Personalized Diapause: Reducing Radio Energy Consumption of Smartphones by Network-Context Aware Dormancy Predictions

A large portion of radio energy in smartphones is wasted during a special waiting period, known as the tail time, after a transmission is completed. In order to save the wasted energy during the tail time, it is important to accurately predict whether a subsequent transmission will occur in the tail period. In this paper, we propose a novel general-purpose predictive dormancy technique, called Personalized Diapause (PD). By automatically extracting meaningful network activities as network contexts, our proposed technique takes advantage of per-user usage characteristics of each network context in deciding when to release a radio connection within the tail time. Our experimental results using real network usage logs from 25 users show that PD can save the radio energy consumption by up to 36% with about 10% reconnection increase.