GRIMCELL: A Graph Neural Network to Predict the Impact of New Cells in Mobile Networks
Joaquín Manuel Sánchez-Martín, Juan Luis Bejarano-Luque, Carolina Gijón, Matias Toril, Salvador Luna-Ramírez · Machine Learning and Knowledge Extraction · 2026
Not cached yet. This record was fetched live for this request and is stored after the lookup. Reopening the page should serve the cached copy.
Machine Learning and Knowledge Extraction · Multidisciplinary Digital Publishing Institute · article · 2026
Abstract
Network densification will play a vital role in next-generation cellular networks, as it addresses coverage and capacity issues in the radio access domain. However, new cell deployments can negatively impact neighbor cells, requiring careful planning. Unfortunately, the complexity of advanced radio resource management schemes implemented in Beyond 5G and future 6G networks makes it challenging to predict the impact of radio deployments in the existing cells accurately. This work presents GRIMCELL, a novel data-driven method to estimate the impact of radio deployments (i.e., new carriers, sectors, or sites) on cell performance.
For this purpose, GRIMCELL combines radio planning, configuration management and performance management data gathered in commercial vendor equipment. The core of GRIMCELL is a proven message passing graph neural network (XENet) to forecast the performance of both new and existing cells after the deployment. Assessment over data from a commercial LTE-A Pro network has shown that GRIMCELL provides high accuracy and flexibility across diverse deployment scenarios.
Open the resolved locator · 10.3390/make8090260
Metadata licence: OpenAlex metadata (CC0)