Prediction of Optimal Locations for 5G Base Stations in Urban Environments Using Neural Networks and Satellite Image Analysis

Iván García Aguilar, Jesús Galeano-Brajones, Francisco Luna-Valero, Javier Carmona-Murillo, José David Fernández-Rodríguez, Rafael M. Luque-Baena

Abstract: Deploying 5G networks in urban areas is crucial for meeting the increasing demand for high-speed, low-latency wireless communications. However, the complex topography and diverse building structures in urban environments have challenges in identifying suitable locations for base stations. This research explores leveraging deep learning neural networks to analyze satellite imagery, creating a predictive tool for identifying potential rooftop locations. Integrating these predictions into a user-friendly desktop application simplifies the site selection process, reducing the need for costly and labor-intensive site visits in 5G network deployment. This approach democratizes the deployment process, making it accessible to a broader audience. The combination of advanced technology and satellite imagery offers a promising solution to efficiently deploy 5G base stations in urban landscapes, contributing to the widespread adoption of this technology in densely populated areas and advancing 5G connectivity globally.