Application-aware scaling governor for wearable devices

Jae Min Kim, Minyong Kim, Sung Woo Jung

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Application characteristics include useful information that enhances power management techniques; for instance, a QoS-sensitive application does not need to be run any faster, as long as its QoS is preserved. In recently emerged wearable devices, power management techniques can easily utilize the characteristics, since the number of applications is limited and almost all applications are downloaded from one single application market. In this paper, we analyze the power savings by application-aware scaling governor that manages dynamic voltage frequency scaling (DVFS). Our real measurement results show that the application-aware scaling governor reduces system-wide energy consumption (12% on average) and enhances the performance (10% on average), compared to the conventional scaling governors in case of performance-sensitive applications. In addition, the application-aware scaling governor saves power (10% on average) without any noticeable QoS degradation in case of QoS-sensitive applications.

Original languageEnglish
Title of host publication2014 24th International Workshop on Power and Timing Modeling, Optimization and Simulation, PATMOS 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Print)9781479954124
DOIs
Publication statusPublished - 2014 Nov 10
Event2014 24th International Workshop on Power and Timing Modeling, Optimization and Simulation, PATMOS 2014 - Palma de Mallorca, Spain
Duration: 2014 Sep 292014 Oct 1

Other

Other2014 24th International Workshop on Power and Timing Modeling, Optimization and Simulation, PATMOS 2014
CountrySpain
CityPalma de Mallorca
Period14/9/2914/10/1

Fingerprint

Governors
Scaling
Quality of service
Power Management
Power Saving
Energy Consumption
Degradation
Energy utilization
Voltage

Keywords

  • DVFS
  • Power Management
  • Wearable Devices

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Modelling and Simulation

Cite this

Kim, J. M., Kim, M., & Jung, S. W. (2014). Application-aware scaling governor for wearable devices. In 2014 24th International Workshop on Power and Timing Modeling, Optimization and Simulation, PATMOS 2014 [6951876] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/PATMOS.2014.6951876

Application-aware scaling governor for wearable devices. / Kim, Jae Min; Kim, Minyong; Jung, Sung Woo.

2014 24th International Workshop on Power and Timing Modeling, Optimization and Simulation, PATMOS 2014. Institute of Electrical and Electronics Engineers Inc., 2014. 6951876.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kim, JM, Kim, M & Jung, SW 2014, Application-aware scaling governor for wearable devices. in 2014 24th International Workshop on Power and Timing Modeling, Optimization and Simulation, PATMOS 2014., 6951876, Institute of Electrical and Electronics Engineers Inc., 2014 24th International Workshop on Power and Timing Modeling, Optimization and Simulation, PATMOS 2014, Palma de Mallorca, Spain, 14/9/29. https://doi.org/10.1109/PATMOS.2014.6951876
Kim JM, Kim M, Jung SW. Application-aware scaling governor for wearable devices. In 2014 24th International Workshop on Power and Timing Modeling, Optimization and Simulation, PATMOS 2014. Institute of Electrical and Electronics Engineers Inc. 2014. 6951876 https://doi.org/10.1109/PATMOS.2014.6951876
Kim, Jae Min ; Kim, Minyong ; Jung, Sung Woo. / Application-aware scaling governor for wearable devices. 2014 24th International Workshop on Power and Timing Modeling, Optimization and Simulation, PATMOS 2014. Institute of Electrical and Electronics Engineers Inc., 2014.
@inproceedings{298e699b9dbd4fc0b966aa781eb46928,
title = "Application-aware scaling governor for wearable devices",
abstract = "Application characteristics include useful information that enhances power management techniques; for instance, a QoS-sensitive application does not need to be run any faster, as long as its QoS is preserved. In recently emerged wearable devices, power management techniques can easily utilize the characteristics, since the number of applications is limited and almost all applications are downloaded from one single application market. In this paper, we analyze the power savings by application-aware scaling governor that manages dynamic voltage frequency scaling (DVFS). Our real measurement results show that the application-aware scaling governor reduces system-wide energy consumption (12{\%} on average) and enhances the performance (10{\%} on average), compared to the conventional scaling governors in case of performance-sensitive applications. In addition, the application-aware scaling governor saves power (10{\%} on average) without any noticeable QoS degradation in case of QoS-sensitive applications.",
keywords = "DVFS, Power Management, Wearable Devices",
author = "Kim, {Jae Min} and Minyong Kim and Jung, {Sung Woo}",
year = "2014",
month = "11",
day = "10",
doi = "10.1109/PATMOS.2014.6951876",
language = "English",
isbn = "9781479954124",
booktitle = "2014 24th International Workshop on Power and Timing Modeling, Optimization and Simulation, PATMOS 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Application-aware scaling governor for wearable devices

AU - Kim, Jae Min

AU - Kim, Minyong

AU - Jung, Sung Woo

PY - 2014/11/10

Y1 - 2014/11/10

N2 - Application characteristics include useful information that enhances power management techniques; for instance, a QoS-sensitive application does not need to be run any faster, as long as its QoS is preserved. In recently emerged wearable devices, power management techniques can easily utilize the characteristics, since the number of applications is limited and almost all applications are downloaded from one single application market. In this paper, we analyze the power savings by application-aware scaling governor that manages dynamic voltage frequency scaling (DVFS). Our real measurement results show that the application-aware scaling governor reduces system-wide energy consumption (12% on average) and enhances the performance (10% on average), compared to the conventional scaling governors in case of performance-sensitive applications. In addition, the application-aware scaling governor saves power (10% on average) without any noticeable QoS degradation in case of QoS-sensitive applications.

AB - Application characteristics include useful information that enhances power management techniques; for instance, a QoS-sensitive application does not need to be run any faster, as long as its QoS is preserved. In recently emerged wearable devices, power management techniques can easily utilize the characteristics, since the number of applications is limited and almost all applications are downloaded from one single application market. In this paper, we analyze the power savings by application-aware scaling governor that manages dynamic voltage frequency scaling (DVFS). Our real measurement results show that the application-aware scaling governor reduces system-wide energy consumption (12% on average) and enhances the performance (10% on average), compared to the conventional scaling governors in case of performance-sensitive applications. In addition, the application-aware scaling governor saves power (10% on average) without any noticeable QoS degradation in case of QoS-sensitive applications.

KW - DVFS

KW - Power Management

KW - Wearable Devices

UR - http://www.scopus.com/inward/record.url?scp=84916918844&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84916918844&partnerID=8YFLogxK

U2 - 10.1109/PATMOS.2014.6951876

DO - 10.1109/PATMOS.2014.6951876

M3 - Conference contribution

AN - SCOPUS:84916918844

SN - 9781479954124

BT - 2014 24th International Workshop on Power and Timing Modeling, Optimization and Simulation, PATMOS 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -