Mass-Count Disparity in Mobile Traffic

摘要

Mass-count disparity is a basis of the elephants and mice phenomenon in Internet traffic analysis. Mobile applications tend to minimize transmission overhead by reducing object size. Assuming the mice get smaller, we first look at properties of mass-count disparity in the smart device traffic. We find the existence of elephants and represent an accurate inequality measure using the Gini coefficient where the heavy-tail property is not clearly visible in the trace. The Gini coefficients range from 0.71 (web) to 0.98 (application market traffic), implying a heavy inequality distribution toward 1. The cutoff point of elephants is 1.55 MB that is even comparable with small size photos. Our hypothesis from the early analysis indicates that every mobile user is potentially generating elephant flows. We observe that a significant stance of application market traffic is responsible for such phenomenon.