1. Information about the paper


Yoon, Chanmin, Dongwon Kim, Wonwoo Jung, Chulkoo Kang, and Hojung Cha. “AppScope: Application Energy Metering Framework for Android Smartphone Using Kernel Activity Monitoring.” In USENIX Annual Technical Conference, pp. 387-400. 2012.


Understanding the energy consumption of a smartphone application is a key area of interest for end users, as well as application and system software developers. Previous work has only been able to provide limited information concerning the energy consumption of individual applications because of limited access to underlying hardware and system software. The energy consumption of a smartphone application is, therefore, often estimated with low accuracy and granularity. In this paper, we propose AppScope, an Android-based energy metering system. This system monitors application’s hardware usage at the kernel level and accurately estimates energy consumption. AppScope is implemented as a kernel module and uses an event-driven monitoring method that generates low overhead and provides high accuracy. The evaluation results indicate that AppScope accurately estimates the energy consumption of Android applications expending approximately 35mW and 2.1% in power consumption and CPU utilization overhead, respectively.


2. My review of the paper

  1. It offers new way to infer power consumption on mobile device with three major contribution:

a. Online and autonomous estimation in real-time

– No external measurement device

b. Fine-grained energy consumption information

– Process & hardware component-level granularit

c. System portability

– No modification in system software

  1. Comparison with Power Tutor. The closest previous work is the Power Tutor app. The paper should compare itself with Power Tutor in terms of accuracy. It said there is problem with the way Power Tutor works, but Power Tutor looks like easier to deploy since it is an Android app, not a kernel image. Does this AppScope actually perform better than Power Tutor that worth the difficulty deploying the kernel image.