RT Journal Article
T1 Federated deep reinforcement Learning for ENDC optimization
A1 Martin, Adrian
A1 De la Bandera Cascales, Isabel
A1 Mendo, Adriano
A1 Outes, Jose
A1 Ramiro, Juan
A1 Barco-Moreno, Raquel
K1 Telecomunicaciones
K1 Aprendizaje automático (Inteligencia artificial)
AB 5G New Radio (NR) network deployment in Non-Stand Alone (NSA) mode means that 5G networks rely on the control plane of existing Long Term Evolution (LTE) modules for control functions, while 5G modules are only dedicated to the user plane tasks, which could also be carried out by LTE modules simultaneously. The first deployments of 5G networks are essentially using this technology. These deployments enable what is known as E-UTRAN NR Dual Connectivity (ENDC), where a user establish a 5G connection simultaneously with a pre-existing LTE connection to boost their data rate. In this paper, a single Federated Deep Reinforcement Learning (FDRL) agent for the optimization of the event that triggers the dual connectivity between LTE and 5G is proposed. First, single Deep Reinforcement Learning (DRL) agents are trained in isolated cells. Later, these agents are merged into a unique global agent capable of optimizing the whole network with Federated Learning (FL). This scheme of training single agents and merging them also makes feasible the use of dynamic simulators for this type of learning algorithm and parameters related to mobility, by drastically reducing the number of possible combinations resulting in fewer simulations. The simulation results show that the final agent is capable of achieving a tradeoff between dropped calls and the user throughput to achieve global optimum without the need for interacting with all the cells for training.
PB IEEE
YR 2025
FD 2025-05-07
LK https://hdl.handle.net/10630/38565
UL https://hdl.handle.net/10630/38565
LA eng
NO A. Martin et al., "Federated Deep Reinforcement Learning for ENDC Optimization" in IEEE Transactions on Mobile Computing, vol. 24, no. 06, pp. 5525-5535, June 2025, doi: 10.1109/TMC.2025.3534661.
NO This work was supported in part by Ericsson under Grant MA-2020-003774, through Project 702C2000043 in part by R&D&I Support Program Line through the Junta de Andalucía (Andalusian Regional Government) in part by the Ministerio de Asuntos Económicos y Transformación Digital in part by European Union - NextGenerationEU, and in part by the Recuperación, Transformación y Resiliencia y elMecanismo de Recuperación y Resiliencia through Project MAORI.
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 20 ene 2026