A HIERARCHICAL MARKOV RELIABILITY MODEL FOR DATA STORAGE SYSTEMS WITH MEDIA SELF-RECOVERY

Author:

JIN TONGDAN1,XING LIUDONG2,YU YING3

Affiliation:

1. Ingram School of Engineering, Texas State University, San Marcos, TX, USA

2. Department of Electrical and Computer Engineering, University of Massachusetts, Dartmouth, MA, USA

3. Department of Automation, Shanghai University, Shanghai, China

Abstract

A Redundant Array of Independent Disks (RAID) system with n disks or hard drives can be modeled as a k-out-of-n repairable system for which at least k operational disks are required. This paper proposes a hierarchical Markov model to estimate the reliability of RAID systems. The method encompasses Markov models for evaluating the reliability of individual disks at the lower level and the redundant model for evaluating the reliability of entire RAID at the system level. Both hardware and media failures are considered, and the media failures can be potentially recovered via the disk self-restoration mechanism. The system mean-time-to-data-loss is also derived and results are compared to those estimated from system-based Markov models. The major contribution of this work is that the reliability for RAID systems is approached by combining the redundant modeling technique with the single disk-based Markov model, thus simplifying the computational efforts. The proposed method is applied on RAID-5 and RAID-6 systems to demonstrate the applicability and performance of the new model.

Publisher

World Scientific Pub Co Pte Lt

Subject

Electrical and Electronic Engineering,Industrial and Manufacturing Engineering,Energy Engineering and Power Technology,Aerospace Engineering,Safety, Risk, Reliability and Quality,Nuclear Energy and Engineering,General Computer Science

Cited by 9 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Internet of Things support reliability;Reliability and Resilience in the Internet of Things;2024

2. Reliability in Internet of Things: Current Status and Future Perspectives;IEEE Internet of Things Journal;2020-08

3. Design and maintenance for the data storage system considering system rebuilding process;Reliability Engineering & System Safety;2019-11

4. Balancing Reliability and Cost in Cloud-RAID Systems with Fault-Level Coverage;International Journal of Mathematical, Engineering and Management Sciences;2019-10-01

5. Optimizing Imperfect Coverage Cloud-RAID Systems Considering Reliability and Cost;International Journal of Reliability, Quality and Safety Engineering;2019-09-23

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3