Please use this identifier to cite or link to this item:
Title: Increasing Energy Efficiency on Smartphones through Data forecashing
Authors: Xu, Jiuyun
Yang, Dan
Wang, Jiazhen
Guan, Chao
Reiff-Marganiec, Stephan
Shen, Huilin
First Published: 2016
Presented at: 5th IEEE International Conference on Mobile Services, 2016, San Francisco, USA
Start Date: 27-Jun-2016
End Date: 2-Jul-2016
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Citation: Mobile Services (MS), 2016 IEEE International Conference on
Abstract: Smartphones are widely used in daily life to access services and various functions require continuous communication, which leads to increased energy consumption. However, the development of battery and related energy saving technology can not meet the demand for energy consumption. Much of current research work focuses on energy models caring much about energy consumption of every single application. In this paper, we propose a data forecasting-based strategy for increasing energy efficiency on smartphones based on the predictability of data to be accessed. To achieve this, a combination of Collaborative filtering with the k-means algorithm categorize users with similar user groups and speculate use increased for the data users will access. With this model, we also adopt data pre-storing model and dynamic updating model. The simulation results illustrate that our approach is leading to energy saving.
DOI Link: 10.1109/MobServ.2016.30
Version: Post-print
Status: Peer-reviewed
Type: Conference Paper
Rights: Creative Commons “Attribution Non-Commercial No Derivatives” licence CC BY-NC-ND, further details of which can be found via the following link: Archived with reference to SHERPA/RoMEO and publisher website.
Appears in Collections:Conference Papers & Presentations, Dept. of Computer Science

Files in This Item:
File Description SizeFormat 
Paper4MobileEnergy.pdfPost-review (final submitted author manuscript)506.78 kBAdobe PDFView/Open

Items in LRA are protected by copyright, with all rights reserved, unless otherwise indicated.