A method and system for online prediction of the remaining service life of a hard disk device

A technology for hard disks and equipment, applied in the field of online prediction of the remaining service life of hard disk equipment, can solve problems such as inaccurate prediction results of hard disk service life, overcome gradient disappearance and explosion, improve accuracy, and reduce root mean square error and mean absolute error. Effect

Active Publication Date: 2021-06-11
HUAZHONG UNIV OF SCI & TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the defects of the prior art, the purpose of the present invention is to solve the technical problem of inaccurate hard disk life prediction results in the prior art

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A method and system for online prediction of the remaining service life of a hard disk device
  • A method and system for online prediction of the remaining service life of a hard disk device
  • A method and system for online prediction of the remaining service life of a hard disk device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0058] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0059] like figure 1 Shown, a kind of residual service life online prediction method of hard disk device, this method comprises the following steps:

[0060] S1. regularly collect SMART information and I / O status information of hard disk equipment from the data center and store them as historical status data sets and real-time status data sets, and the I / O status information includes consumption of I / O requests on hard disk devices time;

[0061] S2. Through feature engineering, convert the historical state data set into a data pair type data set accepted by the bidirectional long short-term memo...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a method and system for online prediction of the remaining service life of a hard disk device, belonging to the technical field of computer storage. Based on the SMART information and I / O state information of the hard disk device, the present invention performs online prediction of the remaining service life of the hard disk device. The SMART data records a number of reliability indicators of the hard disk operating state, and the I / O state information includes I / O The time consumed by the request on the hard disk device removes the time irrelevant to the life of the hard disk device; based on the collected I / O status information, several derived variable attributes are generated. These derived variables are strongly related to the hard disk life and reflect the hard disk status information Intrinsic relationship with faults; use group label assignment to avoid using large-changing temporary variables to affect the training effect, and use bidirectional long-short-term memory neural network as the prediction model, combined with the front and rear hidden layers to make reasonable predictions for the current value, the root mean square Both the error and the mean absolute error are effectively reduced, thereby improving the accuracy of hard disk life prediction.

Description

technical field [0001] The invention belongs to the technical field of computer storage, and more particularly relates to a method and system for online prediction of the remaining service life of a hard disk device. Background technique [0002] In recent years, more and more software applications have chosen to be deployed as online services on cloud computing platforms such as Microsoft, Google, and Amazon. Although most cloud service providers claim to provide high availability, in reality cloud services still fail, leading to user dissatisfaction and financial loss. The reasons for system service unavailability mainly include: operation error, virus damage, hardware system failure or software failure (memory error, network failure light), equipment hardware failure, etc. Compared with other components such as CPU and memory, and the hard disk has the characteristics of large volume and short remaining service life, it is the main part of hardware failure of storage dev...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06F3/06G06N3/04G06N3/08
CPCG06F3/0616G06F3/0653G06F3/0674G06N3/049G06N3/08G06N3/045
Inventor 谭支鹏张鑫䶮冯丹王芳谢燕文徐高翔
Owner HUAZHONG UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products