Research on prediction model for NAND flash bit errors

Debao Wei; Liyan Qiao; Shiyuan Wang; Ning Fu; Xiyuan Peng

doi:10.1109/ICEMI.2015.7494259

Research on prediction model for NAND flash bit errors

School of Electronics and Information Engineering

Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

8 Scopus citations

Abstract

NAND flash memory has become more and more widespread storage medium due to its outstanding read/write performance. With the aggressive scaling of NAND flash memory, the storage reliability continued decreasing. While there are lacks of effective evaluation methods for modeling the NAND flash bit errors, most current studies only focus on the single program disturb error or the data retention error. If conducting a method to completely evaluate NAND flash error distribution, it will provide significative guidance for Flash Translation Layer (FTL) algorithms and Error Correction Codes (ECC) to improve the performance of NAND flash. To solve these problems, we have obtained a large amount of data about bit errors from our experimental platform for NAND flash. According to the measured data, we first proposed a polynomial evaluation model for NAND flash bit errors. To achieve the effective prediction, we compared the effectiveness of different evaluation models. The detailed test results show that our polynomial prediction model for NAND flash bit errors has good approximation ability and strong error tolerance, and the model will have comprehensive applications prospect.

Original language	English
Title of host publication	2015 IEEE 12th International Conference on Electronic Measurement and Instruments, ICEMI 2015
Editors	Cui Jianping, Wu Juan
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	233-238
Number of pages	6
ISBN (Electronic)	9781479976195
DOIs	https://doi.org/10.1109/ICEMI.2015.7494259
State	Published - 16 Jun 2016
Event	12th IEEE International Conference on Electronic Measurement and Instruments, ICEMI 2015 - Qingdao, China Duration: 16 Jul 2015 → 18 Jul 2015

Publication series

Name	2015 IEEE 12th International Conference on Electronic Measurement and Instruments, ICEMI 2015
Volume	1

Conference

Conference	12th IEEE International Conference on Electronic Measurement and Instruments, ICEMI 2015
Country/Territory	China
City	Qingdao
Period	16/07/15 → 18/07/15

Keywords

Bit error prediction
Modelling
NAND flash
Neural
Polynomial

Access to Document

10.1109/ICEMI.2015.7494259

Cite this

Wei, D., Qiao, L., Wang, S., Fu, N., & Peng, X. (2016). Research on prediction model for NAND flash bit errors. In C. Jianping, & W. Juan (Eds.), 2015 IEEE 12th International Conference on Electronic Measurement and Instruments, ICEMI 2015 (pp. 233-238). Article 7494259 (2015 IEEE 12th International Conference on Electronic Measurement and Instruments, ICEMI 2015; Vol. 1). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICEMI.2015.7494259

Wei, Debao ; Qiao, Liyan ; Wang, Shiyuan et al. / Research on prediction model for NAND flash bit errors. 2015 IEEE 12th International Conference on Electronic Measurement and Instruments, ICEMI 2015. editor / Cui Jianping ; Wu Juan. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 233-238 (2015 IEEE 12th International Conference on Electronic Measurement and Instruments, ICEMI 2015).

@inproceedings{4d7f550cae284d8d93fab477292748ea,

title = "Research on prediction model for NAND flash bit errors",

abstract = "NAND flash memory has become more and more widespread storage medium due to its outstanding read/write performance. With the aggressive scaling of NAND flash memory, the storage reliability continued decreasing. While there are lacks of effective evaluation methods for modeling the NAND flash bit errors, most current studies only focus on the single program disturb error or the data retention error. If conducting a method to completely evaluate NAND flash error distribution, it will provide significative guidance for Flash Translation Layer (FTL) algorithms and Error Correction Codes (ECC) to improve the performance of NAND flash. To solve these problems, we have obtained a large amount of data about bit errors from our experimental platform for NAND flash. According to the measured data, we first proposed a polynomial evaluation model for NAND flash bit errors. To achieve the effective prediction, we compared the effectiveness of different evaluation models. The detailed test results show that our polynomial prediction model for NAND flash bit errors has good approximation ability and strong error tolerance, and the model will have comprehensive applications prospect.",

keywords = "Bit error prediction, Modelling, NAND flash, Neural, Polynomial",

author = "Debao Wei and Liyan Qiao and Shiyuan Wang and Ning Fu and Xiyuan Peng",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 12th IEEE International Conference on Electronic Measurement and Instruments, ICEMI 2015 ; Conference date: 16-07-2015 Through 18-07-2015",

year = "2016",

month = jun,

day = "16",

doi = "10.1109/ICEMI.2015.7494259",

language = "英语",

series = "2015 IEEE 12th International Conference on Electronic Measurement and Instruments, ICEMI 2015",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "233--238",

