Multi-Functional RIS-Enabled in SAGIN for IoT: A Hybrid Deep Reinforcement Learning Approach with Compressed Twin-Models

Abstract

A space-air-ground integrated network (SAGIN) for Internet of Things (IoT) network architecture is investigated, empowered by multi-functional reconfigurable intelligent surfaces (MF-RIS) capable of simultaneously reflecting, amplifying, and harvesting wireless energy. The MF-RIS plays a pivotal role in addressing the energy shortages of low-Earth orbit (LEO) satellites operating in the shadowed regions, while accounting for both communication and computing energy consumption across the SAGIN nodes. To maximize the long-term energy efficiency (EE) of IoT devices, we formulate a joint optimization problem over the MF-RIS parameters, including signal amplification, phase-shifts, energy harvesting ratio, and active element selection as well as the SAGIN parameters of beamforming vectors, high-altitude platform station (HAPS) deployment, IoT device association, and computing capability. The formulated problem is highly non-convex and non-linear and contains mixed discrete-continuous parameters. To tackle this, we conceive a compressed hybrid twin-model enhanced multi-agent deep reinforcement learning (CHIMERA) framework, which integrates semantic state-action compression and parametrized sharing under hybrid reinforcement learning to efficiently explore suitable complex actions. The simulation results have demonstrated that the proposed CHIMERA scheme substantially outperforms the conventional benchmarks, including fixed-configuration or non-harvesting MF-RIS, traditional RIS, and no-RIS cases, as well as centralized and multi-agent deep reinforcement learning baselines in terms of the highest EE. Moreover, the proposed SAGIN-MF-RIS architecture in IoT network achieves superior EE performance due to its complementary coverage, offering notable advantages over either standalone satellite, aerial, or ground-only deployments.

References in corpus (6)

• Five Facets of 6G: Research Challenges and Opportunities
• Simultaneously Transmitting and Reflecting Surface (STARS) for Terahertz Communications
• Multi-Functional Reconfigurable Intelligent Surface: System Modeling and Performance Optimization
• Channel Estimation and Beamforming Design for MF-RIS-Aided Communication Systems
• Federated Deep Reinforcement Learning for Energy Efficient Multi-Functional RIS-Assisted Low-Earth Orbit Networks
• Joint Active and Passive Beamforming for Energy-Efficient STARS with Quantization and Element Selection in ISAC Systems