mlsanityData to 14 Oct 2026

GCN-Driven Reinforcement Learning for Probabilistic Real-Time Guarantees in Industrial URLLC

arXiv 2506.15011 ↗First posted 17 Jun 2025cs.NI cs.LGcited by 0

On the map: Deep reinforcement learning methods → RL for energy, networks and operations

Abstract (arXiv)

Ensuring packet-level communication quality is vital for ultra-reliable, low-latency communications (URLLC) in large-scale industrial wireless networks. We enhance the Local Deadline Partition (LDP) algorithm by introducing a Graph Convolutional Network (GCN) integrated with a Deep Q-Network (DQN) reinforcement learning framework for improved interference coordination in multi-cell, multi-channel networks. Unlike LDP's static priorities, our approach dynamically learns link priorities based on real-time traffic demand, network topology, remaining transmission opportunities, and interference patterns. The GCN captures spatial dependencies, while the DQN enables adaptive scheduling decisions through reward-guided exploration. Simulation results show that our GCN-DQN model achieves mean SINR improvements of 179.6%, 197.4%, and 175.2% over LDP across three network configurations. Additionally, the GCN-DQN model demonstrates mean SINR improvements of 31.5%, 53.0%, and 84.7% over our previous CNN-based approach across the same configurations. These results underscore the effectiveness of our GCN-DQN model in addressing complex URLLC requirements with minimal overhead and superior network performance.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods. Builds on 6 of its 15 references that are in the map. First posted on arXiv 17 Jun 2025.

Builds on

6 of 15 references.

References · 6

  1. 2019A Vision of 6G Wireless Systems: Applications, Trends, Technologies, and Open Research Problemscited by 160
  2. 2022Asynchronous Hybrid Reinforcement Learning for Latency and Reliability Optimization in the Metaverse over Wireless Communicationscited by 9
  3. 2021Scheduling with Probabilistic Per-Packet Real-Time Guarantee for URLLCcited by 2
  4. 2023Task-Oriented Delay-Aware Multi-Tier Computing in Cell-free Massive MIMO Systemscited by 2
  5. 2023Joint Uplink and Downlink Resource Allocation Towards Energy-efficient Transmission for URLLCcited by 2
  6. 2019Minimum Age TDMA Schedulingcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Graph Reinforcement Learning for QoS-Aware Load Balancing in Open Radio Access Networks
  2. 2026Temporally Consistent Graph Q-Networks for Intelligent Network Control
  3. 2025Towards Ultra-Reliable 6G in-X Subnetworks: Dynamic Link Adaptation by Deep Reinforcement Learning
  4. 2026A Constrained RL Approach for Cost-Efficient Delivery of Latency-Sensitive Applications
  5. 2025Power Allocation for Delay Optimization in Device-to-Device Networks: A Graph Reinforcement Learning Approach
  6. 2025Deep Reinforcement Learning for Dynamic Resource Allocation in Wireless Networks
  7. 2024Statistical QoS Provision in Business-Centric Networks
  8. 2025A Flexible Multi-Agent Deep Reinforcement Learning Framework for Dynamic Routing and Scheduling of Latency-Critical Services