DWM-RO: Decentralized World Models with Reasoning Offloading for SWIPT-enabled Satellite-Terrestrial HetNets

TL;DR

This paper introduces DWM-RO, a decentralized learning framework for satellite-terrestrial networks with SWIPT, significantly improving convergence speed, spectral efficiency, and robustness through world models and reasoning offloading.

Contribution

The paper proposes a novel decentralized world model with reasoning offloading framework that enhances learning efficiency and coordination in SWIPT-enabled satellite-terrestrial networks.

Findings

DWM-RO converges 5 times faster than baselines.

Achieves 34.7% higher spectral efficiency.

Reduces constraint violations by 40%.

Abstract

Wireless networks are undergoing a paradigm shift toward massive connectivity with energy-efficient operation, driving the integration of satellite-terrestrial architectures with simultaneous wireless information and power transfer (SWIPT). Optimizing transmit beamforming and power splitting in such systems faces formidable challenges, e.g., time-varying channels and multi-tier interference, which create a complex decision landscape where conventional model-free multi-agent reinforcement learning (MARL) suffers from sample inefficiency due to rarely-encountered state transitions and poor coordination as decentralized agents act independently. This paper proposes the Decentralized World Model with Reasoning Offloading (DWM-RO) framework to address these fundamental limitations. Specifically, each agent employs a world model to learn compact predictive representations of environment dynamics, enabling imagination-based policy training that dramatically reduces required environment interactions. An uncertainty-aware offloading gate monitors local interference levels and model reconstruction errors to trigger selective edge coordination. When activated, a lightweight latent decorrelation mechanism at the edge refines agents' strategic representations, guiding them toward orthogonal actions that minimize resource conflicts. Extensive simulations demonstrate that DWM-RO converges 5 times faster than state-of-the-art baselines while achieving 34.7% higher spectral efficiency and reducing constraint violations by 40%. In dense network scenarios with 10 users, DWM-RO maintains violation rates below 20% while baselines exceed 70%, validating superior robustness.