Calibrating parameters and formulas for process-level energy consumption profiling in smartphones

Battery-powered mobile devices substantially constrain energy resources. Process-level energy profiling tools can identify the most energy-consuming process and detail the energy usage of hardware components. With the help of energy profiling tools, programmers can fine-tune the energy consumption o...

Full description

Saved in:
Bibliographic Details
Published in:Journal of network and computer applications 2014-09, Vol.44, p.106-119
Main Authors: Lin, Ying-Dar, Rattagan, Ekarat, Lai, Yuan-Cheng, Chang, Li-Pin, Yo, Yun-Chien, Ho, Cheng-Yuan, Chang, Shun-Lee
Format: Article
Language:English
Subjects:
Android
Applied sciences
Computer science
control theory
systems
Computer systems and distributed systems. User interface
Embedded system
Energy estimation calibration
Energy profiling
Equipments and installations
Exact sciences and technology
Mobile radiocommunication systems
Radiocommunications
Software
Telecommunications
Telecommunications and information theory
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Battery-powered mobile devices substantially constrain energy resources. Process-level energy profiling tools can identify the most energy-consuming process and detail the energy usage of hardware components. With the help of energy profiling tools, programmers can fine-tune the energy consumption of processes to extend battery lifetime. However, profiling tools are highly dependent on hardware and must be calibrated for each hardware platform. Furthermore, for any new hardware components, new energy estimation formulas must be created. To solve these two problems regarding off-the-shelf products, this work proposes a two-phase calibrating approach. The first phase reconstructs the power table with a power meter, while the second creates new energy estimation formulas using linear regression analysis. The accuracy of the calibrated tool was evaluated in five scenarios and its error ratio is proven to be below 10%, occasionally less than 5%. Hence, this proposed approach to energy consumption profiling represents a major step in off-the-shelf devices.
ISSN:1084-8045
1095-8592
DOI:10.1016/j.jnca.2014.04.014