New.

Geoffrey Challen
1 parent 6ccfdb28
Showing 4 changed files with 15 additions and 36 deletions
figures/survey.pdf
figures/survey.py
paper.tex
results.tex
@@ -61,6 +61,6 @@ ax.set_xlabel(&#39;\\textbf{%d Responses}&#39; % (len(scores)), labelpad=6)
 ax.set_ylabel('\\textbf{Score}')
 fig.subplots_adjust(right=0.99,top=0.98,left=0.07,bottom=0.10)
-fig.set_size_inches(6.5,2.5)
+fig.set_size_inches(6.5,2.0)
 fig.savefig('survey.pdf')
 \input{./include/start.tex}
 \def\theconference{HotMobile'15}
-\def\thetitle{The Missing Numerator: Towards a Value Measure for Smartphone
+\def\thetitle{The Missing Numerator: Toward a Value Measure for Smartphone
 Apps}
 \def\theauthors{Anudipa Maiti and Geoffrey Challen}
@@ -12,45 +12,24 @@ access to a representative group of participants balanced between genders and
 across a wide variety of age brackets, making our results more
 representative.
-Understanding fine-grained energy consumption dynamics such as what apps ran
-for how long and how much energy each interactive session consumed while
-running in the background required more information than Android normally
-exposes to apps. In addition, to explore our content deliver metric we also
-wanted to capture information about app usage---including foreground and
-background time and use of the display and audio interface---that was not
-possible to measure on unmodified Android devices.
-
-So to collect our dataset we took advantage of \PhoneLab{}'s ability to
-modify the Android platform itself. Our modification augmented the platform
-to collect the fine-grained energy consumption and app behavior information
-required to understand smartphone energy consumption. We instrumented the
+Understanding fine-grained energy consumption dynamics required more
+information than Android normally exposes to apps. In addition, to explore
+components of our value measure we also wanted to capture information about
+app usage---including foreground and background time and use of the display
+and audio interface---that was not possible to measure on unmodified Android
+devices. So to collect our dataset we took advantage of \PhoneLab{}'s ability
+to modify the Android platform itself. We instrumented the
 \texttt{SurfaceFlinger} and \texttt{AudioFlinger} Android platform components
 to record usage of the screen and audio, and altered the Activity Services
 package to record energy consumption at each app transition, allowing energy
 consumption by components such as the screen to be accurately attributed to
 the foreground app, a feature that Android's internal battery monitoring
-component (the Fuel Gauge) lacks. The dataset of 67~GB of compressed log
-files represents \num{6806} user days during which \num{1328}~apps were
-started \num{277785} times and used for a total of \num{15224} hours of
-active use.
-
-At \PhoneLab{} based on the analysis of data collected about foreground and
-background energy consumption by applications running on the participants'
-smartphones, we tried to formulate design for requirements for an energy
-efficiency metric to apply to smartphone apps. First, it must scale with
-usage, respecting the differences in baseline consumption between users and
-the temporal variation of apps. Second, it must try to avoid targeting top
-apps, even if they tend to consume a great deal of energy, as these may not
-be apps that users are willing to uninstall. Finally, we use the analysis of
-background energy consumption as a hint about where to start, given that
-background energy consumption should match foreground usage in most cases.
-
-We tried characterizing app energy consumption in multiple ways: via the
-total amount, by consumption rate, and scaled against foreground energy
-consumption and a new content-delivery metric we design that incorporates use
-of both the display and the audio device. In each case we examine the app
-consumption data generated by our usage monitoring study and use each metric
-to shed light on app energy consumption.
+component (the Fuel Gauge) lacks. Changes were distributed to \PhoneLab{}
+participants in November, 2013, via an over-the-air (OTA) platform update.
+The resulting 2~month dataset of 67~GB of compressed log files represents
+\num{6806} user days during which \num{1328}~apps were started \num{277785}
+times and used for a total of \num{15224} hours of active use by
+107~\PhoneLab{} participants.
 \subsection{Total Consumption}