Learning Cellular Coverage from Real Network Configurations using GNNs
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.
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