Sensor validation in computer systems

A. Urmanov; B. Guenin; K. Gross; A. Gribok

Sensor validation in computer systems

A. Urmanov
, B. Guenin
, K. Gross
, A. Gribok

Nuclear Science & Technology

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

Abstract

A method is described for real time temperature-sensor operability validation to enhance the reliability, availability and serviceability (RAS) of high-end servers. The method can be used in any situation in which system's components are cooled using natural convection, forced airflow or liquid cooling. The method is based on indirect measurements with an approximately known measurement equation obtained using a data-driven inferential sensing technique. A thermal model of a component is derived using the thermal RC networks technique and transformed into a regression problem. Available measurements on the component already mounted and operating in the system are collected over a time period and used to estimate the regression model parameters. The regression problem in our case is ill-conditioned because it is a discretized version of the system identification problem which is inherently ill-posed. The analytical solution shape for the thermal model is used to regularize the solution of the regression problem. The obtained regularized measurement equation is used for the inferential measurement of the component's internal temperature and for sensor operability validation. Experimental results are presented for operability validation of temperature sensors in the components of high-end servers.

Original language	English
Title of host publication	Proceedings of the International Conference on Artificial Intelligence, IC-AI'04 and Proceedings of the International Conference on Machine Learning; Models, Technologies and Applications, MLMTA'04)
Publisher	CSREA Press
Pages	1083-1091
Number of pages	9
ISBN (Print)	1932415335, 9781932415339
State	Published - 2004
Event	2004 International Conference on Artificial Intelligence, IC-AI 2004 - Las Vegas, NV, United States Duration: Jun 21 2004 → Jun 24 2004

Publication series

Name	Proceedings of the International Conference on Artificial Intelligence, IC-AI'04
Volume	2

Conference

Conference	2004 International Conference on Artificial Intelligence, IC-AI 2004
Country/Territory	United States
City	Las Vegas, NV
Period	06/21/04 → 06/24/04

Keywords

Availability and serviceability
High-end servers
Ill-posed problems
Indirect measurements
Regularization
Reliability
Sensor validation

Cite this

Urmanov, A., Guenin, B., Gross, K., & Gribok, A. (2004). Sensor validation in computer systems. In Proceedings of the International Conference on Artificial Intelligence, IC-AI'04 and Proceedings of the International Conference on Machine Learning; Models, Technologies and Applications, MLMTA'04) (pp. 1083-1091). (Proceedings of the International Conference on Artificial Intelligence, IC-AI'04; Vol. 2). CSREA Press.

Urmanov, A. ; Guenin, B. ; Gross, K. et al. / Sensor validation in computer systems. Proceedings of the International Conference on Artificial Intelligence, IC-AI'04 and Proceedings of the International Conference on Machine Learning; Models, Technologies and Applications, MLMTA'04). CSREA Press, 2004. pp. 1083-1091 (Proceedings of the International Conference on Artificial Intelligence, IC-AI'04).

@inproceedings{2fbfa465a0864f508e79e2beeebb8a0a,

title = "Sensor validation in computer systems",

abstract = "A method is described for real time temperature-sensor operability validation to enhance the reliability, availability and serviceability (RAS) of high-end servers. The method can be used in any situation in which system's components are cooled using natural convection, forced airflow or liquid cooling. The method is based on indirect measurements with an approximately known measurement equation obtained using a data-driven inferential sensing technique. A thermal model of a component is derived using the thermal RC networks technique and transformed into a regression problem. Available measurements on the component already mounted and operating in the system are collected over a time period and used to estimate the regression model parameters. The regression problem in our case is ill-conditioned because it is a discretized version of the system identification problem which is inherently ill-posed. The analytical solution shape for the thermal model is used to regularize the solution of the regression problem. The obtained regularized measurement equation is used for the inferential measurement of the component's internal temperature and for sensor operability validation. Experimental results are presented for operability validation of temperature sensors in the components of high-end servers.",

keywords = "Availability and serviceability, High-end servers, Ill-posed problems, Indirect measurements, Regularization, Reliability, Sensor validation",

author = "A. Urmanov and B. Guenin and K. Gross and A. Gribok",

year = "2004",

language = "English",

isbn = "1932415335",

series = "Proceedings of the International Conference on Artificial Intelligence, IC-AI'04",

publisher = "CSREA Press",

pages = "1083--1091",

booktitle = "Proceedings of the International Conference on Artificial Intelligence, IC-AI'04 and Proceedings of the International Conference on Machine Learning; Models, Technologies and Applications, MLMTA'04)",

note = "2004 International Conference on Artificial Intelligence, IC-AI 2004 ; Conference date: 21-06-2004 Through 24-06-2004",

