Time-Varying Mobile Edge Computing for Capacity Maximization

Abstract

Capacity is a fundamental metric for mobile edge computing scenarios, where the system state plays an important role. Previous studies have mostly been based on the premise that the system state is stable. In reality, the network is dynamic and the system state changes with time. In this paper, we study the capacity of a mobile edge system in which users continuously join or leave the coverage of base station. We first change the problem of maximum network capacity into a minimum transmission distance problem. We observe that both the probability of the files being requested and the distance of the files transmission are related to the degree of files, i.e., the number of users who are interested in a file and request it with a certain probability. Then, we evaluate the degree of files in a time-varying situation, and calculate the probability of the files being requested and the transmission distance according to the degree of files. Finally, we calculate the capacity of the network under time-varying conditions. In the experimental section, we analyze the degree of files, the optimal copies number, and the change in network capacity over time. In addition, we compare the capacity in our system with classic studies. The experimental results verify the superiority of the proposed method. INDEX TERMS Mobile edge computing, Capacity, Time-varying, Degree of files, Transmission distance.