Green Emergency Communications in RIS- and MA-Assisted Multi-UAV SAGINs: A Partially Observable Reinforcement Learning Approach

TL;DR

This paper introduces a novel reinforcement learning approach for UAVs in disaster recovery SAGINs, effectively handling partial observability and improving communication efficiency and network coverage in urban environments.

Contribution

It proposes a spatiotemporal A2C method with local messaging and belief encoding, addressing partial observability and outperforming existing MARL techniques.

Findings

Outperforms existing MARL methods in convergence speed and reward.

Reduces TD and advantage errors significantly.

Achieves better throughput-energy trade-off.

Abstract

In post-disaster space-air-ground integrated networks (SAGINs), terrestrial infrastructure is often impaired, and unmanned aerial vehicles (UAVs) must rapidly restore connectivity for mission-critical ground terminals in cluttered non-line-of-sight (NLoS) urban environments. To enhance coverage, UAVs employ movable antennas (MAs), while reconfigurable intelligent surfaces (RISs) on surviving high-rises redirect signals. The key challenge is communication-limited partial observability, leaving each UAV with a narrow, fast-changing neighborhood view that destabilizes value estimation. Existing multi-agent reinforcement learning (MARL) approaches are inadequate--non-communication methods rely on unavailable global critics, heuristic sharing is brittle and redundant, and learnable protocols (e.g., CommNet, DIAL) lose per-neighbor structure and aggravate non-stationarity under tight bandwidth. To address partial observability, we propose a spatiotemporal A2C where each UAV transmits prior-decision messages with local state, a compact policy fingerprint, and a recurrent belief, encoded per neighbor and concatenated. A spatial discount shapes value targets to emphasize local interactions, while analysis under one-hop-per-slot latency explains stable training with delayed views. Experimental results show our policy outperforms IA2C, ConseNet, FPrint, DIAL, and CommNet--achieving faster convergence, higher asymptotic reward, reduced Temporal-Difference(TD)/advantage errors, and a better communication throughput-energy trade-off.