Predicting Reliability of Storage Systems
Rahul Nandgave1, Amar Buchade2

1Rahul Nandgave*, Department of Computer Engineering, Pune Institute of Computer Technology, Pune, India.
2Dr. A. R. Buchade, Department of Computer Engineering, Pune Institute of Computer Technology, Pune, India.
Manuscript received on May 13, 2020. | Revised Manuscript received on May 25, 2020. | Manuscript published on June 10, 2020. | PP: 386-388 | Volume-9 Issue-8, June 2020. | Retrieval Number: 100.1/ijitee.F4640049620 | DOI: 10.35940/ijitee.F4640.069820
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Large Organizations have to make use of various storage devices like HDD and SDD to provide storage of information of their clients as well as themselves. These Storage devices are present in large numbers and are the basic building blocks that are used to store information and in case of failure occurs then replacing these devices can halt some services which can cause loss to the Organization in terms of money and time as well. To remediate this we can monitor each of the storage devices, as these storage devices come with a SMART (Self Monitoring and Reporting Technology) system that monitors and reports the stats back to the user. Thus with the help of these SMART Parameters we can train a machine learning model to predict if the hard disk will experience failure in the near future or not. In this study we did a survey of various techniques are based on various machine learning models and provide a brief overview of each of the techniques. Among these techniques we find that random forest and deep learning methods provide better results than the other methods discussed in various studies. 
Keywords: Failure Detection, Machine Learning, Storage Devices, SMART Parameter.
Scope of the Article: Machine Learning