CN116932331A - RAID card, battery health monitoring method, system and storage medium thereof - Google Patents

RAID card, battery health monitoring method, system and storage medium thereof Download PDF

Info

Publication number
CN116932331A
CN116932331A CN202310981732.2A CN202310981732A CN116932331A CN 116932331 A CN116932331 A CN 116932331A CN 202310981732 A CN202310981732 A CN 202310981732A CN 116932331 A CN116932331 A CN 116932331A
Authority
CN
China
Prior art keywords
card
data
historical
health degree
battery
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202310981732.2A
Other languages
Chinese (zh)
Inventor
李景彪
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Inspur Power Commercial Systems Co Ltd
Original Assignee
Inspur Power Commercial Systems Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Inspur Power Commercial Systems Co Ltd filed Critical Inspur Power Commercial Systems Co Ltd
Priority to CN202310981732.2A priority Critical patent/CN116932331A/en
Publication of CN116932331A publication Critical patent/CN116932331A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
    • G06F11/3034—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system component is a storage system, e.g. DASD based or network based
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/3051—Monitoring arrangements for monitoring the configuration of the computing system or of the computing system component, e.g. monitoring the presence of processing resources, peripherals, I/O links, software programs
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/3065—Monitoring arrangements determined by the means or processing involved in reporting the monitored data
    • G06F11/3072—Monitoring arrangements determined by the means or processing involved in reporting the monitored data where the reporting involves data filtering, e.g. pattern matching, time or event triggered, adaptive or policy-based reporting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/10—Pre-processing; Data cleansing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/243—Classification techniques relating to the number of classes
    • G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
    • 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
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
    • Y02E60/10—Energy storage using batteries

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Quality & Reliability (AREA)
  • Computing Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application provides a RAID card, a battery health monitoring method, a system and a storage medium thereof, wherein the method comprises the following steps: acquiring historical composite source data comprising RAID card and card battery operation data; generating an abnormal data recognition rule based on a pre-trained health degree recognition model, recognizing composite source data through the abnormal data recognition rule to obtain a historical abnormal data set, taking the historical abnormal data set as input, executing the health degree recognition model, extracting and reducing noise on abnormal data information of the historical abnormal data set in the operation card and the card battery to obtain interference source data; the method comprises the steps of loading the interference-free source data, calculating the card health degree related to the interference-free source data based on a health degree identification model, monitoring historical composite source data in real time through a health degree monitoring module, calculating the card health degree related to the interference-free source data through the health degree identification model, evaluating and predicting the health of the board card, and finally giving a real-time alarm when the health degree of the board card reaches a threshold value.

