Abstract
Low-Earth orbit (LEO) satellite Internet has become an important infrastructure for enabling ubiquitous connectivity to align with the International Telecommunication Union vision for 6G telecommunications networks. However, current LEO satellite Internet observations often suffer from missing data, complicating data augmentation tasks and limiting the expansion of representative datasets. Given the complex characteristics of these datasets, generative AI (GenAI) presents a promising approach, yet its application in this domain has received little attention to date.
In this paper, we propose a GenAI-based framework to synthesize high-fidelity data directly from incomplete LEO network observations. We propose representative data missing scenarios and evaluate the performance with the latest GAN- and VAE-based GenAI models on the recent WetLinks dataset. We design block-wise and point-wise missing scenarios to closely simulate the data loss that occurs in real-world LEO satellite networks.
Our results demonstrate the effectiveness of our proposed GAN-based framework, with the GT-GAN model exhibiting the best performance among all models in both missing scenarios. Even under extreme conditions (e.g., 40% of the input data is missing), GT-GAN shows the highest robustness, consistently capturing the underlying input data distribution and being the least affected in terms of generalization. Our findings shed light on future directions for GenAI-based data augmentation methods and data-driven research on satellite network measurement.
Blogger's Review: The proposed GAN framework shows remarkable performance under data missing conditions, especially its robustness in extreme loss scenarios is noteworthy. As satellite internet becomes more widespread, efficiently leveraging generative models for data augmentation will be a significant research direction. This study provides new insights and methodological support for related fields.