Disk failure prediction based on multi-layer domain adaptive learning

TL;DR

This paper introduces a multi-layer domain adaptive learning approach to improve disk failure prediction accuracy, especially when failure samples are scarce, by transferring knowledge from fault-rich data to fault-poor data.

Contribution

It proposes a novel domain adaptive learning method that enhances disk failure prediction by leveraging data from different fault domains, addressing data scarcity issues.

Findings

Improved failure prediction accuracy on limited failure data

Effective transfer of diagnostic knowledge between domains

Demonstrated reliability of the proposed model

Abstract

Large scale data storage is susceptible to failure. As disks are damaged and replaced, traditional machine learning models, which rely on historical data to make predictions, struggle to accurately predict disk failures. This paper presents a novel method for predicting disk failures by leveraging multi-layer domain adaptive learning techniques. First, disk data with numerous faults is selected as the source domain, and disk data with fewer faults is selected as the target domain. A training of the feature extraction network is performed with the selected origin and destination domains. The contrast between the two domains facilitates the transfer of diagnostic knowledge from the domain of source and target. According to the experimental findings, it has been demonstrated that the proposed technique can generate a reliable prediction model and improve the ability to predict failures on disk data with few failure samples.