Description

RAID card, battery health monitoring method, system and storage medium thereof
Technical Field
The application relates to the technical field of data storage, in particular to a RAID card, a battery health monitoring method, a system and a storage medium thereof.
Background
RAID (Redundant Arrays of Independent Disks, redundant array of independent disks) cards are a technology that combines multiple independent disks (physical disks) in different ways to form a hard disk group (logical disk), which can provide higher storage performance and data backup than a single disk.
In order to ensure the safety of data, the RAID card system often has a super capacitor, and the super capacitor can discharge to work under the condition that the system is powered down, so that the data running in the memory is stored in Flash of the RAID card for permanent storage.
However, in practical use, the reliability of the RAID card needs to be further ensured, the RAID card enters an aging period after production is completed, the storage time can affect the service life and the use reliability of the RAID card, and the power failure times of the RAID card can affect the service life and the use reliability of a battery (super capacitor) of the RAID card.
The health monitoring of the RAID card and the battery (super capacitor) of the current server mainly judges the health degree of the RAID card through the working state, if the RAID card cannot protect data in unexpected power failure, the RAID card has faults, or if the RAID card has leakage bulge phenomena in the appearance of the battery or the super capacitor through regular maintenance, the RAID card has faults; however, the prior art cannot predict the occurrence of faults, so that the problem of easy loss of stored data exists.
Therefore, in order to solve the problems, there is a need to provide a better RAID card, and a method, a system and a storage medium for monitoring the battery health of the RAID card.
Disclosure of Invention
In view of the above, the present application is directed to an improved RAID card, and a method, a system and a storage medium for monitoring battery health thereof, so as to improve the prediction rate of faults.
The application provides a RAID card and a battery health monitoring method thereof, which comprises the steps of obtaining historical composite source data containing RAID card and card battery operation data, generating an abnormal data identification rule based on a pre-trained health identification model, identifying the composite source data through the abnormal data identification rule to obtain a historical abnormal data set, removing interference data in abnormal data information to obtain interference-free source data, loading the interference-free source data, and calculating the card health degree related to the interference-free source data based on the health degree identification model. According to the embodiment of the application, the historical composite source data is monitored in real time through the health degree monitoring module, the card health degree associated with the interference source data is calculated through the health degree identification model, the health of the board is estimated and predicted, and finally, real-time warning is carried out when the health degree of the board reaches the threshold value.
Based on the above object, in one aspect, the present application provides a RAID card and a battery health monitoring method thereof, where the method includes the following steps:
acquiring historical composite source data comprising RAID card and card battery operation data;
generating an abnormal data identification rule based on the pre-trained health degree identification model, and identifying the composite source data through the abnormal data identification rule to obtain a historical abnormal data set;
acquiring a historical abnormal data set, taking the historical abnormal data set as input, executing a health degree identification model, extracting and reducing noise of abnormal data information of the historical abnormal data set in the operation card and the card battery, and removing interference data in the abnormal data information to obtain interference source removal data;
and loading the interference-free source data, and calculating the card health degree associated with the interference-free source data based on the health degree identification model.
In some embodiments of the RAID card and battery health monitoring method according to the present application, the method further comprises:
judging whether the card health degree is smaller than a preset health threshold value, and if so, sending an alarm instruction by the health degree monitoring module.
In some embodiments of the RAID card and battery health monitoring method thereof according to the present application, the method for obtaining historical composite source data comprising RAID card and card battery operational data comprises:
reading operation data of the RAID card and the card battery at the current moment through the health monitoring module, and generating a priority processing queue at the current moment according to the operation frequency of the RAID card and the card battery at the current moment;
setting a sequencing consistency threshold of a current time priority processing queue and a historical time priority processing queue, judging the sequencing consistency of the RAID card and the card battery priority processing queue at the current time based on the operation data and the operation frequency of the RAID card and the card battery in a known historical time period, and judging whether to adjust the current time priority processing queue according to the sequencing consistency threshold;
if the operation data and the operation frequency are consistent with the historical operation data and the operation frequency, transmitting a priority processing queue containing the composite source data;
if the running data and the running frequency are inconsistent with the historical running data and the running frequency, the priority processing queue at the current moment is used as the priority processing queue, the priority processing queue at the historical moment is adjusted, and the priority processing queue containing the composite source data is sent.
In some embodiments of the RAID card and the method for monitoring the health of a battery according to the present application, the method for training the health recognition model specifically includes:
reading standard composite source data as model sample data, and dividing the model sample data into a training set, a verification set and a test set according to the proportion of 3:3:1;
training the training set based on a random forest model, and constructing an initial health degree identification initial model in a cross verification mode until the health degree identification initial model converges;
extracting weight parameters of the health degree identification initial model through the verification set, and constructing a network topology graph of the health degree identification initial model based on the weight parameters;
performing structural analysis on the network topological graph of the health degree identification initial model to obtain structural analysis information, and verifying the weight of the structural analysis information through a verification set to obtain a verification result;
and adjusting weight parameters of the health degree identification initial model based on the verification result of the sample data, and continuing training until training conditions are met.
In some embodiments of the RAID card and the method for monitoring battery health of the RAID card according to the present application, the method for extracting and denoising abnormal data information of a historical abnormal data set in a running card and a card battery specifically includes:
the health degree identification model is used for checking the historical abnormal data set;
judging whether the single group of data in the historical abnormal data set is legal data or not, and if not, screening out the single group of data in the historical abnormal data set;
