Reducing energy consumption of smartphones using user-perceived response time analysis

Abstract

We propose a novel power optimization framework based on user-perceived response time analysis. Unlike most existing power optimization approaches, our framework takes explicit account of the quality of user experience into applying low-power techniques. We divide an execution of a given user-interactive session into two intervals, one where the system response time directly affects user experience and the other where the system response time does not affect user experience. For the user-oblivious response time interval, our framework allows more aggressive applications of low-power techniques for a higher energy efficiency. In order to identify the user-perceived response time of smartphone applications during run time, we developed an on-line user-perceived response time analyzer (ura) for Android-based smartphones. Based on the analysis result of ura, our proposed power optimization framework employs more aggressive low-power techniques in the user-oblivious interval. Our experimental results on a smartphone development board show that the proposed technique can reduce the CPU energy consumption by up to 65.6% over the Android's default ondemand cpufreq governor.