CODES/ISSS '10 Proceedings of the eighth IEEE/ACM/IFIP international conference on Hardware/software codesign and system synthesis
| Hi-index | 0.00 |
Reducing the energy consumed in the use of smart phones has become a major challenge for application developers. While this problem can be addressed at various levels, it is important to reduce the energy consumption of individual applications which can vary greatly depending on the behavior of the application. Energy profiling methods are required in order to identify the points in which the applications are consuming excessive energy and to examine how to reduce overall energy consumption by applications. The existing power estimating method[1, 2] can estimate the energy consumption of entire terminal using data obtained from the OS (e.g. CPU-time, amount of access to file systems, traffic, etc.). It is, however, unable to identify points where excessive energy is consumed and to take into account all possible usage patterns and environments since developers are able to use the limited number of test cases in the profiling. This paper proposes a novel method to analyze and visualize energy consumption of applications that run on Android OS under actual users' real usage. This method consists of four phases: 1) embedding logging codes to obtain hardware resource consumption from the OS for estimating the energy consumption in an application using AspectJ[3], 2) distributing the application to the users, 3) gathering that data from the application, and 4) creating visual of the data. To explore the potential of the method, we profiled Crowdroid[4], an open-source twitter client, with four users and estimated the energy consumption for each activity with our method. An activity in the Android is an object that corresponds to the screen of the application. In order to calculate energy consumption from data we logged, we employ a model for estimation proposed by the existing power estimating method[1].