Evaluating System Identification Methods for Predicting Thermal Dissipation of Heterogeneous SoCs

Joel Öhrling; Sébastien Lafond; Dragos Truscan

doi:https://doi.org/10.48550/arXiv.2112.10121

Evaluating System Identification Methods for Predicting Thermal Dissipation of Heterogeneous SoCs

Joel Öhrling, Sébastien Lafond, Dragos Truscan

Information Technology

Tutkimustuotos: Artikkeli kirjassa/raportissa/konferenssijulkaisussa › Konferenssiartikkeli › Tieteellinen › vertaisarvioitu

8 Lataukset (Pure)

Abstrakti

In this paper we evaluate the use of system identification methods to build a thermal prediction model of heterogeneous SoC platforms that can be used to quickly predict the temperature of difierent configurations without the need of hardware. Specifically, we focus on modeling approaches that can predict the temperature based on the clock frequency and the utilization percentage of each core.
We investigate three methods with respect to their prediction accuracy: a linear state-space identification approach using polynomial regressors, a NARX neural network approach and a recurrent neural network approach configured in an FIR model structure. We evaluate the methods on an Odroid-XU4 board featuring an Exynos 5422 SoC. The results show that the model based on polynomial regressors significantly outperformed the other two models when trained with 1 hour and 6 hours of data.

Alkuperäiskieli	Englanti
Otsikko	Embedded Computer Systems: Architectures, Modeling, and Simulation. SAMOS 2021.
Kustantaja	Springer
Sivut	144-160
Sivumäärä	17
ISBN (painettu)	978-3-031-04579-0
DOI - pysyväislinkit	https://doi.org/10.48550/arXiv.2112.10121 https://doi.org/10.1007/978-3-031-04580-6_10
Tila	Julkaistu - 2022
OKM-julkaisutyyppi	A4 Artikkeli konferenssijulkaisuussa
Tapahtuma	21st International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation, SAMOS 2021 - Virtual, Online Kesto: 4 heinäk. 2021 → 8 heinäk. 2021

Julkaisusarja

Nimi	Lecture Notes in Computer Science
Kustantaja	Springer
Vuosikerta	13227
ISSN (painettu)	0302-9743

Konferenssi

Konferenssi	21st International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation, SAMOS 2021
Kaupunki	Virtual, Online
Ajanjakso	04/07/21 → 08/07/21

Pääsy asiakirjaan

Muut tiedostot ja linkit

Author version, Arxiv.org

Kielletty (embargo) dokumentti

Camera ready version
Hyväksytty kirjoittajan käsikirjoitus, 755 KB
Lisenssi: Publisher rights policy
Kielto päättyy: 27/04/23

AIDOaRT
Porres Paltor, I., Truscan, D., Nybom, K. & Logacheva, E.
01/04/21 → 31/03/24
Projekti: EU

Viittausmuodot

Öhrling, J., Lafond, S., & Truscan, D. (2022). Evaluating System Identification Methods for Predicting Thermal Dissipation of Heterogeneous SoCs. teoksessa Embedded Computer Systems: Architectures, Modeling, and Simulation. SAMOS 2021. (Sivut 144-160). ( Lecture Notes in Computer Science; Vuosikerta 13227). Springer. https://doi.org/10.48550/arXiv.2112.10121, https://doi.org/10.1007/978-3-031-04580-6_10

@inproceedings{2cacc30d0fbe4c94bc6ff164a283e777,

title = "Evaluating System Identification Methods for Predicting Thermal Dissipation of Heterogeneous SoCs",

abstract = "In this paper we evaluate the use of system identification methods to build a thermal prediction model of heterogeneous SoC platforms that can be used to quickly predict the temperature of difierent configurations without the need of hardware. Specifically, we focus on modeling approaches that can predict the temperature based on the clock frequency and the utilization percentage of each core.We investigate three methods with respect to their prediction accuracy: a linear state-space identification approach using polynomial regressors, a NARX neural network approach and a recurrent neural network approach configured in an FIR model structure. We evaluate the methods on an Odroid-XU4 board featuring an Exynos 5422 SoC. The results show that the model based on polynomial regressors significantly outperformed the other two models when trained with 1 hour and 6 hours of data.",

keywords = "energy dissipation, Temperature, Multicore processing, System identification",

author = "Joel {\"O}hrling and S{\'e}bastien Lafond and Dragos Truscan",

note = "Funding Information: Part of this work was carried out with financial support from the Nordic Master programme (contract NMP-2016/10169) and ECSEL-JU AIDOaRt project (grant agreement No. 101007350). Publisher Copyright: {\textcopyright} 2022, Springer Nature Switzerland AG.; 21st International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation, SAMOS 2021 ; Conference date: 04-07-2021 Through 08-07-2021",

year = "2022",

doi = "https://doi.org/10.48550/arXiv.2112.10121",

language = "English",

isbn = "978-3-031-04579-0",

series = " Lecture Notes in Computer Science",

publisher = "Springer",

pages = "144--160",

booktitle = "Embedded Computer Systems: Architectures, Modeling, and Simulation. SAMOS 2021.",

}

Öhrling, J, Lafond, S & Truscan, D 2022, Evaluating System Identification Methods for Predicting Thermal Dissipation of Heterogeneous SoCs. julkaisussa Embedded Computer Systems: Architectures, Modeling, and Simulation. SAMOS 2021. . Lecture Notes in Computer Science, Vuosikerta 13227, Springer, Sivut 144-160, 21st International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation, SAMOS 2021, Virtual, Online, 04/07/21. https://doi.org/10.48550/arXiv.2112.10121, https://doi.org/10.1007/978-3-031-04580-6_10

Evaluating System Identification Methods for Predicting Thermal Dissipation of Heterogeneous SoCs. / Öhrling, Joel; Lafond, Sébastien ; Truscan, Dragos.

Embedded Computer Systems: Architectures, Modeling, and Simulation. SAMOS 2021. . Springer, 2022. s. 144-160 ( Lecture Notes in Computer Science; Vuosikerta 13227).

Tutkimustuotos: Artikkeli kirjassa/raportissa/konferenssijulkaisussa › Konferenssiartikkeli › Tieteellinen › vertaisarvioitu

TY - GEN

T1 - Evaluating System Identification Methods for Predicting Thermal Dissipation of Heterogeneous SoCs

AU - Öhrling, Joel

AU - Lafond, Sébastien

AU - Truscan, Dragos

N1 - Funding Information: Part of this work was carried out with financial support from the Nordic Master programme (contract NMP-2016/10169) and ECSEL-JU AIDOaRt project (grant agreement No. 101007350). Publisher Copyright: © 2022, Springer Nature Switzerland AG.

PY - 2022

Y1 - 2022

N2 - In this paper we evaluate the use of system identification methods to build a thermal prediction model of heterogeneous SoC platforms that can be used to quickly predict the temperature of difierent configurations without the need of hardware. Specifically, we focus on modeling approaches that can predict the temperature based on the clock frequency and the utilization percentage of each core.We investigate three methods with respect to their prediction accuracy: a linear state-space identification approach using polynomial regressors, a NARX neural network approach and a recurrent neural network approach configured in an FIR model structure. We evaluate the methods on an Odroid-XU4 board featuring an Exynos 5422 SoC. The results show that the model based on polynomial regressors significantly outperformed the other two models when trained with 1 hour and 6 hours of data.

AB - In this paper we evaluate the use of system identification methods to build a thermal prediction model of heterogeneous SoC platforms that can be used to quickly predict the temperature of difierent configurations without the need of hardware. Specifically, we focus on modeling approaches that can predict the temperature based on the clock frequency and the utilization percentage of each core.We investigate three methods with respect to their prediction accuracy: a linear state-space identification approach using polynomial regressors, a NARX neural network approach and a recurrent neural network approach configured in an FIR model structure. We evaluate the methods on an Odroid-XU4 board featuring an Exynos 5422 SoC. The results show that the model based on polynomial regressors significantly outperformed the other two models when trained with 1 hour and 6 hours of data.

KW - energy dissipation

KW - Temperature

KW - Multicore processing

KW - System identification

UR - https://arxiv.org/abs/2112.10121

U2 - https://doi.org/10.48550/arXiv.2112.10121

DO - https://doi.org/10.48550/arXiv.2112.10121

M3 - Conference contribution

AN - SCOPUS:85129800655

SN - 978-3-031-04579-0

T3 - Lecture Notes in Computer Science

SP - 144

EP - 160

BT - Embedded Computer Systems: Architectures, Modeling, and Simulation. SAMOS 2021.

PB - Springer

T2 - 21st International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation, SAMOS 2021

Y2 - 4 July 2021 through 8 July 2021

ER -

Evaluating System Identification Methods for Predicting Thermal Dissipation of Heterogeneous SoCs

Abstrakti

Julkaisusarja

Konferenssi

Pääsy asiakirjaan

Muut tiedostot ja linkit

Kielletty (embargo) dokumentti

Sormenjälki

Projektit

AIDOaRT

Viittausmuodot