply equipment sent by the power supply parameter detection node are stored in a magnetic disk;
Further comprises:
extracting historical power supply parameters which are abnormal parameters from the magnetic disk, extracting characteristic information of the historical power supply parameters, clustering the characteristic information of the historical power supply parameters as input of a self-organizing map neural network to obtain a plurality of historical power supply parameter sets, and obtaining a first fault type of the corresponding historical power supply parameter sets according to the characteristic information;
generating a first fault text according to the first fault type, performing word segmentation processing on the first fault text to obtain a plurality of first words, performing vectorization processing on the plurality of first words to obtain a plurality of first word segmentation vectors, summing the plurality of first word segmentation vectors, and taking an average value to obtain a first fault vector;
establishing a fault recognition model based on a deep learning LSTM network, training a plurality of historical power supply parameter sets by using the LSTM model, calculating through forward propagation, outputting a second fault type by using a last layer of network, generating a second fault text according to the second fault type, performing word segmentation on the second fault text to obtain a plurality of second words, performing vectorization on the plurality of second words to obtain a plurality of second word vectors, summing the plurality of second word vectors, averaging to obtain a second fault vector, calculating error values of the first fault vector and the second fault vector according to a preset loss function, judging whether the error value is smaller than a preset error value, and finishing training when the error value is determined to be smaller than the preset error value to obtain a trained fault recognition model;
Inputting the power supply parameters with the comparison result being the abnormal parameters into a trained fault identification model, and outputting a third fault type;
inquiring a preset fault type-solution table according to the third fault type, acquiring a corresponding solution and sending the solution to a maintenance personnel terminal;
before storing the power supply parameters of the corresponding target power supply equipment sent by the power supply parameter detection node to the disk, the method further comprises:
acquiring working information of the magnetic disk;
calculating the fault rate of the disk according to the working information, judging whether the fault rate is larger than a preset fault rate, and storing the power supply parameters of the corresponding target power supply equipment sent by the power supply parameter detection node into a standby disk when the fault rate is determined to be larger than the preset fault rate;
the calculating the failure rate of the disk according to the working information comprises the following steps:
calculating the preset time of the magnetic diskIn the interior, the energy actually consumed +.>As shown in formula (3):
；
wherein,operating power for the disk; />The energy required for the disk start; />For the magnetic disk at a preset time +.>The number of internal starts; />Energy required for stopping the magnetic disk; / >For the magnetic disk at preset timeThe number of internal stalls; />The diameter of the innermost ring of the magnetic disk; />A bit density for the disk; />For the magnetic disk at a preset time +.>An average rotational speed within;
according to the preset time of the magnetic diskIn the interior, the energy actually consumed +.>Calculating the failure rate of the disk>As shown in formula (4):
；
wherein,the reliability coefficient of the magnetic disk; />Is a natural constant; />The effective utilization rate of the disk space is realized; />The data quantity of the stored power supply parameters for the magnetic disk; />Is the total capacity of the disk; />For the magnetic disk at a preset time +.>In, the consumed energy is preset.
2. The method for detecting machine room power supply parameters for a data center according to claim 1, wherein the obtaining the machine room power supply topology relation data and generating the machine room power supply topology relation graph according to the machine room power supply topology relation data comprise:
the machine room power supply topological relation data comprise first operation data of a machine room power grid and a machine room GIS map;
processing the first operation data based on a data checking algorithm to obtain second operation data, and performing topology analysis on the second operation data based on a network topology analysis algorithm to obtain a topology analysis result;
And generating a machine room power supply topological relation diagram according to the machine room GIS map and the topological analysis result.
3. The method for detecting a machine room power supply parameter for a data center according to claim 1, wherein configuring a power supply parameter detection node for the target power supply device includes:
and acquiring the position information of the target power supply equipment in the machine room power supply topological relation diagram, and configuring a power supply parameter detection node for the target power supply equipment according to the position information.
4. The method for detecting the power supply parameters of the machine room for the data center according to claim 1, wherein the comparing the power supply parameters with standard power supply parameters corresponding to target power supply equipment respectively to obtain a comparison result includes:
acquiring the equipment type of the target power supply equipment;
inquiring a preset equipment type-standard power supply parameter table according to the equipment type to obtain corresponding standard power supply parameters;
and comparing the power supply parameters with standard power supply parameters to obtain a comparison result.
5. The machine room power supply parameter detection method for a data center according to claim 4, wherein:
the power supply parameters comprise a first power generation amount, a first active power, a first power factor and a first apparent power;
The standard power supply parameters comprise a second power generation amount, a second active power, a second power factor and a second apparent power.
