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 Djeziri; Nacer M'Sirdi; Aziz Naamane

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 ^{1, 2, 3} Mohand Djeziri ⁴ Nacer M'Sirdi Aziz Naamane ⁴

1 SASV - Systèmes Automatisés à Structure Variable

LIS - Laboratoire d'Informatique et Systèmes

2 LIS - Laboratoire d'Informatique et Systèmes

3 AMU - Aix Marseille Université

4 LSIS - Laboratoire des Sciences de l'Information et des Systèmes

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.

Keywords : Smartphone Power Consumption Data Fitting Embedded Systems Modeling NARX Neural Nets

Document type :

Conference papers

Domain :

Engineering Sciences [physics] / Automatic

Cognitive science / Computer science

Physics [physics] / Physics [physics] / Data Analysis, Statistics and Probability [physics.data-an]

Complete list of metadatas

Cited literature [20 references] Display Hide Download

https://hal-amu.archives-ouvertes.fr/hal-01856579
Contributor : Oussama Djedidi <>
Submitted on : Friday, August 17, 2018 - 7:26:59 PM
Last modification on : Tuesday, April 2, 2019 - 2:03:20 AM
Long-term archiving on : Sunday, November 18, 2018 - 12:42:49 PM

ICINCO_2018_209.pdf

Explicit agreement for this submission

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

File

Identifiers

Collections

Citation

Export

Metrics

335

218

Contact

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

File

Identifiers

Collections

Citation

Export

Share

Metrics

335

218

Contact