Computing and power resources are often limited in real-time embedded control systems. In this paper, we resolve the trade-off problem between control performance and power consumption in a real-time embedded control system with a dynamic voltage and frequency scaling (DVFS) uniprocessor implementing multiple control tasks. We formulate an optimization problem whose cost function depends on both the control performance and the power consumption. We introduce an adapter into the real-time embedded control system that adaptively assigns deadlines of jobs and clock frequencies according to the plant's stability and schedulability by solving the optimization problem. In numerical simulations, we show that the proposed adapter can reduce the power consumption while maintaining the control performance.
Tatsuya YOSHIMOTO
Osaka University
Toshimitsu USHIO
Osaka University
Takuya AZUMI
Osaka University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Tatsuya YOSHIMOTO, Toshimitsu USHIO, Takuya AZUMI, "Adaptive Assignment of Deadline and Clock Frequency in Real-Time Embedded Control Systems" in IEICE TRANSACTIONS on Fundamentals,
vol. E98-A, no. 1, pp. 323-330, January 2015, doi: 10.1587/transfun.E98.A.323.
Abstract: Computing and power resources are often limited in real-time embedded control systems. In this paper, we resolve the trade-off problem between control performance and power consumption in a real-time embedded control system with a dynamic voltage and frequency scaling (DVFS) uniprocessor implementing multiple control tasks. We formulate an optimization problem whose cost function depends on both the control performance and the power consumption. We introduce an adapter into the real-time embedded control system that adaptively assigns deadlines of jobs and clock frequencies according to the plant's stability and schedulability by solving the optimization problem. In numerical simulations, we show that the proposed adapter can reduce the power consumption while maintaining the control performance.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E98.A.323/_p
Copy
@ARTICLE{e98-a_1_323,
author={Tatsuya YOSHIMOTO, Toshimitsu USHIO, Takuya AZUMI, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Adaptive Assignment of Deadline and Clock Frequency in Real-Time Embedded Control Systems},
year={2015},
volume={E98-A},
number={1},
pages={323-330},
abstract={Computing and power resources are often limited in real-time embedded control systems. In this paper, we resolve the trade-off problem between control performance and power consumption in a real-time embedded control system with a dynamic voltage and frequency scaling (DVFS) uniprocessor implementing multiple control tasks. We formulate an optimization problem whose cost function depends on both the control performance and the power consumption. We introduce an adapter into the real-time embedded control system that adaptively assigns deadlines of jobs and clock frequencies according to the plant's stability and schedulability by solving the optimization problem. In numerical simulations, we show that the proposed adapter can reduce the power consumption while maintaining the control performance.},
keywords={},
doi={10.1587/transfun.E98.A.323},
ISSN={1745-1337},
month={January},}
Copy
TY - JOUR
TI - Adaptive Assignment of Deadline and Clock Frequency in Real-Time Embedded Control Systems
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 323
EP - 330
AU - Tatsuya YOSHIMOTO
AU - Toshimitsu USHIO
AU - Takuya AZUMI
PY - 2015
DO - 10.1587/transfun.E98.A.323
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E98-A
IS - 1
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - January 2015
AB - Computing and power resources are often limited in real-time embedded control systems. In this paper, we resolve the trade-off problem between control performance and power consumption in a real-time embedded control system with a dynamic voltage and frequency scaling (DVFS) uniprocessor implementing multiple control tasks. We formulate an optimization problem whose cost function depends on both the control performance and the power consumption. We introduce an adapter into the real-time embedded control system that adaptively assigns deadlines of jobs and clock frequencies according to the plant's stability and schedulability by solving the optimization problem. In numerical simulations, we show that the proposed adapter can reduce the power consumption while maintaining the control performance.
ER -