Spatiotemporal Continual Learning for Mobile Edge UAV Networks: Mitigating Catastrophic Forgetting
This work addresses the challenge of catastrophic forgetting in conventional deep reinforcement learning approaches when mobile edge drone networks undergo abrupt user distribution shifts during dynamic spatiotemporal scenario transitions, such as from urban to rural environments, which often necessitates frequent retraining and causes service interruptions. To mitigate this, the authors propose a Spatiotemporal Continual Learning (STCL) framework that integrates Group-Decoupled Multi-Agent Proximal Policy Optimization (G-MAPPO) with dynamic z-score normalization. The framework employs a Group-Decoupled Policy Optimization (GDPO) mechanism to online balance heterogeneous objectives—including energy efficiency, fairness, and coverage—and leverages 3D drone mobility as a spatial compensation layer. Experimental results demonstrate that the proposed method restores service reliability to approximately 0.95 after scenario transitions and achieves a 20% higher effective capacity than MADDPG under extreme load, significantly alleviating knowledge forgetting while ensuring service continuity.