GCN-Driven Reinforcement Learning for Probabilistic Real-Time Guarantees in Industrial URLLC
This work addresses the challenge of reliable, low-latency communications for industrial wireless networks, representing an incremental improvement over existing methods.
The paper tackles the problem of ensuring packet-level communication quality in industrial URLLC networks by enhancing the Local Deadline Partition algorithm with a GCN-DQN model for dynamic interference coordination, achieving mean SINR improvements of up to 197.4% over LDP and up to 84.7% over a previous CNN-based approach.
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.