RT Conference Proceedings
T1 Asignación de cabezales radio a procesadores banda base mediante redes neuronales de grafos.
A1 Sánchez-Martín, Joaquín Manuel
A1 Toril-Genovés, Matías
A1 Walshaw, Chris
A1 Bejarano-Luque, Juan Luis
A1 Gijón-Martín, Carolina
K1 Sistemas de comunicaciones inalámbricos
K1 Radio
K1 Redes neuronales (Informática)
AB In 5G networks, Cloud-Radio Access Network (C-RAN) architecture divides legacy base stationsinto Radio Remote Heads (RRH) and Base Band Units (BBU). RRHs transmit and receive radiosignals, whereas BBUs process those signals. Thus, BBUs can be centralized in cloud processingcenters serving different groups of RRHs. An adequate allocation of RRHs to BBUs is essentialto guarantee C-RAN performance. With the latest advances in machine learning, this task canbe automatically addressed through supervised learning. This paper proposes a methodology forallocating RRHs to BBUs in heterogeneous cellular networks relying on graph partitioningthrough a graph neural network. Model performance is assessed over a dataset built with a radioplanning tool that implements a realistic Long-Term Evolution (LTE) heterogeneous network.Results have shown that the proposed method improves performance of a patented state-of-thearttool based on graph partitioning.
YR 2023
FD 2023
LK https://hdl.handle.net/10630/27592
UL https://hdl.handle.net/10630/27592
LA spa
NO Universidad de Málaga. Campus de Excelencia Internacional Andalucía Tech.
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 19 ene 2026