editor = "Cui Jianping and Wu Juan",

booktitle = "2015 IEEE 12th International Conference on Electronic Measurement and Instruments, ICEMI 2015",

address = "美国",

}

Wei, D , Qiao, L, Wang, S, Fu, N & Peng, X 2016, Research on prediction model for NAND flash bit errors. in C Jianping & W Juan (eds), 2015 IEEE 12th International Conference on Electronic Measurement and Instruments, ICEMI 2015., 7494259, 2015 IEEE 12th International Conference on Electronic Measurement and Instruments, ICEMI 2015, vol. 1, Institute of Electrical and Electronics Engineers Inc., pp. 233-238, 12th IEEE International Conference on Electronic Measurement and Instruments, ICEMI 2015, Qingdao, China, 16/07/15. https://doi.org/10.1109/ICEMI.2015.7494259

Research on prediction model for NAND flash bit errors. / Wei, Debao ; Qiao, Liyan; Wang, Shiyuan et al.
2015 IEEE 12th International Conference on Electronic Measurement and Instruments, ICEMI 2015. ed. / Cui Jianping; Wu Juan. Institute of Electrical and Electronics Engineers Inc., 2016. p. 233-238 7494259 (2015 IEEE 12th International Conference on Electronic Measurement and Instruments, ICEMI 2015; Vol. 1).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Research on prediction model for NAND flash bit errors

AU - Wei, Debao

AU - Qiao, Liyan

AU - Wang, Shiyuan

AU - Fu, Ning

AU - Peng, Xiyuan

PY - 2016/6/16

Y1 - 2016/6/16

N2 - NAND flash memory has become more and more widespread storage medium due to its outstanding read/write performance. With the aggressive scaling of NAND flash memory, the storage reliability continued decreasing. While there are lacks of effective evaluation methods for modeling the NAND flash bit errors, most current studies only focus on the single program disturb error or the data retention error. If conducting a method to completely evaluate NAND flash error distribution, it will provide significative guidance for Flash Translation Layer (FTL) algorithms and Error Correction Codes (ECC) to improve the performance of NAND flash. To solve these problems, we have obtained a large amount of data about bit errors from our experimental platform for NAND flash. According to the measured data, we first proposed a polynomial evaluation model for NAND flash bit errors. To achieve the effective prediction, we compared the effectiveness of different evaluation models. The detailed test results show that our polynomial prediction model for NAND flash bit errors has good approximation ability and strong error tolerance, and the model will have comprehensive applications prospect.

AB - NAND flash memory has become more and more widespread storage medium due to its outstanding read/write performance. With the aggressive scaling of NAND flash memory, the storage reliability continued decreasing. While there are lacks of effective evaluation methods for modeling the NAND flash bit errors, most current studies only focus on the single program disturb error or the data retention error. If conducting a method to completely evaluate NAND flash error distribution, it will provide significative guidance for Flash Translation Layer (FTL) algorithms and Error Correction Codes (ECC) to improve the performance of NAND flash. To solve these problems, we have obtained a large amount of data about bit errors from our experimental platform for NAND flash. According to the measured data, we first proposed a polynomial evaluation model for NAND flash bit errors. To achieve the effective prediction, we compared the effectiveness of different evaluation models. The detailed test results show that our polynomial prediction model for NAND flash bit errors has good approximation ability and strong error tolerance, and the model will have comprehensive applications prospect.

KW - Bit error prediction

KW - Modelling

KW - NAND flash

KW - Neural

KW - Polynomial

UR - https://www.scopus.com/pages/publications/84978858560

U2 - 10.1109/ICEMI.2015.7494259

DO - 10.1109/ICEMI.2015.7494259

M3 - 会议稿件

AN - SCOPUS:84978858560

T3 - 2015 IEEE 12th International Conference on Electronic Measurement and Instruments, ICEMI 2015

SP - 233

EP - 238

BT - 2015 IEEE 12th International Conference on Electronic Measurement and Instruments, ICEMI 2015

A2 - Jianping, Cui

A2 - Juan, Wu

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 12th IEEE International Conference on Electronic Measurement and Instruments, ICEMI 2015

Y2 - 16 July 2015 through 18 July 2015

ER -

Wei D , Qiao L, Wang S, Fu N , Peng X. Research on prediction model for NAND flash bit errors. In Jianping C, Juan W, editors, 2015 IEEE 12th International Conference on Electronic Measurement and Instruments, ICEMI 2015. Institute of Electrical and Electronics Engineers Inc. 2016. p. 233-238. 7494259. (2015 IEEE 12th International Conference on Electronic Measurement and Instruments, ICEMI 2015). doi: 10.1109/ICEMI.2015.7494259

Research on prediction model for NAND flash bit errors

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this