Online prediction method and system for remaining service life of hard disk equipment

Abstract

The invention discloses an online prediction method and system for the remaining service life of hard disk equipment, and belongs to the technical field of computer storage. According to the invention, SMART information and I/O state information of hard disk equipment are taken as the basis; remaining service life online prediction of the hard disk equipment is carried out, SMART data records reliability indexes of multiple hard disk operation states, I/O state information comprises time consumed by an I/O request on the hard disk equipment, and time irrelevant to the service life of the harddisk equipment is removed; based on the collected I/O state information, a plurality of derivative variable attributes are generated, and the derivative variables are strongly related to the service life of the hard disk and reflect the internal relation between the hard disk state information and faults; group label assignment is adopted, the training effect is prevented from being affected by using temporary variables with large changes, a bidirectional long-short-term memory neural network is selected as a prediction model, a current value is reasonably predicted in combination with front and back hidden layers, the root mean square error and the average absolute error are effectively reduced, and therefore the hard disk life prediction precision is improved.

Description

Technical field [0001] The invention belongs to the field of computer storage technology, and more specifically, relates to an online prediction method and system for 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 fact cloud services will still fail, resulting in user dissatisfaction and economic losses. The main reasons for the unavailability of system services include: operational errors, virus damage, hardware system failures or software failures (memory errors, network failure lights), equipment hardware failures, etc. Compared with other components such as CPU and memory, the hard disk has the characteristics of large volume and short remaining service life, which is the main part of the hardware failu...

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

Images