A Scheme of Estimating Mobile Traffic Data without Coarse-Grained Process using Conditional SR-GAN

Abstract

In recent years, a scheme for generating a large amount of mobile traffic data has been proposed. In the state-of-the-art of the schemes, Generative Adversarial Networks (GANs) is used to transform a large amount of traffic data into a coarse-grained representation and to generate the original traffic data from the coarse-grained data. However, in order to generate the original traffic data, the coarse-grained data must be preserved and it takes waste storage cost. In this paper, we propose a scheme for generating the mobile traffic data without requiring a coarse-grained process by using Conditional SR-GAN. In evaluation using real mobile traffic data, our proposed scheme not only does reduce the storage cost by more than 25% compared to the traditional scheme, but also can generate the original mobile traffic data with 94% accuracy.