🤖 AI Summary
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.
📝 Abstract
This paper addresses the critical challenge of coordinating mobile edge UAV networks to maintain robust service in highly dynamic spatiotemporal environments. Conventional Deep Reinforcement Learning (DRL) approaches often suffer from catastrophic forgetting when transitioning between distinct task scenarios, such as moving from dense urban clusters to sparse rural areas. These transitions typically necessitate computationally expensive retraining or model resets to adapt to new user distributions, leading to service interruptions. To overcome these limitations, we propose a computationally efficient Spatiotemporal Continual Learning (STCL) framework realized through a Group-Decoupled Multi-Agent Proximal Policy Optimization (G-MAPPO) algorithm. Our approach integrates a novel Group-Decoupled Policy Optimization (GDPO) mechanism that utilizes dynamic $z$-score normalization to autonomously balance heterogeneous objectives, including energy efficiency, user fairness, and coverage. This mechanism effectively mitigates gradient conflicts induced by concept drifts without requiring offline retraining. Furthermore, the framework leverages the 3D mobility of UAVs as a spatial compensation layer, enabling the swarm to autonomously adjust altitudes to accommodate extreme density fluctuations. Extensive simulations demonstrate that the proposed STCL framework achieves superior resilience, characterized by an elastic recovery of service reliability to approximately 0.95 during phase transitions. Compared to the MADDPG baseline, G-MAPPO not only prevents knowledge forgetting but also delivers an effective capacity gain of 20\% under extreme traffic loads, validating its potential as a scalable solution for edge-enabled aerial swarms.