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

2024-03-27

AI Summary

To address the challenges of dynamic QoS intent evolution, stochastic task arrivals, and time-varying wireless channels in Industrial IoT (IIoT), this paper proposes an intent-driven deep reinforcement learning (DRL) framework for dynamic uplink NOMA resource scheduling. We innovatively design a graph-structured state–action space reduction mechanism, leveraging graph neural networks (GNNs) for effective state abstraction, and implement centralized power-domain multiple access scheduling via PPO or DQN. Compared to polling, semi-static, and heuristic baselines, the proposed method significantly improves QoS intent fulfillment rates. Specifically, task success rates increase by 23.6% over conflict-free and 31.4% over conflict-prone baselines. Moreover, the framework exhibits rapid convergence and strong cross-scenario policy generalization capability.

Technology Category

• Planning, Routing, and Scheduling: Learning for Planning and Scheduling
• Intelligent Robots: Learning & Optimization for ROB
• Application Domains: Internet of Things, Sensor Networks & Smart Cities

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

We investigate the problem of supporting Industrial Internet of Things user equipment (IIoT UEs) with intent (i.e., requested quality of service (QoS)) and random traffic arrival. A deep reinforcement learning (DRL) based centralized dynamic scheduler for time-frequency resources is proposed to learn how to schedule the available communication resources among the IIoT UEs. The proposed scheduler leverages an RL framework to adapt to the dynamic changes in the wireless communication system and traffic arrivals. Moreover, a graph-based reduction scheme is proposed to reduce the state and action space of the RL framework to allow fast convergence and a better learning strategy. Simulation results demonstrate the effectiveness of the proposed intelligent scheduler in guaranteeing the expressed intent 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.

Problem

• Resource Allocation
• Industrial IoT
• Dynamic Network Adaptation

Innovation

• Advanced Learning Method
• Intelligent Scheduling System
• Industrial IoT Resource Allocation