if so, replacing the missing or nonstandard data of the historical abnormal data set by using the regular expression, and performing outlier processing on the historical abnormal data set.
In some embodiments of the RAID card and battery health monitoring method according to the present application, the method further comprises: the method for extracting and denoising the abnormal data information of the historical abnormal data set in the operation card and the card battery further comprises the following steps:
and carrying out noise removal and resampling processing on the processed historical abnormal data set.
In another aspect of the present application, there is also provided a RAID card and a battery health monitoring system thereof, including:
the data acquisition module is used for acquiring historical composite source data containing the RAID card and the card battery operation data;
the model generation module generates an abnormal data identification rule based on the pre-trained health degree identification model, and identifies the composite source data through the abnormal data identification rule to obtain a historical abnormal data set;
the health degree monitoring module is used for acquiring a historical abnormal data set, taking the historical abnormal data set as input, executing a health degree identification model, extracting and reducing noise of abnormal data information of the historical abnormal data set in the operation card and the card battery, and removing interference data in the abnormal data information to obtain interference source removal data;
the health degree calculating module is used for loading the interference source removing data and calculating the card health degree related to the interference source removing data based on the health degree identification model.
In some embodiments of the system for chip testing according to the present application, the data acquisition module comprises:
the processing queue generating unit reads the operation data of the RAID card and the card battery at the current moment through the health monitoring module and generates a priority processing queue at the current moment according to the operation frequency of the RAID card and the card battery at the current moment;
the consistency judging unit is used for setting a sequencing consistency threshold of the priority processing queue at the current moment and the priority processing queue at the historical moment, judging the sequencing consistency of the RAID card and the priority processing queue of the card battery at the current moment based on the operation data and the operation frequency of the RAID card and the card battery in a known historical time period, and judging whether to adjust the priority processing queue at the current moment according to the sequencing consistency threshold;
the queue adjusting unit is used for adjusting the historical time priority processing queue and sending the priority processing queue containing the composite source data.
In some embodiments of the system for chip testing according to the present application, the health monitoring module comprises:
the micro control unit is used for monitoring the battery voltage and monitoring the card power supply voltage;
and the monitoring module power supply part is electrically connected with the micro control unit and is used for supplying power when the RAID card is stored and powered off and the peripheral circuit works in a low-power consumption mode.
In yet another aspect of the present application, there is also provided a computer readable storage medium storing computer program instructions that when executed implement any one of the above-described RAID cards and battery health monitoring methods thereof according to the present application.
It should be noted that the following abbreviations and key terms are defined in the present application:
RAID: redundant Arrays of Independent Disks, disk arrays;
MCU: microcontroller Unit, the micro control unit is used for monitoring the battery voltage and monitoring the card power supply voltage;
IIC: inter-Integrated Circuit, IICBus for short, integrated circuit bus.
The application has at least the following beneficial technical effects: the application provides a RAID card and a battery health monitoring method thereof, wherein a health monitoring module is used for monitoring historical composite source data in real time, calculating the card health degree related to interference source data through a health degree identification model, evaluating and predicting the health of the board card, and finally giving a real-time alarm when the health degree of the board card reaches a threshold value.
According to the embodiment of the application, the health degree recognition model is continuously trained, so that the output training result is more accurate, meanwhile, the health degree recognition model is combined with the neural network model and is based on the random forest model, the problem of inaccurate health degree recognition can be avoided, and the monitoring and analyzing capacity of the health degree monitoring module is further improved.
When the noise removal is carried out on the processed historical abnormal data set, the tolerance calculation function is used for carrying out tolerance calculation on the historical abnormal data, the prior failure standby mechanism is adopted, the information of the historical abnormal data set which is not clearly identified is filtered and removed, and when the information is removed, the dark channel is used for removing the noise of the processed historical abnormal data set, so that the calculation load of the health degree identification model can be remarkably reduced.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are necessary for the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application and that other embodiments may be obtained according to these drawings without inventive effort for a person skilled in the art.
In the figure:
FIG. 1 shows a schematic diagram of an implementation flow of a RAID card and a battery health monitoring method thereof;
FIG. 2 is a schematic diagram of an implementation flow of a method of obtaining historical composite source data comprising RAID card and card battery operational data;
FIG. 3 shows a schematic flow diagram of an implementation of a training method of a health recognition model;
FIG. 4 is a schematic flow chart of an implementation of a method for extracting and denoising anomaly data information of a historical anomaly data set in a run card and a card battery;
FIG. 5 is a schematic diagram showing an implementation flow of a method for noise-removing and resampling a processed historical anomaly data set;
FIG. 6 shows a schematic diagram of a RAID card and its battery health monitoring system.
FIG. 7 shows a schematic diagram of a data acquisition module;
fig. 8 shows a schematic structural diagram of the health monitoring module.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the following embodiments of the present application will be described in further detail with reference to the accompanying drawings.
It should be noted that, in the embodiments of the present application, all the expressions "first" and "second" are used to distinguish two non-identical entities with the same name or non-identical parameters, and it is noted that the "first" and "second" are only used for convenience of expression, and should not be construed as limiting the embodiments of the present application. Furthermore, the terms "comprise" and "have," and any variations thereof, are intended to cover a non-exclusive inclusion, such as a process, method, system, article, or other step or unit that comprises a list of steps or units.
Briefly, the application provides a RAID card and a battery health monitoring method thereof, which comprises the steps of obtaining historical composite source data containing RAID card and card battery operation data, generating an abnormal data identification rule based on a pre-trained health identification model, identifying the composite source data through the abnormal data identification rule to obtain a historical abnormal data set, removing interference data in abnormal data information to obtain interference-free source data, loading the interference-free source data, and calculating the card health degree associated with the interference-free source data based on the health degree identification model. According to the embodiment of the application, the historical composite source data is monitored in real time through the health degree monitoring module, the card health degree associated with the interference source data is calculated through the health degree identification model, the health of the board is estimated and predicted, and finally, real-time warning is carried out when the health degree of the board reaches the threshold value.
Example 1
The embodiment of the application provides a RAID card and a battery health monitoring method thereof, as shown in fig. 1, which shows an implementation flow diagram of the RAID card and the battery health monitoring method thereof, wherein the RAID card and the battery health monitoring method thereof specifically comprise the following steps:
step S10, historical composite source data containing RAID card and card battery operation data is obtained;
step S20, generating an abnormal data identification rule based on a pre-trained health degree identification model, and identifying the composite source data through the abnormal data identification rule to obtain a historical abnormal data set;
step S30, a historical abnormal data set is obtained, the historical abnormal data set is taken as input, a health degree identification model is executed, abnormal data information of the historical abnormal data set in the operation card and the card battery is extracted and noise reduction is carried out, interference data in the abnormal data information is removed, and interference source removal data are obtained;
step S40, loading the interference source removing data, and calculating the card health degree related to the interference source removing data based on the health degree identification model;
step S50, judging whether the card health degree is smaller than a preset health threshold value, and if so, sending an alarm instruction by the health degree monitoring module.
It should be noted that the historical composite source data includes, but is not limited to, the number of times, time and duration of power-on of the RAID card, and includes the number of times of charge and discharge, full voltage, stop-and-go voltage, etc. of the RAID card battery (or super capacitor), and the storage time, running time and running AC power-off time after production.
According to the embodiment of the application, the historical composite source data is monitored in real time through the health degree monitoring module, the card health degree associated with the interference source data is calculated through the health degree identification model, the health of the board is estimated and predicted, and finally, real-time warning is carried out when the health degree of the board reaches the threshold value.
The embodiment of the application provides a method for acquiring historical composite source data containing RAID card and card battery operation data, as shown in fig. 2, which shows an implementation flow diagram of the method for acquiring the historical composite source data containing RAID card and card battery operation data, the method for acquiring the historical composite source data containing RAID card and card battery operation data specifically comprises the following steps:
step S101, reading operation data of a RAID card and a card battery at the current moment through a health monitoring module, and generating a priority processing queue at the current moment according to the operation frequency of the RAID card and the card battery at the current moment;
step S102, setting a sequencing consistency threshold of a current time priority processing queue and a historical time priority processing queue, judging the sequencing consistency of the RAID card and the card battery priority processing queue at the current time based on the operation data and the operation frequency of the RAID card and the card battery in a known historical time period, and judging whether to adjust the current time priority processing queue according to the sequencing consistency threshold;
step S103, if the operation data and the operation frequency are consistent with the historical operation data and the operation frequency, a priority processing queue containing the composite source data is sent;
step S104, if the operation data and the operation frequency are inconsistent with the historical operation data and the operation frequency, the historical time priority processing queue is adjusted based on the current time priority processing queue, and the priority processing queue containing the composite source data is sent.
It should be noted that, the running frequency of the RAID card and the card battery at the current moment is calculated by using the specific gravity of the RAID card and the card battery combination system occupied by the number of times, the moment and the duration of powering up the RAID card, and meanwhile, the ranking consistency threshold is generally set to 1, if the single group of data in the historical moment priority processing queue is inconsistent with the current moment priority processing queue, the consistency threshold is exceeded, so that the historical moment priority processing queue needs to be adjusted, so that the historical moment priority processing queue is consistent with the current moment priority processing queue.
Example 2
The embodiment of the application provides a training method of a health degree identification model, as shown in fig. 3, which shows an implementation flow diagram of the training method of the health degree identification model, wherein the training method of the health degree identification model specifically comprises the following steps:
step S201, reading standard composite source data as model sample data, and dividing the model sample data into a training set, a verification set and a test set according to the ratio of 3:3:1;
step S202, training the training set based on a random forest model, and constructing an initial health degree identification initial model in a cross verification mode until the health degree identification initial model converges;
step S203, extracting weight parameters of the health degree identification initial model through the verification set, and constructing a network topological graph of the health degree identification initial model based on the weight parameters;
step S204, carrying out structural analysis on the network topological graph of the health degree identification initial model to obtain structural analysis information, and verifying the weight of the structural analysis information through a verification set to obtain a verification result;
step S205, based on the verification result of the sample data, adjusting the weight parameters of the health degree identification initial model, and continuing training until the training condition is met.
It should be noted that, the continuous training of the health degree recognition model can make the output training result more accurate, the health degree recognition model is a machine neural network model based on a neural network model and a random forest model, the neural network (NeuralNetworks, NN) is a complex neural network system formed by widely interconnecting a plurality of simple processing units (called neurons), which reflects many basic characteristics of the brain function of a person, and is a highly complex nonlinear power learning system. In brief, it is a mathematical model.
According to the embodiment of the application, the health degree recognition model is continuously trained, so that the output training result is more accurate, meanwhile, the health degree recognition model is combined with the neural network model and is based on the random forest model, the problem of inaccurate health degree recognition can be avoided, and the monitoring and analyzing capacity of the health degree monitoring module is further improved.
The embodiment of the application provides a method for extracting and denoising abnormal data information of a historical abnormal data set in an operation card and a card battery, as shown in fig. 4, which shows an implementation flow diagram of the method for extracting and denoising the abnormal data information of the historical abnormal data set in the operation card and the card battery, wherein the method for extracting and denoising the abnormal data information of the historical abnormal data set in the operation card and the card battery specifically comprises the following steps:
step S301, checking a historical abnormal data set by using a health degree identification model;
step S302, judging whether the single group data in the historical abnormal data set is legal data or not, if not, screening out the single group data in the historical abnormal data set;
and step S303, if yes, replacing the missing or nonstandard data of the historical abnormal data set by using the regular expression, and performing abnormal value processing on the historical abnormal data set.
And step S304, performing noise removal and resampling processing on the processed historical abnormal data set.
When the noise is removed from the processed historical abnormal data set, tolerance calculation is performed on the historical abnormal data through a tolerance calculation function, the prior failure standby mechanism is adopted, the information of the historical abnormal data set which is not clearly identified is filtered and removed, and when the information is removed, the information is removed through a dark channel, the noise is removed from the processed historical abnormal data set, so that the calculation load of the health degree identification model can be remarkably reduced.
The embodiment of the application provides a method for carrying out noise removal and resampling processing on a processed historical abnormal data set, and as shown in fig. 5, the method for carrying out noise removal and resampling processing on the processed historical abnormal data set is shown as an implementation flow diagram of the method, and specifically comprises the following steps:
step S3041, calculating a historical abnormal data set through a frame difference algorithm to obtain a resampling result;
step S3042, judging whether the resampling result is larger than a trigger threshold set by a preset trigger rule, if so, resampling is not needed;
and step S3043, if the trigger threshold value is smaller than the trigger threshold value, generating an application resampling twin rule, realizing quantitative resampling and real-time monitoring of the complex historical abnormal data set, and resampling associated data sources and associated traceability.
Specifically, when the historical abnormal data set is calculated through a frame difference algorithm, four adjacent groups of data of the historical abnormal data set are selected through a health monitoring module, a first group, a second group, a third group and a fourth group are defined, then two groups of difference values are calculated respectively to obtain gray scale associated values, and the calculated gray scale associated values are subjected to AND operation to obtain an analysis data information function, when output information is 1, resampling is needed, and when the output information is 0, resampling is not needed.
Example 3
The embodiment of the application also provides a RAID card and a battery health monitoring system thereof, as shown in FIG. 6, which shows a structural schematic diagram of the RAID card and the battery health monitoring system thereof, and the RAID card and the battery health monitoring system thereof specifically comprise:
the data acquisition module 100 is used for acquiring historical composite source data comprising RAID card and card battery operation data;
the model generation module 200 generates an abnormal data identification rule based on the pre-trained health degree identification model, and identifies the composite source data through the abnormal data identification rule to obtain a historical abnormal data set;
the health monitoring module 300 is configured to obtain a historical abnormal data set, take the historical abnormal data set as input, execute a health recognition model, extract and reduce noise of abnormal data information of the historical abnormal data set in the operation card and the card battery, and remove interference data in the abnormal data information to obtain interference source removal data;
the health degree calculating module 400 is configured to load the interference source removing data, and calculate the card health degree associated with the interference source removing data based on the health degree identifying model.
According to the embodiment of the application, the historical composite source data is monitored in real time through the health degree monitoring module, the card health degree associated with the interference source data is calculated through the health degree identification model, the health of the board is estimated and predicted, and finally, real-time warning is carried out when the health degree of the board reaches the threshold value.
It should be noted that, the data acquisition module 100, the model generation module 200, the health monitoring module 300, and the health calculation module 400 implement data interaction in a 5G or DTU communication manner, and the health monitoring module 300 views basic information of the physical machine, performance information of the physical machine, hardware device status of the physical machine, network card of the physical machine, HBA card of the physical machine, and disk function of the physical machine through the physical machine.
The embodiment of the present application further provides a data acquisition module 100, as shown in fig. 7, which shows a schematic structural diagram of the data acquisition module, where the data acquisition module 100 specifically includes:
a processing queue generating unit 110, wherein the processing queue generating unit 110 reads the operation data of the RAID card and the card battery at the current moment through the health monitoring module, and generates a priority processing queue at the current moment according to the operation frequency of the RAID card and the card battery at the current moment;
a consistency judging unit 120, where the consistency judging unit 120 is configured to set a ranking consistency threshold between a priority processing queue at a current time and a priority processing queue at a historical time, judge ranking consistency between the priority processing queue at the current time and the priority processing queue at the current time based on operation data and operation frequency of the RAID card and the card battery in a known historical time period, and judge whether to adjust the priority processing queue at the current time according to the ranking consistency threshold;
and the queue adjusting unit 130 is used for adjusting the priority processing queue at the historical moment and sending the priority processing queue containing the composite source data.
The embodiment of the present application further provides a health monitoring module 300, as shown in fig. 8, which shows a schematic structural diagram of the health monitoring module 300, where the health monitoring module 300 specifically includes:
the micro control unit 310, the micro control unit 310 is used for monitoring the battery voltage and monitoring the card power supply voltage;
the monitoring module power supply part 320 is electrically connected with the micro control unit 310, and the monitoring module power supply part 320 is used for supplying power when the RAID card is stored and powered off and the peripheral circuit works in a low power consumption mode.
It should be noted that, the micro control unit 310 and the monitoring module power supply part 320 can read the monitoring information in-band and out-of-band through the IIC bus, the micro control unit 310 is specifically a low-power consumption MCU, the monitoring module power supply part 320 is specifically a power supply battery, the micro control unit 310 can select STM8L series, and monitor the voltage of the RAID card battery by using the ADC on the chip thereof, and monitor the voltage of the RAID card power supply by using the IO on the chip thereof; the monitoring module power supply unit 320 is specifically. The CR2450 battery, the capacity of the CR2450 battery is about 550mAh, and when the RAID card is in warehouse and is powered off, the STM8L101 and the peripheral circuit work in a low-power consumption mode and are powered by the CR2450 battery, and the full-period power supply of the monitoring circuit can be met through calculation.
The health degree is calculated by the following way:
health = initial health-k1 x warehouse time-k2 x power-on run time-k3 x power-off protection times.
It should be noted that: the initial health, K1, K2, K3, will vary from RAID card to RAID card and from battery to battery (super capacitor), and will alert when the health is less than a threshold (typically zero).
In a third aspect of the embodiments of the present application, a computer readable storage medium is provided, and fig. 5 is a schematic diagram of a computer readable storage medium of a RAID card and a battery health monitoring method according to an embodiment of the present application. The computer readable storage medium stores computer program instructions executable by a processor. Which when executed, performs the method of any of the embodiments described above.
It should be appreciated that all of the embodiments, features and advantages set forth above with respect to a RAID card and battery health monitoring method thereof according to the present application are equally applicable to a system and storage medium for chip testing according to the present application without conflict.
In a fourth aspect of the embodiments of the present application, there is also provided a computer device comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, implements the method of any of the embodiments described above:
step S10, historical composite source data containing RAID card and card battery operation data is obtained;
step S20, generating an abnormal data identification rule based on a pre-trained health degree identification model, and identifying the composite source data through the abnormal data identification rule to obtain a historical abnormal data set;
step S30, a historical abnormal data set is obtained, the historical abnormal data set is taken as input, a health degree identification model is executed, abnormal data information of the historical abnormal data set in the operation card and the card battery is extracted and noise reduction is carried out, interference data in the abnormal data information is removed, and interference source removal data are obtained;
step S40, loading the interference source removing data, and calculating the card health degree related to the interference source removing data based on the health degree identification model;
step S50, judging whether the card health degree is smaller than a preset health threshold value, and if so, sending an alarm instruction by the health degree monitoring module.
A processor and a memory are included in the computer device, and may further include: input means and output means. The processor, memory, input devices, and output devices may be connected by a bus or other means, as illustrated by a bus connection. The input device may receive input numeric or character information and generate signal inputs related to chip testing. The output means may comprise a display device such as a display screen.
The memory is used as a non-volatile computer readable storage medium for storing non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions/modules corresponding to the RAID card and the battery health monitoring method according to the embodiments of the present application. The memory may include a memory program area and a memory data area, wherein the memory program area may store an operating system, at least one application program required for a function; the storage data area may store a RAID card, data created using the battery health monitoring method, and the like. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory optionally includes memory remotely located relative to the processor, the remote memory being connectable to the local module through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The processor executes various functional applications and data processing of the server by running nonvolatile software programs, instructions and modules stored in the memory, namely, the RAID card and the battery health monitoring method thereof in the method embodiment are realized.
Those of skill would further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the disclosure herein may be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as software or hardware depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.
Finally, it should be noted that the computer-readable storage media (e.g., memory) herein can be either volatile memory or nonvolatile memory, or can include both volatile and nonvolatile memory. By way of example, and not limitation, nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM), which acts as external cache memory. By way of example, and not limitation, RAM may be available in a variety of forms such as synchronous RAM (DRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), and Direct Rambus RAM (DRRAM). The storage devices of the disclosed aspects are intended to comprise, without being limited to, these and other suitable types of memory.
The various illustrative logical blocks, modules, and circuits described in connection with the disclosure herein may be implemented or performed with the following components designed to perform the functions herein: a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof. A general purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP and/or any other such configuration.
The foregoing is an exemplary embodiment of the present disclosure, but it should be noted that various changes and modifications could be made herein without departing from the scope of the disclosure as defined by the appended claims. The functions, steps and/or actions of the method claims in accordance with the disclosed embodiments described herein need not be performed in any particular order. Furthermore, although elements of the disclosed embodiments may be described or claimed in the singular, the plural is contemplated unless limitation to the singular is explicitly stated.
According to the embodiment of the application, the historical composite source data is monitored in real time through the health degree monitoring module, the card health degree associated with the interference source data is calculated through the health degree identification model, the health of the board is estimated and predicted, and finally, real-time warning is carried out when the health degree of the board reaches the threshold value.
It should be understood that as used herein, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly supports the exception. It should also be understood that "and/or" as used herein is meant to include any and all possible combinations of one or more of the associated listed items. The foregoing embodiment of the present application has been disclosed with reference to the number of embodiments for the purpose of description only, and does not represent the advantages or disadvantages of the embodiments.
Those of ordinary skill in the art will appreciate that: the above discussion of any embodiment is merely exemplary and is not intended to imply that the scope of the disclosure of embodiments of the application, including the claims, is limited to such examples; combinations of features of the above embodiments or in different embodiments are also possible within the idea of an embodiment of the application, and many other variations of the different aspects of the embodiments of the application as described above exist, which are not provided in detail for the sake of brevity. Therefore, any omission, modification, equivalent replacement, improvement, etc. of the embodiments should be included in the protection scope of the embodiments of the present application.

Claims (10)

1. A magnetic disk array card and a battery health monitoring method thereof are characterized by comprising the following steps:
acquiring historical composite source data comprising disk array card and card battery operation data;
generating an abnormal data identification rule based on the pre-trained health degree identification model, and identifying the composite source data through the abnormal data identification rule to obtain a historical abnormal data set;
acquiring a historical abnormal data set, taking the historical abnormal data set as input, executing a health degree identification model, extracting and reducing noise of abnormal data information of the historical abnormal data set in the operation card and the card battery, and removing interference data in the abnormal data information to obtain interference source removal data;
and loading the interference-free source data, and calculating the card health degree associated with the interference-free source data based on the health degree identification model.
2. The method according to claim 1, wherein the method further comprises:
judging whether the card health degree is smaller than a preset health threshold value, and if so, sending an alarm instruction by the health degree monitoring module.
3. The method of claim 2, wherein the method of obtaining historical composite source data comprising disk array card and card battery operational data comprises:
reading operation data of the disk array card and the card battery at the current moment through the health monitoring module, and generating a priority processing queue at the current moment according to the operation frequency of the disk array card and the card battery at the current moment;
setting a sequencing consistency threshold of a current time priority processing queue and a historical time priority processing queue, judging the sequencing consistency of the disk array card and the card battery priority processing queue at the current time based on the operation data and the operation frequency of the disk array card and the card battery in a known historical time period, and judging whether to adjust the current time priority processing queue according to the sequencing consistency threshold;
if the operation data and the operation frequency are consistent with the historical operation data and the operation frequency, transmitting a priority processing queue containing the composite source data;
if the running data and the running frequency are inconsistent with the historical running data and the running frequency, the priority processing queue at the current moment is used as the priority processing queue, the priority processing queue at the historical moment is adjusted, and the priority processing queue containing the composite source data is sent.
4. A method according to any one of claims 1 to 3, characterized in that the training method of the health recognition model specifically comprises:
reading standard composite source data as model sample data, and dividing the model sample data into a training set, a verification set and a test set according to a proportion;
training the training set based on a random forest model, and constructing an initial health degree identification initial model in a cross verification mode until the health degree identification initial model converges;
extracting weight parameters of the health degree identification initial model through the verification set, and constructing a network topology graph of the health degree identification initial model based on the weight parameters;
performing structural analysis on the network topological graph of the health degree identification initial model to obtain structural analysis information, and verifying the weight of the structural analysis information through a verification set to obtain a verification result;
and adjusting weight parameters of the health degree identification initial model based on the verification result of the sample data, and continuing training until training conditions are met.
5. A method according to any one of claims 1 to 3, wherein the method for extracting and denoising the abnormal data information of the historical abnormal data set in the operation card and the card battery specifically comprises:
the health degree identification model is used for checking the historical abnormal data set;
judging whether the single group of data in the historical abnormal data set is legal data or not, and if not, screening out the single group of data in the historical abnormal data set;
if so, replacing the missing or nonstandard data of the historical abnormal data set by using the regular expression, and performing outlier processing on the historical abnormal data set.
6. The method of claim 5, wherein the method of extracting and denoising the anomaly data information of the historical anomaly data set in the run card and the card battery further comprises:
and carrying out noise removal and resampling processing on the processed historical abnormal data set.
7. The utility model provides a disk array card and battery health degree monitored control system thereof which characterized in that, disk array card and battery health degree monitored control system includes:
the data acquisition module is used for acquiring historical composite source data containing the operation data of the disk array card and the card battery;
the model generation module generates an abnormal data identification rule based on the pre-trained health degree identification model, and identifies the composite source data through the abnormal data identification rule to obtain a historical abnormal data set;
the health degree monitoring module is used for acquiring a historical abnormal data set, taking the historical abnormal data set as input, executing a health degree identification model, extracting and reducing noise of abnormal data information of the historical abnormal data set in the operation card and the card battery, and removing interference data in the abnormal data information to obtain interference source removal data;
the health degree calculating module is used for loading the interference source removing data and calculating the card health degree related to the interference source removing data based on the health degree identification model.
8. The system of claim 7, wherein the data acquisition module comprises:
the processing queue generating unit reads the operation data of the disk array card and the card battery at the current moment through the health monitoring module and generates a priority processing queue at the current moment according to the operation frequency of the disk array card and the card battery at the current moment;
the consistency judging unit is used for setting a sequencing consistency threshold of the priority processing queue at the current moment and the priority processing queue at the historical moment, judging the sequencing consistency of the priority processing queue of the disk array card and the card battery at the current moment based on the operation data and the operation frequency of the disk array card and the card battery in a known historical time period, and judging whether to adjust the priority processing queue at the current moment according to the sequencing consistency threshold;
the queue adjusting unit is used for adjusting the historical time priority processing queue and sending the priority processing queue containing the composite source data.
9. The system of claim 8, wherein the health monitoring module comprises:
the micro control unit is used for monitoring the battery voltage and monitoring the card power supply voltage;
and the monitoring module power supply part is electrically connected with the micro control unit and is used for supplying power when the disk array card is stored and powered off and the peripheral circuit works in a low-power consumption mode.
10. A computer readable storage medium, storing computer program instructions which, when executed, implement the disk array card and its battery health monitoring method according to any one of claims 1-6.
CN202310981732.2A 2023-08-04 2023-08-04 RAID card, battery health monitoring method, system and storage medium thereof Pending CN116932331A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310981732.2A CN116932331A (en) 2023-08-04 2023-08-04 RAID card, battery health monitoring method, system and storage medium thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310981732.2A CN116932331A (en) 2023-08-04 2023-08-04 RAID card, battery health monitoring method, system and storage medium thereof

Publications (1)

Publication Number Publication Date
CN116932331A true CN116932331A (en) 2023-10-24

Family

ID=88378989

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310981732.2A Pending CN116932331A (en) 2023-08-04 2023-08-04 RAID card, battery health monitoring method, system and storage medium thereof

Country Status (1)

Country Link
CN (1) CN116932331A (en)

Similar Documents

Publication Publication Date Title
CN110688617B (en) Fan vibration abnormity detection method and device
CN113708493B (en) Cloud edge cooperation-based power distribution terminal operation and maintenance method and device and computer equipment
CN112559305B (en) Method, device and equipment for predicting performance of key module in uninterruptible power supply system
CN111262750B (en) Method and system for evaluating baseline model
CN112433907A (en) Method and device for processing host operation parameter data of uninterruptible power supply and electronic device
Levitin et al. Optimal operation and maintenance scheduling in m-out-of-n standby systems with reusable elements
CN111445034A (en) System and method for predicting industrial equipment failure
CN116663746A (en) Power load prediction method and device, computer equipment and storage medium
CN110136841B (en) Disease onset prediction method, device and computer readable storage medium
CN116894539A (en) Clothing production monitoring method, system and medium
CN113487182B (en) Device health state evaluation method, device, computer device and medium
CN113919546A (en) Visual prediction system of equipment life
CN116502544B (en) Electric screw press life prediction method and system based on data fusion
CN116932331A (en) RAID card, battery health monitoring method, system and storage medium thereof
CN112907911A (en) Intelligent anomaly identification and alarm algorithm based on equipment process data
CN109934499B (en) Method, device, equipment and storage medium for evaluating low-voltage fault of equipment
CN113808727B (en) Device monitoring method, device, computer device and readable storage medium
CN115827318A (en) Data center exception handling method and device, electronic equipment and medium
CN114089206A (en) Method, system, medium and device for predicting service life of battery redundancy module
CN115018366B (en) Energy storage system working state monitoring method and device, storage medium and electronic equipment
CN117906240A (en) Air conditioner fault detection method and device, electronic equipment and storage medium
CN116842723A (en) Performance degradation and reliability association method suitable for server
CN117761444A (en) Method and system for monitoring service life of surge protector
CN117608990A (en) Method, system, equipment and medium for judging data abnormality based on file size
CN117453977A (en) Method and device for displaying running state of metering equipment, storage medium and equipment

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