UAV-Assisted Resilience in 6G and Beyond Network Energy Saving: A Multi-Agent DRL Approach

TL;DR

This work tackles resilience and energy efficiency in 6G-and-beyond networks by enabling UAVs to compensate for sleeping or failed GBSs in NES scenarios. It introduces a centralized training, decentralized execution MADDPG framework (CTDE-MADDPG) to jointly optimize UAV trajectories, transmit powers, and user-UAV associations under a sleeping-cell strategy. Key contributions include a POMDP formulation for UAV control, a CTDE-MADDPG architecture with PER and interference-aware training, and comprehensive simulations showing improved coverage and reduced UAV energy. Results indicate about 24% UAV energy reduction relative to all-GBS-on configurations while maintaining comparable service levels, highlighting practical potential for sustainable, resilient UAV-enabled 6G networks.

Abstract

This paper investigates the unmanned aerial vehicle (UAV)-assisted resilience perspective in the 6G network energy saving (NES) scenario. More specifically, we consider multiple ground base stations (GBSs) and each GBS has three different sectors/cells in the terrestrial networks, and multiple cells are turned off due to NES or incidents, e.g., disasters, hardware failures, or outages. To address this, we propose a Multi-Agent Deep Deterministic Policy Gradient (MADDPG) framework to enable UAV-assisted communication by jointly optimizing UAV trajectories, transmission power, and user-UAV association under a sleeping ground base station (GBS) strategy. This framework aims to ensure the resilience of active users in the network and the long-term operability of UAVs. Specifically, it maximizes service coverage for users during power outages or NES zones, while minimizing the energy consumption of UAVs. Simulation results demonstrate that the proposed MADDPG policy consistently achieves high coverage ratio across different testing episodes, outperforming other baselines. Moreover, the MADDPG framework attains the lowest total energy consumption, with a reduction of approximately 24\% compared to the conventional all GBS ON configuration, while maintaining a comparable user service rate. These results confirm the effectiveness of the proposed approach in achieving a superior trade-off between energy efficiency and service performance, supporting the development of sustainable and resilient UAV-assisted cellular networks.

Figures (5)

• Figure 1: System Model Illustration
• Figure 2: CTDE-MADDPG Framework
• Figure 3: Training convergence curve, showing the average reward per step over the training process.
• Figure 4: omparison of instantaneous reward per step, averaged over 15 testing episodes.
• Figure 5: Comparison of Total Coverage Ratio per Episode