Research on disk failure prediction based on random forest algorithm

Chao Li; Dengke Jin; Dashuai Wang; Chuanji Gao

doi:10.1117/12.2642584

28 July 2022 Research on disk failure prediction based on random forest algorithm

Chao Li, Dengke Jin, Dashuai Wang, Chuanji Gao

Proceedings Volume 12303, International Conference on Cloud Computing, Internet of Things, and Computer Applications (CICA 2022); 123032C (2022) https://doi.org/10.1117/12.2642584
Event: International Conference on Cloud Computing, Internet of Things, and Computer Applications, 2022, Luoyang, China

Abstract

Aiming at the problem of low recall and precision of threshold-based disk failure prediction methods, this paper studies disk failure prediction through machine learning methods. By labeling the disk examples in the data set and balancing the number of examples with different labels, after selecting the features that have a greater impact on the results, the machine learning method of random forest is used to train the prediction model, and the performance of the model is verified. When the random forest method predicts the failure of the disk, the recall and the precision are both higher than those of the threshold-based disk failure prediction method.

Citation Download Citation

Chao Li, Dengke Jin, Dashuai Wang, and Chuanji Gao "Research on disk failure prediction based on random forest algorithm", Proc. SPIE 12303, International Conference on Cloud Computing, Internet of Things, and Computer Applications (CICA 2022), 123032C (28 July 2022); https://doi.org/10.1117/12.2642584

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available