English

Learning Cellular Coverage from Real Network Configurations using GNNs

Networking and Internet Architecture 2023-04-21 v1 Machine Learning

Abstract

Cellular coverage quality estimation has been a critical task for self-organized networks. In real-world scenarios, deep-learning-powered coverage quality estimation methods cannot scale up to large areas due to little ground truth can be provided during network design & optimization. In addition they fall short in produce expressive embeddings to adequately capture the variations of the cells' configurations. To deal with this challenge, we formulate the task in a graph representation and so that we can apply state-of-the-art graph neural networks, that show exemplary performance. We propose a novel training framework that can both produce quality cell configuration embeddings for estimating multiple KPIs, while we show it is capable of generalising to large (area-wide) scenarios given very few labeled cells. We show that our framework yields comparable accuracy with models that have been trained using massively labeled samples.

Keywords

Cite

@article{arxiv.2304.10328,
  title  = {Learning Cellular Coverage from Real Network Configurations using GNNs},
  author = {Yifei Jin and Marios Daoutis and Sarunas Girdzijauskas and Aristides Gionis},
  journal= {arXiv preprint arXiv:2304.10328},
  year   = {2023}
}

Comments

Accepted at 2023 IEEE VTC-Spring

R2 v1 2026-06-28T10:12:29.736Z