Extend Capability of Low-End Android Devices by Scheduling Apps Between Local and Cloud

In this paper, we propose a multi-layer mobile application (app) scheduling method to extend the capability of low-end Android devices. With a quantitative analysis, we find that the increase of installed apps will negatively affect quality of experience (QoE) of the user, e.g., the action response time of a mobile device, by producing more periodically or irregularly background tasks. On the other hand, the user tends to install more apps than needed in case they could play a role someday, as indicated by the consumer app usage statistics. When the storage is running out, being forced to choose an app to uninstall due to space budget is a painful experience for the user. This contradiction is intensified for low-end devices due to limited resources. We try to reduce this dilemma by a multi-layer app scheduling (MAS) schema, along with a cloud service. For the first layer, we utilize the “freeze”feature of Android to prevent non-essential background activities. For the second layer, it is a network scheduler, which automatically schedules the available apps, together with their data, between local and cloud according to user's personal policy generated by big data analysis. By dynamically scheduling the apps among three states, QoE of a low-end Android device is improved. At the same time, with the help of an app state recovery mechanism, the user can directly access a large number of apps provided by the cloud with consistent app view. Experimental results on a low-end smartphone, i.e., Samsung Galaxy ON5, and a smart watch based on Newton2_Plus wearable development board show the benefits of the proposed MAS schema.