Reliability prediction model of NAND flash memory based on random forest algorithm

Debao Wei; Liyan Qiao; Mengqi Hao; Hua Feng; Xiyuan Peng

doi:10.1016/j.microrel.2019.06.063

Reliability prediction model of NAND flash memory based on random forest algorithm

Debao Wei
, Liyan Qiao^*
, Mengqi Hao
, Hua Feng
, Xiyuan Peng

^*Corresponding author for this work

School of Electronics and Information Engineering, Harbin Institute of Technology

Research output: Contribution to journal › Article › peer-review

17 Scopus citations

Abstract

Nowadays, NAND flash is widely used for its excellent characteristics. However, the increasing storage capability leads to the decrease of reliability of NAND flash. Therefore, improving the reliability of NAND flash chip has become a hot issue to be solved. If we can find an effective method to predict the error rate distribution of NAND flash, it will provide significant guidance for adapting appropriate error correction algorithm and wear-leveling algorithm. Based on the 200 days of measured data from NAND flash experimental platform, a comprehensive error rate prediction model of NAND flash is established using the random forest algorithm, and the experimental results of the model are analysed and evaluated. And the results show that the proposed stochastic forest algorithm not only has high prediction accuracy, but also operates fast.

Original language	English
Article number	113371
Journal	Microelectronics Reliability
Volume	100-101
DOIs	https://doi.org/10.1016/j.microrel.2019.06.063
State	Published - Sep 2019
Externally published	Yes

Access to Document

10.1016/j.microrel.2019.06.063

Cite this

@article{dbe45c5f689d454497adf3e33e6c3b33,

title = "Reliability prediction model of NAND flash memory based on random forest algorithm",

abstract = "Nowadays, NAND flash is widely used for its excellent characteristics. However, the increasing storage capability leads to the decrease of reliability of NAND flash. Therefore, improving the reliability of NAND flash chip has become a hot issue to be solved. If we can find an effective method to predict the error rate distribution of NAND flash, it will provide significant guidance for adapting appropriate error correction algorithm and wear-leveling algorithm. Based on the 200 days of measured data from NAND flash experimental platform, a comprehensive error rate prediction model of NAND flash is established using the random forest algorithm, and the experimental results of the model are analysed and evaluated. And the results show that the proposed stochastic forest algorithm not only has high prediction accuracy, but also operates fast.",

author = "Debao Wei and Liyan Qiao and Mengqi Hao and Hua Feng and Xiyuan Peng",

note = "Publisher Copyright: {\textcopyright} 2019 Elsevier Ltd",

year = "2019",

month = sep,

doi = "10.1016/j.microrel.2019.06.063",

language = "英语",

volume = "100-101",

journal = "Microelectronics Reliability",

issn = "0026-2714",

publisher = "Elsevier Ltd",

}

TY - JOUR

T1 - Reliability prediction model of NAND flash memory based on random forest algorithm

AU - Wei, Debao

AU - Qiao, Liyan

AU - Hao, Mengqi

AU - Feng, Hua

AU - Peng, Xiyuan

PY - 2019/9

Y1 - 2019/9

N2 - Nowadays, NAND flash is widely used for its excellent characteristics. However, the increasing storage capability leads to the decrease of reliability of NAND flash. Therefore, improving the reliability of NAND flash chip has become a hot issue to be solved. If we can find an effective method to predict the error rate distribution of NAND flash, it will provide significant guidance for adapting appropriate error correction algorithm and wear-leveling algorithm. Based on the 200 days of measured data from NAND flash experimental platform, a comprehensive error rate prediction model of NAND flash is established using the random forest algorithm, and the experimental results of the model are analysed and evaluated. And the results show that the proposed stochastic forest algorithm not only has high prediction accuracy, but also operates fast.

AB - Nowadays, NAND flash is widely used for its excellent characteristics. However, the increasing storage capability leads to the decrease of reliability of NAND flash. Therefore, improving the reliability of NAND flash chip has become a hot issue to be solved. If we can find an effective method to predict the error rate distribution of NAND flash, it will provide significant guidance for adapting appropriate error correction algorithm and wear-leveling algorithm. Based on the 200 days of measured data from NAND flash experimental platform, a comprehensive error rate prediction model of NAND flash is established using the random forest algorithm, and the experimental results of the model are analysed and evaluated. And the results show that the proposed stochastic forest algorithm not only has high prediction accuracy, but also operates fast.

UR - https://www.scopus.com/pages/publications/85074519547

U2 - 10.1016/j.microrel.2019.06.063

DO - 10.1016/j.microrel.2019.06.063

M3 - 文章

AN - SCOPUS:85074519547

SN - 0026-2714

VL - 100-101

JO - Microelectronics Reliability

JF - Microelectronics Reliability

M1 - 113371

ER -

Reliability prediction model of NAND flash memory based on random forest algorithm

Abstract

Access to Document

Other files and links

Fingerprint

Cite this