Storage device fault prediction method and system

Abstract

The invention discloses a storage device fault prediction method and system, and belongs to the technical field of computer storage. The method comprises the following steps: S1, acquiring SMART attribute data of N storage devices at different time points; S2, disordering the sequence of all the storage devices and selecting the j = 1 storage device; S3, using the SMART attribute data of the storage device at each time point as small-batch samples and input into a fault prediction model for training, and an output result is obtained; S4, dynamically adjusting the label and feedback weight of each sample according to the state of the time point tn of the storage device, the output result, the LTMIN and the LTMAX; s5, calculating the comprehensive loss Lossj of the batch; S6, selecting a next storage device, and repeating the steps S3 to S6; S5, calculating the total loss Lossfinal of all the storage devices in the period until all the storage devices are taken out; S7, judging whether Lossfinal is converged or not, if yes, obtaining a trained prediction model, entering the step S8, and otherwise, entering the step S2; and S8, inputting the current SMART attribute data of the to-be-predicted storage device into the trained prediction model to obtain a prediction result.

Description

technical field [0001] The invention belongs to the technical field of computer storage, and more particularly relates to a storage device failure prediction method and system. Background technique [0002] Due to the low price per storage capacity and mature technology, disks are widely deployed in data centers and are often used in cold data storage, long-term storage, backup storage and other applications. Once the disk fails, it will cause huge data loss if the data is not backed up, and if there is a backup, restoring the data will incur huge overhead, which will easily cause disk and network I / O bursts, affecting Use of Online Business. [0003] Usually, the data center collects the SMART data of the disk and I / O load statistical data, and uses the machine learning model to build a fault prediction model to evaluate the wear degree of the disk, speculate whether the disk will fail in the near future, and analyze the Potentially high-risk disks take fault handling mea...

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 problems that the labels of the training samples of the prior art disk failure prediction method are difficult to determine, resulting in unstable model construction and difficult control of the advance prediction time

Images