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 producing 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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Learning Cellular Coverage from Real Network Configurations using GNNs


    Contributors:


    Publication date :

    2023-06-01


    Size :

    1170038 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Toward Global Snow from Space: Coverage of Snow Observation Constellation Configurations

    Kim, Edward / Forman, Barton A. / Wang, Lizhao et al. | NTRS | 2019


    Optimal Coverage Analysis of a Cellular Device-to-Device Communication Network

    Jaswanth, Darsi / Dash, Soumya P. / Joshi, Sandeep | IEEE | 2020


    Interpreting Cellular Coverage for Transportation Applications

    Walton, Scott / Meyer, Eric | Transportation Research Record | 2003


    Test Vehicle Patterns on Cellular Coverage

    Eskelinen | Online Contents | 1997