DOLG amortizes non-convex joint optimization in THz CF-ISAC systems into a graph transformer-guided distributed RL policy that balances communication and sensing performance better than baselines in simulations.
Cell-free massive MIMO versus small cells
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
eess.SP 4verdicts
UNVERDICTED 4representative citing papers
A fully distributed OTA beamforming design for full-duplex cell-free massive MIMO that jointly optimizes UL/DL sum MSE while suppressing UE-to-UE pilot contamination via projection and best-response updates.
Closed-form SE expressions and a differential evolution algorithm enable power and mode allocation in flexible full-duplex cell-free massive MIMO, delivering good total performance even when some user rate requirements cannot be met.
A multi-agent DRL framework for distributed precoding in cell-free massive MIMO within O-RAN achieves higher aggregate throughput than distributed baselines and similar performance to centralized methods with lower signaling overhead.
citing papers explorer
-
Distributed Optimization-Learning with Graph Transformers for Terahertz Cell-Free Integrated Sensing and Communication Systems
DOLG amortizes non-convex joint optimization in THz CF-ISAC systems into a graph transformer-guided distributed RL policy that balances communication and sensing performance better than baselines in simulations.
-
Over-the-Air Beamforming Design for Full-Duplex Cell-Free Massive MIMO Systems
A fully distributed OTA beamforming design for full-duplex cell-free massive MIMO that jointly optimizes UL/DL sum MSE while suppressing UE-to-UE pilot contamination via projection and best-response updates.
-
Network-Assisted Full-Duplex Cell-Free Massive MIMO Systems Under Infeasible Circumstances
Closed-form SE expressions and a differential evolution algorithm enable power and mode allocation in flexible full-duplex cell-free massive MIMO, delivering good total performance even when some user rate requirements cannot be met.
-
Distributed Precoding for Cell-free Massive MIMO in O-RAN: A Multi-agent Deep Reinforcement Learning Framework
A multi-agent DRL framework for distributed precoding in cell-free massive MIMO within O-RAN achieves higher aggregate throughput than distributed baselines and similar performance to centralized methods with lower signaling overhead.