Personalized power saving profiles generation analyzing smart device usage patterns

Despite much advancement in mobile computing technologies, the smart devices still suffer from battery limitations. The power consumption largely depends on how the end-users interact with their smart devices. Continuous usage of exotic hardware, inbuilt sensors, network and bright colorful display shorten battery life significantly. Thus the key to develop

power saving solutions is to understand the user interactions of smart devices. This paper describes a client-server architecture that proposes personalized power saving profiles by analyzing individual usage patterns. The client is an Android app named "Power Monitor" running on the Android devices. It periodically records usage information from the devices and communicates them to a remote server after a week of monitoring. The server applies an algorithm to generate the usage pattern for each user. Further processing of the patterns provides to power saving profiles and they are sent back to the smart devices. These

profiles are highly personalized since they are developed by analyzing individual usage patterns. The profiles will automatically evolve if the usage patterns change over time. We

also present two real-life usage patterns and the respective power saving profiles to demonstrate the efficiency of the architecture. The battery level gain using Power Monitor is compared with two popular power saving Android applications. It is shown that Power Monitor can increase the battery life by almost 90 percent. Some related privacy issues are also addressed and privacy preserving usage pattern generation is also discussed.