6. The method for detecting the power supply parameter of the machine room for the data center according to claim 5, wherein the determining that the power supply parameter is an abnormal parameter according to the comparison result comprises:
calculating a first difference absolute value of the first power generation amount and the second power generation amount, judging whether the first difference absolute value is in a preset first difference range, and determining the power supply parameter as an abnormal parameter when the first difference absolute value is not in the preset first difference range;
or (b)
Calculating a second difference absolute value of the first active power and the second active power, judging whether the second difference absolute value is within a preset second difference range, and determining the power supply parameter as an abnormal parameter when the second difference absolute value is not within the preset second difference range;
or (b)
Calculating a third difference absolute value of the first power factor and the second power factor, judging whether the third difference absolute value is in a preset second difference range, and determining the power supply parameter as an abnormal parameter when the third difference absolute value is not in the preset third difference range;
Or (b)
And calculating a fourth difference absolute value of the first apparent power and the second apparent power, judging whether the fourth difference absolute value is in a preset fourth difference range, and determining the power supply parameter as an abnormal parameter when the fourth difference absolute value is not in the preset fourth difference range.
7. The method for detecting a machine room power supply parameter for a data center according to claim 1, further comprising:
acquiring target power supply equipment information;
calculating a residual service life evaluation value of the target power supply equipment according to the target power supply equipment information, judging whether the residual service life evaluation value is smaller than a preset residual service life evaluation value, and marking the target power supply equipment in the machine room power supply topological relation diagram and carrying out a second alarm prompt when the residual service life evaluation value is smaller than the preset residual service life evaluation value.
8. The machine room power supply parameter detection method for a data center according to claim 7, wherein the calculating the remaining service life evaluation value of the target power supply equipment according to the target power supply equipment information includes:
calculating a health coefficient of the target power supply device As shown in formula (1):
；
wherein,a coefficient of performance for the target power supply device; />A fatigue coefficient for the target power supply device; />Historical maintenance times for the target power supply device; />Is->The damage degree of the target power supply equipment is achieved during secondary maintenance;an aging coefficient for the target power supply device; />A power supply duration for the target power supply device; />The factory life of the target power supply equipment is prolonged;
according to the health coefficient of the target power supply equipmentCalculating a remaining service life evaluation value of the target power supply equipmentAs shown in formula (2):
；
wherein,a stability factor for the target power supply device; />An attenuation coefficient for the performance of the target power supply equipment affected by the external environment; />Attenuation coefficient for the target power supply device performance which is influenced internally; ->A natural attenuation coefficient for the target power supply device performance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110396105.3A CN113191074B (en) | 2021-04-13 | 2021-04-13 | Machine room power supply parameter detection method for data center |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110396105.3A CN113191074B (en) | 2021-04-13 | 2021-04-13 | Machine room power supply parameter detection method for data center |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113191074A CN113191074A (en) | 2021-07-30 |
| CN113191074B true CN113191074B (en) | 2023-11-21 |
Family
ID=76975658
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110396105.3A Active CN113191074B (en) | 2021-04-13 | 2021-04-13 | Machine room power supply parameter detection method for data center |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113191074B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113687259B (en) * | 2021-09-23 | 2023-11-24 | 北京中大科慧科技发展有限公司 | Machine room UPS detection method and system for data center |
| CN114780622B (en) * | 2022-06-27 | 2022-09-02 | 天津能源物联网科技股份有限公司 | Intelligent heat supply data analysis method and system based on big data platform |
| CN115343086B (en) * | 2022-08-04 | 2024-05-03 | 上海智能新能源汽车科创功能平台有限公司 | Online pre-detection method and system for high-pressure hydrogenation machine |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7800856B1 (en) * | 2009-03-24 | 2010-09-21 | Western Digital Technologies, Inc. | Disk drive flushing write cache to a nearest set of reserved tracks during a power failure |
| CN106603274A (en) * | 2016-11-21 | 2017-04-26 | 中国电力科学研究院 | Power distribution network fault locating method based on multidimensional communication data |
