Network Agile Preference-Based Prefetching for Mobile Devices
For mobile devices, communication via cellular networks consumes more energy, and has a lower data rate than WiFi networks, and suffers an expensive limited data plan. However the WiFi network coverage range and density are smaller than those of the cellular networks. The key challenge is how to help users reduce the energy and monetary cost of data communication while not sacrificing the user experience when users are able to occasionally get access to WiFi networks.
Since web browsing and news reading account for a large proportion of the time and data used by smartphones, in this work we present a behavior-aware and preference-based approach to automatically prefetch news webpages that a user will be interested in and access, by exploiting the WiFi network connections. In our solution, we design an efficient preference-learning algorithm, which will keep track of the userís changing interests. Moreover, by predicting the appearance and durations of the WiFi network connections, our prefetch approach then optimizes when to prefetch what webpages to maximize the user experience while lowing the prefetch cost. Our prefetch approach exploits the idle period of WiFi connections to reduce the tail-energy consumption. We implement our approach in iPhone. Our extensive evaluations show that our system achieves about 60% hit ratio, saves about 50% cellular data usage, and reduces the energy cost by 7.5%.