}

Urmanov, A, Guenin, B, Gross, K & Gribok, A 2004, Sensor validation in computer systems. in Proceedings of the International Conference on Artificial Intelligence, IC-AI'04 and Proceedings of the International Conference on Machine Learning; Models, Technologies and Applications, MLMTA'04). Proceedings of the International Conference on Artificial Intelligence, IC-AI'04, vol. 2, CSREA Press, pp. 1083-1091, 2004 International Conference on Artificial Intelligence, IC-AI 2004, Las Vegas, NV, United States, 06/21/04.

Sensor validation in computer systems. / Urmanov, A.; Guenin, B.; Gross, K. et al.
Proceedings of the International Conference on Artificial Intelligence, IC-AI'04 and Proceedings of the International Conference on Machine Learning; Models, Technologies and Applications, MLMTA'04). CSREA Press, 2004. p. 1083-1091 (Proceedings of the International Conference on Artificial Intelligence, IC-AI'04; Vol. 2).

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

TY - GEN

T1 - Sensor validation in computer systems

AU - Urmanov, A.

AU - Guenin, B.

AU - Gross, K.

AU - Gribok, A.

PY - 2004

Y1 - 2004

N2 - A method is described for real time temperature-sensor operability validation to enhance the reliability, availability and serviceability (RAS) of high-end servers. The method can be used in any situation in which system's components are cooled using natural convection, forced airflow or liquid cooling. The method is based on indirect measurements with an approximately known measurement equation obtained using a data-driven inferential sensing technique. A thermal model of a component is derived using the thermal RC networks technique and transformed into a regression problem. Available measurements on the component already mounted and operating in the system are collected over a time period and used to estimate the regression model parameters. The regression problem in our case is ill-conditioned because it is a discretized version of the system identification problem which is inherently ill-posed. The analytical solution shape for the thermal model is used to regularize the solution of the regression problem. The obtained regularized measurement equation is used for the inferential measurement of the component's internal temperature and for sensor operability validation. Experimental results are presented for operability validation of temperature sensors in the components of high-end servers.

AB - A method is described for real time temperature-sensor operability validation to enhance the reliability, availability and serviceability (RAS) of high-end servers. The method can be used in any situation in which system's components are cooled using natural convection, forced airflow or liquid cooling. The method is based on indirect measurements with an approximately known measurement equation obtained using a data-driven inferential sensing technique. A thermal model of a component is derived using the thermal RC networks technique and transformed into a regression problem. Available measurements on the component already mounted and operating in the system are collected over a time period and used to estimate the regression model parameters. The regression problem in our case is ill-conditioned because it is a discretized version of the system identification problem which is inherently ill-posed. The analytical solution shape for the thermal model is used to regularize the solution of the regression problem. The obtained regularized measurement equation is used for the inferential measurement of the component's internal temperature and for sensor operability validation. Experimental results are presented for operability validation of temperature sensors in the components of high-end servers.

KW - Availability and serviceability

KW - High-end servers

KW - Ill-posed problems

KW - Indirect measurements

KW - Regularization

KW - Reliability

KW - Sensor validation

UR - https://www.scopus.com/pages/publications/12744281469

M3 - Conference contribution

AN - SCOPUS:12744281469

SN - 1932415335

SN - 9781932415339

T3 - Proceedings of the International Conference on Artificial Intelligence, IC-AI'04

SP - 1083

EP - 1091

BT - Proceedings of the International Conference on Artificial Intelligence, IC-AI'04 and Proceedings of the International Conference on Machine Learning; Models, Technologies and Applications, MLMTA'04)

PB - CSREA Press

T2 - 2004 International Conference on Artificial Intelligence, IC-AI 2004

Y2 - 21 June 2004 through 24 June 2004

ER -

Urmanov A, Guenin B, Gross K, Gribok A. Sensor validation in computer systems. In Proceedings of the International Conference on Artificial Intelligence, IC-AI'04 and Proceedings of the International Conference on Machine Learning; Models, Technologies and Applications, MLMTA'04). CSREA Press. 2004. p. 1083-1091. (Proceedings of the International Conference on Artificial Intelligence, IC-AI'04).

Sensor validation in computer systems

Abstract

Publication series

Conference

Keywords

Other files and links

Fingerprint

Cite this