| CN109657912A (en) * | 2018-11-15 | 2019-04-19 | 国网浙江省电力有限公司金华供电公司 | A kind of visual power grid risk management and control method and system |
| CN111737496A (en) * | 2020-06-29 | 2020-10-02 | 东北电力大学 | Power equipment fault knowledge map construction method |
| CN111881971A (en) * | 2020-07-24 | 2020-11-03 | 成都理工大学 | Power transmission line fault type identification method based on deep learning LSTM model |
| CN111915063A (en) * | 2020-07-09 | 2020-11-10 | 国网冀北电力有限公司信息通信分公司 | Power supply path network topology analysis display method, system and storage medium based on micro-service architecture |
| CN112182205A (en) * | 2020-08-24 | 2021-01-05 | 华北电力大学（保定） | Processing method for recognizing monitoring data in electrical equipment by using character recognition |
| CN112526251A (en) * | 2020-10-22 | 2021-03-19 | 国网浙江省电力有限公司嘉兴供电公司 | Transformer substation power equipment fault diagnosis method based on data driving |
| CN112541600A (en) * | 2020-12-07 | 2021-03-23 | 上海电科智能系统股份有限公司 | Knowledge graph-based auxiliary maintenance decision method |
-
2021
- 2021-04-13 CN CN202110396105.3A patent/CN113191074B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7800856B1 (en) * | 2009-03-24 | 2010-09-21 | Western Digital Technologies, Inc. | Disk drive flushing write cache to a nearest set of reserved tracks during a power failure |
| CN106603274A (en) * | 2016-11-21 | 2017-04-26 | 中国电力科学研究院 | Power distribution network fault locating method based on multidimensional communication data |
| CN109657912A (en) * | 2018-11-15 | 2019-04-19 | 国网浙江省电力有限公司金华供电公司 | A kind of visual power grid risk management and control method and system |
| CN111737496A (en) * | 2020-06-29 | 2020-10-02 | 东北电力大学 | Power equipment fault knowledge map construction method |
| CN111915063A (en) * | 2020-07-09 | 2020-11-10 | 国网冀北电力有限公司信息通信分公司 | Power supply path network topology analysis display method, system and storage medium based on micro-service architecture |
| CN111881971A (en) * | 2020-07-24 | 2020-11-03 | 成都理工大学 | Power transmission line fault type identification method based on deep learning LSTM model |
| CN112182205A (en) * | 2020-08-24 | 2021-01-05 | 华北电力大学（保定） | Processing method for recognizing monitoring data in electrical equipment by using character recognition |
| CN112526251A (en) * | 2020-10-22 | 2021-03-19 | 国网浙江省电力有限公司嘉兴供电公司 | Transformer substation power equipment fault diagnosis method based on data driving |
| CN112541600A (en) * | 2020-12-07 | 2021-03-23 | 上海电科智能系统股份有限公司 | Knowledge graph-based auxiliary maintenance decision method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113191074A (en) | 2021-07-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113191074B (en) | Machine room power supply parameter detection method for data center | |
| CA2936006C (en) | Smart grid topology estimator | |
| Trakas et al. | Spatial risk analysis of power systems resilience during extreme events | |
| US20230083626A1 (en) | Pipeline monitoring methods and internet of things based on smart gas pipeline network safety | |
| US20190041445A1 (en) | Maintaining connectivity information for meters and transformers located in a power distribution network | |
| US9816836B2 (en) | Correlating meter data to detect mismappings | |
| CN102953936A (en) | Unit commitment for wind power generation | |
| Kaneriya et al. | A range-based approach for long-term forecast of weather using probabilistic markov model | |
| US10389600B2 (en) | Network management based on modeling of cascading effect of failure | |
| CN113554526A (en) | Fault early warning method and device for power equipment, storage medium and processor | |
| CN116187552A (en) | Abnormality detection method, computing device, and computer storage medium | |
| CN110866634A (en) | Underground cable fault early warning method and device based on model selection | |
| CN117390403A (en) | Power grid fault detection method and system for new energy lighthouse power station | |
| EP3449267A1 (en) | A method for identifying the phases of a multi-phase distribution grid | |
| CN114726740A (en) | Method and system for identifying platform area topology and intelligent fusion terminal | |
| CN113993005A (en) | Power grid equipment inspection method and device, computer equipment and storage medium | |
| CN110807014B (en) | Cross validation based station data anomaly discrimination method and device | |
| CN117668692A (en) | Intelligent electric energy monitoring method, device, equipment and medium based on fault detection | |
| CN111614504A (en) | Power grid regulation and control data center service characteristic fault positioning method and system based on time sequence and fault tree analysis | |
| CN117235664A (en) | Fault diagnosis method and system for power distribution communication equipment and computer equipment | |
| US11379091B2 (en) | Operation support device and operation support method | |
| CN111221849A (en) | Satellite fault positioning method, device, terminal and computer readable medium | |
| CN109633329B (en) | Fault detection method and device for multi-loop energy storage equipment, terminal equipment and medium | |
| CN113570473A (en) | Equipment fault monitoring method and device, computer equipment and storage medium | |
| CN110020472A (en) | A kind of product method for predicting residual useful life, device and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |