WO2022001125A1 - Procédé, système et dispositif pour prédire une défaillance de mémorisation dans un système de mémoire - Google Patents

Procédé, système et dispositif pour prédire une défaillance de mémorisation dans un système de mémoire Download PDF

Info

Publication number
WO2022001125A1
WO2022001125A1 PCT/CN2021/076815 CN2021076815W WO2022001125A1 WO 2022001125 A1 WO2022001125 A1 WO 2022001125A1 CN 2021076815 W CN2021076815 W CN 2021076815W WO 2022001125 A1 WO2022001125 A1 WO 2022001125A1
Authority
WO
WIPO (PCT)
Prior art keywords
neural network
state data
network model
storage medium
operating state
Prior art date
Application number
PCT/CN2021/076815
Other languages
English (en)
Chinese (zh)
Inventor
晏海龙
张东
颜秉珩
Original Assignee
苏州浪潮智能科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 苏州浪潮智能科技有限公司 filed Critical 苏州浪潮智能科技有限公司
Publication of WO2022001125A1 publication Critical patent/WO2022001125A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/32—Monitoring with visual or acoustical indication of the functioning of the machine
    • G06F11/324—Display of status information
    • G06F11/327—Alarm or error message display
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • 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
    • 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
    • G06N3/045—Combinations of 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

Definitions

  • Q is the minimum utilization rate of preset information, p>m and m is a positive integer;
  • the present application realizes the prediction of the failure of the storage medium based on the operating state data of the storage medium with time-series characteristics and the recurrent neural network for processing the time-series characteristic data, which can significantly advance the failure prediction time, at least several days in advance.
  • the application processes the operation state data of the storage medium to obtain the operation state data whose correlation with the operation change of the storage medium is higher than a certain value for model training, so as to ensure important data. Reduce the amount of data for model training under the principle of less information loss to speed up model training.
  • the subsequent step of testing the first recurrent neural network model based on the test set is not performed until the verification result is that the training of the first recurrent neural network model meets the standard.
  • the application can record the storage failure prediction result of the storage system in the system log, as a basis for subsequent analysis of the storage failure of the system; at the same time, the application can also display the storage failure prediction result on the management interface of the storage system for use. Managers check in time.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Biomedical Technology (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Quality & Reliability (AREA)
  • Debugging And Monitoring (AREA)

Abstract

La présente invention concerne un procédé et un dispositif de prédiction de défaillance de mémorisation dans un système de mémoire. Sur la base de données d'état de fonctionnement d'un support d'informations ayant des caractéristiques de série temporelle et un réseau neuronal cyclique permettant de traiter des données caractéristiques de série temporelle, une prédiction de défaillance pour un support d'informations est obtenue, qui peut avancer de manière significative le moment auquel une défaillance est prédite, permettant de prédire la défaillance du support d'informations au moins quelques jours à l'avance, ce qui permet d'augmenter la sécurité du système. En outre, les données d'état de fonctionnement du support d'informations sont traitées pour obtenir des données d'état de fonctionnement, la corrélation entre lesdites données et les conditions de variation de fonctionnement du support d'informations étant supérieure à une certaine valeur, et un apprentissage de modèle est réalisé, de sorte que la quantité de données pour l'apprentissage de modèle soit réduite selon le principe de garantir que des données et des informations importantes subissent une perte moindre, de façon à augmenter la vitesse d'apprentissage de modèle.
PCT/CN2021/076815 2020-06-30 2021-02-19 Procédé, système et dispositif pour prédire une défaillance de mémorisation dans un système de mémoire WO2022001125A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010616525.3A CN111858265A (zh) 2020-06-30 2020-06-30 一种存储系统的存储故障预测方法、系统及装置
CN202010616525.3 2020-06-30

Publications (1)

Publication Number Publication Date
WO2022001125A1 true WO2022001125A1 (fr) 2022-01-06

Family

ID=72989652

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/076815 WO2022001125A1 (fr) 2020-06-30 2021-02-19 Procédé, système et dispositif pour prédire une défaillance de mémorisation dans un système de mémoire

Country Status (2)

Country Link
CN (1) CN111858265A (fr)
WO (1) WO2022001125A1 (fr)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111858265A (zh) * 2020-06-30 2020-10-30 苏州浪潮智能科技有限公司 一种存储系统的存储故障预测方法、系统及装置
CN112737834A (zh) * 2020-12-25 2021-04-30 北京浪潮数据技术有限公司 一种云硬盘故障预测方法、装置、设备及存储介质
CN112822099A (zh) * 2020-12-29 2021-05-18 北京浪潮数据技术有限公司 一种网卡工作模式的切换方法、装置和介质
CN115758225B (zh) * 2023-01-06 2023-08-29 中建科技集团有限公司 基于多模态数据融合的故障预测方法、装置与存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110106734A1 (en) * 2009-04-24 2011-05-05 Terrance Boult System and appartus for failure prediction and fusion in classification and recognition
CN108647136A (zh) * 2018-05-10 2018-10-12 南京道熵信息技术有限公司 基于smart信息和深度学习的硬盘损坏预测方法及装置
CN109634790A (zh) * 2018-11-22 2019-04-16 华中科技大学 一种基于循环神经网络的磁盘故障预测方法
CN109919335A (zh) * 2019-03-11 2019-06-21 西安电子科技大学 基于深度学习的磁盘故障预测系统
CN110471820A (zh) * 2019-08-05 2019-11-19 南开大学 一种基于循环神经网络的云存储系统磁盘故障预测方法
CN111858265A (zh) * 2020-06-30 2020-10-30 苏州浪潮智能科技有限公司 一种存储系统的存储故障预测方法、系统及装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110106734A1 (en) * 2009-04-24 2011-05-05 Terrance Boult System and appartus for failure prediction and fusion in classification and recognition
CN108647136A (zh) * 2018-05-10 2018-10-12 南京道熵信息技术有限公司 基于smart信息和深度学习的硬盘损坏预测方法及装置
CN109634790A (zh) * 2018-11-22 2019-04-16 华中科技大学 一种基于循环神经网络的磁盘故障预测方法
CN109919335A (zh) * 2019-03-11 2019-06-21 西安电子科技大学 基于深度学习的磁盘故障预测系统
CN110471820A (zh) * 2019-08-05 2019-11-19 南开大学 一种基于循环神经网络的云存储系统磁盘故障预测方法
CN111858265A (zh) * 2020-06-30 2020-10-30 苏州浪潮智能科技有限公司 一种存储系统的存储故障预测方法、系统及装置

Also Published As

Publication number Publication date
CN111858265A (zh) 2020-10-30

Similar Documents

Publication Publication Date Title
WO2022001125A1 (fr) Procédé, système et dispositif pour prédire une défaillance de mémorisation dans un système de mémoire
Bodik et al. Fingerprinting the datacenter: automated classification of performance crises
Lin et al. Predicting node failure in cloud service systems
KR102522005B1 (ko) 가상 네트워크 관리를 위한 머신 러닝 기반 vnf 이상 탐지 시스템 및 방법
US11558272B2 (en) Methods and systems for predicting time of server failure using server logs and time-series data
CN105677538B (zh) 一种基于故障预测的云计算系统自适应监测方法
CN108052528A (zh) 一种存储设备时序分类预警方法
CN111177714B (zh) 异常行为检测方法、装置、计算机设备和存储介质
Oliner et al. Alert detection in system logs
US10373065B2 (en) Generating database cluster health alerts using machine learning
CN110164501B (zh) 一种硬盘检测方法、装置、存储介质及设备
US20110078106A1 (en) Method and system for it resources performance analysis
WO2022089202A1 (fr) Procédé d'entraînement de modèle d'identification de défaillance, procédé d'identification de défaillance, appareil et dispositif électronique
KR101948634B1 (ko) 스마트 컴퓨팅을 위한 시스템 자원의 장애 예측 방법
CN112596964B (zh) 磁盘故障的预测方法及装置
Lim et al. Identifying recurrent and unknown performance issues
CN111124732A (zh) 一种磁盘故障的预测方法、系统、设备及存储介质
CN114325405A (zh) 电池组一致性分析方法、建模方法、装置、设备及介质
CN116701033A (zh) 主机切换异常检测方法、装置、计算机设备和存储介质
CN116821646A (zh) 数据处理链构建方法、数据缩减方法、装置、设备及介质
CN117170915A (zh) 数据中心设备故障预测方法、装置和计算机设备
CN111858108A (zh) 一种硬盘故障预测方法、装置、电子设备和存储介质
CN115729761B (zh) 一种硬盘故障预测方法、系统、设备及介质
CN115964211A (zh) 一种根因定位方法、装置、设备和可读介质
CN111400122A (zh) 一种硬盘健康度评估方法及装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21833792

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21833792

Country of ref document: EP

Kind code of ref document: A1