ZipNet-GAN: Inferring Fine-grained Mobile Traic Paerns via a Generative Adversarial Neural Network

Large-scale mobile trac analytics is becoming essential to digital infrastructure provisioning, public transportation, events planning, and other domains. Monitoring city-wide mobile trac is however a complex and costly process that relies on dedicated probes. Some of these probes have limited precision or coverage, others gather tens of gigabytes of logs daily, which independently o‚er limited insights. Extracting €ne-grained paŠerns involves expensive spatial aggregation of measurements, storage, and post-processing. In this paper, we propose a mobile trac super-resolution technique that overcomes these problems by inferring narrowly localised trac consumption from coarse measurements. We draw inspiration from image processing and design a deep-learning architecture tailored to mobile networking, which combines Zipper Network (ZipNet) and Generative Adversarial neural Network (GAN) models. Œis enables to uniquely capture spatio-temporal relations between trac volume snapshots routinely monitored over broad coverage areas (‘low-resolution’) and the corresponding consumption at 0.05 km2 level (‘high-resolution’) usually obtained a‰er intensive computation. Experiments we conduct with a real-world data set demonstrate that the proposed ZipNet(-GAN) infers trac consumption with remarkable accuracy and up to 100× higher granularity as compared to standard probing, while outperforming existing data interpolation techniques. To our knowledge, this is the €rst time super-resolution concepts are applied to large-scale mobile trac analysis and our solution is the €rst to infer €ne-grained urban trac paŠerns from coarse aggregates.