QoE-based energy reduction by controlling the 3g cellular data traffic on the smartphone

One of the most influencing factors on the overall end-user perceived quality from applications and services, i.e., QoE, running on the smartphones is their limited battery life. Particular cloud-based applications/services on the smartphone with a constrained battery life might consume high energy even when the smartphone is in screen-OFF state. The cellular radio module of the smartphone is one of the most power-consuming components, which depends on the running applications' information polling characteristics that eventually cause the radio module to toggle occasionally between the cellular data energy states even during a sleep state. In this paper, we investigate the energy consumption of a set of applications that tend to retain up-to-date information via aggressive polling patterns. We show that limiting the network traffic and increasing the resource utilization efficiency amongst the applications and services can highly reduce the total energy consumption. We control the network activity of a smartphone with different cellular data-enabled and data-disabled durations at the screen-OFF state. First, we run controlled-lab energy measurements to have a ground truth on the power consumption patterns of a set of cloud-based popular applications/services; and next we conduct a subjective study with our proposed solution (ExpCO2), to understand first the user behaviour on the smartphone and then present how the reduced polling intervals of applications and notifications influence the end-user perceived quality. We indicate that ExpCO2 has a potential to save energy.