Authors:
Oussama Djedidi
;
Mohand A. Djeziri
;
Nacer K. M’Sirdi
and
Aziz Naamane
Affiliation:
Aix-Marseille University, Université de Toulon, CNRS, LIS, SASV, Marseille and France
Keyword(s):
Data Fitting, Embedded Systems, Modeling, NARX, Neural Nets, Power Consumption, Smartphone.
Related
Ontology
Subjects/Areas/Topics:
Industrial Engineering
;
Informatics in Control, Automation and Robotics
;
Intelligent Control Systems and Optimization
;
Machine Learning in Control Applications
;
Modeling, Simulation and Architectures
;
Neural Networks Based Control Systems
;
Robotics and Automation
;
Signal Processing, Sensors, Systems Modeling and Control
;
Software Agents for Intelligent Control Systems
;
System Identification
;
System Modeling
;
Systems Modeling and Simulation
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.