A Novel Easy-to-construct Power Model for Embedded and Mobile Systems - Using Recursive Neural Nets to Estimate Power Consumption of ARM-based Embedded Systems and Mobile Devices

Oussama Djedidi, Mohand A. Djeziri, Nacer K. M’Sirdi, Aziz Naamane

Abstract

This paper features a novel modeling scheme for power consumption in embedded and mobile devices. The model hereafter presented is built thought data fitting techniques using a NARX nonlinear neural net. It showcases the advantages of using a nonlinear model to estimate power consumption over the widely used linear regression models, where The NARX neural net is simpler, easier to implement, and more importantly more suitable as power changes are not always linear. Finally, experimental results validate the model with one with an accuracy of 97.1% on a smartphone.

Download


Paper Citation


in Harvard Style

Djedidi O., Djeziri M., M’Sirdi N. and Naamane A. (2018). A Novel Easy-to-construct Power Model for Embedded and Mobile Systems - Using Recursive Neural Nets to Estimate Power Consumption of ARM-based Embedded Systems and Mobile Devices.In Proceedings of the 15th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO, ISBN 978-989-758-321-6, pages 541-545. DOI: 10.5220/0006915805410545


in Bibtex Style

@conference{icinco18,
author={Oussama Djedidi and Mohand A. Djeziri and Nacer K. M’Sirdi and Aziz Naamane},
title={A Novel Easy-to-construct Power Model for Embedded and Mobile Systems - Using Recursive Neural Nets to Estimate Power Consumption of ARM-based Embedded Systems and Mobile Devices},
booktitle={Proceedings of the 15th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,},
year={2018},
pages={541-545},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006915805410545},
isbn={978-989-758-321-6},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,
TI - A Novel Easy-to-construct Power Model for Embedded and Mobile Systems - Using Recursive Neural Nets to Estimate Power Consumption of ARM-based Embedded Systems and Mobile Devices
SN - 978-989-758-321-6
AU - Djedidi O.
AU - Djeziri M.
AU - M’Sirdi N.
AU - Naamane A.
PY - 2018
SP - 541
EP - 545
DO - 10.5220/0006915805410545