The role of mobile devices, like smartphones or tablets, is becoming more and more important in everyday life, at the point that their unavailability due to early or unexpected battery discharge is perceived as a serious issue. Therefore, there is an urge for smart and efficient battery management algorithms that can prolong the duration of the battery charge. To this end, a reliable prediction of the battery discharging process would represent a precious tool to enable energy-efficiency optimization mechanisms. In this paper, we address this challenge by considering different machine learning techniques to provide an accurate and user-dependent prediction of the discharging time of a mobile device and, eventually, we propose a Deep Neural Network model that provides the best performance. Unlike previous solutions proposed in the literature, our method exploits space-time data from the device operating system (Android) to learn the specific battery usage pattern of the user, thus offering a customized prediction of the discharge process. We show that such model outperforms the other machine-learning methods considered in this study, and achieves much better performance than the deterministic linear fitting methods widely used in commercial devices.

A Deep Neural Network Approach for Customized Prediction of Mobile Devices Discharging Time

GENTIL, MATTIA;GALEAZZI, ALESSANDRO;Chiariotti, Federico;Polese, Michele;Zanella, Andrea;Zorzi, Michele
2017

Abstract

The role of mobile devices, like smartphones or tablets, is becoming more and more important in everyday life, at the point that their unavailability due to early or unexpected battery discharge is perceived as a serious issue. Therefore, there is an urge for smart and efficient battery management algorithms that can prolong the duration of the battery charge. To this end, a reliable prediction of the battery discharging process would represent a precious tool to enable energy-efficiency optimization mechanisms. In this paper, we address this challenge by considering different machine learning techniques to provide an accurate and user-dependent prediction of the discharging time of a mobile device and, eventually, we propose a Deep Neural Network model that provides the best performance. Unlike previous solutions proposed in the literature, our method exploits space-time data from the device operating system (Android) to learn the specific battery usage pattern of the user, thus offering a customized prediction of the discharge process. We show that such model outperforms the other machine-learning methods considered in this study, and achieves much better performance than the deterministic linear fitting methods widely used in commercial devices.
2017
GLOBECOM 2017 - 2017 IEEE Global Communications Conference
9781509050192
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11577/3255755
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? 1
social impact