Intent-Aware DRL-Based NOMA Uplink Dynamic Scheduler for IIoT

We investigate the problem of supporting Industrial Internet of Things user equipments (IIoT UEs) with specific intents (i.e., requested quality of service (QoS)) and random traffic arrivals. We propose a centralized dynamic scheduler for time-frequency resources based on deep reinforcement learning (DRL) to efficiently allocate communication resources among IIoT UEs. The proposed scheduler leverages a DRL framework to adapt to the dynamic changes in the wireless communication system and traffic arrivals. Moreover, we introduce a graph-based reduction scheme to reduce the state and action space of the DRL framework to allow fast convergence and a better learning strategy. Simulation results demonstrate the effectiveness of the proposed intelligent scheduler in guaranteeing the expressed intents of IIoT UEs compared to several traditional scheduling schemes, such as round-robin, semi-static, and heuristic approaches. The proposed scheduler also outperforms the contention-free and contention-based schemes in maximizing the number of successfully computed tasks.